跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+3新增论文
+3其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-12 17:17 · 全站最近入库：2026-11-12 06:37各信源进度 →

统计口径与数据新鲜度

统计 2026-11-11 17:45 — 2026-11-12 17:45（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-12 17:17最近发现新增版本：2026-11-12 06:37库内论文最新更新时间：2026-11-11 08:00

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

21,675 已收录论文18,323 AI 相关6,056 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 4,903 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-12 17:15（北京时间）
版本更新 · v6arXiv:2603.23101

SpecXMaster Technical Report

Yutang Ge, Yaning Cui, Hanzheng Li, Jun-Jie Wang, Fanjie Xu, Jinhan Dong, Yongqi Jin, Dongxu Cui 等 21 位作者

原文摘要

Intelligent spectroscopy serves as a pivotal element in AI-driven closed-loop scientific discovery, functioning as the critical bridge between matter structure and artificial intelligence. However, conventional expert-dependent spectral interpretation encounters substantial hurdles, including susceptibility to human bias and error, dependence on limited specialized expertise, and variability across interpreters. To address these challenges, we propose SpecXMaster, an intelligent framework leveraging Agentic Reinforcement Learning (RL) for NMR molecular spectral interpretation. SpecXMaster enables automated extraction of multiplicity information from both 1H and 13C spectra directly from raw FID (free induction decay) data. This end-to-end pipeline enables fully automated interpretation of NMR spectra into chemical structures. It demonstrates superior performance across multiple public NMR interpretation benchmarks and has been refined through iterative evaluations by professional chemical spectroscopists. We believe that SpecXMaster, as a novel methodological paradigm for spectral interpretation, will have a profound impact on the organic chemistry community.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11916

LBSNet: Lightweight Brain State Modeling via Learnable Spectral Prototypes for EEG-Based Fatigue Detection

Kun Jia, Zhenyu Cao, Hanlin Yu, Zeyuan Li, Yixuan Liu, Zhongye Xia, Sen Song, Zhiyuan Ma

原文摘要

EEG-based fatigue detection requires modeling spectral information across bands and its temporal variation. Recent methods combine multi-band modeling with adaptive temporal processing, yet how spectral structure across bands should influence the contribution of each temporal interval remains insufficiently explored. We propose LBSNet, a lightweight network that uses prototype-based brain-state modeling to link local spectral structure with temporal aggregation. LBSNet extracts compact multi-band features through band-specific temporal convolution, shared spatial projections, and cross-band recalibration. Within each window, relative spectral activity is encoded as a normalized descriptor and softly matched to learnable spectral prototypes. Prototype assignments and learned prototype importance jointly determine temporal weights for power aggregation, allowing the spectral pattern of each window to guide its contribution to the prediction. Subject-independent experiments on SEED-VIG and SADT show that LBSNet outperforms seven baselines while maintaining low computational cost. Ablation and visualization analyses support prototype-guided temporal weighting, while the learned prototypes reveal a gradual redistribution of relative cross-band spectral states with increasing fatigue. The code is publicly available at https://github.com/zy0929/LBSNet.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11914

CRAFT-GBM: Selecting Best Features for Gradient-Boosted Machine Learning

Basil Kuok, Yi Zhou, Yao Xuan, Shuping Li, Ke-Wei Huang

原文摘要

Feature subsampling is used to accelerate gradient-boosted trees, yet standard approaches fix the feature count in advance and largely ignore the split-gain evidence accumulated during training. We introduce CRAFT-GBM (Confidence-Ranked Adaptive Feature Tracking), a native LightGBM extension that uses this evidence to adapt which---and, by default, how many---features are searched each boosting round. CRAFT-GBM transforms root-split gains into bounded observations and constructs joint time-uniform bounds valid under adaptive, non-stationary training histories. In its default endogenous mode, after initialization, CRAFT-GBM retains exactly the features that cannot yet be ruled out as best, letting the selected feature-set size $K_t$ emerge from training history rather than a pre-specified fraction. With probability at least $1-δ$, every feature with the largest expected gain is retained jointly across all rounds after initialization. When a feature fraction $f$ is specified instead, CRAFT-GBM ranks features by their interval point estimates and provides an approximate top-$K$ guarantee for feature budget $K_f$. We implement CRAFT-GBM within LightGBM while preserving its native feature-bundling representation, and evaluate it across 14 public and synthetic dataset families and four noise-augmented settings. In the fully endogenous setting, CRAFT-GBM reduces per-fit training time by 39.74\% with 1.04\% lower test loss in the geometric mean across all 18 RQ1 experiments. Under pre-specified feature fraction $f$, Exogenous CRAFT-GBM also yields aggregate training-time reductions up to 13.52 percentage points larger than random feature subsampling, with no increase in aggregate test loss relative to full-feature LightGBM. Accumulated training evidence can thus support adaptive feature search with statistical guarantees while retaining the practical advantages of native gradient boosting.

cs.LG · math.ST

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11910

Late but Valuable: Why Deadlines Change the Measured Value of LLM Reasoning

Sina Barazandeh, Benjamin E. Lundell, Jose Lugo-Martinez

原文摘要

Large language models (LLMs) increasingly plan and run experiments in automated laboratories. These experiments keep running while the model reasons and run on schedules with hard deadlines. If an LLM-generated answer arrives late, the system executes a safe fallback action instead, such as rejecting a sample. This creates a systems problem that standard serving metrics do not capture. An answer that matches the fallback adds no value, and answers that differ from the fallback may require more reasoning time. Reporting answer quality and latency separately can therefore overstate the value of reasoning. We test this on synthetic sample decisions, where the best choice is known exactly and a runtime enforces the deadline. We compare one LLM's fast mode, which answers directly, with its thinking mode, which reasons first. In a prespecified replay of 1,200 new decisions, thinking answers that missed a deadline were worth about five times as much as on-time ones. Multiplying the on-time rate by the mean answer value predicted about twice the value that thinking delivered. This prediction overstated thinking's advantage over fast mode by 0.0241 per decision, and by 0.0191 in a repeat on 300 new decisions. Both 95% confidence intervals excluded zero. In a single-GPU Qwen3-8B experiment using simultaneous request bursts, raising the number of requests from 8 to 56 reduced the share of thinking answers that met a 45 s deadline from 79.2% to 1.4%, although total output tripled. Evaluations of LLM agents for laboratories should therefore measure each answer's value and arrival time together and score the action that actually runs.

cs.LG · cs.AI · cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11906

RBA: A Read-out Basis Adapter for Parameter-Efficient Interactive OCTA Vessel Segmentation with SEEM

Jaafar M. Al-Ghabban, Mohammad Reza Mohammadi

原文摘要

Retinal disease monitoring with optical coherence tomography angiography (OCTA) relies on segmentation of vessels and the foveal avascular zone (FAZ). Promptable models such as SEEM (Segment Everything Everywhere All at Once) allow click-based refinement, but without adaptation SEEM segments thin vessels poorly and needs many clicks. Fully fine-tuning its 342 million parameters on a few hundred images is costly and risks overfitting, and parameter-efficient methods such as low-rank adaptation (LoRA) usually adapt only the encoder. Yet SEEM reads every candidate mask from one feature map at quarter resolution, too coarse for vessels one to three pixels wide. This study introduces the Read-out Basis Adapter (RBA), whose read-out branch generates 32 image-specific basis maps at half resolution. Each candidate accesses them through its own vector and a zero-initialised projection, so the model starts exactly as SEEM. The encoder branch, a standard rank-1 LoRA, supplies the information needed to tell arteries from veins. RBA adds 0.47 million trainable parameters. Under simulated error-driven clicks, with the ground truth used only to place them, RBA outperforms LoRA, Conv-LoRA andAdaptFormer on OCTA-500 3mmlarge vessels. Averaged over three seeds, it reaches an intersection over union (IoU) of 85.16% and a Dice score of 91.93%, 2.90 and 1.72 percentage points above Conv-LoRA. On the 6 mm subset, one run gives margins of 4.35 and 2.76 points. The gain extends to arteries, veins and ROSE-O but not to the FAZ. In SEEM, adaptation capacity pays more at the mask read-out than in the encoder.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11905

On the Global Convergence of Stochastic Adam for Physics-Informed Neural Networks

Yihang Gao

原文摘要

The Adam optimizer is widely used to train neural networks with highly nonlinear and nonconvex objective functions. Remarkably, Adam often drives the empirical training loss nearly to zero. This phenomenon has been partially explained by neural tangent kernel (NTK) analyses of gradient descent (GD) and stochastic gradient descent (SGD). However, analyzing Adam presents additional challenges. Its first-moment momentum couples stochastic gradients across iterations, while its adaptive second-moment preconditioner depends on the same stochastic gradient used in the update. In this paper, we establish linear convergence guarantees for Adam in training sufficiently wide two-layer neural networks with either full-batch or minibatch gradients. For full-batch Adam, we construct a Lyapunov function to control the effect of historical momentum. For minibatch Adam, our analysis builds on an exact virtual-iterate representation, a conditional analysis of the dependence between stochastic gradients and adaptive preconditioners, and uniform concentration bounds for the second-moment estimates. We prove geometric decay of the empirical loss for full-batch Adam and geometric decay in restricted expectation on a high-probability event for minibatch Adam. Beyond regression, we extend our convergence analysis to physics-informed neural networks (PINNs) for solving the Poisson equation, where differential operators and separate sampling of interior and boundary points introduce additional challenges. We establish analogous global convergence guarantees for both deterministic and stochastic Adam under explicit conditions on network width and Adam's parameters, characterizing the effects of minibatch size on convergence. These results help bridge the gap between Adam's empirical success and its theoretical understanding, providing sharper convergence guarantees for PINNs than existing analyses.

cs.LG · math.NA · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11902

Spectral Unlearning: Transformer Structure-Preserving Updates for Language Models

Sung Il Choi, Junhao Cai, Dohun Kim, Changhee Joo

原文摘要

Machine unlearning in large language models (LLMs) aims to remove specific learned knowledge, capabilities, or behaviors while preserving model utility. Existing methods have mostly focused on the design of unlearning objectives, while largely overlooking the intrinsic matrix structure of transformer weights. In particular, standard optimizers operate on independent scalar coordinates, thereby ignoring this matrix structure. We propose spectral unlearning, an update framework that combines standard unlearning objectives with matrix-structured optimization. We show that the spectral update corresponds to the steepest-descent direction for transformers composed of linear layers with normalized inputs and outputs. Our approach is applied on top of existing unlearning methods and evaluated across complementary axes of memorization, privacy, and utility, summarized via their harmonic mean. Spectral unlearning consistently outperforms a broad range of baselines and closes most of the gap to a retain-trained reference. Code is available at https://github.com/unlearn-ml/spectral-unlearning/.

cs.LG · cs.CL · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11899

How Far Must a Test Explore? Certifying Composable Read-Write Interfaces from Their Own Random Edits

Jiaxuan Guo, Xingyu Ren, Jingxin Yang, Youran Sun, Haizhao Yang

原文摘要

Random tests of stateful code check laws, like reading back a written value, at states that random writes reach. The laws hold at every state exactly when the code behaves like a record with hidden data, so a pass is taken as evidence. This can fail: the laws can hold at every sample while the code is far from any record. The laws are local, but behaving like a record is global. Self-testing and stability theorems bridge this gap when the query distribution is controlled by the tester or preserved by the tested maps, but here it is generated by the tested writes, which need not be invertible. We ask how far a test must explore. An interface has $m$ binary variables, each with a read and two writes; in a record, reads return their bits and writes set only their bits. Samples are the ends of geometric runs of mean $\ell$ of uniformly random writes from a start distribution; a tester adds its own write chains of depth $d$. The distance is the least, over records with hidden data, of the largest probability that a read or write differs from it at a sample. From one start state, law checks at $O(m^2\log m/ε)$ samples certify, at fixed confidence, any threshold $ε$ after geometric runs of every positive mean, while runs of fixed positive length can pass at distance $1/2$. For the worst start distribution, take $ε=m^{-β}$ with fixed $0<β\le1$. For $d\le cm$ with fixed $c<1/2$, a polynomial budget of samples and writes exists exactly when $\ell=Ω(m)$, where law checks suffice. With no runs, the least depth for this budget is $(1/2+o(1))m$. Counting samples alone, in the worst case at $ε=1/(32m)$ and $d\le m/16$, the critical mean for a polynomial budget is $Θ(m\log(m/d)/\log m)$, by exhaustive search. So one start state needs only law checks, and the worst case at these thresholds needs exploration linear in $m$ if writes are counted.

cs.DS · cs.LG · cs.PL · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11894

Distilling Instructions into Weights: Closed-Form Edits Fix a Robot Policy's Misreading

Ali-Adeeb Abbas, Esmaeil Seraj

原文摘要

Generalist robot policies often fail at one step of a task they can otherwise perform. We ask whether such a failure can be repaired by editing the policy's weights directly, without gradients, training data, or a change to the instruction. Told to put the cube then the banana in the bowl, a zero-shot $π_{0.5}$ vision-language-action policy in RoboLab releases the cube before it reaches the bowl. Replaying 21 of these decisions under rewordings shows that it binds "in the bowl" to the wrong object. Closed-form instruction distillation copies the per-layer effect of an explicit rewording into the language model's MLP weights. On 128 held-out seeds, success rises from 27 to 106 episodes, with 81 fixed and 2 broken ($p=7\times10^{-22}$), while an update of the same size in random directions leaves success unchanged. The edit also lifts two other tasks without detectable harm on the remaining 13, and a variant that stores 0.16% of the parameter count keeps most of its effect. Placed in the action expert or action head instead, the same distillation helps less or not at all. Our released tool reproduced the fix end to end on new held-out seeds, from 8/64 to 36/64. Edits aimed at perception, a missing grasp, contact physics, or the gripper threshold did not help, and of seven blind Claude Opus editors, only the one given the misread instruction produced an edit that passed held-out scoring. These results suggest that weight edits work best when a known-good input already exists to distil. Because reruns with unchanged weights flip about a third of paired outcomes, evaluations should pair seeds, rerun the unedited policy, and confirm gains on held-out seeds.

cs.RO · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13017

Multi-Future Drafting: Mixture Block Drafters for Tree-Verified Speculative Decoding

Haoyu Huang, Jialiang Kang, Linlin Yang, Xiao Yang, Baochang Zhang

原文摘要

Block drafters such as DFlash draft a block of future tokens in one forward pass, and draft trees such as DDTree verify the prefixes ranked highest by the product of the drafter's per-position distributions. Under tree verification, the expected number of accepted tokens is the probability mass the tree covers. We show that a product misallocates it: when the continuation can follow several futures, it splices them into chimeras, prefixes stitched together from different futures that the target never produces, and gives them as much budget as the futures themselves. Barring ties, no product-ranked tree can hold two futures that disagree in $m$ positions without $2^{m-1}-1$ chimeras, however well the drafter is trained, and in practice chimeras make up 27-33% of a 64-node tree. We propose Multi-Future Drafting (MFD), which restores the coupling with a latent variable instead of the chain rule: $K$ learned mode embeddings at the drafter's input draft $K$ coherent blocks in the same pass, and a mixture DDTree lets the verifier pick the future the target takes, losslessly and with $K+1$ extra vectors. On four Qwen targets from 4B to 27B parameters, at batch size 1, MFD reaches up to 7.8$\times$ speedup, 5-8% faster than the best single-mode tree trained identically and, on Qwen3-4B and Qwen3-8B, 9-16% faster than the released DARTree trained on the same prompts.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11892

When Answer Decodability Is Not a Decision: Separating Final-Answer and Imminent-Emission Signals in Chain-of-Thought

Hyojung Han, Jongmin Kim, Seung-Hun Jeon

原文摘要

Answer probes applied to chain-of-thought hidden states are often read as evidence that a language model has already decided its final response. This reading overlooks a competing signal, the candidate the model is about to mention. We introduce emission-controlled dual-target probing (ECDP), which fits the same low-rank reader family separately to the imminent mention and to the final answer at identical positions, with target-specific nulls and thresholds fixed before any fit. On correct DecisionDepth (DD) rollouts in which a distractor is mentioned before the final answer, Qwen3.5-4B decodes the next mention at .966 (null .234) but the final answer only at .221 (null .186), an emission gap of .696 [.648, .744]; Llama-3.1-8B gives .575 [.514, .632]. This pattern is not universal. In a pre-specified evaluation of Qwen3-8B with thinking enabled on held-out MMLU questions, using a full-prefix attention reader over every thinking position, both targets are decodable and the final answer is read far more strongly (mention-minus-answer lift -.398 [-.459, -.336] at layer 22 over 467 questions). Model, task, positions, and reader change together between these settings, and an attempted matched comparison on DD produced no valid statistics because the imminent-mention probe did not train reliably, so we do not identify what reverses the order. On DD, planted-signal controls show that the reader recovers an injected final-answer signal at one tenth of full dose. Answer-candidate decodability is therefore target-relative and protocol-dependent: a strong answer readout does not by itself establish when a model commits, and a probe that fails to train is not evidence that the information is absent. ECDP is a practical control for distinguishing imminent text emission from evidence of a settled decision.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.07732

Efficient Adaptive Data Analysis over Dense Distributions

Joon Suk Huh

原文摘要

Modern data workflows are inherently adaptive, repeatedly querying the same dataset to refine and validate sequential decisions, but such adaptivity can lead to overfitting and invalid statistical inference. Adaptive Data Analysis (ADA) mechanisms address this challenge; however, there is a fundamental tension between computational efficiency and sample complexity. For $T$ rounds of adaptive analysis, computationally efficient algorithms typically incur suboptimal $O(\sqrt{T})$ sample complexity, whereas for arbitrary distributions, algorithms with $O(\log T)$ sample complexity are computationally intractable under standard cryptographic assumptions. In this work, we shed light on this trade-off by identifying a natural class of data distributions under which both computational efficiency and logarithmic sample complexity in $T$ are achievable. We propose a computationally efficient ADA mechanism that attains $O(\log T)$ sample complexity, optimal in its dependence on $T$, when the data distribution is dense with respect to a known prior. This setting includes, in particular, feature-label data distributions arising in distribution-specific learning. As a consequence, our mechanism also yields a sample-efficient (i.e., $O(\log T)$ samples) statistical query oracle in the distribution-specific setting. Moreover, although our algorithm is not based on differential privacy, it satisfies a relaxed privacy notion known as Predicate Singling Out (PSO) security (Cohen and Nissim 2020) whenever the number of its possible update transcripts is polynomial in the sample size. Our results thus reveal an inherent connection between adaptive data analysis and privacy beyond differential privacy.

cs.LG · cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11887

How Many Candidates Does a One-Step World Model Need? A Random-Codebook Account of Nearest-of-m Training on Frozen DINO Tokens

Yong Hwi Song, Keon Myung Lee

原文摘要

One-step stochastic world models avoid the mode averaging of deterministic feature predictors without the tens of network evaluations per step that diffusion and flow matching require. The simplest such objective is nearest-of-m matching (conditional implicit maximum likelihood estimation, IMLE): draw m candidate futures and pull only the one closest to the observed outcome. Recent work conjectures that a small m suffices for feature-space world models and that a strictly proper energy score should replace the hard minimum. We test both claims with one-step world models on frozen DINOv2/v3 patch tokens, using benchmarks whose futures can be enumerated. Under mode-like uncertainty, nearest-of-m with m=16 covers the enumerated futures better than 50-step flow matching (at about 1/30 of its latency), one-step flow generators and an energy-score generator at matched parameter counts, and its rollouts stay on the token manifold where flow rollouts drift. One quantity governs the choice of m: the nearest-of-m objective is the expected distortion of a random codebook of m draws from the generator. This view yields three predictions, recorded before the corresponding runs: (i) memorization of the realized outcome in contexts that never repeat, whose strength is governed by the codebook's miss distortion I(m) rather than its miss probability, and which an energy-score generator does not escape by raising m; (ii) a flattening of mode probabilities with m, matching a known optimum within 0.01; and (iii) under-dispersion on continuous high-dimensional outcomes, which bounds the method on real robot video. Per-step matching on self-rollouts cuts long-horizon error by a third on a stochastic Push-T variant; an ablation separates its manifold and coverage benefits. Planning success does not improve despite accurate risk estimates, a negative result we report with its diagnosis.

cs.LG · cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.06879

Better Protein Function Prediction by Modeling Survivorship Bias

Zhongmou Chao, Poompol Buathong, Ekaterina Selivanovitch, Susan Daniel, Peter I. Frazier

原文摘要

Predicting whether a protein sequence possesses a biochemical property of interest is important for understanding and designing protein functionality. Modern protein sequence databases provide valuable training data for functional prediction, but they exhibit survivorship bias: natural selection favors variants that support organismal survival while eliminating many others before they can be observed, complicating classifier training. This setting motivates positive-unlabeled (PU) learning, which treats observed functional sequences as positive and unobserved sequences as unlabeled rather than nonfunctional. However, existing protein PU methods do not account for cross-sequence heterogeneity in evolutionary accessibility: sequences one nucleotide mutation away from a common variant arise far more readily than distant ones. We introduce PULSE: PU Learning with Surveillance and Evolution, a framework that trains a probabilistic classifier for a target protein function using an evolution-aware observation likelihood. When considering functionality of proteins with high genomic sequence coverage, PULSE combines a probabilistic classifier that estimates whether an amino acid sequence performs the target function with an evolutionary model that estimates the likelihood that its encoding nucleotide sequences emerge and are detected based on mutational accessibility, parental prevalence, and surveillance e!ciency. By coupling these two components, PULSE treats the absence of an evolutionarily accessible sequence as stronger evidence of non-functionality than the absence of one unlikely to arise. Tested on eleven tasks focusing on multiple Spike protein properties spanning five SARS-CoV-2 variants, PULSE ranks first or second on all of them, and achieves the best overall performance among all methods, including standard PU learning, one-class classification methods, and protein language models.

cs.LG · q-bio.QM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11881

When Does Physics Beat Data? Data-Efficient Traffic State Estimation with Amortized PINNs

Anna Lazareva, Alexander Tarakanov

原文摘要

Traffic state estimation (TSE) reconstructs traffic density at unmonitored locations from a sparse set of sensors. Data-driven models work well when sensors are dense but degrade sharply as coverage thins. We show that imposing the Lighthill-Whitham-Richards conservation law as a physics-informed prior makes TSE more data-efficient. On four real corridors (NGSIM, I-80, PeMS04, PeMS08), physics-informed estimators generalise to held-out sensors where data-driven models, including classical and deep kriging, overfit the observed ones. On the two shock-rich corridors the effect is a clear crossover: as more sensors are held out, data-driven models collapse while the physics-informed estimator degrades gracefully, leading the no-physics network by about 26-38% at 85-90% held out and the strongest classical kriging by about 10-21% at 90%. A matched smoothness prior does not reproduce the gain, and an extended Kalman filter on the same LWR model is outperformed on the shock corridors, so the advantage comes from how the conservation law is imposed. Finally, one loss-conditional PINN removes the per-corridor loss-weight search, matching a 20-point search at about 5x lower cost.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.19235

GAE Falls Short in Imperfect-Information Self-Play Reinforcement Learning

Zhiyuan Fan, Gabriele Farina

原文摘要

Competitive multi-agent reinforcement learning in imperfect-information games requires agents to act under partial observability and against adversarial opponents, necessitating stochastic policies. While self-play reinforcement learning with Proximal Policy Optimization (PPO) has achieved strong empirical success, its standard advantage estimator, generalized advantage estimation, suffers from additional variance due to the sampling of stochastic future actions. This variance is amplified in equilibrium self-play because of the stochastic nature of the equilibrium policy and persists even when the critic is exact. We address this bottleneck by introducing $Q$-boosting, a variance-reduced advantage estimator based on a centralized action-value critic, and propose Variance-Reduced Policy Optimization (VRPO), incorporating this new estimator. The algorithm replaces sampled multi-step backups with a multi-step Expected SARSA$(λ)$ trace, computing policy expectations at each step to average out action-sampling noise, while retaining PPO's clipped objective and on-policy actor updates. Empirically, VRPO achieves strong performance in various games: In mid-sized games where exploitability is computable, VRPO lowers the exact exploitability by more than 15% compared to tuned baselines. In Dou Dizhu, it sets a new state of the art over PerfectDou. In Heads-Up No-Limit Texas Hold'em, it posts a positive win rate against Slumbot without any blueprint raise sizes, search, or subgame solving at test time.

cs.LG · cs.GT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11877

Tropical Gaussian Anticoncentration: Optimal Instance-Dependent Bounds for Online Learning in Extensive-Form Games

Ashkan Soleymani, Zhiyuan Fan, Lillian J. Ratliff, Patrick Jaillet, Gabriele Farina

原文摘要

We study the minimax regret of full-information online decision making in extensive-form games. For prediction with expert advice, the optimal regret is $Θ(\sqrt{T\log K})$, where $K$ is the number of experts, or equivalently, the number of normal-form actions. For treeplex strategy spaces, existing efficient algorithms, including KOMWU and online mirror descent with the weight-one dilated entropy regularizer, achieve regret $\mathcal{O}(\sqrt{T\log|\mathcal{V}|})$, where $\mathcal{V}$ is the set of reduced normal-form strategies. We prove that this logarithmic dependence is minimax optimal in the worst-case full-information reward model. The main difficulty is that pure plans in a treeplex are not independent experts: their rewards are correlated through the recursive structure of decisions and observations. To capture this correlation, we introduce tropical Gaussian formulae, recursive Gaussian expressions built from maxima and normalized sums which preserve the variance. The index count of such a formula matches the number of reduced normal-form continuation plans in the corresponding subtree. Our main analytic result shows that every log-balanced tropical Gaussian formula with index count $N$ has Gaussian width $Ω(\sqrt{\log N})$. While a direct approach struggles to recover this lower bound, our proof uses a spherical entropy profile to measure scale-dependent separation among the Gaussian directions, and then applies Turán's theorem and Sudakov minoration to obtain the width lower bound. Applying this result to treeplexes gives an oblivious hard distribution with valid transition outcome and Rademacher terminal rewards, establishing a regret lower bound of $Ω(\sqrt{T\log|\mathcal{V}|})$. This matches known upper bounds up to universal constants and shows that the DilEnt/KOMWU dependence on the reduced normal-form complexity is unavoidable.

cs.LG · cs.GT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.01298

UDT: Reconciling U-Nets and Diffusion Transformers with Data-Adaptive Token Reduction

Junno Yun, Yaşar Utku Alçalar, Mehmet Akçakaya

原文摘要

Diffusion Transformers (DiTs) have emerged as a core architecture in generative modeling due to their scalability and adaptability to multimodal tasks. DiTs comprise isotropic transformer blocks, and learn representations progressively across depth, where the denoising objective drives later layers to focus on fine-detail reconstruction. This results in degraded representation quality and an imbalanced encoder-decoder behavior. Prior approaches such as representation alignment (REPA) mitigate this by encouraging stronger early representations via training regularization. Alternatively, U-Net-style DiT architectures introduce explicit multi-scale encoder-decoder structures for improved convergence. But they build on standard U-Net wisdom via learnable operators for spatial downsampling, which are not well-suited to transformer architectures, introducing inefficiencies and compatibility issues with components such as cross-attention and representation regularization. In this work, we propose UDT, a U-Net diffusion transformer that combines the representation power of DiTs with the encoding-decoding benefits of U-Nets, through data-adaptive token merging for downsampling and upsampling, while preserving the DiT token dimension. Our baseline UDT architecture outperforms existing U-Net DiTs and achieves performance comparable to REPA across all model sizes. Furthermore, using architectural optimization and REPA, UDT outperforms SiT's 7.9 FID at 1400 epochs (w/o CFG) within 40 epochs (~ 40x faster convergence) for XL model size on 256x256 ImageNet. Finally, it achieves strong image generation performance with CFG, reaching FID of 1.38 (320 epochs) with SD-VAE and 1.35 (500 epochs) with VA-VAE, providing a new backbone for DiTs with strong empirical benefits. Code is available at https://github.com/JN-Yun/UDT

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11866

DeFSM: Robust and Efficient Decentralization of Federated Submodular Maximization

Duc A. Tran, Dung Truong, Duy Le

原文摘要

Submodular maximization seeks a small subset best representing a large dataset. In its federated setting, the server is a single point of failure and some clients may be Byzantine. Removing the server raises a trilemma of decentraliza- tion, efficiency, and security. We propose DeFSM, a Byzantine-robust and communication-efficient architecture that replaces the server with a lightweight smart contract and a pool of independent, consensus-free agents. Its aggregation rule, SafeGM, builds on two notions from combinatorial geometry: Tukey depth and safe points (the points lying in the convex hull of the good points wherever the bad points are). SafeGM makes the robust decision on 2D Gaussian random projections, which the contract can compute efficiently, and lifts it back as a convex combination of actual updates. Since lifting loses information, it uses the projected geometric median only when its depth certifies it, and otherwise a Tukey median. The share of bad updates is then bounded only by a count: how many there are, not what they contain. We prove, and confirm empirically, that this bound controls the solution quality. On CIFAR10 and PathMNIST, with up to 30% Byzantine clients and agents, DeFSM never collapses and retains on average about 91% of the quality of the ideal reference, the geometric median at a trusted central server. The geometric median decentralized in its best setting would retain about 96%, but the contract cannot compute it, and so each agent would have to download six times more data, or each client twice as much.

cs.DC · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11862

Are UFOs Real? Introducing Unified Factored Organizers

Thomas X. Sheppard, Alon Albalak, Joel Lehman, Kenneth O. Stanley

原文摘要

Implicit in much research in deep learning is the assumption that if a network achieves low loss, then it must have learned a good representation of its training data. Recent work by Kumar et al. (2025, arXiv:2505.11581) questions this assumption, arguing that networks trained with conventional gradient descent achieve low loss despite learning fractured entangled representations (FER), leaving related concepts disconnected and unrelated concepts entangled inappropriately. Kumar et al. further show that dramatically better representations are possible: a network evolved through an open-ended, human-in-the-loop process learned unified factored representations (UFR) that capture the regularities of the domain far better than a counterpart with nearly identical outputs trained with conventional gradient descent. Inspired by UFR, this paper introduces unified factored organizers (UFOs), networks trained to model regularities in the representations of other networks. A network can then be trained both to achieve low loss on its task objective and to align its representations with the model learned by the UFO. Networks trained with UFOs are shown to learn qualitatively superior representations in an image-regression domain where representations are easily interpretable. To provide quantitative evidence for the impact of UFOs on representation learning, a transformer is trained with and without UFO regularization to grok a modular arithmetic problem set. When combined with weight decay, UFOs can reduce the number of transformer training steps needed to grok by more than 10x relative to weight decay alone. Without weight decay, UFOs can reduce the number of transformer training steps needed to grok by more than 100x relative to an unregularized baseline. If UFOs are real, they suggest a new paradigm where loss functions themselves are trained to learn an effective model of good representation.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11861

Scaling Adaptive Prompt Injection Attacks with Agent Swarms

Alexey Kurakin, Vishal Karande, Alex Bie, Chongyang Shi, Shuang Song, Saeed Mahloujifar, Abdullatif Köksal, Jamie Hayes 等 11 位作者

原文摘要

Prompt injections have emerged as one of the top security risks faced by AI agents today. Early work in prompt injection attacks looked at simple tool-call agents and static attack payloads, and were saturated since mid-2025. As of Fall 2026, human red-teaming may be nearing saturation, especially on the Gemini family of models. In this work, we argue that despite this apparent plateau, prompt injection attacks are still possible and continued effort into prompt injection defense is needed. We design a new synthetic evaluation dataset which uses random non-malicious actions as adversarial goals. Such dataset design helps us to evaluate prompt injection robustness as a model ability to respect instruction hierarchy, and disentangle this ability from model knowledge of security practices. We show that an agentic attacker of increased capabilities can reliably trick model to follow instructions in tool output in our evaluation, even for models previously considered robust on public prompt injection benchmarks such as GraySwan Arena. This shows that current frontier defenses may require proactive, automated red-teaming to remain resilient to increasingly capable adversaries.

cs.CR · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.07246

KG-Neighbor: Knowledge-Guided Neighborhood Construction for Embedding Visualization

Chang Won Kim, Jaewook Lee, Haeun Min, JunNyeong Jeong, Minwoo Sim, Barom Kang, Kyohoon Jin

原文摘要

In embedding visualizations, nearby instances are interpreted as semantically related, although neighborhoods derived from input embeddings may not reflect content relationships. Neighborhood-based dimensionality reduction (DR) methods can propagate this limitation by optimizing layouts from embedding-based neighborhood graphs. We propose Knowledge-Guided Neighborhood Graph Construction (KGN), which represents relational knowledge derived from each instance as a set of knowledge graph (KG) triples. It uses the degree of triple sharing as pairwise semantic evidence to adjust embedding distances and reconstruct the top-k neighborhood graph; neither KG extraction nor neighborhood construction uses class labels. We also introduce IDProfile (IDP), which interprets residual mismatches by independently assessing whether the source content supports the assigned class label and the neighborhood-majority class. Across eight text and image dataset-encoder conditions, we characterize KGN over the full guidance-strength sweep and four KG similarity measures. Across this sweep, the maximum NMI and LT_2D each exceed the corresponding kNN baseline in all eight conditions, with the largest gains reaching 0.68 and 1.35, respectively. The gains and the extent of neighborhood reconfiguration vary across conditions and are larger under encoder conditions with lower kNN baseline scores. The IDP analysis shows that the largest reductions are concentrated in Placement Issue candidates, whereas Label Issue and Unresolved Case instances account for a larger share of the remaining review set. These results indicate that KGN can narrow the evaluated gap between embedding-based neighborhoods and content-supported semantic relations, while IDP shows that a residual mismatch should not automatically be interpreted as a projection failure.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13016

Permutation-Based Pre-trained Model Merging via Reciprocal Orthogonality

Akira Ito, Daiki Chijiwa, Atsutoshi Kumagai

原文摘要

Ito et al. (2026) showed that sufficiently wide, independently trained neural networks can exhibit linear mode connectivity (LMC) with softmax temperature calibration, even without permutation. LMC means that a low-loss linear path connects the models' parameters. This behavior is explained by layerwise exponentially weighted connectivity (LEWC), whereby each merged layer outputs an exponentially weighted sum of the original models' corresponding representations, yielding ensemble-like predictions. However, prior work observed LEWC with substantial widening, such as 8192 units per hidden layer for MLPs and $16\times$ width for VGG-11, raising the question of whether such widths are necessary. We therefore search for permutations that encourage reciprocal orthogonality (RO), which suppresses interference between each model's weights and the other model's representations. This allows both models' computations to coexist in the merged network, promoting LEWC at smaller widths. We formulate the search as independent layerwise quadratic assignment problems and approximately solve their continuous relaxations using Frank--Wolfe. Experiments show that our method facilitates LMC with less width expansion. It also merges models trained on different data distributions, where weight matching, which maximizes weight similarity through permutations, struggles. The merged predictions approximate those of a logit ensemble of the original models.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11856

DeltaForge: A Post-hoc Mixture-of-Experts VLA for Multi-Domain Autonomous Driving

Bingzhang Wang, Mo Poorsartep, Yasaman Esfandiari

原文摘要

Fleets of driving vision-language-action (VLA) models are developed one domain at a time: each operator finetunes a shared base model on private data, producing specialized experts that are costly to consolidate into a single model. Weight merging loses accuracy as heterogeneous domains accumulate, and dense mixture-of-experts routing is prohibitively expensive to combine them. We present DeltaForge, to our knowledge the first post-hoc mixture-of-experts VLA for driving, which consolidates N independently finetuned per-domain models into a single multi-domain model from their weights and a small proxy set alone. When different operators finetune the same base model, their weight updates end up sharing a lot of structure. We exploit this by decomposing all the updates together using singular value decomposition (SVD), splitting each one into a shared part (the same across all domains) and a tiny domain-specific part. The router then only needs to work with those tiny domain-specific pieces, not the full expert weights, which is what keeps the approach efficient. Then two cooperating clip-level blind routers, one over the VLM reasoning experts and one over the flow-matching dynamics experts, are trained from soft labels on the proxy dataset. Across six diverse domains spanning urban, off-road, and highway driving on cars, trucks, and all-terrain vehicles (ATVs), DeltaForge approaches the accuracy of the per-domain experts and surpasses every merging, routing, centralized, and federated baseline at close to single-model parameter and compute cost. Adding a new domain requires only projecting its weight update onto the shared basis with no end-to-end retraining needed. The resulting model also generalizes to domain combinations it was never explicitly trained on.

cs.LG · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11852

Identifiable but Hard to Estimate: Rotation in Equally Spaced Overcomplete ICA

Wenjun Xiao, Yinghao Fang, Hanxin Chen, Sihan Jia, Vince D Calhoun, Yuda BI

原文摘要

How many observations are needed to estimate a common rotation in two-dimensional overcomplete independent component analysis? We study equally spaced mixing columns with known source count, common source law, and column norm. For a fixed non-Gaussian fourth-order Gram-Charlier source law, the rotation is identifiable modulo the column spacing. Yet the sample size for fixed relative angular accuracy grows exponentially with the source count. We characterize this sample size, up to absolute constants, by the reciprocal of the squared Hellinger distance between two rotations separated by half the column spacing. An explicit radially weighted phase estimator attains this scale uniformly over the rotation family, using the observation radius to prevent cancellation in the mean of an angular harmonic. We also determine the exact exponential decay rate of single-observation total variation for the same pair. This gives bounds on the sample size exponent; its exact value remains open. Finally, a noisy binary-source example shows how an exact zero line of the observed characteristic function can have an exponentially small normal derivative.

cs.LG · cs.IT · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11847

Severity-Controlled Prediction Sets for Medication Recommendation

Yu Gu, Zijun Yu, Chi-Kuang Yeh, Xinyu Wang, Ziyang Song

原文摘要

Medication recommendation is a multi-label prediction task. However, existing prediction-set evaluation and calibration methods rely mainly on exact-overlap metrics and therefore treat all missed medications as equally severe, overlooking how closely the prediction set matches them within the medication hierarchy. To address this, we introduce Conformal Severity Control (CSC), a post-hoc framework for calibrating medication prediction sets under hierarchy-aware mismatch severity. CSC uses the Anatomical Therapeutic Chemical (ATC) hierarchy to quantify mismatch severity and controls patient-level severity without retraining the predictor, supporting both average severity and upper-quantile severity for the highest-severity mismatches. Experiments on MIMIC-IV show that CSC tracks user-specified severity tolerances and shifts prediction sets away from distant mismatches toward exact or close matches.

cs.LG · stat.AP · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.08506

Structure is in the zoom: probing neural symmetry through dimensionality scaling

Adil Amin

原文摘要

Scaling exponents of neural dimensionality are read as properties of the code, and used to compare representations and benchmark models against cortex. Yet one recording of 11,311 mouse V1 neurons gives 0.25, 0.30 or 0.35, depending only on how it is subsampled. We show that such an exponent measures the population and the probe together. We split it exactly into a floor, which random subsets of the same sizes give, and a shift, which a declared axis of stimulus classes adds. The usual random-subsample exponent is almost all floor. Stimulus direction lifts the exponent in every grating recording by reading both symmetry sectors of the code: orientation, which repeats every half turn, and direction, which does not. The lift lives in trial-to-trial fluctuations that differ between directions, while the class means, which linear decoders read, pull it down. Two measured terms, how much the classes' fluctuations overlap and how the means sit against them, account for the shift. They give its sign where it changes: in Allen Neuropixels recordings, whose class means mostly raise the exponent, and in macaque V1. In an XY lattice whose classes stay on one orbit, temperature flips the sign as the two terms say, and in GPT-2 the shift ranks the indirect-object circuit's name-mover and backup heads. Reported with its path, its floor and its shift, an exponent says how much structure a probe finds and what carries it. Our open tool, rung, reports all three for any labelled neural recording or language-model layer: https://github.com/adilamin89/structure-in-the-zoom

q-bio.NC · cond-mat.dis-nn · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11839

MOOD: Benchmarking Post-Hoc OOD Detection for Materials Property Prediction

Shirley X. Yu, Amey P. Pasarkar, Adji Bousso Dieng

原文摘要

Out-of-distribution (OOD) detection is essential for deploying machine learning models in high stakes scientific applications, yet methods that flag OOD inputs without retraining the model have been validated almost exclusively on image classification. We introduce MOOD (Materials Out-of-Distribution Detection), a benchmark for evaluating whether these post-hoc OOD detectors transfer to graph neural networks (GNNs) on materials property prediction. MOOD evaluates 15 post-hoc detectors and 2 supervised diagnostic probes across 4 GNN architectures, 5 MatBench tasks, and 15 physically motivated compositional and structural shifts, yielding 264 evaluation settings and over 13,000 AUROC measurements across three encoder training seeds. Our evaluation reveals three key findings. First, current post-hoc detectors perform near chance; all 15 detectors achieve an AUROC around 0.5. Second, detector failures decompose into two regimes: method bottlenecks and encoder bottlenecks. Method bottlenecks arise when supervised probes can separate in-distribution (ID) from OOD samples but unsupervised detectors fail, meaning that the embeddings contain OOD signal that current detectors do not extract. Encoder bottlenecks arise when even supervised probes fail to separate ID from OOD samples, indicating that the relevant shift is not accessible in the frozen GNN representation. Third, when OOD prediction error exceeds ID error, the AUROC of distance-based and density-based detectors correlates with the size of that gap. Collectively, these findings indicate that reliable OOD detection in scientific domains requires representation learning strategies that explicitly preserve OOD relevant signal, particularly for tasks where current GNN architectures encode no extractable signal at all.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11833

Answer or Defer? Testing VLMs' Stated Confidence on Brain MRI

Amir Sabbaghziarani, Parsa Ghazvinian, Sepehr Salem, Sergey Plis

原文摘要

Vision-language models (VLMs) could support medical-image interpretation, but their use requires deciding which interpretations to accept and which images to refer to a clinician. We test whether thresholding stated confidence can retain useful coverage while limiting errors among accepted answers, and how this depends on the population. Eight open-weight VLMs, including two reasoning models, assess 3,888 brain MRI slices from post-treatment glioma patients (BraTS 2024) and healthy volunteers (IXI) for tumor or gross abnormality. BraTS labels are mask-derived; IXI slices are treated as negatives. On BraTS, no threshold selects a nonempty set with at most 5% empirical error for any model, even when chosen retrospectively. This also holds for four models evaluated on a large-lesion, distant-negative subset. At a 10% error budget, Gemma-4-12B retains 24.4% of slices and every other model at most 2.5%. To investigate this limited selection ability, we separate confidence differences between predicted answers from differences within each answer. For four models with available outcome-level summaries, pooled mean confidence differs more between answers than between correct and incorrect responses within each answer. A covariance decomposition explains how this pattern can produce opposite confidence-correctness associations across populations. At a 20% error budget, accepting every "tumor" answer covers more slices than any confidence threshold for two models. These findings caution against using unvalidated stated confidence as a standalone deferral signal and support population-specific validation before deployment. Code is available at https://github.com/amir-sbg/VLM-Answer-or-Defer.

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11827

KKT-Perturbation-Aware Communication for Fully Distributed Online Convex Optimization with Nonseparable Coupling

Zhaoye Pan, Tao Li, Yunjie Guo, Guanpu Chen

原文摘要

Nonseparable costs and coupled constraints in distributed online convex optimization often arise when system performance and operational constraints depend on the joint configuration of all agents and cannot be decomposed into individual contributions. Such nonseparability leads to fully distributed decision-making with challenging partial local information, where each agent evaluates its local primal-dual update using estimated global information via a local belief of the joint action and the shared Lagrange multiplier to be exchanged with neighbors. While the belief consensus established by prior works ensures no-regret learning, exchanging beliefs comprising full-dimensional primal and dual states at every round imposes a communication overhead that scales with both the joint decision dimension and the network size. Existing event-triggered schemes typically activate communication according to state variation or consensus error. Under nonseparable coupling, however, errors of equal magnitude can produce markedly different perturbations after passing through the KKT operator. We therefore propose a randomized KKT-perturbation-aware communication mechanism, where the triggering of each agent's primal and dual communication channels depends on their impact on the KKT operator. The proposed mechanism transfers the adaptive-sampling principle of coordinate descent from allocating computation across decision blocks to allocating communication across information channels: channels with larger estimated perturbations receive greater priority for refresh. Under standard regularity assumptions, the resulting algorithm achieves $O({T}^{2/3})$ expected static regret and $O({T}^{2/3})$ expected cumulative constraint violation. Numerical experiments demonstrate improved learning and constraint-enforcement performance per transmitted bit over belief consensus baselines.

cs.LG

查看论文
arXiv ↗PDF ↗