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

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 16:31 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 16:49 — 2026-11-09 16:49（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：2026-11-09 16:31最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 02:59

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。

18,172 已收录论文15,506 AI 相关4,527 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 18,172 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 16:29（北京时间）
新论文 · v1arXiv:2610.37405

Clearing the FoG: Training KG Agents to Retrieve the Evidence Behind Their Answers

Zongyuan Sun, Shuai Zhao, Yingjun Du, Ke Shu, Ziyue Zhu, Haoran Luo

原文摘要

Large language models (LLMs) can answer many factual questions correctly, but a correct answer is not necessarily a supported one. For an LLM agent, a knowledge graph (KG) plays two roles: as a source of answers, it supplies facts that the model lacks; as a source of evidence, it supplies the supporting triples that make an answer traceable and auditable. However, existing KG agents treat the KG only as a source of answers: their training data carries answers but not evidence, and their training rewards check the answer but not the retrieved evidence, so agents often answer correctly without retrieving the supporting triples. We propose FoG, a framework that trains KG agents to retrieve the evidence behind their answers. FoG consists of evidence-grounded synthesis, a KG interaction agent, and an evidence-coverage process reward (ECPR): the synthesis recursively hides explicit entities behind verifiable sub-questions, so that every question carries its supporting triples by construction; the agent records the triples returned by the KG; and ECPR credits each supporting triple to the turn that first retrieves it. Experiments on three KGQA benchmarks demonstrate that FoG enables 3B--4B open-source agents to outperform substantially larger baselines in answer accuracy and evidence coverage, with zero-shot cross-KG transfer.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2507.16648

An Unconditional Lower Bound for the Active-Set Method in Almost-Linear Programming

Eleon Bach, Yann Disser, Sophie Huiberts, Nils Mosis

原文摘要

We prove that, for every fixed $ε\in(0,1]$, the active-set method requires exponentially many iterations in the worst case to maximize a convex objective of the form $(x_1)^{1+ε}+\vec c^{\top}\vec x$ subject to linear constraints, regardless of the pivot rule used. Our lower bound therefore holds for objectives arbitrarily close to the linear case $ε=0$, where the active-set method coincides with the simplex method and a lower bound for all pivot rules would constitute a major breakthrough. The special case $ε=1$ yields a lower bound in convex quadratic maximization. This improves on the best previously known lower bound [IPCO 2025] requiring polynomial objectives of degree $ω(\log d)$ in dimension $d$ and firmly resolves the open question of whether a constant degree suffices. Our result is based on a novel extended formulation, recursively constructed using deformed products. Its key feature is that it projects onto a polygonal approximation of a parabola while preserving all of its exponentially many vertices. We define a convex objective with a single non-linear variable that forces the active-set method to follow the parabolic boundary of this projection, without allowing any shortcuts along chords corresponding to edges of its full-dimensional preimage.

cs.DM · cs.CC · cs.DS · math.CO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37403

AuRaSim: A Ray-Tracing Based Automotive FMCW Radar Simulator for Dynamic Scenarios

Zhaoze Wang, Changxu Zhang, Tai Fei, Christopher Grimm, Yi Jin, Claas Tebruegge, Markus Gardill

原文摘要

Modern simulators can generate synthetic camera and LiDAR data with accurate annotations for downstream tasks. In contrast, automotive radar simulation remains less mature because it requires not only a 3D engine to model dynamic objects in the scenes but also electromagnetic material properties, antenna configurations, wave propagation mechanisms, and coherent signal synthesis. Existing frameworks are either proprietary or overly simplified, limiting the scalability of radar raw measurements. This paper presents AuRaSim, a ray-tracing-based automotive frequency-modulated continuous wave (FMCW) radar simulation framework for dynamic scenarios. Rather than implementing all components from scratch, AuRaSim builds on Blender for efficient dynamic-scene construction and Sionna RT for graphics processing unit (GPU) accelerated electromagnetic ray tracing, while introducing radar-specific adaptations for path-resolved propagation with complex coefficients, motion-aware Doppler modeling, and subsequently coherent multi-channel analog-to-digital converter (ADC) cube synthesis based on waveform configurations. Quantitative comparison between simulated and measured range-Doppler maps in digital-twin scenarios achieves a root-mean-square error (RMSE) of 0.147 and a peak signal-to-noise ratio (PSNR) of 16.93 dB, demonstrating the accuracy and fidelity of the synthetic signal. AuRaSim therefore provides a complete and extensible platform for reproducible automotive radar simulation and research. Project homepage: https://wangzhaoze.github.io/aurasim.

cs.RO · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37398

An end-to-end framework for uncertainty-aware validation of generative models

Giada Badaracco, Sean Benevedes, Christina Reissel, Philip Harris, Gaia Grosso

原文摘要

Density estimation with generative models is a common task in the physical sciences, for example in background estimation in particle physics. Existing machine learning techniques, however, lack methods to quantify uncertainties that can be propagated into a statistical test. That limits the validation of generative models to standard goodness-of-fit tests, in which the generative model is treated as exact (point-null hypothesis). But a model fitted to a finite training set is never exact, so if its uncertainties are neglected, any sufficiently powerful goodness-of-fit test will eventually reject it once the test set is large enough to resolve this estimation error. We propose SIGMA, an end-to-end framework combining density estimation with principled uncertainty quantification. We use Gaussian mixture models, for which uncertainties are tractable, and further construct a new goodness-of-fit test in which these uncertainties are profiled as nuisance parameters to account for the statistical error of the fit, promoting the conventional point-null test to a composite one. A rejection then signals genuine mismodeling rather than a test set large enough to resolve the error of the fit, provided the propagated uncertainties faithfully cover that error. We demonstrate the framework on a controlled two-dimensional toy model and on a collider physics benchmark modeling the QCD background process. With uncertainties included, the same model can be trusted on test sets up to an order of magnitude larger than the standard test allows. Our work thus provides a statistically grounded basis for a robust use of generative models in the physical sciences.

stat.ML · cs.LG · hep-ex · hep-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37397

Game-Theoretic Solvers with Bayesian Opponent Modeling and Moral Rhetoric Framing for GLEE

Hayden Arnold

原文摘要

We describe the agent we submitted to the GLEE Competition, which plays bargaining, negotiation, and persuasion games against a shared pool of human and AI opponents. The agent is built around three central components: a classical game-theoretic solver to compute numeric moves, an online Bayesian layer to estimate opponent archetypes, and a language model to write accompanying messages. We utilize Rubinstein bargaining for bargaining, Faratin concession for negotiation, and Kamenica--Gentzkow disclosure for persuasion, and adapt those models to live opponents using two separate layers: a Bayesian estimate of the opponent's hidden discount factor, reservation value, or signaling reliability, and a Thompson sampling bandit over five moral-foundation framings coupled with an evidence-intuition spectrum to establish message register. Most of the development effort went into the recurring problem that theoretically optimal policies perform poorly in certain live settings; we report associated failure modes, guardrails we built, and our hypotheses. We additionally evaluate our model over 13,200 Monte Carlo games against 11 synthetic opponent archetypes, an ablation of the opponent-modeling layer, and an extensive analysis of 9,337 live-game messages in which moral rhetoric framing in the persuasion setting is strongly correlated with whether the buyer purchased ($χ^2=616.7$, $p \approx 3.7\times10^{-132}$), surviving controls for quality, round, and configuration.

cs.GT · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37395

Code uniqueness of 4-cell connected disjoint clusters in spatial chromatic model

Weining Zhu

原文摘要

The spatial chromatic model (SCM) is a novel entity-oriented spatial data model proposed in recent years. Spatial tessellations formed by SCM have been applied in preliminary analyses of spatial point pattern recognition,spatial topology, and Voronoi diagram generation. Unlike previous spatial tessellation models, a key feature of SCM is that each subspace (cell) possesses a chromatic code, which serves as the foundation for various theoretical analyses and applications of SCM. The uniqueness of cell cluster codes in SCM constitutes an important property of the model. Previous studies have demonstrated the uniqueness of the chromatic codes of 2-cell and 3-cell connected disjoint clusters. Building on this analysis of connected cluster code characteristics, this paper proves the uniqueness of the chromatic codes of 4-cell connected disjoint clusters. The proof results and the new concepts introduced in this study help further refine the spatial chromatic model and provide a theoretical foundation for its subsequent applications.

cs.CG · cs.IT · math.CO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2502.04309

Targeted Learning for Inference on Data Fairness

Joseph H. Rudoler, Alexander Asemota, Giles Hooker

原文摘要

As algorithmic decision making has become increasingly ubiquitous even in high-stakes settings, significant effort has been invested in defining, detecting, and eliminating unfair model-driven outcomes. Prior work has largely focused on estimating the fairness properties of a given predictive model, and quantifying uncertainty based on variability in a fixed model's performance across evaluation datasets. Alternatively, we can also ask about uncertainty that the model inherits from its training data; here we evaluate data fairness - fairness in the data generating process used for training. We perform inference on data fairness using targeted learning, a flexible framework for nonparametric inference, and derive estimators for demographic parity, equal opportunity, and conditional mutual information. Simulations show that our data fairness estimators improve confidence-interval coverage and reduce false detections of population unfairness relative to fixed-model inference. We also demonstrate their application to real data.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37393

Learning Quality-Controllable Robot Policies with Iterative Hindsight Relabeling

Sinjae Kang, Dong Kyu Shin, Jaehong Kim, Kamin Lee, Hyoeun Kim, Kaixin Wang, Li Zhao, Seonghyeon Ye 等 9 位作者

原文摘要

Robot policy evaluation often relies on a binary success signal for task completion. In real-world deployment, however, desired execution behaviors are also defined by quality attributes such as execution speed and motion smoothness, which need to be dynamically controlled according to task requirements. To address this, we introduce Quality-Controllable Policy (QCP), a robot policy that enables inference-time control over both individual quality attributes and their combinations. To extend the controllable quality range beyond initial demonstrations, we further propose an iterative hindsight relabeling loop: QCP collects online rollouts under target quality labels, adds successful trajectories to the dataset, relabels the accumulated trajectories in hindsight according to their measured quality, and fine-tunes the policy. Experiments on Robomimic and RoboEval demonstrate that QCP consistently improves both task execution quality and success rates across iterations, producing successful rollouts that exceed the quality of the initial demonstrations. Finally, we validate QCP on real-world manipulation tasks, where controlling speed increases throughput in conveyor operations and controlling transport stability improves success when carrying wine glasses, demonstrating that quality-controllable policies yield practical gains in physical deployment.

cs.RO · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37391

JEPA-Inspired Latent Field Prediction for Sparse-Pilot MIMO-OFDM Channel Reconstruction

Yuzhi Yang, Brahim Mefgouda, Hang Zou, Lina Bariah, Anis Bara, Yuhuan Lu, Hao Zhang, Merouane Debbah

原文摘要

Accurate acquisition of full channel state information (CSI) is essential for multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) wireless systems, while dense pilot-based estimation incurs substantial overhead. Directly minimizing the prediction error over raw CSI coefficients is fragile in realistic propagation environments, since small-scale fading, mobility, local scattering, and small spatial perturbations can induce large phase-sensitive variations. Nevertheless, wireless channels contain strong spatial, temporal, and frequency-domain correlations that can be more predictably represented in a latent propagation-field domain. Motivated by this observation, we propose a joint-embedding predictive architecture (JEPA)-inspired field world model, defined as a latent predictive model of the wireless propagation field, for sparse-pilot channel reconstruction. The model maps CSI observations into latent time-frequency tokens, predicts masked or future latent field states from historical multi-band context, and fuses the predicted latent prior with sparse noisy current pilots to reconstruct the full MIMO-OFDM channel. Ray-tracing experiments show that the proposed method improves normalized mean square error (NMSE) over pilot-only and direct reconstruction baselines, supporting latent field prediction as an effective prior for sparse-pilot channel acquisition.

eess.SP · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37390

LinMix: Data Mixing as Linear Domain Attribution

Hubert Baniecki, Przemyslaw Biecek, Martin Pawelczyk

原文摘要

Language model performance depends strongly on the mixture of domains in the pretraining data corpus. Popular data mixing methods select these domain weights by training many small proxy models on random mixes and then fitting a regression model to predict performance from the mix. We recognize this practice as a domain attribution problem, where the regression measures each domain's contribution to the target metric. Through this lens, the standard Dirichlet sampling of proxy data mixes is a poor regression design that requires tuning and cannot support a linear fit for hundreds of domains. Building on classical optimal experimental design, we introduce LinMix, which samples mixes at the vertices of the capped simplex so that each domain is at its cap or absent. This hyperparameter-free vertex sampling decorrelates domain effects, enabling an interpretable linear model whose coefficients are the domain attributions. The optimal mix given by LinMix provably keeps only domains with positive attribution values and requires no search over candidate mixes. We further establish the optimality of vertex sampling, and prove that Dirichlet sampling inflates the attribution error when its mixes concentrate around the prior data mix. Pretraining experiments with 1B-parameter OLMo2 and 4B Qwen3.5 language models show that LinMix outperforms Dirichlet-based data mixing across reasoning, code, and math benchmarks, with relative gains of 46% on MBPP and 14% on GSM8K. At 288 fine-grained domains, only vertex sampling supports a linear fit, and LinMix improves benchmark accuracy by 11% on average over the best nonlinear baseline.

cs.LG · cs.CL · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37389

How Many and How Much? Contrastive Learning with Negative Samples for Knowledge Graph Embedding

Sooho Moon, Yunyong Ko

原文摘要

Knowledge graph embedding (KGE), a fundamental technique for knowledge-centric Web and KG-augmented AI applications, is commonly trained through contrastive learning with negative samples to learn discriminative representations. Despite its empirical success, two crucial questions regarding negative samples remain underexplored: (Q1) how many negative samples should be used for each positive sample and (Q2) how much should each negative sample contribute to learning? To answer these questions, we propose RADAR, a novel contrastive learning framework for KGE models with two effective strategies, respectively: (1) Risk-aware negative budget allocation quantifies false-negative sampling risk by modeling an open-world KG as a stochastic partial observation of its closed-world counterpart and adaptively assigns a negative budget to each positive sample based on its risk; (2) Distribution-calibrated negative weighting assigns negative weights by calibrating the weighting strength for each positive based on two complementary characteristics of the negative-score distribution: dispersion and concentration. Extensive experiments on 3 real-world KGs with 4 KGE models reveal that RADAR achieves the best KGE performance on average across all model--KG combinations and reduces sampled false negatives by over 90% compared with conventional fixed-budget methods.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37388

Para-Gaussian Approximations of Random Deep Neural Networks

Mihai Nica, Janosch Ortmann

原文摘要

It is known that randomly initialized neural networks have Gaussian behaviour in the $n\to \infty$ limit. Unfortunately, this approximation can be poor for finite $n$ and gets worse as one goes deeper into the network. In this work, we develop a more accurate approximation that is \emph{slightly} non-Gaussian, which we call the para-Gaussian distribution and is constructed from the Hermite polynomials. We show how this para-Gaussian approximation can lead to a practical recursive method to approximate the deeper layers of the network. Finally, we apply this theory to linear neural networks (where things can be solved exactly) and to ReLU neural networks (where things can be approximated).

cs.LG · math.PR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37386HF 社区推荐

Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data

Geunhyoung Kim, Sung Ju Hwang

原文摘要

Mixture-of-Experts (MoE) models are bottlenecked by loading routed-expert weights from memory during interactive decoding at small batch sizes. Because most intermediate channels in a routed expert contribute little to any single token, channel selectors predict which channels matter and read only their weights, typically keeping channels above a threshold calibrated on offline data. We show that channel selection needs no calibration data. First, a calibrated threshold does not fix how much a selector reads, because the number of channels passing it varies across inputs; Prox with thresholds calibrated for an 18% read budget actually reads only 12.9% on average across our benchmarks. Second, top-k keeps each token's k highest-scoring channels and needs no calibration data. At the calibrated budget, a selector's top-k version matches or beats its threshold version on the same score in 40 of 43 comparisons at 13% and 18% budgets, including all 23 on generation tasks. The top-k versions also avoid the repetition-loop collapse that calibrated thresholds cause on Gemma 4. Calibrating a threshold thus provides neither of the two things selectors use it for: a known read budget and a consistent accuracy gain at that budget. We furthermore introduce a reader built entirely from the model's weights, which screens channels with a ternary sketch and recovers the skipped ones with a low-rank map. Across three post-trained MoE models, our reader retains 98.1% of full-model accuracy at 17.8% of routed-expert reads, with Triton kernels running MoE blocks 1.60 to 1.90x faster than optimized vLLM at batch one and up to 2.69x at larger batches on the same three models.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.18007

Semantic Reranking at Inference Time for Hard Examples in Rhetorical Role Labeling

Anas Belfathi, Nicolas Hernandez, Laura Monceaux, Warren Bonnard, Richard Dufour

原文摘要

Rhetorical Role Labeling (RRL) assigns a functional role to each sentence in a document and is widely used in legal, medical, and scientific domains. While language models (LMs) achieve strong average performance, they remain unreliable on hard examples, where prediction confidence is low. Existing approaches typically handle uncertainty implicitly and treat labels as discrete identifiers, overlooking the semantic information encoded in label names. We introduce RISE, an inference-time semantic reranking framework that leverages label semantics to refine predictions on hard instances. RISE automatically identifies low-confidence predictions and reranks model outputs using contrastively learned label representations, without retraining or modifying the underlying model. Experiments on eight domain-specific RRL datasets with seven LMs, including encoder-based and causal architectures, show an average gain of +9.15 macro-F1 points on hard examples. For explainability, we further propose manual hardness annotations to study difficulty from both model and human perspectives, revealing a moderate agreement with Cohen's kappa = 0.40.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37380

Same Verdict, Different Readers: Personalizing Fact-Checking Explanations from Relative Preferences

Haokun Wen, Xuemeng Song, Mong-Li Lee, Wynne Hsu

原文摘要

Fact-checking explanations help Web users understand why a claim receives its verdict, yet the same explanation may not satisfy readers with different backgrounds and preferences. We formulate Faithful Personalized Fact-Checking Explanation Rewriting, which adapts an existing explanation to individual readers while preserving factual fidelity. Rather than relying on reader-written reference explanations, we learn personalized rewriting from the relative preferences of LLM-simulated readers. However, this presents two challenges: distinguishing persona-specific preferences from general explanation quality and learning beyond a limited set of predefined explanation styles. To address these challenges, we propose Personalized Explanation Rewriting via Preference Learning (PERPL), a framework consisting of two components. Simulated Preference Construction derives persona-specific supervision from simulated reader preferences through cross-persona reciprocal pairing. Progressive Preference Learning first trains a lightweight rewriter on the constructed supervision and then refines it through exploration-guided preference optimization, enabling it to discover preferred explanations beyond the predefined styles. Extensive experiments demonstrate that PERPL outperforms much larger general-purpose LLMs in personalized preference alignment while maintaining high factual fidelity.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37379

Decomposing Directed Graphs into Partial Orders is Hard

Grzegorz Gutowski, Dominik Jilg, Antonio Lauerbach, Mikołaj Rams

原文摘要

Comparability graphs represent partial orders and provide natural building blocks for representing a graph as a union of simpler graphs. The analogous task in the directed setting is to represent a digraph as a union of partial orders. Aboulker et al. [arXiv, 2026] recently introduced the partial order decomposition number as a useful structural parameter in their study of tournaments. Formally, a partial order decomposition of a digraph $D$ is a cover of its arc set by transitive acyclic subdigraphs, each representing a strict partial order on the vertex set of $D$. The partial order decomposition number is the minimum number of such subdigraphs needed. We also consider the partitioning variant, in which every arc belongs to exactly one of the partial orders in the decomposition. We prove that, for every fixed $k\geq 2$, deciding whether a digraph admits a decomposition into at most $k$ partial orders is NP-complete, even for directed acyclic graphs (DAGs). For $k=2$, we reduce from NAE-3-SAT. For $k\geq 3$, we reduce from $k$-Coloring, and the reduction yields DAGs with triangle-free underlying graphs. Both reductions establish hardness for both variants. We further show that the minimum cover size and the minimum partition size can differ even on DAGs.

cs.CC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37378

VLA-Stem: A Lightweight Safety Mechanism for Vision-Language-Action Models via Reinforcement Learning

Bojun Zou, Wenhao Yu, Jiaohao Li, Jiaxuan Lin, Guanting Ye, Haohan Geng, Weihao Yu, Yanyong Zhang 等 9 位作者

原文摘要

Vision-Language-Action (VLA) models integrate high-level reasoning with low-level action execution for end-to-end robotic control. However, most VLA models target static manipulation in unconstrained environments, overlooking spatial constraints and dynamic obstacles. Fine-tuning VLAs on obstacle-avoidance data is a straightforward solution, but collecting such data is costly, especially for dynamic scenarios, and may degrade their original task capabilities. To address these limitations, we propose VLA-Stem, a lightweight, reinforcement-learning-based safety mechanism for VLA systems. Without fine-tuning the underlying VLA policy, VLA-Stem converts its action chunks into motion references and uses trajectory-level guidance to preserve their spatial intent while allowing flexible motion and timing adjustments. Conditioned on these references, robot proprioception, and local obstacle information, the Stem policy adaptively modifies execution at inference time, preserving the original task intent while enabling responsive adaptation to spatial constraints and dynamic obstacles. For robust and sample-efficient training, we combine teacher-student distillation with curriculum learning. We evaluate VLA-Stem on reference following, static spatial constraints, and dynamic obstacle avoidance. Across six constrained simulation settings, VLA-Stem achieves 52.8% average collision-free task success versus 23.7% for the strongest safety baseline, while preserving base-policy performance in obstacle-free settings; real-world experiments further show consistent collision reductions under static and dynamic obstacles. These results demonstrate that VLA-Stem couples high-level VLA task intent with rapid, reflex-like responses to immediate physical risks, providing a brainstem-inspired mechanism for robust robot execution.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33460

Semantic-First: Temporal Scheduling in Flow Matching for Reliable Emotional Image Generation

Zhenxuan Wang

原文摘要

Affect-controlled image generation should change how a scene feels while preserving what the prompt specifies. We study the temporal allocation of stochastic exploration and policy optimization in flow-matching models as a means of controlling this balance. During RL training, our semantic-first schedule uses deterministic ordinary differential equation (ODE) sampling during the high-noise phase and confines stochastic differential equation (SDE) exploration and group relative policy optimization (GRPO) to a late window. Controlled experiments separate exploration location, optimization location, and terminal-step sampling, showing distinct semantic benefits from late exploration and late updates. On FLUX.1-dev, semantic-first improves prompt faithfulness, independently evaluated affect accuracy, and human-rated semantic preservation and overall preference. The expanded semantic audit records 2.7% subject drift, while GRPO training time decreases by 41.1% relative to original full-path Flow-GRPO. Window-width experiments characterize the affect-semantic and computational trade-offs, and replication on SD3.5-Medium reproduces the scheduling advantage. These results establish denoising time as a practical control dimension for reliable emotional image generation.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.10697

A Better Analysis For PPSZ For 3-SAT

Tao Jiang, Shaowei Cai

原文摘要

The PPSZ algorithm of Paturi, Pudlák, Saks, and Zane solves 3-SAT by processing the variables in a uniformly random order, setting a variable whenever a bounded number of clauses implies its value, and guessing it otherwise. Its running time is determined by how many variables are forced in this process, and the exact exponent is a central question in the study of exponential-time satisfiability algorithms. Scheder showed that the classical analysis of PPSZ is not tight for 3-SAT. We ask how much further a sharper analysis of the unmodified algorithm can go. Our analysis uses auxiliary distributions on variable orderings that correlate the positions of variables sharing critical clauses. Such correlations make forcing more likely for some variables, can make it less likely for others, and incur an entropy cost. We choose the correlated pairs at random on short components, so that every pair is selected with the same probability, and we express the forcing loss as a sum of weights attached to these pairs in advance. Gains and losses then scale by the same factor and can be compared directly. Combining the resulting estimate with the complementary estimate of Scheder through an explicit linear-programming certificate gives a uniform improvement for every uniquely satisfiable formula. We prove that the original PPSZ algorithm, with a sufficiently large but fixed implication strength, solves Unique-3-SAT in randomized time $O^*(1.306969598^n)$. Through the lifting framework of Scheder and Steinberger, it solves general 3-SAT in randomized time $O^*(1.307031578^n)$. Both bounds improve the guarantees obtained from the analysis of Scheder for the same algorithm. These improvements follow entirely from the analysis, while PPSZ continues to use a uniformly random variable order and unbiased guesses. It shows that the known guarantees for PPSZ can be strengthened by analysis alone.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37375

Agent-Conditioned Routing: Diverse Reasoning Paths Within One Frozen Model

Ananth Kalyanasundaram, Ankush Kadu, Athira Gopal, Aswanth Krishnan

原文摘要

Generating several solutions can expose alternative methods, but additional trajectories often paraphrase one dominant approach. We investigate whether the conditional capacity of a frozen sparse mixture-of-experts (MoE) model can provide such diversity from one problem prompt, without user-assigned roles, prescribed methods, fine-tuning, or model copies. Agent-Conditioned Routing (ACR) assigns $m$ parallel trajectories persistent, untrained shared/private expert-eligibility masks while preserving the learned, input-dependent token router. On a screened 126-question multi-mode mathematics and physics benchmark, with model judges reading the reported derivations in full, we count the number of problems yielding at least two distinct primary methods among soft-correct solutions in four trajectories. ACR reaches approximately twice as many such problems as the strongest temperature setting under GLM 5.3 (37.3 versus 18.7), and 1.67 times as many under GPT-5.6 Sol (45.00 versus 27.00), at matched output budgets. A blinded four-expert audit on a stratified sample of 30 problems also finds more multi-method solutions with ACR on both backbones, with lower correctness. Matched-eligibility ablations show modest multi-method count advantages for ACR, while token-resampled masks attain higher correctness. An informed sequential prompt elicits more diversity still, using previous solutions and explicit requests for alternative methods. ACR adds about 160 KiB of mask state. In a three-problem microbenchmark capped at 1,024 tokens, its latency and peak VRAM usage remain within 3% of batched temperature sampling.

cs.AI · cs.LG · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37374

Comparing Temporal Deep Learning Architectures for Discrete Cross-User Myoelectric Control

Ethan Eddy, Evan Campbell, Scott Bateman, Erik Scheme

原文摘要

The recognition of dynamic gestures via discrete myoelectric control is becoming an attractive input modality for event-based human-machine interaction. While recent work suggests that discrete cross-user models are possible (i.e., no calibration data is required from the end user), few have evaluated techniques to optimize these systems and their generalizability to new randomly prompted data simulating real-world discrete control is relatively unknown. Using the 612-user EMG-EPN dataset, this work benchmarks five temporal deep-learning approaches, evaluates the tradeoff between performance and model complexity, and compares hand-crafted and machine-learned feature extraction techniques. The CNN-GRU achieved the best accuracy of 93% when tested on 184 previously unseen users. These models were then evaluated on a different, more realistic, unsegmented dataset, wherein users were randomly prompted to elicit discrete gestures during a continuous data collection. This dataset was recorded five years apart and in a separate country from the data used to train the original model. Results show that the cross-user results scale to this new dataset (accuracies of 96%) even though no feedback was given to users during the elicitation of gestures. These findings highlight the exciting potential of discrete zero-shot cross-user myoelectric control and offer valuable insights for the continued advancement of this promising technology.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37373

Euclidean Crowding-Driven Adaptive Euclidean-Hyperbolic Graph Learning

Hao Chen, Jian Sun, Chuan Shi, Hongying Zhang

原文摘要

Hyperbolic graph representation learning has emerged as a powerful paradigm for modeling hierarchical data. Unlike Euclidean space, which exhibits polynomial volume growth, hyperbolic space grows exponentially with radius, naturally accommodating tree-like structures without the geometric distortion known as Euclidean crowding. Despite strong empirical performance, the theoretical mechanisms underlying hyperbolic embeddings remain poorly understood. In this work, we provide a geometric quantifcation research for Euclidean crowding, a generalization-theoretic explanation for the superiority of hyperbolic space on hierarchical data, and further develop an adaptive Euclidean-hyperbolic fusion learning framework toward bridging this gap. Specifically, we \textbf{first} establish a geometric quantification of Euclidean crowding by analyzing layer-wise minimum separation in node embeddings, proving that fixed-dimensional Euclidean embeddings of tree-like graphs inevitably exhibit layer-wise crowding that leads to weaker margin-based generalization bounds. \textbf{Second}, we provide a generalization-bound for the superiority of hyperbolic geometry on hierarchical data. \textbf{Third}, we propose EH-Fusion, a geometry-adaptive framework that lifts Euclidean GNN representations into hyperbolic space via exponential mapping and adaptively fuses both geometries based on node-level neighborhood expansion patterns. Extensive experiments validate our theoretical insights and demonstrate the effectiveness of EH-Fusion on benchmark datasets.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37370

The Geometry of Manifold Learning: Singular foliations via Deep Learning models

Gabriele Novelli, Eliot Tron, Emanuele Latini, Rita Fioresi

原文摘要

Deep learning algorithms have become widely used and successful across a wide range of tasks. A key challenge is determining whether these algorithms truly capture the intrinsic geometry of their training data in order to better understand what they learn from data. In this theoretical work, we explore a new geometric structure defined on the data space by a trained neural network through the Data Information Matrix (DIM), a variation of the Fisher Information Matrix. This new geometric structure is a foliation and the main focus of this work is to explore the non-smooth case of ReLU activation functions, where traditional geometric tools often fail. The foliation is defined through a distribution spanned by the columns of the DIM. We first prove that this distribution is non-smooth in the sense of distributions, rendering the existence of an associated foliation much more complex. To circumvent this issue, we introduce a smoothed version of this distribution that differs from the original only on a set of measure zero. Finally, we prove that this smoothed distribution induces a singular foliation on the data space, which is based on the data the network has been trained with. Our theoretical contributions provide a geometric framework to better understand how neural networks organize their input space in non-smooth settings, bridging differential geometry and deep learning theory.

math.DG · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37364HF 社区推荐

EmbeddingGemma 2: Unified and Efficient Multimodal Representations

Henrique Schechter Vera, Sahil Dua, Jovan Andonov, Sara Smoot, Sebastian Russo, Ivan Llanos, Max Matveev, Jae Hyeon Yoo 等 73 位作者

原文摘要

We present EmbeddingGemma 2, an open multimodal embedding model which natively represents text, images, audio, video, and combinations thereof in a unified space. Our approach introduces improvements such as simplified per-layer embeddings and a multi-stage curriculum with modality and objective progression which ensure strong quality across unimodal, cross-modal, and mixed-modal evaluations. Notably, in comprehensive embedding benchmarks across all modalities, EmbeddingGemma 2 establishes a new Pareto frontier, outperforming both specialist models and models two to twelve times larger. Furthermore, our design offers flexibility for resource-constrained environments, supporting selective modality encoder loading, adjustable vision token budgets, truncatable embedding dimensions, and quantized weights. We present ablations analyzing key decisions and release EmbeddingGemma 2 to promote further research.

cs.LG · cs.CL · cs.CV · cs.SD

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.02343

Hard Constraints, Smooth Gradients: Learning Feasible Inventory Policies via Differentiable Projection

Patrick Helm, Jan-Niklas Doerr, Joren Gijsbrechts, Stefan Minner

原文摘要

Many operational problems are constrained sequential decision processes with combinatorial action spaces and interdependent constraints. Mixed-integer linear programs (MILPs) handle such constraints flexibly but scale poorly in stochastic environments. Deep reinforcement learning (DRL) promises scalable decision rules, but existing methods either penalize constraints rather than enforce them, or rely on feasibility mechanisms that break down once constraints interact. We bridge this gap by embedding a differentiable optimization module inside the policy: a neural network proposes continuous action targets, a quadratic program projects them onto the relaxed feasible set, and a dual-informed integer mapping restores integrality while preserving feasibility. Given a differentiable simulator, the policy trains end-to-end from sampled trajectories using pathwise gradients, while handling hard constraints with similar flexibility to MILPs. We show that our approach has bounded error relative to an exact integer projection and ensures the entire feasible action space is reachable. We apply the method to multi-echelon production-inventory planning under shared resource and material constraints. Our policy attains an average optimality gap of 1% on 3-item instances and consistently outperforms a rolling-horizon multi-stage stochastic program by at least 5.6% in 10-item networks. Compared to state-of-the-art echelon base-stock policies, savings reach 15.3% on 40-item instances. On an industry-scale case study with nonstationary demand from ASML, we reduce average cost by up to 1.8% relative to the best-known benchmark policy. The savings are largest where planning is hardest: in tightly capacitated systems with high demand variability. More broadly, we show that DRL can improve upon state-of-the-art baselines in sequential decision problems with hard constraints, which are widespread in practice.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37737

Anisotropic Trust Region Warping for Prior-Data Fitted Networks in Bayesian Optimisation

Samuel Younger, Tinkle Chugh, George De Ath

原文摘要

Prior-Data Fitted Networks (PFNs) replace the hyperparameter refitting of Gaussian Process (GP) surrogates in Bayesian optimisation with a single forward pass, at the cost of a prior that is fixed at meta-training time. We show empirically that a PFN's predictive log-likelihood falls increasingly behind that of a refitted GP as the objective function's lengthscale grows beyond the mode of the PFN's meta-training prior, and that this deficit carries over to optimisation performance. To correct the mismatch without retraining the network, we introduce Anisotropic Trust Region (ATR) warping. Per-dimension lengthscales are estimated by kernel target alignment, and an affine rescaling of the input space maps the objective onto the lengthscale the PFN expects, with a trust region around the anchor determining which observations are retained, leaving the PFN's $\mathcal{O}(d \cdot N^2)$ inference cost unchanged. On functions drawn from a Matérn-3/2 kernel, ATR warping improves optimisation performance of the PFN at both extremes of the lengthscale range. Our implementation is publicly available at https://github.com/youngers2006/Trust-Region-Warping-For-PFNs.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37361

Online Interval Selection with Binary Predictions: Optimal Consistency and a Continuous Robustness Tradeoff

Zhong Han

原文摘要

We study online interval selection with binary predictions of membership in a final optimal solution. Requests arrive in arbitrary order; accepted requests may be revoked, but rejected or revoked requests cannot be recovered. With rewards proportional to interval length, the best consistency under finite strict robustness is $d=(3+\sqrt5)/2$ when both guarantees hold almost surely on each fixed input, including for randomized algorithms. A continuous lower bound forces consistency strictly above $d$ at every robustness budget below $4\varphi+3\approx9.472$, whereas our deterministic algorithm attains $d$ with exact robustness $\varphi^5\approx11.090$, where $\varphi=(1+\sqrt5)/2$. Each held interval inherits a ledger recording positive prediction mass lost through irrevocable decisions. A tunable replacement cost gives a continuous family with exact consistency throughout and exact robustness on two parameter intervals, including $(C,R)=(25/9,10)$ and $(4,7)$. Randomization permits expected consistency approaching one with finite expected robustness, whereas almost-sure robustness forces expected consistency strictly above two at every finite budget.

cs.DS · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37358

When Is Additional Retrieval Worthwhile? A Cost-Aware Study of Evidence Gain and Answer Reliability in RAG

Zhouting Zhao

原文摘要

Retrieval-augmented generation (RAG) can benefit from more sophisticated retrieval, but extra retrieval may be unnecessary for many questions and gains in evidence retrieval may not translate into faithful or correct answers. We study a cost-aware, two-action retrieval policy that chooses between a dense-retrieval-plus-reranking baseline and a hybrid lexical--dense retriever. Rather than classifying baseline retrieval as simply successful or unsuccessful, we estimate the question-specific incremental evidence-retrieval benefit of hybrid retrieval using features available before the routing decision. A regularized linear model and decision threshold are selected using document-grouped cross-validation and frozen prior to held-out evaluation. On 60 previously unseen QASPER training-split articles (188 questions, 169 evidence-evaluable), the policy triggers hybrid retrieval on 46 questions (24.5\%) and obtains the same evidence Hit@10 as always-hybrid retrieval (78.70\%, versus 76.92\% for always-keep). Paired, paper-cluster bootstrap intervals do not establish a reliable utility advantage. We further compare generated answers from a 4-bit Qwen3-4B model under the three retrieval policies. Provisional answer-level assessments show no clear correctness or faithfulness improvement after partial review, despite the evidence-retrieval result. The generation assessments remain model-assisted and lack independent human validation. These results expose an important distinction between retrieving relevant evidence efficiently and improving the reliability of the generated answer. The work is presented as a reproducible empirical study, not a claim of statistically established answer-quality superiority.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37353

Cost-based variable selection for prediction models

Lasai Barreñada, Andrew Vickers, Laure Wynants, Bieke Tack, Dirk Timmerman, Ewout Steyerberg, Ben Van Calster

原文摘要

Objective: Variable selection for clinical prediction models is commonly done on statistical grounds related to model fit. Statistical approaches ignore the cost of misclassifications and the harm of measuring a variable. We aim to develop a decision-analytic variable selection algorithm based on net benefit. Materials and Methods: The proposed algorithm selects the set of predictors by exhaustively comparing the net benefit of all combinations using cross validation, with an extension based on backward elimination for settings with many predictors. Variables are selected if the increased net benefit from better predictiveness exceeds the net benefit reduction from the harm of variable measurement. Harm includes financial expense, time, resource allocation, and patient burden. We illustrate the algorithm through a simulated example and three real case studies. We compare its performance to traditional backward elimination and LASSO. Results: Across the case studies, parsimonious models were generated that optimized clinical utility with minimal impact on discrimination and calibration. Penalizing predictors based on their cost ensured that expensive or burdensome variables were only selected if they offer sufficient clinical utility. The algorithm was implemented in the R package NBvarsel. Discussion: Decision-analytic variable selection allows prediction models to maximize patient benefit while minimizing unnecessary clinical burden and costs. Conclusion: Clinical utility should not be an afterthought reserved only for implementation. By integrating a harm-adjusted net benefit metric directly into the variable selection process, NBvarsel allows researchers to select only the variables that sufficiently improve clinical utility.

stat.ME · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2412.07672

DYNASHIELD: A Black-Box Moving Target Defense for LLMs via Dynamic Decoding Customization

Xiaoqun Liu, Weiming Qi, Qiben Yan

原文摘要

Large language models (LLMs) remain vulnerable to jailbreak attacks in which adversarial prompts induce harmful outputs. Existing defenses often require access to the model internals or additional training, limiting their applicability for service providers deployed through black-box APIs. In this paper, we propose DYNASHIELD, a moving target defense framework that improves robustness by customizing decoding hyperparameters and system prompts at inference time. DYNASHIELD includes two key steps: (1) it identifies decoding configurations that reduce attack success probability, and (2) it probabilistically samples from a weighted configuration pool to introduce controlled variability in model behavior. We evaluate DYNASHIELD across 7 open-source LLMs under 4 state-of-the-art jailbreak attacks, using adversarial prompts from AdvBench. Results show substantial reductions in attack success rate compared with 7 baseline defenses, while maintaining response quality and incurring minimal inference overhead. Because DYNASHIELD operates solely through exposed runtime controls, it requires no retraining or model-internal access. These results suggest that safety-aware dynamic decoding is a promising and practically lightweight defense mechanism for black-box LLM deployments.

cs.CR · cs.CL

查看论文
arXiv ↗PDF ↗