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

+2新增论文
+2其中 AI 相关
+0已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-13 00:53 · 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 2026-11-12 01:15 — 2026-11-13 01:15（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：2026-11-13 00:53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 2026-11-13 00:50（北京时间）
版本更新 · v3arXiv:2601.02915

ChemBART: Pre-training a Reaction Language Model for Comprehensive Synthesis Planning

Kenan Li, Yijian Zhang, Jin Wang, Haipeng Gan, Zeying Sun, Xiaoguang Lei, Hao Dong

原文摘要

Recent advances in large language models (LLMs) have demonstrated transformative potential across diverse fields. However, in computer-aided synthesis planning (CASP), current LLM methodologies are often restricted to single-molecule representations, limiting their application to isolated, single-task scenarios such as precursor prediction. Addressing this gap, we present ChemBART, a BART-based language model that adopts a reaction-centric pre-training strategy. By leveraging a mask-filling pre-training task on holistic reaction expressions (Reactant > Reagent > Product), ChemBART effectively solves a variety of chemical problems, including precursor/reagent generation, temperature-yield regression, and molecular property classification. The reaction-centric pre-training further enables the integration of ChemBART with Monte Carlo tree search (MCTS) for multi-step synthesis route design, where the model serves to optimize the policy and value functions within a reinforcement learning framework. Beyond single-molecule pre-trained LLMs that are constrained to specific applications, ChemBART unifies diverse chemical tasks to facilitate synthesis planning with comprehensive implementation information. Most significantly, the proposed multi-step synthesis routes and reaction conditions were validated in the wet lab, confirming the discovery of shorter synthetic pathways with a >20% yield improvement over established literature benchmarks. Our work highlights the potential of reaction-focused pre-training and showcases the broad utility of ChemBART in closing the loop between in silico prediction and wet-lab synthesis.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11141

TALK: One-Shot Batch Design for Protein Variant Effect Prediction

Qiao Huang, Ao Shen, Jie Du, Manning Wang

原文摘要

Protein variant effect prediction is central to understanding protein function and guiding protein engineering, yet experimental labels remain costly. In many protein experiments, the variants that can be assayed are dictated by protocol constraints, while the variants that need accurate prediction may lie in a different or broader region of the landscape. This assay-prediction mismatch makes candidate-local criteria such as predicted function, uncertainty, or exploration value insufficient for measurement design. Given a protocol-defined accessible space and a limited budget, we ask which variants should be assayed so that the resulting data best improves landscape prediction. We propose TALK, which estimates each candidate's contribution through posterior coupling between accessible and target variants and reduces redundant information within the batch. Across retrospective ProteinGym and FLIP protocols, TALK generally improves target-space prediction under limited measurement budgets. These results point to a practical two-stage workflow: first, spend a limited assay budget on variants selected to be informative for the target landscape and train a predictive model from the measured labels; then use this model to score and prioritize high-potential variants. Code is available at https://github.com/joehuang618/TALK.

cs.CE · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.01425

Why Does Train-Validation Separation Emerge? Update-Pressure Density Dynamics in Pretrained Backbones

Yuchen Li, Zongqi Fan, Ken-Tye Yong, Nguyen H. Tran

原文摘要

During fine-tuning, training accuracy often continues to improve after validation accuracy levels off, widening the empirical gap. We propose a support-transfer account: early updates reuse broadly shared structure, while later fitting relies increasingly on narrower structure with less benefit for held-out examples. From fixed training probes, we normalize per-example gradient magnitudes and measure their pooled dispersion, $D_{\mathrm{den}}$, and their probe-count-weighted within-class dispersion, $D_{\mathrm{within}}^{\mathrm{wt}}$. A local model gives conditions for dispersion and directional cross-entropy separation to grow together, separating uniform logit scaling; additional decision-boundary conditions characterize accuracy-gap growth. A controlled five-level hierarchy tests the effect of sample-private support. A 240-branch intervention matrix crosses training-progress anchors, batch sizes, private shares, and gradient-differentiation doses. The negative gap dose response is clearer at later training stages and is retained across the four batch sizes. A further 48 branches replicate its direction across additional seeds at a fixed stage and batch. Both normalized readouts are positively associated with the accuracy gap in all 90 language fine-tuning runs across three backbones and six tasks. The same direction holds in all 20 vision runs across four datasets. Together, the controlled hierarchy, targeted intervention, and real-model trajectories support a connection between evolving gradient differentiation and train-validation separation.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.23522

Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models

Jade Zou, Tao Huang, Weijie Kong, Junzhe Li, Yue Wu, Qi Tian, Jiangfeng Xiong, Jianwei Zhang 等 10 位作者

原文摘要

Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators. A critical step for applying online RL to flow matching is turning the deterministic sampling trajectory into a stochastic policy, typically by replacing the reverse-time Ordinary Differential Equation (ODE) with a Stochastic Differential Equation (SDE). The stochastic sampler, controlling the exploration behavior and denoising dynamics, is thus part of the policy, and its design can significantly affect the reward optimization performance. We break down the sampler design into two interdependent components: choosing the right amount of stochastic exploration, and discretizing the resulting SDE faithfully at the small step counts used in RL. To address the first component, we analyze the inherent tension between exploration and stability in denoising and derive an SDE schedule that balances the two. Turning to the discretization challenge, we use a toy example to show that existing samplers can deviate from the flow-matching process, either by introducing excessive discretization noise or by relying on heuristic rules that do not guarantee convergence to the data distribution. To address these issues, we propose Precise, a new stochastic sampler that balances effective exploration with stability. Crucially, Precise keeps the denoising trajectory SDE-consistent through a novel approximation that freezes the clean-latent posterior mean, resolving the excess noise issue in standard samplers. Extensive experiments demonstrate that this formulation leads to significantly faster and more stable reward optimization via reinforcement learning, achieving state-of-the-art alignment scores (e.g., PickScore, HPSv2.1) while requiring 13.1-53.2% less wall-clock training time to match the best in-domain performance of prior samplers.

cs.LG · cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.01077

Multi-Turn Semantic Caching for Low-Cost LLM Serving

Baran Atalar, Selly Beyene, Xutong Liu, Carlee Joe-Wong

原文摘要

Semantic caching lowers the cost of serving large language models (LLMs) by reusing stored responses for similar requests. In multi-turn conversations, whether a cached response is acceptable depends on both conversations' histories, which embedding similarity of requests and histories predicts poorly (AUC 0.62--0.74 on five workloads). We therefore learn the \emph{reuse risk}, the probability that a cached response is unacceptable, from judge feedback, and choose a budgeted set of conversation states to cache by weighing the generation cost a reuse avoids against a price for unacceptable reuse. We propose CUCB-SC-MT, which learns a cache from logged conversations with a suboptimality guarantee, and CLCB-LS-MT, which learns online and has $\tilde O(\sqrt N)$ regret over $N$ requests when conversation states recur. On math-tutoring (SocraTeach) and movie-ticketing (Taskmaster-3) conversations, both achieve lower loss than prior semantic caching approaches: ContextCache, multi-turn variants of ElastiCache and vCache, and single-turn semantic caching at every cache budget. With 1,000 cache entries, CLCB-LS-MT avoids 35--41\% of the generation cost through acceptable reuses, against at most 22--25\% for the baselines, and lowers estimated serving latency by 19--35\%.

cs.LG · cs.CL · cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11124

Optimal Polynomial-Query Approximation for Consistent Submodular Maximization with Short Lookahead

Vaneet Aggarwal

原文摘要

Elements arrive one at a time, and after each arrival an algorithm holds a set of at most $k$ arrived elements. Its goal is a held set whose value under a monotone submodular function is close to the best value that $k$ arrived elements can achieve. The recourse of an update is the number of elements inserted into or removed from the held set, and we require it to be bounded independently of $k$ and of the number $n$ of arrivals. With evaluations only on sets of arrived elements and polynomially many of them, the best ratio a randomized algorithm can achieve is $2-\sqrt{2}\approx0.5858$. We show that seeing future arrivals raises the best ratio for polynomially many evaluations to $1-1/e\approx0.6321$, for deterministic and for randomized algorithms; no algorithm with polynomially many evaluations exceeds $1-1/e$, even when all elements are available at once. For every $\varepsilon>0$, a deterministic algorithm that sees the next $\lceil\varepsilon k/3\rceil$ arrivals keeps a set of value at least $1-1/e-\varepsilon$ times the optimum at every time, changes $O(\varepsilon^{-3})$ elements per arrival and makes $(n+1)^{O(\varepsilon^{-2})}$ evaluations. With the whole arrival sequence known in advance, a deterministic algorithm attains the same ratio with $O(\varepsilon^{-2})$ changes per arrival. A randomized algorithm with the same short lookahead makes $O(n^2k)$ evaluations, changes $O(\varepsilon^{-2})$ elements per arrival, and attains the same ratio in expectation at each fixed time. The main tool is a greedy algorithm with an explicit guarantee for each of its partial solutions combined with each initial segment of the known future arrivals. A second tool moves between two such solutions one element at a time while keeping the value high, and the deterministic algorithm times each move using upper bounds on the optimum from failed searches.

cs.DS · cs.LG · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11119

Scalable Neural Safety Certification via Monotonicity

Amirreza Alavi, Majid Zamani, Saber Jafarpour

原文摘要

Learning-based safety certification offers a promising route for verifying complex dynamical systems when explicit models are unavailable, but existing data-driven methods often scale poorly: they treat the system as a black box, rely on dense discretizations or Lipschitz bounds, and consequently suffer from sample complexity that grows exponentially with dimension. This paper shows that a common structural property of dynamical systems--monotonicity--can be used to break this curse of dimensionality. We develop a data-driven framework for robust safety verification and safe controller synthesis for unknown monotone systems using only simulator queries. Our main theoretical result proves that, for monotone systems with upper-closed unsafe sets, safety is completely characterized by the existence of monotone inductive barrier certificates. This structure reduces certificate verification over continuous state spaces to localized boundary checks over finitely many cells. To learn such certificates, we introduce Max-Monotone Networks, a monotone neural architecture with universal approximation guarantees for monotone functions. We then propose a training and refinement algorithm that, upon successful termination, returns formally valid neural barrier certificates and, under mild partition assumptions, requires only $O(n)$ simulator queries. Across high-dimensional benchmarks, including oscillator networks with up to $13{,}659$ states and traffic networks with $1{,}000$ states, our method certifies safety in regimes where prior approaches either do not converge or exceed memory limits. These results demonstrate that exploiting order structure can make neural safety certification both scalable and formally sound.

eess.SY · cs.LG · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11118

When gene summaries reveal the answers: Gene Ontology circularity in gene embedding benchmarks

Jiawei Wu, Huishu Wang, Junlin Chen, Hongyi Wang

原文摘要

A gene summary can contain the very annotations used to evaluate an embedding of its text. The Alliance of Genome Resources converts Gene Ontology (GO) annotations into sentences, which NCBI Gene displays and GenePT includes in its input. These summaries covered 6,172 of 19,256 human protein-coding genes (32.1%), including 58% of genes with one to ten linked publications. We embedded the same corpus with and without the generated summaries and refitted a function-prediction probe on each version. Among genes with one to ten publications, removal reduced the reported per-gene area under the receiver operating characteristic curve (AUROC) by 0.078 with a linear probe (95% bootstrap interval 0.072-0.084) and by 0.033 with a multilayer perceptron. These estimates use a historical GO scorer that mishandled ties. The original predictions are unavailable for rescoring. A simple TF-IDF encoder also benefited from the summaries, as did models evaluated only on experimental annotations. Replacing generated summaries with UniProt function descriptions recovered much of the lost performance despite little verbatim overlap. UniProt also curates many of the evaluation labels. In mouse and yeast, we found a similar dependence on the source of the description. We introduce GeneProv to compare encoders on matched text and to examine how representation rankings change across GO recovery, non-GO endpoints and co-essentiality.

cs.LG · q-bio.GN

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11114

Compositional Conformal Risk Control for Multi-Stage LLM Cascades

Yuxia Sun, Jiahuang Wang, Haoting Liu, Zhiwei Huang, Tingrui Pei, Saiqin Long

原文摘要

Multi-stage large language model (LLM) cascades balance accuracy and inference cost, but reliable deployment also requires controlling error risk and identifying its sources across stages. We propose Compositional Conformal Risk Control (CompCRC), a risk-control framework for pre-specified multi-stage LLM cascades. We decompose the risk of accepting incorrect answers into additive stage-wise contributions over the full query population, linking local risk budgets to a system-level guarantee. CompCRC constructs and freezes candidate budget allocations and acceptance thresholds, selects one candidate on independent data, and certifies its stage-wise risk contributions on separate held-out data. Under conditional exchangeability, we establish a finite-sample guarantee: the marginal expected accepted-error risk of the complete deployment procedure does not exceed the global risk budget. At the reported comparison budget of $α=0.45$, all three stages of CompCRC pass their local checks on MMLU, GSM8K, and HellaSwag. Compared with Global-CRC, which passes system-level risk certification at the same budget, CompCRC reduces observed accepted-error risk by 1.33--2.00 percentage points, improves final accuracy by 0.67--2.00 percentage points, and reduces weighted inference cost by 30.37\% on HellaSwag. The selected cost-based budget allocation also improves accuracy per unit cost by 10.6\%--46.7\% over uniform allocation. Further experiments show that stage-wise statistics identify stages that fail local certification checks, providing diagnostic information alongside system-level risk control.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.05435

Active Learning for Conditional Generative Compressed Sensing

Alexander DeLise, Nick Dexter

原文摘要

Generative compressed sensing uses the range of a pretrained generator as a nonlinear model for recovering structured signals from limited measurements. We study a conditional version of this problem for image recovery from subsampled Fourier measurements using prompt-conditioned generative models. Our framework separates two roles of conditioning: the prompt used to design the sampling distribution and the prompt used to define the recovery model. For ReLU and Lipschitz conditional generators, we prove stable recovery bounds showing that prompt-matched Christoffel sampling retains the same Christoffel complexity constant as existing near-optimal generative compressed sensing theory, while prompt mismatch incurs an explicit compatibility penalty. Experiments with Stable Diffusion show that prompts meaningfully reshape Christoffel sampling distributions and influence image recovery. Overall, our results suggest treating prompts as design variables for sensing, approximation, and recovery, opening new directions for the practical use of conditional generative models in compressed sensing, where conditioning, sampling, and optimization must be considered jointly.

cs.LG · math.NA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11108

Evaluating generative samplers for lattice field theory by scale

Satoshi Iso, Lingxiao Wang

原文摘要

Generative samplers for lattice field theory are commonly evaluated by their effective sample size (ESS). We show that a small global ESS need not imply inaccurate long-distance observables: errors spread over many short-distance modes can dominate this diagnostic. We introduce a scale-resolved diagnostic based on the overlap between coarse-grained model and target distributions. At the lattice cutoff, this overlap determines the asymptotic ESS fraction; lower cutoffs isolate long-wavelength errors. In the exactly solvable free theory, two samplers with comparable ESS yield a $32\%$ bias and no bias in the susceptibility, respectively. In two-dimensional $φ^4$ theory near criticality, trained diffusion samplers show the same separation of scales: their path-weight ESS fraction falls rapidly over the volumes studied, while low moments of the magnetization remain close to their target values. Varying the reference parameters substantially changes infrared observables, with little effect on the log-weight variance. Given the target magnetization distribution, a marginal Metropolis test maintains an acceptance rate of order one in our tests. Combined with exact local updates, it reduces the remaining mismatch, although residual bias remains at finite relaxation length. In the free field, uniformly bounded relative errors in the proposal mode variances give a volume-independent bound on the number of updates needed for a prescribed accuracy of the chain's stationary mode variances at fixed correlation length. The target marginal must be supplied or computed separately; estimating it from the samplers' own weights can inherit the poor global overlap.

hep-lat · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11106

Jointly Optimizing Memory, Computing and Offloading for Energy-Efficient DNN Inference

Yunchu Han, Zhaojun Nan, Sheng Zhou, Zhisheng Niu

原文摘要

In edge intelligence systems, computation offloading and dynamic voltage and frequency scaling (DVFS) are widely used to improve energy efficiency. However, as applications like deep neural network (DNN) inference evolve in complexity, their demands for memory resources have progressively increased, establishing memory as a critical bottleneck that impacts both latency and energy consumption. In this paper, we propose a joint optimization scheme integrating memory, computing and offloading for energy-efficient DNN inference. We formulate the energy minimization problem under deadline constraints as a mixed-integer nonlinear programming (MINLP) problem, where the main challenge arises from the coupling between offloading and resource optimization. To address this issue, we decompose the original problem into two subproblems under a fixed offloading policy. The local subproblem is transformed into an equivalent geometric programming (GP) problem to derive the optimal memory frequency and computing frequency, while the edge subproblem is solved via convex optimization. An efficient coordinate descent (CD) algorithm is further developed to jointly optimize all variables. Simulation results demonstrate that our proposed algorithm achieves near-optimal performance with the gap from the optimal policy being at most 9.3%, and reduces the energy consumption of devices by up to 16.1% compared with benchmarks without memory frequency optimization.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11102

Task presentation and execution paths shape LLM mathematical performance

Min Huang, Mingyan Liu

原文摘要

Mathematical performance depends on how a language model receives information, uses generated text and submits an answer. We study these dependencies through paired comparisons that separate submission requirements, draft reuse and candidate availability. On 65 development problems, an instruction permitting continued derivation produced no valid final answers in 390 short-output calls; a single-line submission instruction produced 390 format-valid outputs, including 389 parseable answers. Under the fixed submission protocol, 198 problems with failed initial submissions were answered correctly in 9.09p of cases with the question alone, 33.84p with its draft, 46.46p with candidates, and 59.60p with both. Drafts added 13.13 percentage points with candidates fixed, and candidates added 25.76 points with drafts fixed; both effects were significant after Holm correction and were subadditive on the accuracy scale. Retaining a trailing excerpt outperformed retaining a leading excerpt of similar average length by 10.10 points Holm-adjusted p 0.027. A second completion model showed the same directions of input effects on the fixed materials. In a cohort with parseable initial submissions, candidates added no correct answers when the previous draft was supplied, but added 27 points when it was absent. These results establish a conditional value of generated text: a failed submission can leave useful material, whose contribution depends on what else is supplied and what is retained.

cs.LG · cs.CL · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.13807

AnomaMind: Coarse-to-Fine Agentic Diagnosis via Hybrid Inference for Time Series Anomaly Detection

Xiaoyu Tao, Yuchong Wu, Mingyue Cheng, Ze Guo, Min Wu

原文摘要

Time series anomaly detection (TSAD) supports the analysis of web service key performance indicators (KPIs) by identifying anomalous intervals. Recent large language model (LLM)-based agentic approaches have achieved promising results through reasoning and tool use. Despite their effectiveness, precise anomaly localization remains challenging, as diverse anomaly patterns demand targeted numerical evidence and iterative refinement to accurately determine anomaly boundaries. In this work, we propose AnomaMind, a coarse-to-fine agentic diagnosis framework for TSAD. AnomaMind first identifies suspicious regions from time-series visualizations, then adaptively acquires targeted numerical evidence through multi-turn tool interactions, and finally refines anomaly decisions through self-reflection. This process is supported by a tool engine that integrates knowledge memory and numerical analysis. To coordinate this diagnostic process, we design a hybrid inference strategy that employs frozen general-purpose LLMs for initial localization, tool orchestration, and evaluation, alongside a specialized LLM detector for evidence-grounded interval prediction. We optimize only the specialized detector through supervised fine-tuning (SFT) on diagnostic trajectories and reinforcement learning (RL) with verifiable detection rewards. Experiments on four benchmarks spanning web traffic, service KPIs, and system-monitoring signals, under both in-domain and multi-domain training settings, demonstrate competitive performance and support the effectiveness of coarse-to-fine adaptive diagnosis through targeted evidence acquisition and self-reflective refinement.The code is available at https://github.com/Xiaoyu-Tao/AnomaMind-TS.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2406.13216

CombAlign: Enhancing Model Expressiveness in Unsupervised Graph Alignment

Songyang Chen, Yu Liu, Lei Zou, Zexuan Wang, Youfang Lin

原文摘要

Unsupervised graph alignment finds the node correspondence between a pair of attributed graphs by only exploiting graph structure and node features. One category of recent studies first computes the node representation and then matches nodes with the largest embedding-based similarity, while the other category reduces the problem to optimal transport (OT) via Gromov-Wasserstein learning. However, it remains largely unexplored in the model expressiveness, as well as how theoretical expressivity impacts prediction accuracy. We investigate the model expressiveness from two aspects. First, we characterize the model's discriminative power in distinguishing matched and unmatched node pairs across two graphs. Second, we study the model's capability of guaranteeing node matching properties such as one-to-one matching and mutual alignment. Motivated by our theoretical analysis, we put forward a hybrid approach named CombAlign with stronger expressive power. Specifically, we enable cross-dimensional feature interaction for OT-based learning and propose an embedding-based method inspired by the Weisfeiler-Lehman test. We also apply non-uniform marginals obtained from the embedding-based modules to OT as priors for more expressiveness. Based on that, we propose a traditional algorithm-based refinement, which combines our OT and embedding-based predictions using the ensemble learning strategy and reduces the problem to maximum weight matching. With carefully designed edge weights, we ensure these matching properties and further enhance prediction accuracy. By extensive experiments, we demonstrate a significant improvement of 14.5% in alignment accuracy compared to state-of-the-art approaches and confirm the soundness of our theoretical analysis.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11091

Uncertainty-Guided Reward Labeling for Reinforcement Learning under Limited Feedback

Renhao Zhang, Shreyas Chaudhari, Bruno Castro da Silva

原文摘要

In reinforcement learning from limited feedback (RLLF), only a small fraction of an offline dataset can be labeled with rewards, and the central question is which samples should be labeled to learn a high-performing policy from the resulting partially labeled dataset. Prior work formalized this as a reward-selection problem by focusing on the selection stage while treating downstream policy learning as a black box, in a regime where queried rewards are not retained for reward-model training. We instead study the retained-label setting, where queried rewards can be stored and used to fit a reward model before policy learning. We bound the suboptimality of the learned policy in terms of two sources of error: one arising from offline RL on a fixed, offline dataset, and the other from uncertainty in the reward model. Since reward selection cannot change the offline dataset, the limited labeling budget must be used to strategically reduce reward uncertainty. Motivated by RLLF's observation that useful rewards tend to keep the agent on high-return trajectories, we introduce Successor-Guided Uncertainty REduction (SURE), a novel method that uses successor features to select rewards that are both uncertain and associated with states from which high-valued states are reachable. We formally derive SURE from a bound-induced design objective and characterize its exact one-step marginal gain. Empirically, SURE reaches near full-feedback performance with few reward labels across a variety of domains and offline-RL backbones, yielding an effective method for feedback-efficient reinforcement learning.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.01984

Universal Byte-Level Encoding: UTF-8/UTF-16 Routing to Reduce Cross-Script Token-Budget Disparities

Hyunsik Kim, Youngmoon Jung

原文摘要

Byte-level byte-pair encoding (BBPE) tokenizers are attractive for multilingual large language models because they cover all Unicode text. In UTF-8-based BBPE, however, many scripts start from a higher fallback cost than English: when no learned merges apply, a multibyte character requires multiple byte-derived symbols. We call this worst-case pre-merge cost the encoding floor. A higher floor can increase token counts and per-request cost while shrinking usable context. Changing the whole text encoding can reduce this gap but make already-efficient English spans more expensive in mixed-script text. Thus, we propose Universal Byte-Level Encoding (UBE), a dual-alphabet tokenizer that keeps 1-2-byte UTF-8 characters in UTF-8 and routes 3-4-byte characters through UTF-16. This lowers the encoding floor for 3-byte Basic Multilingual Plane characters, used by many scripts that need more tokens than English, without raising it for any character. UBE changes only the symbols presented to byte-pair encoding, and a Unicode 17 audit confirms exact round trips for every scalar value and every input in three official test suites. UBE also composes with other boundary policies and morphology-based encodings. Across intrinsic evaluations, UBE lowers dispersion in English-normalized token-count ratios (Gini 6-14% lower on FLORES-200 at 16K-64K), reducing cross-lingual token-budget disparity. In multilingual language models, UBE matches BBPE's quality. In the main multilingual settings, UBE reduces token counts most where they are highest and also lowers English counts, yielding more usable context and faster prompt processing in content-matched benchmarks. Byte-level models benefit directly: UBE shortens their inputs by 29-33% in all 39 of the FLORES-200 languages written mostly in 3-byte characters (1.4-1.5 times as much text per context window), lowers byte-level Gini by 28%, and lengthens no input.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.00916

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget

Zhichao Xu, Xueguang Ma, Shengyao Zhuang, Luyu Gao, Wenqian Ye, Yu Wang, Jamie Callan, Jimmy Lin

原文摘要

Training large dense and mixture-of-experts (MoE) rerankers is constrained by GPU memory and distributed-execution efficiency, which has kept academic reranker research largely on dense models. Tevatron trains rerankers through the Hugging Face Trainer with DeepSpeed and PyTorch FSDP1, a stack that stalls on three fronts: DeepSpeed ZeRO-2 has a known gradient-gathering failure on this path, FSDP1 full sharding is memory-safe but throughput-bound, and neither offers the expert parallelism (EP) that MoE training needs. We present Tevatron 3.0, which integrates Megatron-Core as a reranker training backend while preserving Tevatron's data processing, evaluation pipeline, and Hugging Face checkpoint format. For full-parameter dense 8B training, Megatron matches FSDP1 on BEIR-15 NDCG@10 with approximately 4% lower epoch time and twice the peak GPU memory under matched data-parallel and recomputation settings, and approximately 22% lower epoch time in its recommended configuration; it supports both LoRA and full-parameter fine-tuning. Expert parallelism makes it possible to train a 30B-parameter MoE reranker (Qwen3-30B-A3B) on two nodes. A controlled study of architecture, LoRA, and distillation on BEIR-15, with three first-stage retrievers and Hugging Face and vLLM serving, shows that the MoE reranker matches dense-8B quality at less than half the activated parameters and at higher inference throughput. We open-source the framework and trained checkpoints.

cs.IR · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.16262

Compute-Optimal Pretrain--Fine-tune in Ridge Gradient Descent

Alex Buna, Fanghui Liu, Patrick Rebeschini

原文摘要

Pretraining followed by fine-tuning introduces a compute-allocation problem: under a fixed training budget, compute spent improving the upstream objective reduces the compute available for downstream adaptation. Despite its practical importance, this trade-off is not yet well understood theoretically, even in simple models. In this paper, we cast this allocation as a compute-split problem under a two-stage pretrain--fine-tune procedure with fixed total optimisation budget, using regularised least squares trained by gradient descent as a tractable setting. We characterise the optimal split under data-dependent evaluation geometries induced by the fine-tuning problem. Our results show that the allocation depends on how pretraining directions affect fine-tuning predictions and how fine-tuning shifts are seen through downstream data geometry. In particular, the relevant quantities are determined by prediction-relevant spectral components of the pretraining and fine-tuning empirical covariances. Technically, the analysis relies on a basis-invariant, eigenspace-level spectral decomposition, together with perturbative control of the non-commuting pretraining and fine-tuning dynamics.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.30916

Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation

Andreas Haupt, Justin Hartenstein, Anka Reuel, Mykel Kochenderfer, Sanmi Koyejo

原文摘要

AI benchmarks have well-documented limitations, with prior work examining contamination, saturation, and construct underspecification. Aggregation has received far less attention: benchmarks are typically summarized by uniformly averaging item-level scores, implicitly treating every test item as equally valuable. We model benchmarking as a multitask principal-agent game and show that the welfare loss from a benchmark is determined jointly by three item-level primitives: alignment with normative welfare priorities, marginal improvability, and performance variance. We translate the theory into an audit framework that ranks items along each of these three axes, and apply it to OLMES items using WORKBank for welfare, the EvoLM 4B suite for improvability, and the PolyPythias 410M panel for variance. The framework surfaces items that are Pareto-inferior within OLMES subject to a pro-worker welfare operationalization. All code is available at https://github.com/stair-lab/principal-agent-benchmarks.

cs.LG · cs.GT · econ.TH

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11081

A Hierarchical Tokenization Framework for Voxel-Level fMRI Representation Learning

Karanpartap Singh, Yue Zhao, Mohammad H. Abbasi, Ehsan Adeli

原文摘要

We introduce HBAR (Hierarchical Brain Activity Representation), a hierarchical tokenization framework for learning compact, multi-scale representations of neuroimaging data. HBAR organizes voxel-level resting-state fMRI into a hierarchy spanning sub-parcel voxel groups, parcels, and large-scale functional networks, enabling up to 415x compression while preserving fine-grained spatial information beyond conventional parcellation. The framework supports fixed atlas-based, fully learned, and softly prior-guided hierarchies, allowing us to systematically study the role of structured priors in brain representation learning. On HCP-YA, at approximately 415x compression, HBAR achieves higher parcel and network correlations than rate-matched flat tokenizers, while at a lower 52x compression rate, shuffling the anatomical grouping reduces parcel correlation from 0.920 to 0.886. Demographic readouts with autoregressive training also reveal potential gains from the hierarchical structure. By combining sub-parcel inputs, compact discrete tokens, and multiscale brain structure, HBAR offers a practical framework for representation learning in high-dimensional neuroimaging data.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11079

When Calibration Data Matter in Sub-4-Bit Language Model Quantization

Yehong Jiang, Yen-Kuang Chen, Xinmin Tian

原文摘要

Low-bit post-training quantization reduces language-model memory but can sharply degrade downstream task accuracy. Calibration usually relies on generic text, but when task-informed data recover accuracy and which quantizers benefit remain poorly understood. We introduce FragCal-DC, which supplements generic text with training documents from task families with low retention of full-precision accuracy in a two-bit scan. We use a two- to four-bit sweep to locate functional regimes and four-seed calibration comparisons to evaluate six data-dependent methods across six dense models (1.7B-8B) and ten tasks. At their lowest tested functional bit widths, iterative SignRound V2 and OmniQuant improve at two bits, whereas single-pass GPTQ and AWQ show small mean responses at three bits. At two bits, SignRound V2 gains 1.83 percentage points in mean ten-task accuracy over generic-text calibration across six models. At 70 billion parameters, GPTQ and SignRound V2 both improve at two bits, with functional generic-calibration baselines. For two-bit SignRound V2, task-level controls show that recovery concentrates on families included in calibration, while incorrect answer designations retain about 90% of the mean accuracy gain. Changes in reconstruction error do not consistently track accuracy gains. These findings support task-informed calibration as a design principle for preserving downstream accuracy in low-bit quantization.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.36558

Holomorphic Cauchy Networks for Efficient Stationary Tail Computation in High-Dimensional Reflected Brownian Motions

Kehan Wang

原文摘要

Stationary tail computation for high-dimensional reflected Brownian motions (RBMs) remains computationally challenging. Building on NN4MGF's shared-coordinate basic-adjoint-relationship (BAR) framework, we develop Holomorphic Cauchy Networks (HCNs). Native complex-valued rational Cauchy subnetworks enforce holomorphicity on pole-free domains, removing sampled Cauchy-Riemann penalties and their input-derivative graphs. Exact origin anchoring and boundary-coordinate exclusion enforce structural identities, while anchored interactions represent dependent transforms. Under holomorphic-log assumptions, we establish simultaneous value and first-derivative approximation for the constrained architectures and a mixed-derivative lower bound for coordinate-only representations under nonzero cross-covariance. Closed-form real-axis derivatives and sequential backpropagation further control memory. On the same NVIDIA H100 NVL, the tested 30D HCN configuration uses approximately tenfold less peak allocated memory and has 9.7-fold lower mean update time than NN4MGF; extrapolation to the respective scheduled update counts gives a projected full-schedule update-time ratio of 58.2. With 64 million sampled base inputs per high-dimensional run, HCN reaches 50 dimensions on a laptop GPU with 6.367% mean relative error over thresholds 1 through 8. Degree-matched comparisons yield lower reported mean relative errors over the primary evaluation ranges, including 1.422% versus 6.684% on the 2D Harrison non-product benchmark. On a 10D correlated RBM benchmark, HCN achieves 3.829% mean relative error over thresholds 1 through 8 against a simulation reference, compared with 19.386% for an independent-marginal baseline.

cs.LG · math.NA · math.PR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11074

System Prompts Affect Response Bias More Than Discriminability in LLM Safety

Mohan W. Gupta, Sandy Tanwisuth

原文摘要

Large language model safety evaluations often focus on a compliance-refusal tradeoff: models should refuse unsafe requests without refusing safe ones. We argue that this misses a broader form of prompt-conditioned task selection, where the same request can elicit different behaviors depending on the system prompt. We investigate this using a controlled evaluation crossing eight safety-task prompt families with three clarity levels across HarmBench, XSTest, and IHEval. Holding benchmark items fixed, we evaluate 13 models and use signal detection theory to distinguish two possibilities: whether models become better at telling safe from unsafe requests (discriminability), or simply more willing to refuse (response criterion). We find substantial differences in discriminability across models, but system prompts primarily shift the willingness to refuse, with smaller and less consistent effects on discriminability. Increasing prompt clarity makes models more willing to refuse without reliably improving their ability to distinguish safe from unsafe requests. Beyond refusal, prompt families also shift responses among six distinct behavioral policies, including clarification and safe help. Together, these findings show that system prompts primarily change how models respond to safety-relevant requests rather than consistently improving their ability to distinguish safe from unsafe ones.

cs.LG · cs.AI · cs.CL · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2509.23219

WirelessMathBench-XL: An Auditable Benchmark for Wireless Mathematical Reasoning

Xin Li, Mengbing Liu, Yiyang Zhu, Wenhe Zhang, Li Wei, Jiancheng An, Chau Yuen

原文摘要

Benchmarks built from arXiv papers can overlap the arXiv text used in LLM pretraining, yet technical-domain releases rarely ship the per-item evidence needed to check this. We introduce a reverse-probe n-gram audit that indexes the benchmark side and streams the corpus past it, so memory scales with the benchmark rather than the corpus and flags on the distributed problems can be inspected and recomputed. We instantiate it in WirelessMathBench-XL, a 4,027-problem benchmark for wireless mathematical reasoning built from 836 arXiv papers across 20 subfields, with multiple-choice, progressive fill-in, and full-equation-completion formats. Streaming 12.9 B RedPajama-arXiv 13-grams yields a strict zero-hit view $\mathcal{S}_0$ covering 95.7% of the problems, and shows that the Dolma and ProofPile-2 arXiv slices repackage the same RedPajama dump. Filtering to $\mathcal{S}_0$ moves every evaluated model by less than 1 pp. With 30/800 flagged test items, this comparison bounds detected-overlap inflation at 0.31-0.51 pp for frontier models rather than testing for contamination, and it does not cover paraphrase, target-answer, alternate-version, post-training, or closed-corpus exposure. Frontier models reach 86.5-91.3%, and GRPO on the released training split lifts a 7B model 25.1 pp above a size-matched general-math control. We release source-paper identifiers, per-problem audit and threshold metadata, license-aware data files, audit and bootstrap scripts, Croissant metadata, and a Datasheet.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.18516

Signed Rectified Flow: Negativity-Controlled Generation

Runlong Liao, Baiyu Su, Lizhang Chen, Qiang Liu

原文摘要

We introduce Signed Rectified Flow (Signed RF), a generalization of Rectified Flow that targets the signed measure $π^{sign} = (1+α)π^+ - απ^-$, where $α>0$, $π^+$ is the distribution to promote, and $π^-$ is the distribution to suppress. Although direct sampling from a signed measure is not well-defined, Signed RF induces a valid generative process that concentrates probability in regions where the signed measure is positive while provably excluding regions dominated by its negative component. It therefore provides a principled framework for incorporating negative information and exclusion constraints into generative modeling. We analyze the signed continuity equation underlying Signed RF and use a charged-particle interpretation to explain how negative mass forms exclusion barriers. This theory further motivates practical adaptive guidance algorithms. Across several applications, Signed RF improves the fidelity-diversity trade-off on ImageNet, reduces nearest-neighbor similarity in anti-memorization experiments, and reduces nudity induced by adversarial prompts in Stable Diffusion 3.5 while preserving CLIP and aesthetic scores.

cs.LG · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11068

Discrete Diffusion Playground: A 2D Benchmark for Discrete Generative Models

Justin Shao, Sihyun Park, David Ryan Koes, Maria Chikina

原文摘要

Discrete diffusion is a promising framework for categorical generative modeling, but current evaluation protocols often fail to reveal whether models have actually learned the target distribution. We introduce the Discrete Diffusion Playground, a diagnostic benchmark that converts known 2D continuous distributions into binary token sequences through an exact discretized bijection. This creates a rare setting in which models are trained on discrete sequences, but generated samples can be decoded back into 2D and compared directly against a known ground-truth distribution. The benchmark spans smooth Gaussian mixtures and tilted checkerboards with sharp boundaries, disconnected support, and coordinate-dependent structure, allowing it to expose failures that are invisible in standard proxy metrics. It supports exact grid divergences, Wasserstein distances, density visualizations, and nonparametric two-sample tests, providing both quantitative evaluation and interpretable failure diagnosis. Using this testbed, we show that masked diffusion models can learn meaningful adaptive reveal orders but remain less stable than autoregressive baselines on smooth targets and largely fail on tilted checkerboards, where autoregressive models preserve the target geometry. Control experiments with reversed and interleaved token orderings show that autoregressive performance is not explained by favorable bit order alone. The Playground provides a simple but stringent benchmark for stress-testing discrete generative models and for developing evaluation metrics that detect real distributional mismatch rather than proxy performance. Our code is available at https://github.com/shaojus/DiscreteDiffusionPlayground .

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11066

Rescene-ESM: an Earth system model built around a frozen AI weather model

Minjong Cheon, Kaoru Kakinuma

原文摘要

Earth system models underpin climate projections, but their cost limits how many scenarios, ensemble members and impact pathways can be explored. Machine-learning weather models forecast as skillfully as physics-based models at a fraction of the cost, yet coupled to an ocean they have produced weak El Nino variability or have learned it from climate-model output, and none carries the climate through rivers to the people exposed to it. Here we present Rescene-ESM, an Earth system model whose coupler, YAHO, yokes a frozen 20.8-million-parameter AI weather model to physically formulated ocean, sea-ice, land, river, carbon and energy components constrained by observations. Adding the couplings one at a time shows what each contributes: over a climatological ocean the AI atmosphere varies from year to year by a third of the observed amount over the oceans, and an interactive mixed layer, an equatorial wave ocean, the residual of the observed sea surface temperature (SST) equation as stochastic forcing and the land's moisture flux raise this step by step and bring El Nino and its teleconnections, leaving the mean climate almost unchanged. The full model simulates about 1,000 years per day on one graphics processing unit, holds the observed climate for a thousand years without drift, reproduces the observed 1979-2022 global warming, carries forced change with a physically based structure around the frozen network (transient climate response 1.60 K), routes runoff to 212 river gauges with a median seasonal-cycle correlation of 0.79 and, driven by emissions, separates the heatwave exposure of an SSP1 and an SSP3 world by a factor of 4.7 in 2081-2100, three-quarters of it through the warmer climate.

physics.ao-ph · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.06250

Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification

Alex Buna, Shirley Xiaoqi Liu, Patrick Rebeschini

原文摘要

In overparameterised classification, training data can be linearly separable even when the underlying distribution is not. In this setting, gradient descent (GD) on the logistic loss diverges in norm while converging in direction to a max-margin interpolating classifier, whose implicit bias can be statistically suboptimal. In this work, we show that early stopping can overcome this suboptimality: in a Gaussian mixture model with label-flipping noise, GD stopped at an appropriate oracle time achieves minimax-optimal excess zero-one risk for covariance spectra with fast and continuous decay, including polynomial and exponential spectral decays. Our analysis combines a sharp upper bound for the early-stopped iterate with a matching statistical lower bound over arbitrary classifiers, yielding optimal rates that are validated by experiments. A central technical contribution is a new calibration result that converts excess logistic risk into excess zero-one risk; it handles the model misspecification induced by the label-flipping noise, and removes the square-root rate in standard bounds. We also establish a lower bound for linear interpolators, showing that interpolation can require exponentially more samples than early stopping to achieve the same excess risk.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.03502

Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation

Md Sazid Uddin, Md. Khairul Alam Mazumder, M. F. Mridha

原文摘要

Mechanistic edits (ablations, weight edits, activation steering) are the standard tools for unlearning a harmful capability from a neural network while preserving useful ones. Current approaches validate their effects only by testing, which can never cover an entire continuous region of inputs. Prior work at the interpretability-verification boundary certifies descriptions of a model: what a circuit computes, or whether it faithfully explains the whole. We instead certify the behavioral effect of an edit: that disabling a circuit removes one skill and provably preserves another, for every input in a region; a feature non-interference guarantee in the information-flow-security sense. We demonstrate such certified edits from toy ReLU networks up to a standard softmax + LayerNorm transformer, proving removal and preservation over continuous embedding-space regions and reaching roughly 9x the input-perturbation dimension an exact solver can handle by switching to sound bound propagation. Furthermore, we prove that no finite deterministic black-box test can certify removal, exhibiting an edit that passes exhaustive testing yet provably fails on a survivor pocket that can be made arbitrarily small. Guarantees hold on small, standard-architecture networks and, like any removal claim, presuppose that the target skill admits a decidable specification, a property which real-world harms may not have.

cs.LG · cs.AI · cs.CR

查看论文
arXiv ↗PDF ↗