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

+586新增论文
+453其中 AI 相关
+91已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-13 11:13 · 全站最近入库：2026-11-13 11:12各信源进度 →

统计口径与数据新鲜度

统计 2026-11-12 11:59 — 2026-11-13 11:59（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 11:13最近发现新增版本：2026-11-13 11:12库内论文最新更新时间：2026-11-11 22:55

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。

22,261 已收录论文18,776 AI 相关6,286 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 5,087 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-13 11:11（北京时间）
版本更新 · v4arXiv:2510.02945

Ergodic Risk Measures: Towards a Risk-Aware Foundation for Continual Reinforcement Learning

Juan Sebastian Rojas, Chi-Guhn Lee

原文摘要

Continual reinforcement learning (continual RL) seeks to formalize the notions of lifelong learning and endless adaptation in RL. In particular, the aim of continual RL is to develop RL agents that can maintain a careful balance between retaining useful information and adapting to new situations. To date, continual RL has been explored almost exclusively through the lens of risk-neutral decision-making, in which the agent aims to optimize the expected long-run performance. In this work, we present the first formal theoretical treatment of continual RL through the lens of risk-aware decision-making, in which the behaviour of the agent is directed towards optimizing a measure of long-run performance beyond the mean. In particular, we show that the classical theory of risk measures, widely used as a theoretical foundation in non-continual risk-aware RL, is, in its current form, incompatible with continual learning. Then, building on this insight, we extend risk measure theory into the continual setting by introducing a new class of ergodic risk measures, and showing that it is compatible with continual learning. Finally, we provide a case study of continual risk-aware learning, along with empirical results, which show the intuitive appeal of ergodic risk measures in continual settings.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10313

Multi-objective drift-aware MLOps agent for model retraining

Kumuda Valli, Anli Ji

原文摘要

Deployed ML models face non-stationary data and delayed labels, yet most retraining strategies rely on fixed schedules or brittle drift thresholds that ignore operational cost. In this setting, retraining is a sequential decision problem rather than a one-time threshold choice. We present DARE (Drift-Aware Retraining Engine), an offline, event-driven retraining framework that separates ingestion, monitoring, policy decisions, training, and logging through explicit schemas and deterministic replay. We compare DARE against practical heuristic retraining baselines, including fixed-interval, threshold-persistence, and action-rate-matched fixed scheduling policies. On Airline, the locked LinUCB policy achieves a higher mean F1 while substantially reducing intervention frequency relative to heuristic and action-rate-matched baselines. Additional runtime-calibrated evaluation shows that these gains persist when measured using the cumulative update wall-clock time. These results suggest that conservative sequential retraining policies can improve performance while reducing unnecessary operational overhead under delayed feedback.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.05808

Physical policy gradient theorem for in situ stochastic-adjoint training

William Tuxbury, Zin Lin

原文摘要

In situ adjoint training extracts parameter gradients directly from measurement, but has so far been limited to reciprocal or restricted systems. We introduce the physical counterpart of the policy gradient theorem: a stochastic-adjoint gradient estimator that lifts these constraints by trading reciprocity for nondegenerate diffusion. As validation, we train a nonlinear resonator network, whose own dynamics supply the policy, against antagonistic temporal modulations with gradients from measured stochastic trajectories alone, without finite differences or a separate adjoint experiment.

physics.optics · cond-mat.dis-nn · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.22897

From Residuals to Reasons: LLM-Guided Mechanism Inference from Tabular Data

Mohammad R. Rezaei, Rahul G. Krishnan

原文摘要

When software fails, we read the error, form a hypothesis, write a patch, and test it. LLMs now do this for neural networks by editing weights; when a tabular model fails, we usually retune it. Most interpretability methods report which features matter rather than how they combine. Rather than asking an LLM to predict the target over the whole output space, we anchor the prediction with a base model and ask the LLM to debug it. We introduce Multi-Agent Residual In-Context Learning (MARICL), in which LLM agents read high-residual examples, hypothesize the missing structure, and write executable correction terms that are then refined by multi-turn textual gradient optimization. The resulting corrections are readable, executable hypotheses about what the base model misses, rather than validated mechanisms. Across nine benchmarks covering scientific, biomedical, socioeconomic, and synthetic data, MARICL reliably repairs its base model's structured residuals, improving it on every dataset, and on synthetic data absent from pretraining it recovers the hidden structure (two seeds). Against the strongest competing baseline it leads on five of the eight real benchmarks and trails TabPFN on the other three, while adding an inspectable correction that black-box baselines do not provide. Code is available at https://github.com/MrRezaeiUofT/Multi_Agent_Residual_In_Context_Learning.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10307

How Much Is Left Matters: False Positives and False Negatives in Partial-Prompt Contamination Tests

Abhishek Anand

原文摘要

Partial-prompt completion, where a model receives the first part of a benchmark problem and is checked for whether it reproduces the rest, is a widely used test for benchmark contamination. We audit this test on seven open-weight models using MATH-500 and recent AIME 2025/2026 problems, which serve as true negatives. Memorization flags depend strongly on how much text remains: for every model, problems with at most 8 leftover words are flagged several times more often than problems with at least 25 (31.5% vs. 5.5% for Qwen2.5-7B-Instruct), and half to three-quarters of all ROUGE-based flags come from short leftovers. On true negatives, a ROUGE-L >= 0.75 threshold flags up to 6.7% of problems at a 60% prefix, and at an 80% prefix even exact match flags 8.6% (pooled over models; 6.2% on AIME 2026, which postdates every model), against 0% at 40-60%. The test also misses contamination upstream: models distilled from Qwen2.5-Math, whose base is heavily flagged in prior work, show almost no model-specific recall. Calibrating each model against models from other families removes most flags while isolating a consistent Qwen2.5-specific signal at every prefix length. We recommend length-stratified reporting, prefixes of at most 60%, style-matched post-cutoff controls, and cross-family calibration.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.06189

Predictive-Generative Drift Decomposition for Speech Enhancement and Separation

Julius Richter, Yoshiki Masuyama, Christoph Boeddeker, Takahiro Edo, Gordon Wichern, Jonathan Le Roux

原文摘要

We propose Stochastic Interpolant Prior for Speech (SIPS), a plug-and-play framework for speech enhancement and separation that augments pretrained predictors with a generative clean speech prior. Building on stochastic interpolants, we decompose the sampling dynamics into a predictor-induced drift and a score-based denoising component. The predictor guides sampling toward a task-consistent estimate, while a score model trained exclusively on clean speech promotes perceptual naturalness. Unlike prior hybrid approaches, which typically rely on architecture-specific conditioning and are tied to particular predictors or degradation settings, SIPS employs a degradation-agnostic prior that can be reused across predictors and additive degradation tasks without retraining. We evaluate SIPS on speech enhancement and separation using recent predictors such as SEMamba and FlexIO. Across both tasks, SIPS consistently improves non-intrusive speech quality metrics while maintaining competitive performance on reference-based distortion measures and word error rate. For speech enhancement, these improvements are further supported by a subjective listening test.

eess.AS · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.07738

Learnable Chernoff Baselines for Inference-Time Alignment

Sunil Madhow, Yuchen Liang, Ness Shroff, Yingbin Liang, Yu-Xiang Wang

原文摘要

We study inference-time reward-guided alignment for generative models. Existing methods often rely on either architecture-specific adaptations or computationally costly inference procedures. We introduce Learnable Chernoff Baselines (LCBs) as a method for efficiently and approximately sampling from the exponentially tilted kernels that arise from KL-regularized reward alignment. Using only black-box sampling access to the pretrained model, LCBs implement a form of rejection sampling with adaptively selected acceptance probabilities, which allows fine-grained control over inference-compute scaling. We establish total-variation guarantees to the ideal aligned model, and demonstrate in both continuous and discrete diffusion settings that LCB sampling closely matches ideal rejection sampling while using substantially fewer queries to the pretrained model.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.15964

PromptShift-CRC: What Drift-Aware Weighting Adds to Online Conformal Risk Control for Foundation Models

Jeffery Opoku, David Banahene

原文摘要

A risk threshold calibrated on old prompts can stop being valid when prompts to a foundation model drift. We study PromptShift-CRC, a rule that weights past prompts by feature similarity, falls back to recent prompts when the current prompt is unlike the past, and updates its level online. We prove that the update controls the long-run violation rate for any weights, so marginal coverage cannot separate weighting schemes. We give a conditional bound at a fixed level whose cost is a weighted total variation distance, bounded by a computable prompt-drift term up to an unknown Lipschitz constant. We propose a comparison protocol: a matched short-window baseline, a validity and sharpness frontier, 30-seed synthetic streams, and real-output streams ordered without using the model's output. On MMLU, TruthfulQA (Qwen2.5-1.5B) and RealToxicityPrompts (GPT-2, replicated with a second generator and classifier), every online method reaches the target. PromptShift-CRC stays within 0.0055 of the Adaptive CRC frontier and avoids the worst window, but DtACI matches or beats it in most settings. The rule performs like a mid-ranked window without having to choose one. Tests fixed in advance to favor the weights show no consistent gain over the frontier. Code, outputs and streams are released.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10305

Plug-and-Play Verifier for Decoupling Process Reward in Stabilizing Long-Horizon Agentic Reasoning

Mingwei Xu, Jieyuan Pei, Binghao Tu, Hao Fang

原文摘要

Stabilizing long-horizon reasoning requires intelligent agents to sustain useful progress across successive reasoning steps and tool interactions. Such agents are typically trained with reinforcement learning (RL), where actor-critic RL uses a learnable critic network to estimate step advantages, while critic-free methods such as GRPO eliminate critic models and rely mostly on the group variants of sparse outcome-only rewards. Both reward types leave partially useful failed trajectories either implicit or indistinguishable from entirely unproductive ones, and as reasoning horizons grow, it becomes difficult to maintain consistent reasoning trajectories. In this work, we propose a \textit{plug-and-play verifier} framework for stabilizing long-horizon reasoning through explicit verification of intermediate reasoning artifacts. Specifically, the framework decouples process verification through a unified interface that extracts intermediate reasoning artifacts from agent running trajectories, evaluates them using domain-specific verifiers, and aggregates the verification scores as bounded process reward. Then, we combine our dense verified process rewards and the sparse outcome rewards through a two-stage post-training schedule. We showed that with plug-and-play verifiers, we further stabilize the reasoning steps as last-mile self-reflection and self-consistency. Typical evaluation on HotpotQA using Qwen3.5-4B achieves a superior accuracy (60.18\%), outperforming the standard GRPO baseline (57.73\%). Our results suggest that plug-and-play verifiers provide a modular approach to learn more stable and reliable reasoning behaviors over long horizons.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2410.02504

Dual Active Learning for Reinforcement Learning from Human Feedback

Pangpang Liu, Chengchun Shi, Will Wei Sun

原文摘要

Aligning large language models (LLMs) with human preferences is critical to recent advances in generative artificial intelligence. Reinforcement learning from human feedback (RLHF) is widely applied to achieve this objective. A key step in RLHF is to learn the reward function from human feedback. However, human feedback is costly and time-consuming, making it essential to collect high-quality conversation data for human teachers to label. Additionally, different human teachers have different levels of expertise. It is thus critical to query the most appropriate teacher for their opinions. In this paper, we use reinforcement learning (RL) to formulate the alignment problem. Motivated by the idea of $D$-optimal design, we first propose a dual active reward learning algorithm for the simultaneous selection of conversations and teachers. Next, we apply pessimistic RL to solve the alignment problem, based on the learned reward estimator. Theoretically, we show that the reward estimator obtained through our proposed adaptive selection strategy achieves minimal generalized variance asymptotically, and prove that the sub-optimality of our pessimistic policy scales as $O(1/\sqrt{T})$ with a given sample budget $T$. Through simulations and experiments on LLMs, including annotator-level preference data and downstream Best-of-$N$ response-selection evaluations, we demonstrate the effectiveness of our algorithm and its superiority over existing baselines.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2510.02300

Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models

Runqian Wang, Yilun Du

原文摘要

We introduce Equilibrium Matching (EqM), a generative modeling framework built from an equilibrium dynamics perspective. EqM discards the non-equilibrium, time-conditional dynamics in traditional diffusion and flow-based generative models and instead learns the equilibrium gradient of an implicit energy landscape. Through this approach, we can adopt an optimization-based sampling process at inference time, where samples are obtained by gradient descent on the learned landscape with adjustable step sizes, adaptive optimizers, and adaptive compute. Empirically, EqM achieves the best FID among the tested methods, reaching 1.90 on ImageNet 256$\times$256, while remaining competitive on other metrics. Theoretically, we show under standard assumptions that real images are attracting critical points of the learned field and the energy interpretation applies when the field is conservative. Beyond generation, EqM is a flexible framework that naturally handles tasks including partially noised image denoising, OOD detection, and image composition. By replacing time-conditional velocities with a unified equilibrium landscape, EqM offers a tighter bridge between flow and energy-based models and a simple route to optimization-driven inference.

cs.LG · cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10297

Uncertainty, Not Concealment: A Mechanistic Reappraisal of Sycophancy in Vision-Language Models

Mohamed I. Eldagla, Zeyad H. ElShafei, Ahmed M. Anter

原文摘要

Vision-language models (VLMs) in medical retrieval-augmented generation must be able to say when a retrieved report contradicts the X-ray, so understanding whether they can detect such conflicts is important for safe deployment. The sycophancy mask hypothesis holds that these models internally detect conflicts but refuse to report them, concealing a detected contradiction. We introduce a three-part diagnostic that separates concealment from uncertainty: representation probing, activation steering, and two-way forced choice. Across four instruction-tuned VLMs on chest X-rays, we confirm behavioral suppression of contradiction and find that a linear probe separates matched from mismatched inputs, beyond what a simple CLIP model achieves. Steering the learned conflict direction never elicits contradiction, and forcing a binary choice does not recover one; instead, cross-modal attention to the image drops on mismatched pairs. We conclude that these models fail to contradict because the mismatch registers as hedged, gated uncertainty rather than concealed knowledge, calling for re-grounding and uncertainty surfacing. Code is available at https://github.com/mohamed-eldagla/Uncertainty-Not-Concealment/.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10293

Sparse Predict and Demote: Optimal Scheduling with Minimal Size Advice

Chengyi Liu, Thodoris Lykouris, Junxuan Shen, Adam Wierman

原文摘要

Knowledge of job sizes is crucial for optimizing the mean response time in single-server scheduling. However, predictions of job sizes are typically inexact and may be costly to obtain. Thus, a long-standing research question is: what is the minimal information about job sizes required to obtain near-optimal mean response time? We introduce a novel policy, \emph{Sparse Predict and Demote (SPD)}, and prove that it achieves order-optimal mean response time in heavy traffic while requiring only one-bit job-size predictions for a vanishing fraction of arrivals. SPD achieves heavy-traffic order-optimality even in situations when predictions are (i) inexact up to any fixed multiplicative error bound, and (ii) costly, i.e., the server is used to compute predictions and is thus unavailable to serve jobs while processing prediction queries. Finally, we use numerical experiments to illustrate that SPD maintains near-optimal performance beyond the heavy-traffic regime.

cs.PF · cs.DS · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10288

A Clinical Evaluation of Conformal Prediction for Chest Radiograph Report Generation

Nikolaos Kontogeorgis, Pascal Krezer, Klaus-Rudolf Kladny, Arne Estler, Christian F. Baumgartner, Lisa Koch, Saif Afat, Michael Muehlebach

原文摘要

While multimodal large language models (MLLMs) have improved automated radiology report generation, they remain prone to hallucinations, necessitating clinically meaningful risk-control methods. Conformal prediction (CP) provides statistical guarantees, yet existing CP approaches rely on uncalibrated automated extractors and fail to account for the clinical relevance of errors. We introduce clinical admissibility criteria (CLARITY), a framework for evaluating radiology reports that explicitly distinguishes clinically consequential errors from minor deviations. To eliminate reliance on automatic judges, we collected radiologist annotations of MLLM-generated reports using CLARITY. By benchmarking CP strategies and automatic evaluation metrics against these expert annotations, we demonstrate that commonly used admissibility proxies systematically fail to detect clinically relevant errors. Our findings reveal that automated admissibility judgments are largely decoupled from true clinical admissibility.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.29501

Target-Aligned Reinforcement Learning

Leonard S. Pleiss, James Harrison, Maximilian Schiffer

原文摘要

Many value-based deep reinforcement learning algorithms rely on target networks - lagged copies of the online network - to stabilize training. While effective, this mechanism introduces a fundamental stability-recency trade-off: slower target updates improve stability but reduce the recency of learning signals, hindering convergence speed. We propose Target-Aligned Reinforcement Learning (TARL), a simple drop-in refinement for existing algorithms that emphasizes transitions for which the target and online network estimates are highly aligned. By focusing updates on well-aligned targets, TARL mitigates the adverse effects of stale target estimates while retaining the stabilizing benefits of target networks. We empirically demonstrate consistent improvements within discrete and continuous control algorithms across various benchmark environments without any hyperparameter tuning, including a 38.18% median peak score gain on Atari-10, while incurring less than a 4% increase in wall-clock time.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10281

Transit-Oriented Land Use Planning Using Deep Reinforcement Learning

Bo Yang, Yuebing Liang, Zhan Zhao, Fangyi Ding, Yunhan Zheng, Shenhao Wang, Jinhua Zhao

原文摘要

Transit-Oriented Development (TOD) is a key strategy for advancing sustainable urban development by promoting high-density, mixed-use land development within walking distance of public transit stations. However, traditional TOD planning often relies on heuristic methods, making it difficult to efficiently identify quantitatively optimized transit-oriented land use patterns. This paper presents DRL4TOD, a deep reinforcement learning framework that automatically optimizes land use types and floor area ratios (FARs) around transit stations in alignment with TOD principles. DRL4TOD incorporates a graph neural network to capture spatial interdependencies among land parcels, road networks, and metro stations, and uses a DRL-based optimization strategy to assign land-use types and FARs to selected parcels. It jointly optimizes multiple objectives, including land use density, land use diversity, and transit capacity utilization, while minimizing reconstruction costs to account for development feasibility. Applied to two real-world station areas in Shanghai, DRL4TOD consistently outperforms rule-based approaches and genetic algorithms, achieving more effective TOD outcomes with lower reconstruction costs. By adjusting objective weights, the framework enables flexible prioritization, such as placing greater emphasis on cost minimization when financial feasibility is a concern. These results demonstrate DRL4TOD's potential as a decision-support tool for generating coordinated land-use and FAR configurations under planner-specified priorities, rather than prescribing a single fixed design. For policymakers, the framework provides parcel-level, constraint-aware alternatives that make trade-offs among competing objectives explicit and support targeted decisions about development intensity and feasibility.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10279

Restoring General and Improving Domain-Specific Safety in Fine-Tuned LLMs Without Retraining

Vishnu Kabir Chhabra, Ding Zhu, Zhihui Zhu, Xueru Zhang, Mohammad Mahdi Khalili

原文摘要

Safety-aligned language models are known to suffer degradation in refusal behavior following domain-specific fine-tuning, even when the fine-tuning data is entirely benign. The predominant mitigation strategy, preference optimization on the fine-tuned model, is computationally expensive and requires domain-specific preference data that is often unavailable in practice. We propose SPECTRA, a training-free, weight-level method that restores refusal behavior by transferring the base model's refusal direction into the fine-tuned model's weights via an activation-aware, low-rank update, requiring no gradient-based optimization or domain-specific safety data. The low-rank design restricts the intervention to the subspace most causally active on harmful inputs, leaving benign behavior largely undisturbed by construction. Empirically, SPECTRA substantially improves refusal behavior across a comprehensive safety evaluation, while preserving general coherence, domain-specific knowledge, and producing negligible change in false refusal rates.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.03461

Soft-Radial Projection for Constrained End-to-End Learning

Philipp J. Schneider, Daniel Kuhn

原文摘要

Constrained end-to-end learning trains neural networks whose outputs must satisfy feasibility constraints, such as resource, budget, or operational limits. While projection and optimization layers guarantee constraint satisfaction, boundary-based projections can introduce unfavorable optimization geometry: regions of the unconstrained output space are mapped to the same active face of the feasible set. This makes the resulting map locally rank-deficient, suppressing gradients in constrained directions and potentially impairing optimization - a bottleneck known as gradient saturation. We propose Soft-Radial Projection (SRP), a differentiable reparameterization layer that maps unconstrained network outputs into the relative interior of a convex feasible set by smoothly rescaling rays from a strictly feasible anchor point. Unlike hard radial or orthogonal projections, the resulting map is one-to-one and has a full-rank Jacobian almost everywhere, while guaranteeing strict feasibility. We prove that constrained networks equipped with SRP retain universal approximation guarantees. For polytopes and balls, the layer admits a closed-form forward pass, while for general convex sets, the ray-boundary intersection reduces to a one-dimensional search. Experiments on decision-focused learning benchmarks demonstrate strong solution quality at low computational cost, with particularly favorable results in portfolio optimization and substantially lower inference latency than differentiable optimization layers in the evaluated settings.

cs.LG · math.OC · q-fin.CP · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.26994

ImmSET: Sequence-Based Predictor of TCR-pMHC Specificity at Scale

Marco Garcia Noceda, Matthew T Noakes, Andrew FigPope, Daniel E Mattox, Bryan Howie, Harlan Robins

原文摘要

T cells are a critical component of the adaptive immune system, playing a role in infectious disease, autoimmunity, and cancer. T cell function is mediated by the T cell receptor (TCR) protein, a highly diverse receptor targeting specific peptides presented by the major histocompatibility complex (pMHCs). Predicting the specificity of TCRs for their cognate pMHCs is central to understanding adaptive immunity and enabling personalized therapies. However, accurate prediction of this protein-protein interaction remains challenging due to the extreme diversity of both TCRs and pMHCs. Here, we present ImmSET (Immune Synapse Encoding Transformer), a novel sequence-based architecture designed to model interactions among sets of variable-length biological sequences. We train this model across a range of dataset sizes and compositions and study the resulting models' generalization to pMHC targets. We describe a failure mode in prior sequence-based approaches that inflates previously reported performance on this task and show that ImmSET remains robust under stricter evaluation. In systematically testing the scaling behavior of ImmSET with training data, we show that performance scales consistently with data volume across multiple data types and compares favorably with the pre-trained protein language model ESM2 fine-tuned on the same datasets. Finally, we demonstrate that ImmSET can outperform AlphaFold2 and AlphaFold3-based pipelines on TCR-pMHC specificity prediction when provided sufficient training data. This work establishes ImmSET as a scalable modeling paradigm for multi-sequence interaction problems, demonstrated in the TCR-pMHC setting but generalizable to other biological domains where high-throughput sequence-driven reasoning complements structure prediction and experimental mapping.

cs.LG · q-bio.QM

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2508.00110

funOCLUST: Clustering Functional Data with Outliers

Katharine M. Clark, Paul D. McNicholas

原文摘要

Functional data present unique challenges for clustering due to their infinite-dimensional nature and potential sensitivity to outliers. An extension of the OCLUST algorithm to the functional setting is proposed to address these issues. The approach leverages the OCLUST framework, creating a robust method to cluster curves and trim outliers. The methodology is evaluated on both simulated and real-world functional datasets, demonstrating strong performance in clustering and outlier identification.

stat.ML · cs.LG · stat.ME

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.07972

It Just Takes Two: Scaling Amortized Inference to Large Sets

Antoine Wehenkel, Michael Kagan, Lukas Heinrich, Chris Pollard

原文摘要

Neural posterior estimation has emerged as a powerful tool for amortized inference, with growing adoption across scientific and applied domains. In many of these applications, the conditioning variable is a set of observations whose elements depend not only on the target but also on unknown factors shared across the set. Optimal inference therefore requires treating the set jointly, which in turn requires training the estimator at the deployment set size -- a regime where memory and compute quickly become prohibitive. We introduce a simple, theoretically grounded strategy that decouples representation learning from posterior modeling. Our method trains a mean-pool Deep Set on sets of size at most two, producing an encoder that generalizes to arbitrary set sizes. The inference head is then finetuned on pre-aggregated embeddings, making training cost essentially independent of the deployment set size N. Across scalar, image, multi-view 3D, molecular, and high-dimensional conditional generation benchmarks with N in the thousands, our approach matches or outperforms standard baselines at a fraction of the compute.

cs.LG · cs.AI · hep-ex · hep-ph · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10267

Match the Geometry Before the Surrogate: Extreme Low-Budget Optimization in High Dimensions

Michal Průšek, Adam Novozámský, Filip Šroubek

原文摘要

Low-budget molecular optimization is often framed as Bayesian optimization in a learned latent space, but standard benchmarks typically allow hundreds or thousands of evaluations, whereas a realistic wet-lab round may allow only a few dozen. We revisit this regime using a SELFIES molecular variational autoencoder (VAE) with a Gaussian prior and GuacaMol objectives at N = 30 evaluations. The main finding is not a new surrogate model, but an interaction in candidate generation. The encoder means of a reference set of molecules concentrate near a narrow spherical shell, while many high-dimensional optimizers propose candidates from boxes or box-shaped trust regions. We study a simple constraint, the on-sphere scaffold, that restricts candidate generation to this shell. We then introduce two minimal optimizers to probe what remains useful once the support is fixed. GeoWalk performs geodesic local search on the shell without a surrogate. After 30 evaluations, it shows no detected difference from a Gaussian-process (GP) surrogate on the shell, which is ahead earlier in the budget. GeoCMA adds covariance learning in a random subspace. It does not improve on GeoWalk in the molecular benchmark. On LassoBench it has a lower mean loss than GeoWalk, but full-dimensional CMA-ES remains stronger on most tasks. A factorial experiment with a single GP crosses the candidate support (shell or box) with the acquisition maximizer (a finite candidate set or a continuous optimizer). In this benchmark, shell candidates outperformed box candidates when acquisition was maximized over a candidate set, but not with continuous maximization by L-BFGS-B. These results come from a controlled study of one Gaussian-prior VAE benchmark and do not recommend VAEs for molecular optimization. The practical lesson is to control the candidate support and the acquisition maximizer before attributing a gain to the surrogate.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33133

PINND: Physics Informed Neural Networks for Solving the Drift-Diffusion Equations

Luke Ragan, Matteo G. C. Alasio, Enrico Bellotti, Luca Dal Negro

原文摘要

The drift-diffusion equations are the fundamental building block for the modeling, design, and optimization of modern semiconductor devices. Solutions of the drift-diffusion equations rarely give way to analytical forms, and exhibit strong nonlinearity, with the solutions ranging over several orders of magnitude. These attributes have led to research into numerical solvers, and while many commercial Technology Computer Aided Design (TCAD) packages now exist, they may require long simulation times, exhibit sensitivity to initial guesses, and rely on mesh generation. Further, these solvers are not well suited for inverse problems where the design parameters of a device are retrieved from its desired functional characteristics. To address all these challenges, this work demonstrates the usage of Physics Informed Neural Networks for the Drift-diffusion (PINND) equations with errors comparable to traditional simulation software using advanced training techniques to solve problems beyond the well-behaved equilibrium regime. For this study, we specifically choose an abrupt PN-junction in both one and two dimensions that features extreme gradients of the carrier concentrations at the Ohmic contacts and an abrupt discontinuity in the doping profile. Using the proposed PINN architecture, we are able to retrieve accurate results for all observables under all bias conditions. Additionally, we apply the PINN solver towards the inverse problem of retrieving doping profiles directly from desired electric field distributions or electrostatic potentials under non-zero applied biases. Our work establishes a powerful PINNs-based approach for semiconductor device modeling with the ability to solve inverse problems under non-equilibrium conditions for microelectronics research and discovery.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.11776

MUSE: Multi-Tenant Model Serving With Seamless Model Updates

Cláudio Correia, Alberto E. A. Ferreira, Lucas Martins, Miguel P. Bento, Sofia Guerreiro, Ricardo Ribeiro Pereira, Ana Sofia Gomes, Jacopo Bono 等 10 位作者

原文摘要

In binary classification systems, decision thresholds translate model scores into actions. Choosing suitable thresholds relies on the specific distribution of the underlying model scores but also on the specific business decisions of each client using that model. However, retraining models inevitably shifts score distributions, invalidating existing thresholds. In multi-tenant Score-as-a-Service environments, where decision boundaries reside in client-managed infrastructure, this creates a severe bottleneck: recalibration requires coordinating threshold updates across hundreds of clients, consuming excessive human hours and leading to model stagnation. We introduce MUSE, a model serving framework that enables seamless model updates by decoupling model scores from client decision boundaries. Designed for multi-tenancy, MUSE optimizes infrastructure re-use by sharing models via dynamic intent-based routing, combined with a two-level score transformation that maps model outputs to a stable, reference distribution. Deployed at scale by Feedzai, MUSE processes over a thousand events per second, and over 55 billion events in the last 12 months, across several dozens of tenants, while maintaining high-availability and low-latency guarantees. By reducing model lead time from weeks to minutes, MUSE promotes model resilience against shifting attacks, saving millions of dollars in fraud losses and operational costs.

cs.LG · cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.06660

Verifier-Backed Hard Problem Generation for Mathematical Reasoning

Yuhang Lai, Jiazhan Feng, Yee Whye Teh, Ning Miao

原文摘要

Large Language Models (LLMs) demonstrate strong capability in solving scientific and mathematical problems, yet they struggle to produce valid and challenging novel problems -- an essential component for advancing LLM training and enabling autonomous scientific research. Existing problem generation approaches either depend on expensive human expert involvement or adopt naive self-play paradigms, which frequently yield invalid problems due to reward hacking. This work introduces VHG, a verifier-backed hard problem generation framework built upon three-party self-play. By integrating an independent verifier into the conventional setter-solver duality, our design constrains the setter's reward to be jointly determined by problem validity (evaluated by the verifier) and difficulty (assessed by the solver). We instantiate two verifier variants: a Hard symbolic verifier and a Soft LLM-based verifier, with evaluations conducted on indefinite integral tasks and general mathematical reasoning tasks. Experimental results show that VHG substantially outperforms all baseline methods by a clear margin. Our code is available at https://github.com/Miaow-Lab/VHG.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10261

Is Recursive Self-Improvement Safe?

Vincent Conitzer

原文摘要

The phrase recursive self-improvement (RSI) refers to the idea of an AI system designing and creating another, better AI system, which in turn designs and creates an even better one, and so on. While the idea has a long history, it has always been an abstract, futuristic idea -- until recently. Today's frontier AI has attained a set of abilities, including in programming, mathematics, research, tool use, and working coherently over extended periods of time, that make RSI seem plausible. AI companies are starting to pursue it, but many of the involved people are also expressing concerns, asking whether humanity should really set this in motion and under what conditions. I will discuss the situation, argue that we do not even have clear frameworks for thinking about the likely outcomes of RSI, and do a quick game-theoretic analysis of how to choose whether to initiate RSI when another party is making the same choice.

cs.AI · cs.GT · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10258

Beyond the Prompt: Leveraging Pre-Decoding States for Jailbreak Detection in dLLMs

Adam Hazimeh, Amel Abdelraheem, Ke Wang, Mariam Salman, Ljiljana Dolamic, Gérôme Bovet, Pascal Frossard

原文摘要

Diffusion large language models (dLLMs) have recently emerged as a strong alternative to autoregressive models, generating responses by iteratively refining masked tokens in parallel rather than decoding sequentially. While enabling more efficient and flexible inference, dLLMs remain vulnerable to jailbreak attacks, including recent attacks that exploit properties unique to dLLMs such as bidirectional conditioning and parallel masked-token refinement. In this work, we show that these same properties also expose a safety-relevant detection surface absent from standard autoregressive decoding: even when a jailbreak is difficult to identify from prompt representations alone, it can still be detected from hidden states over masked response positions before any tokens are generated. By training linear classifiers on prompt and pre-decoding response representations, we empirically show that neither view strictly dominates, with each detecting attacks that the other misses. We introduce $\texttt{ReFuse}$ (Representation Fusion), an inference-time detector that fuses the sigmoid harmfulness scores of the two classifiers. Without modifying model weights or the decoding procedure, $\texttt{ReFuse}$ reduces average ASR across multiple jailbreaks from 63.29% for the undefended model and 11.27% for a prompt-only classifier to 3.31%, while keeping average benign refusal on standard utility benchmarks below 1% on LLaDA-8B. Together, these results establish $\texttt{ReFuse}$ as a lightweight jailbreak detector for dLLMs that improves safety beyond prompt-only detection.

cs.CL · cs.CY · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2608.26086

TraceML: What Auto-Research Agents Miss in Long-Horizon ML Development

Jiarui Yan, Weiwei Sun, Sijie Li, Wenhan Li, Yiming Yang

原文摘要

Auto-research agents now run machine-learning development unattended for hours, revising data pipelines, models, and validation from their own feedback, yet on most competitions they still finish below strong human competitors. Outcome-based benchmarks record this gap but not its cause, because they grade the final submission and discard the development process behind it. We introduce TraceML, which pairs human and agent work on the same competitions under one version-level schema: 4,465 human Kaggle trajectories across 134 competitions, seven of which are also worked by two agent scaffolds, giving 430 paired human and 207 agent trajectories. Every code version carries its score, its timestamp, and labels for the action taken, its intent, the edit size, and the score effect. Read this way, the gap becomes concrete. Experts alternate data work, validation, model changes, and ensembling, and return to approaches they had set aside. Each agent scaffold instead collapses into a narrow loop: Codex spends its steps re-weighting ensembles and tuning submissions, MLEvolve mutates its model in place, and neither pivots at the human rate nor reopens abandoned work. A short planning prompt distilled from human practice moves the behaviors it names toward the human profile and lifts scores, but the effort profile stays agent-shaped: instruction closes only the part of the gap that reduces to instructions. We release the corpus, the schema, and the labeling models, together with an open-source toolkit that turns a run from any command-line agent into a TraceML trajectory and reads it against the human cohorts.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10249

Beyond Frame-Level Accuracy: Analyzing Video-Level Stability in Transformer-Based Deepfake Forensics

Syed Azmul Hasan, Mowmita Pervin Hera, Afroza Lona Mim, M M Jihad Hossain, Hazrat Ali, Mohammad Farhad Bulbul

原文摘要

Deepfake videos generated by advanced generative models pose serious threats to digital security, misinformation control, and media forensics. Although numerous detection methods have been proposed, their reported performances are often based on heterogeneous preprocessing pipelines, inconsistent data splits, and model-specific training protocols, hindering fair architectural comparison. This work presents a controlled and reproducible comparative study of convolutional neural networks (ResNet-18 and EfficientNet-B0) and a transformer-based architecture (ViT-B/16) within a unified, face-centric deepfake detection framework. All models are trained using identical preprocessing, augmentation, optimization settings, and data splits on Celeb-DF v2 and FaceForensics++, and results are validated across three independent random seeds with bootstrapped confidence intervals. Experimental results show that while CNN-based models perform competitively at the frame level, their performance degrades after video-level aggregation. In contrast, ViT-B/16 demonstrates more stable video-level performance, achieving 92.8\% [95\% CI: 91.7--94.0] video-level accuracy and an AUC of 0.950 [95\% CI: 0.934--0.964] on Celeb-DF v2 (3-seed bootstrapped). Cross-dataset evaluation across the same three random seeds reveals a large, asymmetric generalization gap (AUC 0.79 FF++$\rightarrow$Celeb-DF vs. 0.64 Celeb-DF$\rightarrow$FF++), indicating that in-domain video-level stability does not transfer to unseen manipulation domains. These findings indicate that global self-attention improves robustness and video-level stability for deepfake detection within a given data domain, while highlighting the need for further work on cross-domain generalization.

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10248

FedLoVA: Value-Only Aggregation for Federated LoRA Fine-Tuning of Large Language Models

Ensieh Khazaei, Baturalp Buyukates, Dimitrios Hatzinakos

原文摘要

Low-Rank Adaptation (LoRA) is a popular parameter-efficient fine-tuning (PEFT) method for fine-tuning of large language models (LLMs), especially in federated learning, due to its strong performance and communication efficiency. In practice, LoRA is applied to the query and value projections of transformer layers without considering the distinct roles of these components. In this work, we analyze the impact of these projections in federated fine-tuning of LLMs using LoRA and observe that the value projection converges significantly faster than the query projection. Motivated by this finding, we propose FedLoVA, a federated fine-tuning framework that trains LoRA adapters on both query and value projections locally while sharing only the value projection with the server. This approach reduces communication overhead while improving convergence efficiency. Experiments on natural language understanding, multilingual sentiment analysis, and generation tasks show that FedLoVA reduces the communication cost by up to $7.8\times$ compared to existing federated LLM fine-tuning baselines while achieving comparable or better performance. The code is available at: https://github.com/EnsiehKhazaei/FedLoVA.

cs.LG

查看论文
arXiv ↗PDF ↗