跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

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

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

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

统计口径与数据新鲜度

统计 2026-11-11 17:32 — 2026-11-12 17:32（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

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

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

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

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 4,903 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-12 17:15（北京时间）
版本更新 · v2arXiv:2610.27726

Anytime-Valid Runtime Monitoring of Learned Barrier Certificates

Zhipeng Cao, Taoran Wu, Weiru Cui, Luke Ong, Bai Xue

原文摘要

Learned barrier certificates provide a principled mechanism for establishing safety of stochastic systems, but their validity may deteriorate during deployment when the underlying dynamics differ from those used for training. We propose an anytime-valid runtime monitor that audits a learned barrier certificate using observed closed-loop trajectories. The monitor is intended to detect loss of statistical support for the deployed barrier condition; it does not by itself guarantee detection before unsafe entry or safety of a subsequent intervention. Specifically, the conditional barrier-drift condition is formulated as an episode-wise sequential hypothesis test, and observed barrier increments are transformed into a nonnegative test supermartingale, yielding finite-sample false-alarm control under arbitrary stopping times. Inspired by finite-horizon safety verification, we further introduce a deterministic temporal shaping of the monitoring boundary, making the monitor more conservative early in a prescribed deployment horizon while preserving anytime-validity. The monitor is designed to detect statistical evidence that the safety certificate is no longer consistent with the observed dynamics, rather than to predict unsafe entry. To assess the monitor empirically, we evaluate empirical alarm behavior under valid and invalid certificates. Code and data are available at https://github.com/FormalCert-AI/runtime-barrier-monitor.

eess.SY · cs.AI · cs.LG · math.OC · math.ST

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2510.11370

Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers

Wenhan Ma, Hailin Zhang, Liang Zhao, Yifan Song, Yudong Wang, Zhifang Sui, Fuli Luo

原文摘要

Reinforcement learning (RL) has emerged as a crucial approach for enhancing the capabilities of large language models. However, in Mixture-of-Experts (MoE) models, the routing mechanism often introduces instability, even leading to catastrophic RL training collapse. We analyze the training-inference consistency of MoE models and identify a notable discrepancy in routing behaviors between the two phases. Moreover, even under identical conditions, the routing framework can yield divergent expert selections across repeated forward passes. To address this foundational inconsistency, we propose Rollout Routing Replay (R3), a method that records routing distributions from the inference engine and replays them during training. R3 significantly reduces training-inference policy KL divergence and mitigates extreme discrepancies without compromising training speed. Extensive experiments on various settings confirm that R3 succeeds in stabilizing RL training, preventing collapse and outperforming methods such as GSPO and TIS. We believe this work can offer a new solution for stabilizing RL in MoE models.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12000

HyPLM Technical Report

Haowei Lin, Cai Zhou, Xiangxin Zhou

原文摘要

Protein language models (PLMs) are standard tools for variant-effect prediction, protein annotation and design, but the compute needed to train and serve them keeps growing. We present HyPLM-Flash, an efficient and open PLM trained by Hyra 2.0, the research agent developed by our team. HyPLM-Flash is a 650-million-parameter masked language model trained on 726 billion tokens, 0.73 times the data of ESM-2 650M and a fifth to an eighth of the data of E1-600M and ESM C 600M. It runs on an inference engine with fused kernels and INT8 matrix multiplication, embedding about 130,000 residues per second on a single NVIDIA H20 GPU, 1.9 to 2.7 times faster than other 600M-class encoders. In a matched evaluation against 28 public checkpoints on 32 tasks, HyPLM-Flash reaches a ProteinGym zero-shot Spearman correlation of 0.409, statistically tied with ESM-2 650M, ESM C 600M and E1-600M, and the highest organismal-fitness score among self-supervised single-sequence models. It gives the best long-range contact precision of all models evaluated, including ESM-2 15B and ESM C 6B, and a lower masked-residue loss than ESM-2 650M, ESM C 600M and E1-600M on held-out sequences and on recently released PDB chains. Matching state-of-the-art accuracy at a fraction of the training and inference cost, HyPLM-Flash sets a new Pareto frontier for protein language models. We have released the model weights and the inference engine at https://github.com/Tencent-Hunyuan/hyra-results/tree/main.

cs.LG · q-bio.BM

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.13389

Logit-Conditioned Diffusion Decoding for Frozen Discrete-Token VLMs

Ji Woo Hong, Gwanhyeong Koo, Hee Suk Yoon, Eunseop Yoon, SooHwan Eom, Qi Dai, Chong Luo, Chang D. Yoo

原文摘要

Pre-trained discrete-token VLMs generate images by sampling sequences of codebook indices, but their visual fidelity is bounded by the VQ-VAE decoding stage. Prior work addresses this bottleneck by replacing the discrete tokenizer with continuous or hybrid visual token representations, or by integrating diffusion into the generation pipeline; both require foundation-scale VLM retraining or realignment. We show this is unnecessary: before each token is sampled, discrete-token VLMs already compute a full logit distribution over the codebook, but standard decoding discards it after selecting a single index. Under Otsu's threshold, the pre-sampling logits of capable VLMs assign statistically meaningful probability to at least two codebook entries per token, and recovering this distribution can substantially close the fidelity gap. We propose DCDD, a post-hoc framework that conditions a diffusion decoder on this discarded distribution while leaving the VLM frozen. At inference, DCDD converts the VLM's pre-sampling logits into distribution-weighted code vectors; during training, it uses VQ-VAE encoder-derived proxy logits calibrated to match the distributional statistics of the VLM's inference-time logits. The decoder maps these representations to high-fidelity images as an alternative to the native VQ-VAE decoder. Trained on ImageNet-1K for 50K steps, DCDD reduces reconstruction FID by 74% and Janus-Pro 7B's generation FID on MJHQ-30K by 34%, while semantic alignment across GenEval, DPG-Bench, and WISE remain consistent. Controlled comparisons with diffusion models from the same backbone family, applied either as an image-to-image refiner or as an identically trained decoder on the sampled codes, confirm that the gain stems from conditioning on the VLM's pre-sampling logit distribution rather than from the diffusion model itself.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11998

Reward-Estimated Hypergradient for Bilevel Reinforcement Learning with Black-Box Follower

Shigeki Kusaka, Mikoto Kudo, Takumi Tanabe, Akifumi Wachi, Youhei Akimoto

原文摘要

Hypergradient (HG) methods for bilevel reinforcement learning (RL) typically assume a white-box follower whose reward is known. In practice, however, the leader rarely knows the follower's reward function and can only observe its trajectories. We address this black-box setting and propose Reward-Estimated Hypergradients (RE-HG), which recovers the follower's reward from these trajectories via inverse RL (IRL). Yet IRL identifies the reward only up to potential-based shaping, a transformation that leaves the follower's behavior unchanged but biases the HG. We prove that, for linear rewards, this bias cancels when IRL estimates are aggregated across sufficiently diverse dynamics, which the leader's own updates naturally supply. To handle finite samples, RE-HG truncates small eigenvalues of the aggregated feature covariance, restoring the identifiable subspace and stabilizing the estimation. Experiments show that RE-HG estimates gradients aligned with a white-box Oracle and achieves comparable performance; empirically, the truncation also suppresses HG explosions, letting RE-HG avoid local optima that trap the Oracle in sharp reward landscapes.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11997

HyInv Technical Report

Haowei Lin, Cai Zhou, Xiangxin Zhou

原文摘要

Inverse folding designs amino-acid sequences for a given protein backbone, and screening needs many candidates that are both diverse and well folded. We present HyInv, a 1.96-million-parameter backbone-conditioned graph network with an encoder-decoder architecture, trained by Hyra 2.0, the research agent developed by our team: pretrained with random-order autoregressive sequence modeling, followed by structure-reward reinforcement learning. At inference, a grouped draft-and-rewrite sampler that uses separate draft and rewrite temperatures improves refolding TM-score at matched diversity. An optimized implementation with BF16 numerics designs 128 sequences for a 402-residue backbone in 50.6 ms on a single NVIDIA H20 GPU, about 52 times faster than the reference sampler, and an exact FP32 path that returns the reference sequences is 8.7 times faster. Across five benchmark datasets and seven dataset-predictor combinations, HyInv reaches a higher average scTM than all ten external baselines at comparable or higher sequence diversity, with large margins over ProteinMPNN and ProteinZero V2. The same default setting supports de novo backbones, pocket-constrained libraries, enzyme redesign with the catalytic site kept, and loop redesign. We have released our code and model at https://github.com/Tencent-Hunyuan/Hyra-results/tree/main/AI4Science/hyinv.

cs.LG · q-bio.BM

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.06274

When the Agent Edits Its Own Limits: Evaluating a Write-Time Floor Against Prompt Prohibitions

Sajib Hossain, Moeen Uddin Mahmud

原文摘要

Many agent runtimes give the agent a tool for editing its own configuration. Some settings grant abilities, such as enabling a tool. Others set the agent's limits: where it may write, who may message it, which address it listens on, how callers authenticate, and the gate that blocks risky writes. We measure how often models widen those limits while handling ordinary requests, and how well two kinds of defence hold: a prohibition in the system prompt, in three wordings, and a check at the point of writing that we call a containment floor. Every case records whether a protected write was attempted and whether it was saved, read from the tool's arguments and from the file rather than from the model's reply. With no defence, a frontier model saved a protected value on 25 of 72 requests, often when the request never named the field. A prompt that listed the protected field names stopped every request that used those names and did not reduce writes on requests that only described the goal; a prompt that described the forbidden effects did the reverse. With the floor, 0 of 167 protected writes were saved while 65 were attempted. A single-pass pilot on two further models shows the same pattern. We draw four lessons for evaluating agent safeguards: count attempts beside outcomes, test a prompt defence with requests written in a different vocabulary from the prompt, check that a zero means the safeguard fired, and log what the harness sends to the model, because a request-ordering defect in our own runtime was invisible in the transcripts and was found again, independently, by a later benchmark.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11989

MUTE: Multi-Level Alignment Uncoupling Against Talking-Head Exploitation for Voice Protection

Donghyun Kim, Jin Hong, Seungmin Kim, Dain Kim, Junseok Kwon, Daeseon Choi

原文摘要

Talking-head generation models, which synthesize realistic facial animations from audio, are increasingly vulnerable to misuse in multimodal deepfake scenarios. Protecting such systems remains challenging, as talking-head models fundamentally rely on precise audio-visual alignment, while effective audio protection methods remain largely underexplored. In this work, we propose MUTE, an audio protection framework that uncouples the underlying audio-visual alignment through a multi-level strategy. Specifically, MUTE combines (1) Alignment-level Disruption, which directly perturbs cross-modal attention to disrupt structural alignment, and (2) Representation-level Degradation, which perturbs temporal audio embeddings to degrade their representations. To improve robustness, perturbations are constrained in the STFT domain to high-energy regions, making them resistant to post-processing, denoising, and adaptive attacks. An optional speaker-level objective further mitigates potential bypass via TTS-based resynthesis. Extensive experiments demonstrate that MUTE consistently degrades lip synchronization across both white-box and black-box talking-head models while preserving perceptual audio quality. The proposed method remains effective under real-world transformations and can be combined with image-based approaches to provide stronger multimodal protection. The source code and project page are available at https://github.com/jindl465/MUTE.

cs.SD · cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11985

Trajectory Density Ratios under Weak Support: A Survey across the Sciences

Wei Chen, Lihao Zhuang, Yubing Wu, Delu Zeng

原文摘要

Many problems across the sciences compare two stochastic processes through the sequences they generate. Reinforcement learning asks what a new policy would return from the trajectories of an old one; molecular simulation asks how much more a ligand binds from samples of the unbound state; climate attribution asks how a heat wave shifted under warming; and language-model post-training asks what a deployed agent will do from logged interactions. In every case, one quantity would answer all these questions at once: the ratio of the two probability laws over their generated sequences, the trajectory density ratio. This ratio exists only under strong conditions. When one process reaches states the other cannot, the ratio does not exist; when their overlap is thin, its variance grows without control with the sequence length; and when they concentrate on different lower-dimensional sets, the ratio is undefined altogether. Weak support of this kind is the norm for sequence data, not a sampling accident, and its price is paid in identifiability rather than in noise alone. This survey organizes the field around a three-level diagnosis of weak support and a map of the nine retreats that methods take when the full ratio is out of reach, from direct estimation and reweighting through staged decomposition, stationarization, and partial-identification bounds to smoothing, transport couplings, operator spectra, and direct estimation of a single functional. Each retreat keeps part of what the ratio offers and pays for the rest, and each application domain has standardized the retreat its data force. The survey closes with open problems: testable diagnostics at every level, partial identification at the trajectory level, a rate theory of time-amplified error, and benchmarks with ground truth.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11979

FireGate: Bounding Behaviour Change Before Training in Continual RL Fine-Tuning

Md Anwar Hossen, Ali Jannesari

原文摘要

Fine-tuning a deployed language model on one task after another can change behaviour that should stay fixed, such as earlier skills, general chat or refusals. Today, such forgetting is found only after training, on the benchmarks someone chose to run. This work bounds, before training, how often its outputs change on chosen prompt distributions. FireGate places each task's update, such as a new LoRA, behind a gate, which is a classifier on the model's frozen lower layers that decides for each prompt whether the update is used. Where no gate fires, the model computes exactly what the old one computes. As a result, on any prompt distribution, every bounded behaviour score changes by at most the gates' firing rate there over a whole task stream. Calibrating each gate on unlabeled prompts of what must not change fixes that rate before training, with a PAC guarantee, whatever weights training produces. Forgetting is thus bounded by the gate's false-alarm rate, and its price is the gate's power: no update, gated or not, that changes as few protected outputs can change new-task outputs more often than the best test of that level tells new-task prompts from protected ones. On reinforcement-learning streams of up to five tasks, gated training keeps the earlier tasks and changes 3.3% of held-out chat responses, whereas ungated training changes 91.8%. Across seven models, the gain kept behind the gate follows its firing rate on new-task prompts, measured before training. The certificate covers the gated model as deployed, on the prompt distributions sampled for calibration, not against an adversary who searches for prompts that fire the gate.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11977

MixRoute: Rethinking Single-Distribution Training for Generalizable Neural Routing

Hang Yi, Ziwei Huang, Yining Ma, Zhiguang Cao

原文摘要

Neural Combinatorial Optimization (NCO) is a promising paradigm for solving routing problems, yet its generalization across diverse data distributions remains a critical bottleneck. Existing methods typically tackle cross-distribution generalization through complex multi-distribution training or intricate meta-learning schemes, implicitly presuming that single-distribution training yields a weak zero-shot baseline. In this paper, we demonstrate that the potential of single-distribution training has been substantially underestimated and can be unlocked by a simple architectural inductive bias: Mix Normalization. To approach this, we first construct a comprehensive benchmark spanning three representative routing problems and 179 fine-grained datasets, capturing diverse shifts in node coordinates, customer demands, capacity and time windows. Building on this benchmark, we propose MixRoute, a neural framework that adaptively combines normalization statistics at different granularities to mitigate varying distribution shifts. Trained exclusively on uniform distributions, MixRoute generalizes effectively to a wide range of unseen distributions without any distribution-specific adaptation. Extensive experiments demonstrate that MixRoute consistently achieves state-of-the-art zero-shot generalization. Our work revisits normalization as a parsimonious alternative for zero-shot generalization against complex training-adaptation schemes.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11976

ShiftCache: Fast and Exact Indel Effect Prediction by Reusing Shifted Reference Encodings

Sina Barazandeh, Arth Banka, Jose Lugo-Martinez

原文摘要

Sequence-to-function models such as AlphaGenome and Borzoi read up to a megabase of DNA and score a genetic variant by comparing their predictions for the reference and alternate sequences. Insertions and deletions (indels) are costly to score, because an indel usually shifts the unchanged DNA after it onto a different pooling grid, which prevents direct reuse of the reference's encoder activations. The AlphaGenome Atlas scored more than 100 million indels with three full model passes each, although the DNA after an indel matches the reference shifted by the indel's length. We present ShiftCache, an exact reuse system that encodes each shifted reference once and shares it among all variants scored in the same window with the same shift. ShiftCache copies every encoder output a variant can reuse and recomputes the rest in batched tiles. On held-out AlphaGenome windows shared by many indels, in strict fp32 on one A6000, ShiftCache is 3.5 to 6.5$\times$ faster than deduplicated dense execution and 1.6 to 2.7$\times$ faster than our adaptation of layer-by-layer reuse to indels. It is 3.5 to 4.1$\times$ faster than dense reimplementations of two published analyses with Borzoi and AlphaGenome, and 2.6$\times$ faster than dense execution with Enformer. Scoring each variant in its own centered 131 kb window makes ShiftCache only 1.36$\times$ faster than deduplicated dense execution, and highly diverse insertion lengths or many dispersed edits can make it slower than layer-by-layer reuse or dense execution. For encoders that meet our conditions, ShiftCache computes the same predictions as dense execution in exact arithmetic. On an A6000, every checked output of the default AlphaGenome and Borzoi runs matches dense execution within an absolute and relative tolerance of $10^{-5}$. With larger tile batches, with Enformer or on an H100, a small fraction of values exceeds this tolerance.

cs.LG · cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v7arXiv:2602.14612

Event-Grounded Question Answering over Long Audio via Structured Retrieval

Kartik Hegde, Arvind Krishna Sridhar, Naveen Vakada, Yinyi Guo, Erik Visser

原文摘要

Answering natural-language questions over multi-hour audio requires reliable event recognition, temporal grounding, and efficient retrieval. We present LA-RAG (Long Audio Retrieval-Augmented Generation), a structured framework that converts audio into timestamped event records, stores them in an event database, and answers questions using intent-aware retrieval and LLM-based generation. LA-RAG supports two deployment settings: offline grounding mode, in which long recordings are pre-indexed for low-latency querying, and inference-time grounding mode, which performs query-conditioned grounding over shorter, open-ended clips. We evaluate LA-RAG on two synthetic 24-hour benchmarks, Home-IoT and Industrial-IoT, and on CASTELLA-QA and SpotSound-Bench-QA, which are QA versions of two public audio temporal grounding benchmarks that we construct. The results demonstrate effective long-audio question answering with low query-time latency after grounding and indexing. They also reveal a substantial gap between event detection and temporal localization in current large audio-language models. Explicit timestamped grounding consistently improves temporal localization while maintaining competitive detection accuracy. These findings establish structured grounding and retrieval as a practical complement to generative audio-language models for deployment-oriented long-audio understanding.

eess.AS · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11973

Beyond Prediction Residuals: Conformal Regret Calibration for Robust Contextual Linear Optimization

Lingjie Zhao, Hansheng Jiang, Wei Qi

原文摘要

Predict-then-optimize systems convert contextual forecasts into decisions, yet conformal robust optimization typically calibrates prediction residuals rather than downstream loss. For linear optimization, this parameter-space geometry can be badly misaligned with decision risk: large objective perturbations may preserve the optimizer, while small boundary-crossing perturbations may cause substantial regret. We introduce Conformal Regret Sets, a post-hoc, model-agnostic framework that conformalizes an optimization-derived regret surrogate and uses its calibrated level set for minimax-regret refinement. We first show that directly conformalizing exact regret, although sufficient to certify the nominal predict-then-optimize decision, yields a degenerate robust problem: absent an exogenous bounded support, every alternative decision has unbounded worst-case regret. We therefore use SPO+, a pointwise upper bound on exact regret, as the conformal score, obtaining distribution-free finite-sample marginal regret guarantees under exchangeability. For contextual linear programs, the resulting set decomposes into polyhedral pieces aligned with the normal fan of the feasible polytope. A vertex is active if and only if its predicted suboptimality gap is at most half the calibrated threshold $η$, enabling local, output-sensitive generation of all relevant pieces. Moreover, if $Γ$ is the predicted gap to the closest competing vertex, the nominal and refined decisions admit the sharper worst-case-regret certificate $(η-2Γ)_+$, with an exact early exit when $η\leq 2Γ$. Experiments on contextual fractional knapsack validate the geometry and certificates: continuous refinement reduces the $0.95$-quantile and $\operatorname{CVaR}_{0.95}$ of regret by $9.1\%$ and $13.1\%$ relative to nominal PTO, while vertex-restricted refinement changes only $10.0\%$ of nominal decisions.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11967

Pairwise distortion distribution for compression and quantization

Carl Nuzman, Jeongmin Chae, Kursat Rasim Mestav, Urbashi Mitra

原文摘要

Choosing the latent dimension is a critical challenge in data compression, where conventional hyperparameter optimization is costly and ad hoc. Intrinsic dimension provides a good alternative, which connects information-theoretic notions such as Renyi information dimension (RID) to rate-distortion dimension and random codebook compression. In this work, we introduce the pairwise distortion distribution (PDD) and its asymptotic limit, pairwise dimension (PD), which generalize the correlation integral to general distortion measures. We show that PD bounds RID, and PDD provides a lower bound for random codebook quantization performance, which can guide a practical use for compression, quantization, and dimensionality reduction applications.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11962

Shaping Useful Noise: Energy Distributions Predict Visual Pretraining Quality

Ching Lam Choi, Antonio Torralba, Phillip Isola, Stefanie Jegelka

原文摘要

Synthetic data can scale visual pretraining, but current selection criteria only partially explain which datasets train strong representations. We propose using the energy profile of a dataset--the distribution of log-probability levels it occupies under a normalised real-image density model--as an audit and curation principle for synthetic data. To operationalise this view, we introduce Energy-Level Distribution Distance (ELD), which compares real and synthetic energy distributions. Real images span sparse high-likelihood scenes and dense low-likelihood textures, so useful synthetic data should cover this energy range rather than collapse to likely but low-variation samples. Across diverse synthetic datasets, ELD exposes mismatches missed by FID and predicts pretraining performance beyond FID, LPIPS variation, and feature-space recall, including across CNN and ViT self-supervised settings. We then use ELD to resample and mix synthetic sources, matching the real-image energy histogram while preserving diversity and improving downstream transfer.

cs.LG · cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.22212

A Channel-Boosted Multi-Agent System with Iterative Consultation for Document Sensitivity Classification

Aleesha Zainab, Asifullah Khan, Muhammad Ahmed Khalid, Faheem Ullah Khan

原文摘要

Organizations in critical national infrastructure sectors must assess heterogeneous documents for sensitivity before routing or storage. Manual assessment is slow, inconsistent, and unscalable. Extending our prior leakage-controlled benchmark, BERT established the top single-encoder baseline (89.14% accuracy, 89.33% F1-score under 5-fold cross-validation on the Strategic 16K corpus). However, transformer baselines suffer from a structural limitation: fixed input length truncation discards evidence beyond the retained window-precisely where sensitive cables tend to be longest. We present Channel-Boosted MAS (CB-MAS) and instantiate it as IC-MAS (Iterative Consultation Multi-Agent System) to solve this without long-context computational costs. A Channel Critic Agent learns document-adaptive trust weights governing Gated Channel Boosting between two first-window encoders, while paired Consultation Agents iteratively exchange belief states to reconcile evidence from the beginning and end of long documents. IC-MAS holds computation constant regardless of document length by reconciling fixed windows in a compact representation space. Ablation studies show critic-controlled Channel Boosting provides the bulk of accuracy gains, while consultation recovers recall without precision collapse. Critic-Controlled Gated Channel Boosting with Max-Pool fusion and Blackboard Adaptive Consultation achieves 90.72% accuracy, 91.23% F1-score, 92.01% sensitive recall, and 90.46% sensitive precision, using about 54% less average computation than a fixed-round baseline. Gains over the single-encoder baseline are statistically significant (McNemar's test, p less than 0.000001; paired t-test). We include LIME/SHAP explainability, multi-agent evaluation, and an honest accounting of limitations.

cs.CL · cs.LG · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11960

Operation-aware Multimodal Clinical Decision Support System for ICU Discharge Risk Assessment

Guoqing Zhang, Rafik Hadfi, Takayuki Ito

原文摘要

Unplanned 30-day intensive care unit (ICU) readmission is a critical benchmark for evaluating healthcare quality. Most predictive models assume readmission risk depends solely on a patient's individual pathophysiological state, ignoring hospital operational context and resource capacity. In practice, discharge decisions are dynamic trade-offs between patient stability and bed turnover pressures. To address this gap, we develop an Operation-aware Multimodal Clinical Decision Support System (CDSS) for ICU discharge risk assessment. The system combines multi-agent collaborative extraction with self-evolving retrieval-augmented generation (RAG) to eliminate template noise from progress notes, while constructing departmental workload indicators alongside admission flow features, continuous vital signs, and sparse medical codes (ICD/DRG). Addressing severe class imbalance (about 10.5% readmissions) and alarm fatigue, we implement data normalization, class reweighting, and decision-threshold calibration. In 20 independent runs across 20,000 ICU stays from MIMIC-III, empirical findings demonstrate that: vital signs alone have limited predictive capacity under real-world class imbalance (PR-AUC of 0.1387 +/- 0.0086); directly concatenating raw text embeddings degrades decision tree performance (XGBoost and LightGBM PR-AUC drop to 0.3893 and 0.4030); whereas an end-to-end multimodal fine-tuning architecture (Transformer E2E FineTune) utilizing layer-wise parameter freezing and differential learning rates reverses text negative transfer, achieving the highest AUROC of 0.8288 +/- 0.0110, PR-AUC of 0.4373 +/- 0.0310, and F1-Score of 0.4757 +/- 0.0196. Operational indicators supply independent risk signals, laying an engineering foundation for high-utility clinical decision support tools.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.18309

Alignment Dynamics in LLM Fine-Tuning

Yuhan Huang, Huanran Chen, Yinpeng Dong

原文摘要

Although Large Language Models (LLMs) achieve strong alignment through supervised fine-tuning and reinforcement learning from human feedback, the alignment is often fragile under subsequent fine-tuning. Existing explanations either attribute alignment fragility to gradient geometry or characterize it as a distributional shift in model outputs, yet few provide a unified account that bridges parameter-space learning dynamics with function-space alignment behavior during fine-tuning. In this work, we introduce a tractable alignment score and derive its closed-form update during fine-tuning, yielding a unified framework for alignment dynamics. Our analysis decomposes alignment updates into two competing components: a Rebound Force, governed jointly by the current alignment state and the narrowness of model distribution, and a Driving Force, determined by how the training distribution aligns with outcome-conditioned posteriors over aligned and non-aligned completions. This decomposition explains why prior alignment can be reversed by later fine-tuning and why narrower posterior structure strengthens such reversal. Moreover, our framework predicts a Rehearsal Priming Effect: prior alignment leaves a latent posterior imprint that amplifies the effective Driving Force upon re-exposure, leading to faster re-alignment. We validate these predictions across safety alignment, emergent misalignment, and sentiment settings, demonstrating consistent alignment reversal and accelerated re-alignment under re-exposure. In addition, controlled experiments in safety alignment confirm the predicted dependence of rebound strength on posterior narrowness. Together, these results provide a unified dynamical perspective on how alignment is disrupted and reactivated during LLM fine-tuning.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.08136

How Far Can Untrained Neural Networks Go in Anomaly Detection? From Tables to Pixels

Hyojun Yi, Geunyoung Kim, Hogeon Seo, Seunghyoung Ryu

原文摘要

Anomaly detection (AD) is often framed as a representation-learning problem, where strong performance is expected to require learned features or AD-specific optimization. However, this view can overlook the intrinsic separability of anomalies from normal references, even in the absence of learned representations. We therefore investigate how far untrained neural networks can go in anomaly detection. To this end, we propose PRISM, a framework combining fixed random nonlinear features with normal-reference Mahalanobis scoring for tabular detection and dense visual localization. Across 47 tabular datasets in ADBench, PRISM-T achieves the highest mean AUROC (86.4%) and the second-highest mean AUPRC (65.9%) among the compared methods. On MVTec AD and VisA, covering 27 visual categories, PRISM-V achieves mean image-level and pixel-level AUROCs of 90.4% and 96.4%, respectively. Notably, both models achieve these results without neural weight optimization or pretrained representations. A theoretical analysis further characterizes how nonlinear transformations affect the mean and covariance contributions to the Mahalanobis score gap, while empirical analyses examine the resulting score separability. These findings establish PRISM as both a competitive anomaly detector and a prior-to-learning baseline for assessing the added value of learned representations in anomaly detection.

cs.LG · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.16138

Closing the Approximation Gap in Simulation-free Latent SDEs

Henry D. Smith, Brian L. Trippe, Scott W. Linderman

原文摘要

Recovering dynamical systems from noisy observations is a recurring challenge across scientific domains, including neuroscience and physics. Latent stochastic differential equations (SDEs) address this by modeling the system as an unobserved state that evolves according to a learnable SDE and generates the observations. Variational inference (VI) provides a tractable objective for fitting latent SDEs. Traditional VI algorithms evaluate this objective by numerical simulation over a time discretization, trading fidelity for computational cost. A recent class of algorithms, simulation-free VI, sidesteps this tradeoff by parameterizing the posterior through its instantaneous marginals rather than its drift. In this work, we show that the efficiency of existing simulation-free VI algorithms comes at a price: their parameterizations restrict the approximate posterior to a subset of the SDEs available to simulation-based methods, degrading posterior inference and parameter learning. We propose Helmholtz-SDE, a simulation-free VI algorithm that closes this gap by optimizing over path laws compatible with a prescribed collection of marginals. Helmholtz-SDE recovers dynamics more faithfully than prior simulation-free methods, with the largest gains under high posterior uncertainty. It further matches the performance of simulation-based VI at a fraction of the runtime. Code is available at https://github.com/lindermanlab/helmholtz-sde .

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11949

Watching Itself Watch: Self-Auditing Visual Reliance for Video Reasoning

Rohan Dugad, Mi Luo, Kristen Grauman

原文摘要

Video reasoning hinges on a small number of visually decisive tokens embedded in otherwise largely language-driven chains of thought. Yet prevailing post-training methods such as GRPO overlook this structure, assigning coarse trajectory-level rewards while requiring multiple rollouts and often costly external judges. We introduce Visually-Aware On-Policy Self-Distillation (VIOS), a post-training framework that identifies where a model under-utilizes visual evidence and concentrates learning at those positions. Our key insight is that a model can audit its own visual reliance: the divergence between its next-token distributions with and without the video reveals how strongly each prediction depends on the visual input. Measuring this reliance for both a student and an answer-privileged teacher exposes a per-token reliance gap, identifying positions where the teacher exploits visual evidence that the student overlooks. VIOS translates this signal into dense, targeted supervision through three complementary components: an exponential moving average (EMA) teacher that co-evolves with the student, a contrastive objective that encourages predictions to depend on the video, and a reliance-gap gate that focuses learning on visually under-utilized tokens. Crucially, VIOS requires only a single on-policy rollout from a single model, without external rewards, judges, or larger teachers. Across 12 benchmarks spanning general, temporal, spatial, knowledge-intensive, and long-video understanding, VIOS consistently improves three model backbones and outperforms contemporary video-reasoning systems, while training in over 9x fewer steps, 60x fewer FLOPs, and 111x fewer generated tokens. Project page: https://vision.cs.utexas.edu/projects/VIOS/

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11947

The Relative Value of Demonstration Data: Execution Time Limits and Operator Mixtures in Behavior Cloning

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

原文摘要

Robot demonstration datasets combine demonstrations from teleoperators of uneven experience, so collection teams need to know how many demonstrations from one group match those from another. We measure this with a data multiple: the ratio of the numbers of demonstrations two groups need for their policies to reach the same success rate. On robomimic's simulated Square and Can tasks, we train behavior-cloning policies on demonstrations from the two teleoperators robomimic labels Better and the two it labels Worse, varying dataset size and the share of Worse demonstrations. On Square, within robomimic's 25-second time limit, an all-Worse training set needs 1.55 times as many demonstrations as an all-Better set. Most of this difference is late completion: policies trained on Worse demonstrations finish later, as the Worse teleoperators do, and with a 100-second limit the multiple falls to 1.11. On Can, most of the difference remains at 100 seconds. If each Worse demonstration were worth 1/1.55 of a Better one, as in an all-Worse set, a half-Better, half-Worse set on Square would need 1.22 times as many demonstrations as an all-Better set. In fact, it needs 13% more than that, and this excess persists at every time limit from 20 to 200 seconds. The excess remains when training draws demonstrations uniformly instead of in proportion to their length. On Square, within the 25-second limit, switching to these Worse teleoperators is cheaper at equal success only if they earn less than a third of the Better teleoperators' hourly pay, because Worse demonstrations also take longer to record.

cs.RO · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11946

Decision Aware Origin-Destination Demand Estimation with Structurally Constrained Data

Xianzhe Wang, Yueyue Fan, Johannes Royset

原文摘要

Origin-destination (OD) demand plays an important role in transportation system design and management applications. Conventional OD estimation methods typically judge estimation quality based on how estimated demand aligns with observed traffic data and historical demand patterns. We argue that data alignment alone is insufficient; how errors in OD estimates influence downstream decision quality should also be considered. This paper develops a decision aware OD demand estimation framework that leverages structurally constrained traffic data to characterize an admissible demand region, within which we identify OD estimates that would lead to least regret in the downstream decision. Therefore, our OD estimates are both data-consistent and decision-relevant. Methodologically, we approximate the admissible demand region induced by physical network constraints through a geometric representation, which regularizes the search over feasible OD estimates. Within this regularized region, we use a convex surrogate of downstream regret to obtain a tractable decision aware optimization problem. Numerical experiments show that the proposed framework consistently reduces decision regret relative to conventional estimation benchmarks, demonstrating the value of aligning OD demand estimation with downstream decision quality.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.00580

Scaling Science: Toward a Chain Reaction of Discovery

Yuheng Ding

原文摘要

Scientific discovery advances when evidence from different investigations is brought into contact. Yet paper-centric communication leaves experimental results fragmented, delayed, or unreported, creating a "scientific memory wall" between growing computational capabilities and the evidence accessible to AI systems. Breaking this wall requires a paradigm shift in AI for Science: moving from passively mining questions out of existing datasets to actively generating and recombining experimental data around unresolved scientific questions. In a network of intelligent laboratories, a failed or overlooked experiment in one domain could trigger a hypothesis in another, whose testing generates fresh evidence that stimulates further investigations. To enable these evidence-driven chain reactions, we propose Evolving Scientific Intelligence (ESI), an architectural blueprint that connects shared scientific memory with distributed experimental loops. ESI preserves experimental records -- including negative and anomalous results -- in computable representations, allowing models to recombine evidence across domains into testable hypotheses. Rather than following fixed screening pipelines, the system jointly selects candidates and evaluation methods according to scientific value, reliability, and cost, directing distributed laboratories to produce the exact evidence needed next. Their physical feedback revises both hypotheses and evaluators, while slower meta-control reassesses research objectives and decision criteria to guard against self-reinforcing errors and misguided optimization. We call for an Information Manhattan Project to build this infrastructure for scaling science through experimentally grounded chains of discovery.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11937

Attention Is Only as Good as Its Witnesses: When Higher-Order Layers Help, and When They Do Not

Mostafa 'Neo' Mohsenvand

原文摘要

Transformers stop learning graph search as graphs grow, and learn the card game SET only after many distinct questions, although attention can represent both. We read these failures, and the uneven record of higher-order attention, from what a layer sums over: each layer we study computes the partition function of a family of witnesses and reads it at a temperature. Two laws follow. The depth law is a known result of logic, which we state for these layers: L layers over two-step walks reach exactly 2^L - 1 steps, just as a logical statement with L nested clauses of the form "there is a vertex such that" sees exactly that far. We build a construction that reaches this far, checked in Lean, and, when vertices carry no names, no such network reaches further. The size law is the cost of reading at a temperature, which logic does not have: existence is read correctly at every size, in the worst case, if and only if inverse temperature times margin is at least the logarithm of the number of candidates. Layers built on these laws, and on two principles that we test, learn where Transformers fail. One propagator layer trained on 49-vertex graphs answers every question at every search depth on 250-vertex graphs. Given the modulus 3, exponential Newton computes the softmax of 2-simplicial attention over pairs exactly in 3^d n operations for d clocks; with six clocks it learns SET from as few deals as 2-simplicial attention and transfers from 8- to 20-card tables. On CLRS-30 without hints, a 186,000-parameter block of OR-join and power-mean channels matches (within half a point) or beats a model of at least 73 million parameters on 9 of 12 graph tasks of the official test set, and on 8 of 12 with freshly drawn test graphs. The same account explains where pair layers did not help and where parallel layers must loop.

cs.LG · cs.AI · cs.NE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11936

Constrained Variational Policy Optimization for Hybrid Action Spaces

Shuchang Yan

原文摘要

Constrained reinforcement learning in hybrid action spaces must coordinate discrete modes and mode-conditioned continuous controls under long-horizon cost constraints. Existing constrained hybrid-action methods typically optimize factorized policies directly in parameter space, whereas Constrained Variational Policy Optimization (CVPO) separates nonparametric improvement from parametric projection in its original continuous-action formulation. We introduce Hybrid Constrained Variational Policy Optimization (H-CVPO), extending this variational framework to hybrid action spaces. Under boundedness and strict feasibility, its constrained E-step has zero duality gap and, when the dual optimum is attained at positive temperature, yields a closed-form joint target distribution over hybrid actions through exponential reward-cost reweighting. Using the exact hybrid KL decomposition, we formulate a factorized M-step that fits both policy components to this target under separate discrete and conditional-continuous trust regions. For exact E/M updates, we prove fixed-reference surrogate improvement and conditional reward-cost bounds with a sufficient feasibility-margin condition. For approximate updates, we establish the existence of a dual minimizer under continuity on a compact domain and use residual-based admissibility to determine whether to project the target. Ablations identify cost-aware reweighting as an important contributor to constraint control. Extensive experiments in simulated hybrid-control environments show that H-CVPO achieves favorable reward-cost trade-offs compared with hybrid-action baselines.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11935

AI-Driven Discovery of Entanglement Witness in Spin Hamiltonians

Jiwei Tian, Mouyang Cheng, Mingda Li

原文摘要

Entanglement is a crucial resource in quantum science and engineering, but detecting it in many-body states from experimentally accessible observables remains challenging. Here we introduce EntNet, an AI-driven framework to discover compact combinations of spin observables that accurately distinguish entangled from fully separable many-body mixed states in one-dimensional spin-$1/2$ chains governed by short-range Hamiltonians. We construct local-unitary-invariant representations of measurable Pauli correlators up to four-body order, sparsely select 16 candidate invariant feature channels, and learn their spatial structure using a Transformer architecture with rotary positional embeddings. Using only expectation values of these low-order observables, EntNet achieves $>98\%$ recall on certified entangled states with near-zero false-positive rates on separable states. Remarkably, it exhibits transferability across system sizes and distinct Hamiltonian families, including frustrated and disordered spin models, with minimal loss of accuracy. Beyond detection, EntNet provides physical insight into entanglement detection by revealing a selective spatial organization of pair correlations, while its finite-temperature decision boundary tracks the excitation gap of Jordan-Wigner quasiparticles. These results establish a transferable and physically interpretable framework for data-driven discovery of entanglement witnesses from local correlation functions.

quant-ph · cond-mat.str-el · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.01462

An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models

Mingzhong Sun, Teresa Yeo, Armando Solar-Lezama, Tan Zhi-Xuan

原文摘要

Studies of human reasoning have shown that people are typically stronger at evaluating reasoning than producing it from scratch. In contrast, large reasoning models (LRMs) are trained to excel at producing long chains of reasoning to solve complex problems. How then do LRMs perform at evaluating reasons? We investigate this with the Valid-Answer-Invalid-Reasoning (VAIR) dataset: math problems and solutions with trivial reasoning flaws but valid answers, designed to isolate reasoning evaluation from the confound of reasoning production. Unlike humans, who we find are only 6% worse at grading than solving such problems, we find a substantial production-evaluation gap in LRMs: frontier models score as low as 52% when evaluating VAIR solutions, despite near-perfect solution production. Why this enigma? Through chain-of-thought (CoT) analysis, we find evidence of an answer confirmation bias: LRMs often produce then check for the correct answer instead of carefully verifying each step, fabricating rationalizations even when noticing anomalous reasoning. Linear probes corroborate this, showing that while LRM activations encode some representation of valid reasoning, they fail to robustly represent VAIR solutions as invalid. Causal patching of the final answer's representations causes LRM verdicts and activations to flip at substantial rates, demonstrating that answer validity is a causal factor in models' confirmation biases. These findings indicate an outstanding limitation in dominant approaches to reasoning training, which incentivize LRMs to produce and confirm reasoning towards correct answers, but not to robustly evaluate the underlying reasons

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11921

An Evaluation of Tabular Foundation Models as Training-Free World Models

Xian Yeow Lee, Ryoichi Takase, Ahmed Farahat

原文摘要

World models are widely considered to be a potential key component of model-based reinforcement learning and robot planning, but typically require task-specific training on substantial interaction data. We investigate whether a pretrained tabular foundation model (TabFM) can serve as a training-free dynamics model for world modeling by framing next-state prediction as in-context regression over transition pairs, and where such a model helps and where it breaks. Across synthetic dynamical systems and robot locomotion benchmarks, TabFM is more accurate than LSTM and MLP models trained from scratch on the same limited transitions in almost all settings, and among regressors fitted to the same data it is the most accurate on locomotion, while a Gaussian process is more accurate on smooth low-dimensional systems. However, models trained on the full dataset remain substantially better on most systems. When rolled out autoregressively over multiple steps, TabFM's accuracy depends strongly on how much context it is given. With a short context, its rollouts quickly degrade to the level of a trivial baseline, whereas with a long context they improve substantially and, on one locomotion task, exceed a trained LSTM. Inference is also about three orders of magnitude slower than an LSTM. Overall, in their current state, we find that training-free priors are useful as predictors when data are scarce and enough context is available, but they are not yet a substitute for trained world models in planning.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗