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 13:02 — 2026-11-13 13:02（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 18,776 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 · v2arXiv:2603.14326

ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation

Jungwoo Oh, Hyunseung Chung, Junhee Lee, Min-Gyu Kim, Hangyul Yoon, Ki Seong Lee, Youngchae Lee, Muhan Yeo 等 9 位作者

原文摘要

While Multimodal Large Language Models (MLLMs) show promising performance in automated electrocardiogram interpretation, it remains unclear whether they perform actual step-by-step reasoning or just rely on superficial visual cues. To investigate this, we introduce ECG-Reasoning-Benchmark, a novel multi-turn evaluation framework comprising over 6,400 samples to systematically assess step- by-step reasoning across 17 core ECG diagnoses. Our comprehensive evaluation of state-of-the-art models reveals a systematic shortfall in executing multi-step logical deduction. Although models possess the medical knowledge to retrieve clinical criteria for a diagnosis, they exhibit consistently low success rates in maintaining a complete reasoning chain, primarily failing to ground the corresponding ECG findings to the actual visual evidence in the ECG signal. These results demonstrate that current MLLMs bypass actual visual interpretation, highlighting a limitation in their visual grounding capabilities and motivating robust, reasoning-centric medical AI. The code and data are available at https://github.com/Jwoo5/ecg-reasoning-benchmark.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2507.14492

Verifying Glitches in Decision Tree Ensembles

Satyankar Chandra, Harsh Chaurasia, Ashutosh Gupta, Kaushik Mallik, Krishna Shankaranarayanan, Namrita Varshney

原文摘要

Decision tree ensembles are widely used for tabular prediction tasks in judiciary, healthcare, banking, etc. We show that the piecewise-constant structure of these models can create narrow local oscillations, leading the ensemble score to sharply drop and then rise (a downward spike), or sharply rise and then drop (an upward spike), over a small change in a single feature. We call such patterns glitches. A glitch is not, by definition, an error. Rather, it is a formally checkable audit target requiring inspection. Formally, glitches are witnessed by ordered input triples in which a small monotonic change in a single input feature causes the output to first change in one direction and then revert in the opposite direction. Through a substantial experimental study, we show that glitches have widespread existence in even the state-of-the-art models performing various critical tasks. Our findings also indicate that glitches enrich and extend existing notions like robustness and monotonicity, providing us a more refined tool to isolate anomalies for inspection. On the theoretical side, we prove that deciding whether a decision tree ensemble contains a glitch is NP-complete, even for bounded-depth trees. We then present a mixed-integer linear programming encoding for the global and local glitch verification problems, and implement our algorithm in a verifier for gradient-boosted decision trees. Experiments show our verifier can scale to realistic model sizes from the literature.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38452

When Support Crosses the Line: Evaluating Ethical Boundaries in LLM-Based Mental Health Support in the Chinese Context

Bichen Wang, Yufeng Jin, Yixin Sun, Yanyan Zhao, Bing Qin

原文摘要

Large language models (LLMs) are increasingly explored for mental health support, yet existing benchmarks primarily focus on supportive capabilities rather than whether models consistently adhere to professional ethical boundaries. This issue is particularly important in multi-turn interactions, where users may introduce new information or exert emotional pressure over time. We introduce MindEth-Bench, a benchmark for evaluating ethical boundary adherence in multi-turn mental health interactions. Grounded in professional ethical standards for mental health services in China, MindEth-Bench covers multiple dimensions of ethical conduct and uses Monte Carlo Tree Search (MCTS) to systematically explore interaction trajectories that stress-test model boundaries. Experiments across nine LLMs show that models that initially respond appropriately can shift toward ethical violations over extended interactions, with substantial variation across models and ethical dimensions. These results show that single-turn evaluations may overestimate the ethical reliability of LLM-based mental health support systems and highlight the need to evaluate ethical behavior throughout multi-turn interaction.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.34682

Beyond Multiplicity Correction: Sharp Retrieval Thresholds for Attention with Correlated Distractors

Heehyun Park

原文摘要

Redundant context affects attention in two distinct ways: multiplicity adds normalization mass, while score variation within correlated groups can produce extreme individual scores. We separate these effects in a planted retrieval model with exponentially many Gaussian distractors organized into supplied clusters whose number and size both grow exponentially with dimension. The model is a two-level generalized random energy model, whose classical free energy yields exact retrieval thresholds. Gaussian interpolation further shows that increasing positive correlation at fixed token count lowers the distractor free energy, unlike adding duplicates. Our main result establishes a sharp limitation of count correction, which subtracts the log cluster size from pre-softmax scores: this correction removes multiplicity but retains within-cluster extremes. Even when the inverse temperature is chosen after observing all scores, count correction requires a signal at least $\sqrt{2α_1}$, where $α_1$ is the exponential growth rate of the number of clusters. By contrast, averaging scores before exponentiation suppresses token-level fluctuations and lowers the optimal signal threshold to $\sqrt{2ρα_1}$, where $ρ$ is the within-cluster correlation. This gap persists after adding exponentially many singleton distractors, so group size alone does not identify the target, and extends, under explicit cumulant regularity assumptions, to fixed finite hierarchies of independent-increment scores. Finite-sample, stability, and participation results complement the asymptotic analysis. A controlled retrieval experiment with frozen sentence embeddings illustrates both sides of the distinction: averaging helps when the relevant item is a singleton, but can discard useful evidence when a relevant group contains multiple matching items.

cs.LG · math.PR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.09707

BrainSurgery: Reproducible and Flexible Declarative Weight Manipulations for Model Editing and Upcycling

Gianluca Barmina, Annemette Broch Pirchert, Andrea Blasi Núñez, Lukas Galke Poech, Peter Schneider-Kamp

原文摘要

Checkpoint transformations such as model merging, precision casting, and low-rank rewriting are commonly implemented through Python code or separate task-specific tools. We present BrainSurgery, a tool that consolidates these operations into reusable declarative YAML plans over checkpoint tensors with built-in targeting, validation, diffing, and sharded export; a Web UI supports interactive inspection and plan construction. We compare BrainSurgery with three specialized systems across 13 settings, 11 benchmarks, 8 models, 4 architectures, and model sizes from 1.7B to 32B parameters. Without use-case-specific framework customization, BrainSurgery reproduces their model edits with comparable run cost, often lower memory usage, and close downstream performance. We further perform correctness, preservation, robustness, and scaling checks. Finally, a coding-agent study shows that agents can reliably generate and review BrainSurgery plans, which are substantially shorter and more structurally consistent than equivalent Python implementations. These results support BrainSurgery as a flexible alternative to maintaining separate tools for heterogeneous checkpoint-editing tasks.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38450

CoSTA: Co-Evolving Self-Play Timeline Agents for Complex Temporal Knowledge Graph Question Answering

Haikun Liu, Zhichao Yan, Shaoru Guo, Jiawei Gu, Victor Gutierrez Basulto, Jiapu Wang, Ru Li

原文摘要

Complex Temporal Knowledge Graph Question Answering (TKGQA) involves more than retrieving facts: the timestamp or validity interval of one fact can constrain the search for another, while multiple intervals may jointly determine the answer. Existing single-agent TKGQA methods typically investigate these facts within a single reasoning context, where evidence from different event histories can become interleaved and distractors can misdirect subsequent retrieval. Distributing investigations across agents can separate event-specific evidence into distinct contexts, but effective collaboration must still be learned because question decomposition, subtask investigation, and evidence synthesis are interdependent. To address these limitations, we propose \textbf{Co}-Evolving \textbf{S}elf-Play \textbf{T}imeline \textbf{A}gents (CoSTA), which organizes facts into navigable timelines, delegates investigations to workers, and uses a coordinator to synthesize their original timestamped observations. CoSTA initializes a shared policy through role-conditioned distillation and jointly optimizes both roles through co-evolving self-play with final-answer rewards. Across three benchmarks, CoSTA achieves state-of-the-art overall performance, with particularly strong gains on complex multi-fact questions, while its compact variants outperform the evaluated closed-source LLM agents.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38448

Benchmarking decision models against generative large language models on medical multiple-choice questions

Oscar Freyer, Daniel Glauert, Moritz Hofmann, Max Ostermann, Stephen Gilbert, Jakob Nikolas Kather

原文摘要

Medical workflows often require selecting among predefined options. We compared 13 decision models with 15 generative large language model configurations, including different reasoning settings, using 1,273 four-option MedQA questions under text-only conditions. Accuracy ranged from 67.71% to 89.08% for decision models and from 78.32% to 96.86% for generative configurations. Among the tested configurations, Mercury Decide had the lowest mean final-attempt cost (USD 0.0069 per 1,000 questions), while Clef Omni had the shortest median request duration (0.291 seconds). Decision-model probabilities distinguished correct from incorrect answers, but error rates among answers assigned probabilities of at least 0.90 ranged from 1.71% to 12.77%. Answer agreement across three runs ranged from 92.30% to 100%, while probability repeatability varied. Decision models offered resource advantages alongside lower peak accuracy; selecting models for medical workflows requires considering probability quality and repeatability together with accuracy and the resources needed to detect and correct errors.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38445

DES-JEPA: Learning a Shared Vocabulary for High-Dimensional Discrete Event Sequences

Hugo Math, Maximilian Forstenhäusler, Christos Anagnostopoulos

原文摘要

Temporal foundation models such as Chronos and TimesFM generalize across domains through a shared numerical observation space. In contrast, discrete event sequences (DESs), including operational event logs or patient clinical-event trajectories, have domain-specific event vocabularies whose labels lack a consistent correspondence across domains. Beyond this lack of consistency, the number of distinct events in real-world settings is high enough to challenge both classical temporal point process modeling and current in-context foundation inference models such as FIM-PP. Critically, current foundation models for DESs are limited to a small, fixed number of event types, restricting their applicability to realistic, high-dimensional event streams. To address this, we propose two complementary modules: (i) DES-JEPA, a joint-embedding predictive architecture that learns a shared discrete vocabulary from synthetic stochastic processes with unaligned event vocabularies; and (ii) DES-PFN, a discrete event sequence prior-fitted network that reuses the learned vocabulary for in-context next-event prediction. Without task-specific fine-tuning, this framework achieves competitive zero-shot performance on eight unseen real-world datasets and scales up to 700 distinct event types.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.36410

Expert lithological labels do not improve learning when used to predict marine sediment properties

John M. Aiken, William Gilpin, Thorsten W. Becker

原文摘要

Scientific drilling has produced large archives of physical, chemical and magnetic measurements linked to descriptions of the rock recovered. These archives are mostly incomplete: instruments sample at different intervals, recovery is partial, and destructive analyses preclude later measurement of the same material. We train an self-supervised embedding model on the LILY ocean drilling database using six routinely logged properties (bulk density, magnetic susceptibility, natural gamma radiation, and red, green and blue reflectance) across 236,963 observations from 296 boreholes, with a masked variational autoencoder that has a heteroscedastic Gaussian decoder and learnable mask tokens. The embeddings separate geologist-assigned lithologies as well as a variant trained with those labels, and increasing the weight on the labels degrades reconstruction while leaving classification unchanged. The labels are recoverable from the measurements geologists use to assign them, so training on them adds nothing. Lithological categories compress continuous measurements into classes, and compressing them discards what the measurements record about the processes that produced the rock. The embeddings also predict physical properties that were absent from training, on boreholes the model has never seen. While depth should account for this since sediments compact with burial, it does not. On held-out boreholes depth alone reaches a median $R^2$ of -0.02, against 0.20 for the embedding.

physics.geo-ph · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.09697

PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models

Gianluca Barmina, Federico Torrielli, Sven Harms, Jacob Nielsen, Flavia Filesi, Felix Mächtle, Stine Lyngsø Beltoft, Peter Schneider-Kamp 等 11 位作者

原文摘要

Large language models (LLMs) routinely face requests that should be refused, creating a trade-off between helpfulness and harm prevention. However, refusals themselves can be helpful. In high-risk interactions involving crisis, coercion, or escalating intent, blunt non-compliance may prevent direct harm while still failing to support the needs of the person behind the request. We present PsychoSafe, a psychologically-informed refusal framework that reframes refusal as structured supportive communication grounded in evidence-based intervention strategies. To develop PsychoSafe, we construct a corpus of 8,019 prompt-response pairs spanning five psychologically salient risk domains and apply prompting and parameter-efficient fine-tuning to Qwen 3.5 27B. On a balanced validation set of 500 prompts, evaluated with an LLM judge and validated through human ratings, PsychoSafe prompting improves overall refusal quality by 28.1% over a generic baseline, with particularly strong gains in external resource referral (+46.8%) and psychological grounding (+34.8%), while preserving downstream performance on non-refusal tasks. Fine-tuning achieves near-perfect refusal and resource-referral rates but reduces response relevance. Additional evaluations on SORRY-Bench and XSTest show strong in-domain robustness but limited out-of-domain generalization, suggesting that future work should diversify fine-tuning data to help models apply interventions selectively rather than schematically.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.27321

Physics-Inspired Optimizers beyond the Edge of Stability: Period-Two Orbits and Delayed Instability

Alexander Itin

原文摘要

Gradient descent with momentum can be viewed as a particle moving with friction in the loss landscape. In deep learning the learning rate is usually large, so training is a discrete dynamical system: in many full-batch experiments the sharpness grows to the optimizer's stability limit, the edge of stability (EoS), and training continues there. Physics-inspired optimizers change this motion; Velocity-Regularized Adam (VRAdam), for example, shrinks the step at high speed. We study kinetic maps, in which the step is the gradient of a kinetic energy of the momentum, and ask what they do beyond the EoS. (i) In a reduced model, a kinetic map creates a symmetric period-two orbit beyond the edge, strictly linearly stable if and only if the map's elasticity (the log-log slope of step length versus momentum) lies between 0 and 1; on it, training sits at an effective edge of stability. VRAdam's damper fails above twice the critical learning rate, where its kinetic energy is not convex; the Legendre dual of VRAdam's own Lagrangian is convex and passes at every learning rate. (ii) Because the sharpness rises gradually, the loss of stability is delayed, as in Neishtadt's theory of slowly swept bifurcations. In a network with a controlled sweep, the dynamics match this theory without fitted parameters, including the memory of where the sweep started and its erasure by noise. (iii) With momentum, reaching the oscillation also requires elasticity at large momentum: maps that bound the step have competing period-four and chaotic attractors already at beta1 = 0.9, while the cubic-Legendre map reached the oscillation from every sampled start up to beta1 = 0.99. Experiments on an exact quadratic problem, a full-batch MLP and ResNet-32 support the theory; on ResNet-18, much of the apparent benefit of the maps is reproduced by matching the effective learning rate.

nlin.CD · cond-mat.dis-nn · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38443

Skeleton-Guided Geometry-Aware Auto-Labeling for Robotic Grasping: From 4-DoF Learning to 6-DoF Execution

Ali Sabzejou, Farbod Azimmohseni, Mehdi Tale Masouleh, Ahmad Kalhor

原文摘要

Robotic grasping relies on large manually annotated datasets, which are costly to create. We introduce a straight-skeleton-based algorithm for generating two-finger grasp keypoints and identifying regions suitable for stable, feasible grasps. Our automated pipeline produces consistent grasp annotations without human intervention. We also propose the Skeleton-based Generative Grasp Convolutional Neural Network (SkelGG-CNN), a 4-DoF architecture that learns geometric grasp features from skeleton-based guidance. To extend auto-labeling to 6-DoF grasping, we develop a generalized quasi-3D skeletonization algorithm that operates directly on point clouds. Using automatically generated 4-DoF labels, SkelGG-CNN achieves accuracies of 95.42%, 96.55%, and 97.1% on Jacquard V1, Jacquard V2, and Cornell, respectively. On the GraspNet novel split, 6-DoF auto-labeling achieves an average precision of 18.33, comparable to state-of-the-art model-based approaches. In simulation, the 6-DoF method achieves success rates of 98.4% on Dex-Net and 89.1% on EGAD!. Real-world experiments with a Delta parallel robot show success rates of 97.4% on single household objects and 95.0% in cluttered scenes, outperforming state-of-the-art methods without domain adaptation. The 4-DoF pipeline adapts across environments and produces annotations approaching human-level precision, enabling efficient training of lightweight models on small datasets. The generalized 6-DoF method provides scalable, geometry-aware annotations for cluttered 3D scenes.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2604.21106

How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models

Kristian Schwethelm, Daniel Rueckert, Georgios Kaissis

原文摘要

We measure how much one recurrence is worth to a looped transformer in equivalent unique parameters. From an iso-depth pretraining sweep across recurrence counts $r \in \{1, 2, 4, 8\}$ spanning ${\sim}50\times$ in training compute, we fit a joint scaling law $L = E + A\,(N_\text{once} + r^{\varphi} N_\text{rec})^{-α} + B\,D^{-β}$ and measure a recurrence-equivalence exponent $\varphi = 0.46$. Intuitively, $\varphi$ tells us whether looping a block $r$ times is equivalent in validation loss to $r$ unique blocks of a non-looped model (full equivalence, $\varphi{=}1$) or to a single block run repeatedly with no capacity gain ($\varphi{=}0$). Our $\varphi = 0.46$ sits in between, so replacing unique blocks with shared recurrences increases validation loss at matched training compute. For example, at $r{=}4$ a 410M looped model performs on par with a 580M non-looped model, but incurs the training cost of a 1B non-looped one. We demonstrate the utility of $\varphi$ as a diagnostic tool on two case studies: commonly used truncated backpropagation lowers $\varphi$ to $0.38$, indicating that the loop mechanism is poorly trained under truncation, even though validation loss decreases. Conversely, hyperconnections raise $\varphi$ to $0.65$, a genuine capacity gain. Our method separates true loop improvements from training-side gains, a distinction raw validation loss cannot make. Code is available at https://github.com/kschwethelm/looped-lm-scaling.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38439

Predict the Reward, Not the World: World Reward Models for ML Agents

Yuxiao Lee, Zherui Yang, Fan Liu, Hao Liu

原文摘要

Search-based machine-learning (ML) agents improve a solution by writing candidate programs, executing them, and keeping the best. Execution gives the search reliable feedback, but a single run can take hours, and most runs end in programs the agent discards. Recent agents try to save these runs by letting a large language model act as a world model that predicts how each program would perform. However, a wrong prediction feeds the search false information. We argue that an agent does not need to predict the outcome of execution, only the decision that execution would support. We propose World Reward Models (WRMs), which learn from real execution results to choose directly which candidate will perform better, without predicting any intermediate outcome. We prove that a selector which predicts execution from the same inputs cannot outperform the best direct selector, that predicted outcomes add an error which can make a likelihood-trained world model prefer the worse program on every instance, and that cross-entropy on executed winners drives a WRM toward the optimum. Our WRM, ForeCritic, adapts a 9B typed decision model to 5k executed program pairs. On 12,438 held-out pairs from 26 ML tasks, it picks the better program 79.4% of the time, while general-purpose LLM judges reach 53--62%, and its probabilities are calibrated. Inside AIDE, ML-Master, and ForeAgent, it cuts mean task time by 4.4--7.5 times while keeping their mean scores within 0.01 or raising them.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38438

RoleFUZZER: User-Behaviour Fuzzing for Role-Specification Adherence in Large Language Models

Kshitish Ghate, Michael Saxon, Tadayoshi Kohno, Aylin Caliskan

原文摘要

Large language models (LLMs) are often conditioned into specific roles such as tutors, interviewers, or agents acting for an organisation, through system prompts that specify how they should behave. The extent to which they can actually adhere to these role specifications under multi-turn interactions with realistic and potentially problematic users is understudied. To address this, we propose user behaviour fuzzing, a guided search over plausible user behaviours that can lead a model to violate its role specification, and introduce RoleFUZZER, a framework that adapts coverage-guided fuzzing from software testing to operationalise the search. RoleFUZZER constructs scenarios guided by a user-behaviour coverage grid that crosses a grounded taxonomy of user interaction types and the role specification of the model under test i.e. what is under pressure. With RoleFUZZER, we evaluate LLMs across five role specifications, including tutor, financial advisor, AI interviewer, antagonistic roleplay character, and web agent under organisational policies. Across simulated and validated conversations in 15 campaigns, the framework reaches >= 89% coverage of the 64-cell behaviour grid for every model and role tested, and surfaces specification-grounded failure patterns. At an equal budget of conversations, removing the RoleFUZZER grid and asking an LLM to generate specification targeting users free-form lowers coverage to 39-69% with fewer kinds of violations. The same specification can also fail in opposite directions. For e.g., on the antagonist, open-weight target models override the player's safety signals, while Claude Haiku 4.5 breaks character instead. RoleFUZZER offers a tractable way to uncover vulnerabilities in LLMs across role specifications by testing diverse user behaviours that are likely to violate them.

cs.CL · cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38437

Capacity of the Hopfield-Hebbian dynamics with correlated patterns

Mihailo Stojnic

原文摘要

Allowing for small fraction of errors in retrieved stored binary patterns, Hopfield-Hebbian neural network (NN) associative memory dynamics [14] achieves linearly scaled capacity. The famous proportionality constant $α_c\approx 0.14$ is obtained in a large dimensional scenario as the ratio of the number of reliably stored patterns $m$ and the patterns' length $n$ under the assumption that uniformly randomly chosen binary patterns are \emph{independent} among themselves. While such an idealized scenario is now well understood, more practical scenarios with correlated/noisy datasets remaining challenging even for classical statistical mechanics replica approaches. We consider precisely such practical settings where each \emph{archetype} pattern is replaced with $M$ correlated \emph{examples} with parameter $r$ governing the quality of correlation. We develop a powerful Random Duality Theory (RDT) based framework to analyze correlated data and already on the first level of RDT lifting obtain capacity characterizations that remarkably well match behavior exhibited through simulated dynamics. Moreover, characterizations explicitly feature correlation parameters $M$ and $r$, which allows to precisely determine their effects on phase-transitioning behavior of the underlying dynamics. Our results are also a well-fitting complement to the existing literature. Namely, to circumvent challenging statistical mechanics analyses, an alternative combination of spectral and replica methods is considered in [4]. We confirm that [4]'s elegant spectral characterizations are excellent approximations in the low correlated regime. At the same time, we also close the gap in the regimes with higher correlation levels where spectral methods deviate from the practical dynamics performance.

stat.ML · cond-mat.dis-nn · cs.IT · cs.LG · math.PR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38436

Continual Adaptation Across Modalities: Learning and Forgetting in Unified Multimodal Models

Xinrui Wang, Zhihao Chen, Jia Tang, Alexandra Gomez-Villa, Bartlomiej Twardowski, Joost van de Weijer, Songcan Chen

原文摘要

Unified multimodal models (UMMs), which can process and generate diverse modalities within a single framework, have recently emerged as a powerful paradigm. However, when these models undergo continual learning on multiple tasks across different modalities, their learning and forgetting dynamics remain poorly understood. In this paper, we systematically investigate how architectural design and adaptation method shape intra-modal learning and cross-modal interference between the generation and understanding sides. Specifically, we report three findings. First, the severity of cross-modal interference decreases with the degree of modality-specific parameter isolation. Second, a within-model asymmetry: the generation side of a UMM is markedly more fragile than its understanding side. Third, what post-training adds is the first to be forgotten: purely post-training capabilities such as personalized generation collapse by 84\% to 90\%, while pretraining capabilities remain stable. Together, these results clarify how parameter isolation and post-training fragility shape UMMs' learning and forgetting dynamics, offering a starting point for developing continually evolving UMMs.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.31466

AnyGameRenderer: Entity-Consistent Generative Rendering Across Games and an Entity-Level Benchmark

Ruicong Liu, Liangyang Ouyang, Fengbo Lan, Zhixiang Wang, Kaipeng Zhang

原文摘要

AI coding agents can now build small playable games in minutes, but the results usually look like programmer art: gray blockouts, colored geometric primitives, and flat semantic blobs. We present AnyGameRenderer, a video-to-video generative renderer that turns such footage into high-quality visuals with characters, motion detail, and effects. Throughout, it keeps the layout, camera, and every entity's position and timing intact. Our AnyGameRenderer generalizes across a wide range of genres that agents build, such as tower defense, auto-battlers, top-down survivors, turn-based battles, kart racing, and crowd runners. AnyGameRenderer takes plain video as its game-state input, with no complex representations such as engine G-buffers, per-object class labels, or low-poly proxies. Gray blockouts, colored primitives, semantic maps, and wireframes all work as input. It also preserves entity correspondence: group counts stay correct, and entities appear and disappear on the right frame. We implement AnyGameRenderer by LoRA fine-tuning MiniMax-H3 ref2va, a 33B reference-video-conditioned video generation model. Training uses ~10k paired clips from three sources: (i) multi-stream rendering data from 38 agent-made games; (ii) two-stream rendering data from Unreal Engine, with programmatically controlled crowds, count changes, and entity scales; and (iii) real gameplay recordings, with pairs reconstructed via 3D-box detection. To evaluate the entity correspondence, we propose an entity-level benchmark of 59 held-out cases with 753 entities, scored against ground-truth boxes. Compared with the base model, AnyGameRenderer better preserves entity correspondence: temporal match rises from 50.9% to 62.9%, missed count changes fall from 34.7% to 21.3%, and fewer entities are hallucinated or left unrendered. Project page: https://alaya-lab.github.io/AnyGameRenderer.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38433

Does Chain-of-Thought Reliance Follow a Scaling Law?Larger Models Follow Their Steps More, Independent of Post-Training

Esther Xin

原文摘要

Monitoring a model's chain of thought (CoT) is useful for safety only if the final answer depends on the written steps. Prior measurements use natural tasks where true reasoning is unknown. We measure it against an exact ground truth on a synthetic box-swap task where every intermediate state is known. We replace one step inside a model's own chain with a wrong but valid state and check whether the answer follows the edit. We evaluate 25 open-weight models--Qwen3 (0.6B-14B, base and post-trained), Gemma 3 (1B-12B), Llama 3 (1B-8B), and 8 OLMo 2 checkpoints--on 7,200 items each. We find five results: (1) Reliance rises with size and saturates. In Qwen3, answer reliance rises from 16-18% at 0.6B to 97-100% at 14B; a logistic in log N fits well (R^2 = 0.89), and Gemma 3 and Llama 3 follow this trend. (2) Capability is the main driver. Across all models, reliance and step accuracy correlate at r = 0.99; equally capable models are equally reliant, regardless of family. (3) Size still matters at matched correctness. On problems solved correctly before the edit, reliance increases with size among capable models (rho = 0.80, p = 0.002). (4) Post-training does not change reliance. Base and post-trained Qwen3 differ by at most 0.03 from 4B upward; a large gap at 1.7B matches a large capability gap. (5) No model up to 14B solves the task internally. Without written steps, every capable model is at chance once a problem has four or more swaps. OLMo 2 checkpoints never become capable, making the training-token axis a limitation. On tasks requiring step-by-step computation, scale makes the chain of thought more load-bearing, supporting CoT monitoring in this regime.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.04527

Retrieve in Time, Correct in Frequency

Yuze Fan, Yue Cao, Pengjie Gao, Haojia Gao, Guangqiu Guo, Ziyue Zhang, Junbo Tan, Bokui Chen 等 10 位作者

原文摘要

Frozen vision-language-action (VLA) policies generate temporally extended action chunks, but long-horizon manipulation remains vulnerable to accumulated execution error and visual aliasing across task stages. Successful rollouts provide useful corrective evidence, yet current frame retrieval can return progress-misaligned actions,while direct replay or time-domain fusion can overwrite the reactive structure of the policy proposal. We introduce Retrieve in Time, Correct in Frequency (RTCF), a training-free test-time correction framework that improves frozen VLA performance with low model-side overhead.RTCF separates which experience to retrieve from which part of its action to transfer. Progressive Memory Alignment (PMA) causally aligns the growing visual execution history with complete successful trajectories through incrementally updated monotonic frontiers, jointly identifying a relevant memory and the current aligned memory position without stage labels. From the aligned action chunk,RTCF transfers a coefficient-wise-clipped low-frequency residual on motion channels. Higher-frequency components and gripper decisions remain inherited from the frozen policy. Across four LIBERO suites and 2,000 episodes per condition, RTCF raises aggregate success from 86.4% to 88.4% and improves LIBERO-Long from 61.6% to 68.6%.These gains require no parameter updates, repeated VLA inference, or additional GPU resources: correction can be performed on the client CPU after a single policy invocation, and the median latencies sum to only 10.99 ms per action chunk

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2506.19103

Inverse-and-Edit: Simple and Effective Framework for Fast Image Editing

Ilia Beletskii, Andrey Kuznetsov, Aibek Alanov

原文摘要

Diffusion-based text-to-image models have recently been distilled into few-step samplers and fast generators, reducing inference cost while maintaining high image quality. However, text-guided editing with such accelerated backbones remains challenging: inversion in a small number of steps is unreliable, local errors accumulate along the trajectory, and existing fast-editing methods typically rely on backbone-specific inversion procedures, which limits their transferability. In this work, we propose a simple and universal framework for text-guided image editing with arbitrary accelerated diffusion and flow-matching models. Instead of optimizing local, per-timestep objectives, we directly minimize a global editing objective over the entire inversion-generation trajectory. The framework fine-tunes only 1.5-7 % of the base-model parameters through two lightweight LoRA adapters (forward and backward), trained on fewer than 10 K triplets from the publicly available HQ-Edit dataset. We validate our method on three architecturally distinct backbones: consistency-distilled SD1.5 LCM-Dreamshaper, adversarial-distilled SDXL-Turbo, and rectified-flow-distilled Z-Image-Turbo. On PIE-Bench, our method achieves the strongest editing alignment within each backbone family while ensuring a strong level of content preservation. Inference adds no extra steps beyond the standard inversion and editing passes. The project page with visual results is available at iliabeletskii.github.io/inverse-and-edit.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38431

DecisionUnlearn-Bench: Unlearning Probabilistic Decisions under Changing Schemas

Tiantong Wu, Wei Yang Bryan Lim

原文摘要

Machine unlearning aims to reproduce the behavior of a model trained without designated data. For probabilistic decision models, this target also depends on the candidate options supplied at inference. We introduce DecisionUnlearn-Bench, an empirical framework that compares full, unlearned, and retain-only models across deletion granularities, label renderings, and candidate sets. Across 20 eligible model configurations on the BANKING77 dataset, full-to-oracle displacement increases consistently from example to association to class deletion. Replacing semantic option labels with opaque codes nearly eliminates the retrained oracle's recognition of deleted classes, even with successful acquisition of the full model, whereas changing the candidate set alters both the oracle and the measured unlearning progress. SimNPO satisfies the screening criterion in 19 of 20 configurations, but its gains vary substantially across seeds and deletion targets. Development tuning on the CLINC150 dataset does not establish a positive pooled effect across 48 intents. At approximately matched suppression, methods can differ markedly in oracle fidelity. Recovery experiments further distinguish initial forgetting from subsequent adaptation and show conclusions that depend on both architecture and metric. These results show that evaluating decision-model unlearning relative to a schema-specific retraining target, with separate reporting of effect size, utility, robustness, and recoverability.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.11653

Bet on Features: Anytime-Valid and Feature-Aware Auditing of Conditional Quantile Forecasters

Ivane Antonov, Sohom Mukherjee, Richard Pibernik, Yo Joong Choe

原文摘要

Black-box conditional quantile forecasts are widely used for sequential decisions under asymmetric costs. Once deployed, such forecasters must be monitored continuously as data streams drift and regimes change; this invalidates standard, fixed-horizon backtests for calibration. Further, existing backtests do not take into account that the notion of calibration is, in fact, information-dependent: forecasts can look calibrated to an auditor with coarse information while being miscalibrated to an auditor with richer information. We develop a distribution-free and game-theoretic testing framework for continuously auditing such forecasters with dependent, potentially nonstationary observations. We first formalize notions of conditional quantile calibration relative to the contextual features available to the auditor, showing how coarser information can limit detection. We then identify detectable alternative classes and, for contextual bets linear in the features, derive finite-time detection guarantees without an i.i.d. assumption. The resulting evidence processes provide interpretable, "feature-aware" evidence for miscalibration. We empirically validate these methods on simulated and real data, finding that a popular time series forecaster (Chronos-2) is highly miscalibrated w.r.t. multiple relevant features.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38426

The Code Behind the Layout: AI Agents for Analog Layout Generators

Minxing Chu, Anhang Li, Martins Atilla, Ruichen Qi, Mehdi Saligane

原文摘要

Analog layout remains largely manual and hard to automate. Generator frameworks such as gLayout express layouts as programs, producing layouts from parameterized, design-rule-aware generators; however, writing such generators still takes expert effort. Large language models (LLMs) could now write generator code, and frontier models can even draw layout geometry from design intent. This raises a practical question: if a model can draw the layout itself, what does a generator framework still contribute, and is applying these models to a generator framework better than having them draw a layout from scratch? Through controlled experiments on gLayout in SKY130, we find that the main obstacle to drawing a layout directly is its time and token cost, and that the main advantage of a model building on a generator framework is reusability. Its verified primitives keep each model edit small enough to check, and its parameters allow a single edit to be evaluated across an entire family of layouts. Accordingly, a model is most effective when it develops the layout from the generator source of the family that the design intent belongs to, and tests each edit on the family members most likely to fail, so that one verified change improves every layout the generator produces. The results of these family tests can then serve as supervision for a local model, which learns edits that hold across the family at a fraction of the inference cost.

cs.AR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2509.06585

Detection of trade in products derived from threatened species using machine learning and a smartphone application

Ritwik Kulkarni, WU Hanqin, Enrico Di Minin

原文摘要

Illegal and unsustainable wildlife trade remains a major conservation challenge and is increasingly shifting to online marketplaces where monitoring is difficult. To address this gap, we used real-world images from online platforms, enforcement seizures, and market inspections to develop a deep-learning object detection framework to identify products derived from three highly traded species: elephant, pangolin, and tiger. Our dataset of 39,941 images included both wildlife products and visually similar non-wildlife items, reflecting real enforcement complexity. We used cross-entropy and asymmetric focal loss functions to train Faster Region-based convolutional neural network (Faster R-CNN) models and compared species-specific and multispecies training strategies. The best-performing model, trained with cross-entropy on all species combined, achieved an overall accuracy of 84.2%, with high performance for pangolin (93.6%) and tiger (90.3%) and moderate performance for elephant (71.1%). Although asymmetric focal loss increased recall, it substantially reduced precision. We deployed the optimized model in a prototype smartphone application, potentially usable in real-world settings for monitoring online images. With an independent test set, the application achieved 91.3% accuracy and an F-score of 0.86. These results demonstrate the potential of object detection models to support scalable, real-time monitoring of wildlife trade and enable the rapid triage of suspicious posts, regulatory compliance, and conservation decision-making.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38425HF 社区推荐

IntReal: A Real-World Dataset and Benchmark for Multimodal Interleaved Generation

Shaohan Yu, Jie Qin, Wende Tan, Haiwen Diao, Limeng Qiao, Yueming Lyu, Chenyang Si

原文摘要

Humans routinely consume multimodal content, where textual and visual information is naturally interleaved. Although Unified Multimodal Models (UMMs) can jointly generate text and images, multimodal interleaved generation remains largely underexplored. Progress in this area is hindered by two key limitations: (1) the lack of well-defined interleaved generation tasks and corresponding training data, and (2) the absence of fine-grained evaluation protocols that can reliably diagnose model performance across different capability dimensions. To this end, we present IntReal, comprising two complementary components: IntReal-100K, a real-world dataset of multimodal interleaved samples spanning four major categories, and the IntReal Evaluation Suite, which evaluates model performance across seven complementary dimensions using specialized expert models, enabling coarse-to-fine diagnosis. Extensive experiments validate our evaluation suite through low inter-metric redundancy (max pairwise absolute Spearman's $ρ\leq 0.42$ ), high agreement with human judgments (83.3% accuracy), and strong consistency across different expert evaluators (Spearman's $ρ> 0.9$ ), supporting the complementarity and reliability of our metrics. By benchmarking four families of UMMs, we show that IntReal Evaluation Suite reveals distinct strengths and weaknesses across models. Post-training experiments demonstrate the utility of IntReal-100K for improving interleaved generation and further show that training unimodal generation can also benefit interleaved generation. These findings suggest that interleaved generation can benefit from modality-specific optimization, rather than requiring joint text-image training at every stage.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.21491

Stable but Wrong: When Learning Stabilizes Away from the Truth

Zhipeng Zhang, Fujie Ren, Kai Li, Bo Qiu

原文摘要

Stable training is often treated as evidence that learning is succeeding, but stability characterizes optimization behavior rather than correctness relative to an external objective. We study what happens when the signal being optimized remains persistently biased. We define Stable but Wrong (SBW) as a learning state in which optimization remains active or stabilizes while the learned outcome stays systematically displaced from an independently defined objective. A minimal theoretical model shows that persistent systematic bias can separate a stable convergence point from the true objective even under standard conditions for stable convergence. We then introduce static and dynamic bias in reinforcement learning, supervised learning, and continual fine-tuning of large language models. Across these settings, optimization of the current learning signal continues or stabilizes while correctness relative to the external objective declines or remains displaced. Finally, two controlled challenge-correction experiments with external ground truth test whether a prespecified error can be exposed and changed. In controlled scientific discovery and CIFAR-10, targeted evidence corrects or reduces established errors more effectively than equal-budget general evidence, with no evident harm to paired correct states under the tested protocols. These experiments do not provide a general method for automatically discovering unknown errors. Overall, SBW identifies a basic limit of convergence and other internal optimization metrics as evidence of correctness in systems that learn through persistent bias and feedback.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38422

Deeper Backpropagation or More Updates? Training Looped Language Models Across Budgets

Jiarun Shen, Xiao Li

原文摘要

Repeating transformer layers can improve language model performance without adding parameters. However, the added computational depth increases both forward and backward computation costs during training. Training such models requires choosing a backward window that controls how many final layer repetitions retain gradients during backpropagation. Longer windows improve per-token learning efficiency but increase per-update cost, while shorter windows reduce per-update cost but sacrifice per-token efficiency. Understanding which window performs better requires examining different training budgets. Prior work compares backward windows across computational budgets. When training budgets increase, it remains unclear whether the same window continues to perform best. We measure how the relative performance of two windows shifts as training budgets grow. Our method isolates per-token efficiency by training both windows on identical data, and compares complete training recipes at approximately equal training time at each budget. Results show that shorter windows lose much of their advantage as budgets grow. Controlled experiments show that both benefits decrease at larger budgets, with a greater decline in the benefit of extended training. Backward window comparisons depend on the available budget, and the preferred window among the tested candidates can change as the budget grows.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.30135

Verification-Aware Training for Speculative Decoding

Geonmo Gu, Byeongho Heo, HeeJae Jun, Yoohoon Kang, Sangmin Lee, Sangdoo Yun, Dongyoon Han

原文摘要

Speculative decoding accelerates large language model inference by using a draft model to generate candidate tokens, which are verified by the target model in a single forward pass. Verification proceeds sequentially and discards every position from the first rejection onward, yet existing draft training relies on token-level imitation of the target with a fixed per-position weighting that reflects neither property. We introduce Verification-Aware Training (VAT), a plug-in framework that simulates verification at every training step and turns the resulting accept and reject patterns into supervision. VAT consists of two components: (i) a verification head, a lightweight jointly trained binary classifier that supervises the draft model on whether each position survives sequential verification; (ii) verification-adaptive weighting, which replaces the fixed weighting schedule by keeping full weight up to each sample's first rejection point and re-anchoring the decay to start there. VAT modifies only the training objective, so it can be layered on top of existing methods without changing the draft architecture, the target model, or the inference procedure. Applied to EAGLE-3 and DFlash on Qwen3-4B, Qwen3-8B, and LLaMA-3.1-8B, VAT improves average acceptance length by up to 11.4% and wall-clock speedup by up to 8.7%, with consistent gains across math, code, and chat benchmarks. Code will be available at https://github.com/naver-ai/vat

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38413

Structure-retained low-rank adapters for weather synthesis

Shunxin Wang, Alexandros Stergiou, Luuk Spreeuwers, Estefania Talavera, Nicola Strisciuglio

原文摘要

Real-world deployment of computer vision models, particularly in outdoor scenarios, is often limited by environmental interferences, such as adverse weather. Improving model robustness across weather conditions is thus critical for reliability. However, sourcing high-quality data relevant to isolated weather effects is a significant challenge. Most datasets include changes in dynamic elements across observations of the same scene: subjects such as pedestrians and vehicles change between shots, while camera viewpoints vary. These aspects make it difficult to decouple solely weather-induced distribution shifts from the scene. In this work, we address this with a novel weather synthesis framework that utilizes structure-retaining Low-Rank Adapters (LoRA). We analyze the attention blocks in Stable Diffusion XL (SDXL) and identify where relevant structural information is mostly processed during image-to-image translation. Through an architectural analysis of SDXL, we learn structural LoRA matrices for the corresponding blocks and then leverage them for weather synthesis, eliminating the need for external conditioning such as ControlNet. Experimental results demonstrate that our method improves upon existing synthesis approaches, achieving greater realism while preserving structure. This provides a robust pipeline for generating high-fidelity training and evaluation data for outdoor computer vision applications.

cs.CV

查看论文
arXiv ↗PDF ↗