跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+479新增论文
+361其中 AI 相关
+64已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 21:56各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 01:58 — 2026-11-17 01:58(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:2026-11-16 01:34最近发现新增版本:2026-11-16 21:56库内论文最新更新时间:2026-11-14 02:59

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

23,827 已收录论文19,941 AI 相关6,922 有修订112 HF 社区发现

浏览论文库

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 17,708 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
版本更新 · v2arXiv:2610.30105

Asymmetric On-Policy Distillation Learns In-Context Exploration

Sriyash Poddar, Yanda Bao, Jacob Krantz, Matthew Chang, Xavier Puig, Roozbeh Mottaghi, Natasha Jaques, Abhishek Gupta

原文摘要

Sequential decision-making under partial observability is difficult because agents must explore to infer hidden, task-relevant information before acting effectively. Learning such information-gathering behaviors tabula rasa via online reinforcement learning is sample-inefficient, whereas offline imitation averages expert actions across hidden states and fails to learn exploration. In this work, we propose ASTEROID, a simple and effective student--teacher supervised learning framework that can learn test-time exploration. Although a privileged expert never needs to explore, we demonstrate that a history-conditioned student can learn to do so when trained with on-policy contexts: the student first collects on-policy context under partial observability, and then imitates the privileged expert conditioned on that context. By distilling expert actions directly conditioned on the student's on-policy history, the student learns to systematically resolve partial observability, i.e., search while uncertain and exploit once the hidden state is revealed. This enables efficient test-time exploration (similar to Bayesian posterior sampling) without incurring the impractical training-data costs of reinforcement learning. Across a diverse range of eleven different environments, including discrete exploration benchmarks, robotic manipulation, navigation, and Procgen environments, ASTEROID achieves ~2x higher returns under fixed exploration budgets, uses ~100x fewer interactions than RL baselines, and outperforms frontier models at exploration. Finally, our method transfers policies trained in simulation to vision-denied real-world robot manipulation, exhibiting efficient exploration and increasing success by +40% over standard distillation. Overall, it provides a simple yet surprisingly effective framework to learn efficient test-time exploration.

cs.RO · cs.AI · cs.LG

新论文 · v1arXiv:2611.05577

Readable Is Not Steerable: Pre-Registered Tests of Physical Structure in Learned Fluid Representations

Manvendra Modgil

原文摘要

Self-supervised world models are often said to organize their latents around physical quantities. We test this on 2D decaying Navier-Stokes flow in three pre-registered studies, each tested once on held-out data. In Study 1, a joint-embedding predictive architecture (JEPA) trained to predict the flow fails the pre-registered criteria for organizing its latent around fluid quantities better than an untrained network of the same architecture (not supported); a JEPA trained on non-physical linear dynamics and a static invariance model that never sees time do as well or better. In Study 2, plain autoencoders that render the field make enstrophy prominent in their slowest unsupervised latent directions (best r 0.80-0.86 vs 0.38 untrained; fresh seeds, sealed data). Adding VICReg lowers this prominence in every comparison, though not by the pre-registered margin for vorticity, while raising the autoencoders' linear decodability (partially supported). In Study 3, we build steerable directions ("dials") by routing: the decoder gets overall scale only through a small conditioning code, while its other pathway carries a degraded copy of spectral shape. Label-free rules find a loudness dial in all 8 trained models and a shape dial in 3 of 5 fresh seeds on sealed data, against a pre-registered bar of 4; neither control shows a shape dial (partially supported). Across the studies, what a latent contains and what can be controlled through it come apart. In exploration, a supervised direction reading spectral shape almost perfectly moved nothing when steered. During the build, the loudness dial had to be found by its effect on the output (closest to a pure rescaling), not by data variance; for shape, a variance rule and an effect-constrained rule each worked in 3 of 5 seeds. The program used about 70 logged hours on one consumer GPU; all pre-registrations, deviations, code and outputs are public.

cs.LG · cs.AI · physics.flu-dyn

版本更新 · v2arXiv:2606.23496

TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization

Matan Ben-Tov, Mahmood Sharif

原文摘要

Discrete text-trigger optimization -- searching for text sequences that, when ingested by a model, steer it toward a specified objective -- underpins model red-teaming (e.g., LLM jailbreaks), as well as auditing and interpretability. However, the current state of discrete optimizers hinders their adoption and progress. First, existing optimizers, when open-sourced at all, are scattered across research codebases tied to specific models, objectives, and problem domains. Second, optimizers proliferate, each requiring engineering overhead to use or extend, and remaining hard to compare head-to-head. Together, these raise the bar for adopting optimizers in existing or new domains, and for advancing them via new strategies. We address these gaps with TROPT, the first open-source framework that unifies discrete optimizers' execution and standardizes their development under a single interface. TROPT makes it easy to customize end-to-end optimization recipes by swapping any component -- models, objectives, and optimizers -- extending its reach across domains and new applications. TROPT currently ships with 40+ optimization recipes -- covering applications such as jailbreaking and probing model internals -- built from 15+ optimizers (spanning white-box to black-box access) and 15+ losses, from foundational to state-of-the-art methods. Demonstrating its utility, we leverage TROPT in several studies: (i) controlled, large-scale experiments comparing and enhancing optimization strategies for LLM jailbreaks, revealing potent-yet-underadopted techniques; and (ii) porting optimizers across applications and domains (e.g., from LLM jailbreaks to corpus poisoning). In all, TROPT significantly lowers the barrier to adopting and advancing discrete text optimization.

cs.LG · cs.CR

新论文 · v1arXiv:2611.05574

What Do We Mean When We Say 'F*ck AI'?: Moral Panic, Semantic Indeterminacy, and the Reification of Techno-Capitalism

Sasha Luccioni, Travis LaCroix

原文摘要

Academic and (increasingly) public resistance to artificial intelligence (AI) often blurs the line between legitimate critique of techno-capitalist exploitation and (inflated) existential risk. Moreover, discourse around AI can sometimes resemble a "moral panic" where an apparently clear and identifiable scapegoat is targeted in lieu of the complex systemic problems that are causing (genuine and justified) social anxieties. However, AI is not a monolith. In this paper, we explore the environmental, political, and socio-technical consequences of the semantic indeterminacy of discourse about "AI" in conjunction with the increasing moral panic encompassing these technologies. We argue that since the umbrella term "AI" lacks a coherent, singular referent, the moral panic about AI inadvertently reifies the concept of an autonomous, singular agent with inherent and often autonomous tendencies, which aligns with corporate narratives. Hence, well-intentioned critique, activist pushback, and public protest paradoxically amplifies hype-based discussions of AI, thus validating the "threat" narrative that tech leaders deploy to exaggerate their products' capabilities and market value, further consolidating and centralising their political and socio-economic power. Moreover, if "AI" does not refer to a unified class of technologies, then policy intended to govern "AI" will systematically (and necessarily) fail. We conclude by proposing ways forward to improve AI literacy, enforce accountability, and repurpose existing regulation in order to imagine a more positive AI future.

cs.CY

新论文 · v1arXiv:2611.05572

Just the Facts: How Dialogues with AI Reduce Conspiracy Beliefs

Thomas H. Costello, Gordon Pennycook, David G. Rand

原文摘要

Personalized dialogues with AI substantially reduce conspiracy beliefs. To identify why, we conducted two experiments with U.S. adults recruited online (total N = 2,193) that removed possible causes one at a time. The debunking effect was robust to disclosing the AI's persuasive goal, framing the exchange as a debate, instructing the AI to inform rather than persuade, halving its response length, altering how beliefs were measured, and replacing the dialogue with a single tailored message. Only instructing the AI to persuade without factual evidence and arguments substantially reduced the debunking effect. Content analyses of the AI's output and participants' own accounts linked larger reductions in conspiracy beliefs to factual argumentation rather than rapport, storytelling, or appeals to empathy. AI dialogues appear to reduce conspiracy beliefs primarily by supplying relevant, well-reasoned counterevidence. Our results suggest that humans might be similarly effective if they could supply comparable evidence.

cs.HC · cs.AI

新论文 · v1arXiv:2611.05571

ELA: End-to-End Latent Action Policy Learning from Video Demonstrations

Cheng-Chun Hsu, Peter Stone

原文摘要

Robot imitation learning is limited by the scarcity of action-labeled data, while action-free demonstrations such as videos are abundant. Recent latent-action methods learn action-relevant representations from observation transitions, but they do not optimize latent actions for downstream control, leading to latent representations that are difficult for policies to model and difficult to accurately decode into continuous robot actions. This paper introduces ELA, an end-to-end framework for learning from video demonstrations via latent actions jointly optimized for policy learning and action decoding. ELA jointly trains a latent action model, latent action policy, and action decoder, enabling policies to leverage abundant video data with only a handful of action-labeled robot demonstrations. Experiments on simulated and real-world manipulation tasks show that ELA consistently outperforms prior latent action baselines. Moreover, it integrates seamlessly with existing imitation learning methods through lightweight 4M-parameter action decoders, requiring no changes to policy architectures or training objectives. Additional materials can be found on: https://end2end-latent-action.github.io/

cs.RO

版本更新 · v2arXiv:2608.10459

MD-ProTector: Positioning Multiple Data-Driven Prototypes for LLM-Generated Text Detection

Jinmo Han, Jimin Hong, Chanyeong Moon, Ju Yeon Kang, Seonuk Kim, Nam Soo Kim

原文摘要

As LLM-generated content becomes more sophisticated, detection systems for distinguishing those texts from human-written text must operate at scale while handling diverse writing styles, domains, languages, and generator models. Input-only encoder detectors are suitable for practical deployment setting, but standard binary classification supplies only the class label and does not explicitly organize the substantial variation within either class. We propose MD-ProTector, which represents each class with multiple trainable reference vectors in the encoder embedding space, referred to as prototypes. These prototypes provide separate decision boundaries for different groups of texts within the same class. However, adding multiple prototypes alone does not determine which variation each prototype should represent. MD-ProTector addresses this problem with Prototype Positioning loss, which separates class-level structure from the within-class variation that differentiates individual prototypes. Evaluated across five settings from three large-scale benchmarks covering domain, generator, language, and adversarial variation, MD-ProTector achieves the highest AvgRec on MAGE CDCM and RAID and the highest AUROC and lowest FPR95 on RAID among the compared encoder-based methods.

cs.CL · cs.AI

版本更新 · v2arXiv:2607.08261

Optimal Sparsifiers for Abelian Cayley Graphs

Arpon Basu, Pravesh K. Kothari, Raghu Meka, Stefan Tudose

原文摘要

We prove that for every Cayley graph $\mathcal{G}$ over any finite abelian group $G$, there is a weighted Cayley graph with $O(\log |G|)$ generators that is a spectral sparsifier for $\mathcal{G}$. This bound is optimal. Applying our bound to the group $G = \mathbb{F}_2^n$, yields, as a corollary, $O(n/\varepsilon^2)$-sized code sparsifiers for $\mathbb{F}_2$-linear codes, improving on the work of Khanna, Putterman and Sudan (SODA'24) who obtained a similar result with an additional $\mathrm{polylog}(n)$ loss. Our proof is strongly inspired by a recent work of Reis and Rothvoss for the construction of $\ell_1$-sparsifiers. Following their work, the abelian Cayley sparsification problem can be reduced to establishing a lower bound for the volume of a certain natural convex body. This volume bound follows from a short, elementary argument that relies on character symmetry.

cs.DS · math.CO

新论文 · v1arXiv:2611.05570

ChangeJEPA: Predict Before You Compare for Remote Sensing Change Detection

Buddhi Wijenayake, Dhananjaya Jayasundara, Vishal M. Patel

原文摘要

Remote sensing change detection is typically formulated as Siamese feature comparison, where two images are encoded independently and a decoder determines which discrepancies correspond to meaningful change. This is challenging because the encoders preserve both true scene changes and nuisance variations such as illumination, seasonal, radiometric, and geometric differences. We introduce ChangeJEPA, a bitemporal joint-embedding predictive architecture that reformulates change detection as latent post-state prediction. Given a pre-change image and partial post-change evidence, ChangeJEPA predicts the full post-change representation under two complementary conditions: a prior hypothesis derived from the pre-change scene and an updated hypothesis conditioned on observed post-change context. A joint-embedding predictive loss aligns both hypotheses with the target latent representation, encouraging semantic consistency while suppressing transient appearance variations. Change is then inferred from the disagreement among the pre-change representation, the observed post-change target, and the predicted latent states, capturing complementary evidence of change, prior surprise, contextual update, and prediction reliability. Across SYSU-CD, LEVIR-CD+, and CDD, ChangeJEPA consistently outperforms its decoder matched Siamese baseline by up to 1.51 IoU points and achieves the best IoU and F1-score on all three benchmarks, demonstrating the advantage of latent post-state prediction over direct feature comparison. Page: https://buddhi19.github.io/ChangeJEPA

cs.CV

新论文 · v1arXiv:2611.05569

Role-based Effectiveness of an Epistemic Uncertainty Estimate in Training Models for Semantic Segmentation of 3D LiDAR Point Clouds

Krishnakumar N, Jaya Sreevalsan-Nair

原文摘要

Point cloud segmentation is a fundamental task in 3D data analysis, with applications across robotics, augmented and virtual reality, and remote sensing. However, the inherent sparsity, noise, and unordered nature of point clouds introduce significant challenges, particularly in achieving reliable classification. While the state-of-the-art rely on training models for explicit modeling of uncertainty, there is a gap in exploring different roles that estimated uncertainty using generative approaches can play. This work investigates the impact of deterministic uncertainty in point cloud segmentation by explicitly modeling epistemic uncertainty and using it in different roles, namely, as a feature and in loss function. We evaluate a baseline artificial neural network (ANN) and two uncertainty-aware variants (uncertainty as an additional input feature and as a per-sample confidence weight in the training loss) on four large-scale LiDAR benchmarks spanning airborne and mobile acquisition, namely ISPRS Vaihingen, AHN3, Paris-Lille-3D, and Toronto-3D, together with PointNet++ and RandLA-Net references and their uncertainty-augmented counterparts under canonical spatially disjoint train and test splits. Under this protocol, uncertainty-aware modeling improves mean Intersection over Union, recovers minority classes that the baseline ANN never predicts at all, and in half of the configurations improves the alignment between prediction error and estimated uncertainty as measured by Patch Accuracy versus Patch Uncertainty. Our findings indicate that uncertainty can play multiple roles in the segmentation pipeline rather than as a device for improving accuracy alone.

cs.CV · cs.LG

新论文 · v1arXiv:2611.05567

MESA: An Evaluation Framework for Compositional, Semantic, and Spatial Generalization in Robotics

Albert Wilcox, Frank Chang, Nhi Nguyen, Aishani Chakraborty, Jeremy A. Collins, Vaibhav Saxena, Benjamin Joffe, Siddharth Karamcheti 等 9 位作者

原文摘要

Despite growing interest in foundation models for robotic manipulation, systematic evaluation of their capabilities remains elusive. Existing benchmarks are either narrow and saturated, offering little signal on SOTA methods, broadly scoped, providing diversity at the cost of controlled experimentation, or require training on large, messy open-source datasets. We introduce MESA, an evaluation framework designed for precise, reproducible measurement of language-conditioned policy generalization. MESA provides five evaluation suites that isolate in-distribution performance and four distinct axes of generalization: spatial configuration, object instance, object category, and subtask composition, enabling researchers to diagnose where and why policies fail, not just whether they fail. To populate these suites at scale, we develop MESA-Gen, a pipeline for task and demonstration generation built by improving MimicGen. We instantiate the framework on two platforms and release both: the single-arm MESA suite, and BiMESA, the first large-scale benchmark for bimanual generalization. We evaluate seven baseline methods spanning diffusion policies, VLM-based approaches, and pretrained VLAs, finding that the strongest model achieves only 52% on MESA and 49% on BiMESA, providing meaningful signal while leaving ample room for progress. MESA rankings are broadly consistent with RoboArena scores, suggesting that MESA captures method-level differences relevant beyond simulation. Project website: https://pairlab.github.io/MESA.

cs.RO · cs.AI

版本更新 · v3arXiv:2505.19337

Hindsight Relabeling is All You Need for Reach-Avoid Learning

Kevin Li, Marinka Zitnik

原文摘要

Offline goal-conditioned reinforcement learning methods have shown promise for reach-avoid tasks, where an agent must reach a target state while avoiding undesirable regions of the state space. Existing approaches typically encode avoid-region information into an augmented state space and cost function, which prevents flexible, dynamic specification of novel avoid-region information at evaluation time. They also rely heavily on meticulously designed reward and cost functions, limiting transferability to novel environments and specifications. We introduce RADT, a decision transformer approach for offline, reward-free, goal-conditioned, avoid-region-conditioned RL. RADT encodes goals and avoid-regions directly as prompt tokens, allowing any number of avoid-regions of arbitrary size to be specified at evaluation time. Using only suboptimal offline trajectories from a random policy, RADT can learn reach-avoid behavior in a completely data-driven manner using our novel avoid-region hindsight relabeling approach, without the need for reward/cost supervision. We benchmark RADT against existing offline goal-conditioned RL models across 17 tasks, environments, and experimental settings. RADT generalizes in a zero-shot manner to out-of-distribution avoid-region sizes and counts, outperforming baselines that require retraining. In one such zero-shot setting, RADT achieves 35.7% improvement in normalized cost over the best retrained baseline while maintaining high goal-reaching success. We also apply RADT to cell reprogramming in biology, demonstrating its versatility.

cs.LG · cs.AI · q-bio.QM

新论文 · v1arXiv:2611.05565

Discarded or Unreachable? Diagnosing and Repairing Spatial Relation Failure in Vision--Language Similarity

Mahdi Mostajabdaveh, Zirui Zhou

原文摘要

Contrastive vision-language models score left/right relations near chance, but the symptom has two causes that call for opposite repairs: the relation may survive in the pooled embedding yet be unreachable by native image-text similarity, or pooling may discard it while the dense features retain it. On clean two object photographs, across ten encoders, the lateral polarity is linearly decodable from the flip odd component of the pooled vector at 0.77-0.99, yet a search over a million captions leaves nine of the ten at chance under native scoring: an access failure. On controlled C4 orbits, where the relation is the only thing that varies, pooling keeps the arrangement axis at 0.998-1.000 and loses its polarity, which the patch grid retains: a pooling failure. Both sit downstream of the dense features, so one readout covers both. Our zero parameter, query conditioned spatial moment recomputes the geometry from the patch grid and stores it as a vector beside the native embedding. On a 118,287 image index it raises left/right pairwise accuracy against reversed geometry negatives from 0.51-0.53 to 0.81-0.96 and conditional R@1 among 21 category matched candidates from 0.05 to 0.37-0.75, at under a millisecond per batched query, while reproducing the native ranking exactly for queries that name no relation.

cs.CV · cs.AI

版本更新 · v2arXiv:2605.24301

AcroRL: Learning Aggressive Quadrotor Inversion using Bidirectional Thrust

Gabriel Rodriguez, Henri Sayag, Abhishek Rathod, John Stecklein, Siddharth Saha, Christopher Barngrover, Wennie Tabib

原文摘要

Bidirectional thrust grants quadrotors a second equilibrium condition and increased control authority, expanding the envelope of possible aggressive maneuvers and enabling inverted flight, perching, and sensing. Prior geometric control approaches extend differential flatness through Hopf fibration-based attitude representations to support bidirectional thrust, but struggle with actuator saturation and motor reversal delay during inversions, requiring heuristic thrust posture scheduling and waypoint tuning. We propose a learning-based framework that modulates a constant reference trajectory to perform compact, position-constrained quadrotor inversions while remaining compatible with traditional trajectory generation and tracking across flight regimes. Separate policies are trained via reinforcement learning for nominal-to-inverted and inverted-to-nominal transitions. In JAX-based simulation, the proposed method achieves the lowest position deviation and settling time across all evaluated baselines, reducing position root mean square error (RMSE) by 32% and settling time by 57% relative to the strongest optimization-based baseline. Hardware experiments demonstrate successful inversion across multiple yaw configurations with position RMSE below 0.35m, and compatibility with downstream trajectory generation and control through circular flight in both regimes. Additionally, we provide an open-source implementation of the proposed framework.

cs.RO

新论文 · v1arXiv:2611.05562

Near-Minimax Sample Complexity for Multi-Objective Reinforcement Learning under Generative Models

Yue Wang

原文摘要

In multi-objective reinforcement learning, preferences may be specified only after data collection, requiring one dataset to support a continuum of reward trade-offs. We study finite discounted Markov decision processes with unknown transitions, $S$ states, $A$ actions, and $m$ known reward functions taking values in $[0,1]$, given access to a generative model. The learner must provide an $\varepsilon$-optimal policy for every convex combination of these rewards without further sampling, with a guarantee that holds simultaneously over all preferences and initial states. Writing $H=(1-γ)^{-1}$, we establish the constant-confidence minimax sample complexity $\widetildeΘ\!\left( \frac{SAH^3}{\varepsilon^2}\min\{S,\log(em)\} \right)$, where the suppressed factors are logarithmic in $S,A,H,\varepsilon^{-1}$ and the dependence on $m$ is explicit. Thus, up to these logarithmic factors, the worst-case statistical cost of supporting all preferences grows logarithmically with the number of objectives and saturates at the number of states. The upper bound uses uniform state--action sampling and empirical planning, with reward rounding in the logarithmic-objective regime. Its analysis chains optimal-value increments over covers of the reward hull. A one-sided Bellman variance bound controls signed value differences under a second transition kernel, preserving the $H^3\varepsilon^{-2}$ dependence. A complementary uniform guarantee for all bounded rewards yields the state-dimension saturation. We establish lower bounds matching up to logarithmic factors through a rare-exit construction with subset rewards and action encoding. These bounds apply to adaptive simulator queries and arbitrary randomized history-dependent output policies, while the upper bounds are attained by deterministic stationary policies.

stat.ML · cs.LG

版本更新 · v2arXiv:2610.02480

MEA: A Reward-Driven Multi-Agent System for Faithful Model Explanations

Yuyang Cheng, Raghav Kaushik Ravi, Srivarshinee Sridhar, Sriparna Saha, Akash Ghosh, Chirag Agarwal

原文摘要

Recent years have seen the employment of a plethora of machine learning (ML) models in high-stakes domains, but they remain largely opaque to the practitioners who act on their predictions. While post-hoc explanation methods offer a lens into this model behavior, wielding them effectively demands expertise most domain experts lack: navigating high-dimensional outputs, selecting the best explanations, and synthesizing evidence across disparate tools. To this end, we present MEA, a multi-agent framework that removes the explanation knowledge barrier entirely: a Proposer agent selects and configures explanation tools based on the question and modality, while an Actor agent is optimized end-to-end against faithfulness, transforming the outputs into natural language explanations grounded in model behavior across tabular, text, and vision modalities. Further, we introduce diverse question types spanning feature attribution, counterfactual reasoning, and spurious feature detection, each paired with a perturbation-based faithfulness metric. We find that frontier LLMs systematically produce unfaithful explanations. By optimizing against faithfulness rewards augmented with a modality-adaptive penalty, MEA consistently outperforms post hoc explainers, agentic, and closed-source baselines across six datasets, with reward-driven optimization yielding faithfulness gains of +28% (tabular), +21% (text), and +34% (vision) over the untrained backbone. More broadly, our findings suggest that AI agents themselves can serve as a scalable, adaptable interface to ML explainability, opening a path toward natural-language explainability that generalizes beyond the fixed, single-purpose tools that have long defined the field.

cs.AI

新论文 · v1arXiv:2611.05559

How Finely Can Vision-Language Models See Biology? Bio-VQA: A Benchmark for Taxonomic, Morphological, Spatial and Individual Reasoning

S M Rayeed, Qian Ma, Charles V. Stewart, Yao Ma

原文摘要

In biodiversity monitoring, a single image raises several questions: which taxon, how many, which trait, and whether the individual has been seen before. Vision-language models (VLMs) could answer all of these from the image, but their ability is largely untested in biology, as existing benchmarks focus mostly on species identification within a few taxonomic groups. We present Bio-VQA, the largest biological visual question answering (VQA) benchmark and the only one to span four aspects of biological visual understanding: hierarchical taxonomic reasoning, fine-grained attribute grounding, quantitative spatial reasoning, and individual re-identification. Bio-VQA contains 1.86M questions over 217K images from 11 public datasets, and extends right-or-wrong scoring to graded scoring, so a near-miss counts for more than a distant one. Evaluating 18 open-weight models from 3.75B to 38.4B parameters, we find that general visual capabilities do not transfer to biological organisms: the best model counts animals exactly on 41.7% of images with 2 to 10 individuals, less than half its accuracy on everyday objects at the same counts. Taxonomic accuracy falls to one sixth, from 0.72 at phylum to 0.12 at scientific name, and scaling helps mostly at coarse ranks. The gap to a domain specialist widens accordingly, from 0.731 against BioCLIP-2's 0.874 at class (1.2x) to 0.269 against 0.544 at scientific name (2x). On trait size measurement, 15 of the 18 models do no better than an image-blind baseline that predicts one fixed number for every specimen, and on re-identification, 17 of the 18 models fall below chance under adversarial conditions. These failures persist across a tenfold range of model size. We hope Bio-VQA becomes a standard test of how well VLM capabilities transfer to the biological domain.

cs.CV · cs.AI

新论文 · v1arXiv:2611.05558

Easy Multi-Precision Acceleration via Vectorization

Chansup Byun, Piotr Luszczek, Jeremy Kepner, LaToya Anderson, William Arcand, David Bestor, William Bergeron, Alex Bonn 等 21 位作者

原文摘要

High level programming languages and accelerators are powerful enablers for a wide range of applications. Accelerators offer significant performance via diverse numeric precision and increased memory bandwidth and capacity. These enable new algorithms to be explored. Construction of these algorithms can be enabled by the ready accessibility of these performance features in high-level languages. Achieving scalable vertical (within a compute node), precision (over various numeric precisions), and temporal (over different generations of hardware) performance while retaining productivity requires effective abstractions. Vectorized coding that expresses operations as high-level matrix mathematics has historically been an important method for achieving portable performance. This paper examines the performance availability across a wide range of precisions and hardware using simple vectorized coding techniques applied to several example programs that highlight bandwidth, real and complex matrix multiplication, and 2D convolution. The systems evaluated span nearly a decade of computing hardware, enabling direct comparison of performance gains over this period. This work demonstrates that near hardware peak performance is readily accessible from high-level programming environments. In particular for memory bandwidth, real and complex matrix multiplication in double/single/half precision, and 2D convolutions using the Fast Fourier Transform (FFT). Furthermore, algorithms that trade decreased compute intensity for increased memory intensity have significant potential.

cs.PF · cs.DC

版本更新 · v2arXiv:2610.07739

Cite What You Explore: Budget-Aware LLM Reasoning over Medical KGs with Verifiable Evidence

Chen Chen, Dongjie Wang, Mei Liu, Zijun Yao

原文摘要

Post-discharge risk prediction from electronic health records (EHRs) is difficult because many dependencies that link discharge-time observations to downstream complications, such as comorbidity cascades and drug-disease interactions, are absent from the record. External medical knowledge graphs (KGs) can supply these missing dependencies, but tracing them in a clinical setting demands three properties. KG exploration must remain cost-bounded, retrieved evidence must be differentiated by source quality, and the resulting rationale must be citable for review. Large language models (LLMs) can plan and verify over structured evidence, making them natural candidates for KG reasoning, but existing LLM-based methods do not satisfy these three properties jointly. In this paper, we propose BAR, a Budget-Aware LLM Reasoning framework over medical KGs with three contributions. First, BAR refines the raw KG into disease-specific evidence graphs whose edges carry support scores and provenance records, turning the KG into a quality-annotated reasoning space rather than a static feature source. Second, an LLM reasons over this graph through a plan-navigate-verify loop that decomposes the question into steps, retrieves evidence under a patient-specific budget, and revises when verification fails. Third, a reasoning policy is trained with a reward that compares predictions with and without acquired evidence, combined with acquisition cost and citation-integrity terms. Across 8 diseases and 3 prediction horizons on MIMIC-III and MIMIC-IV, BAR achieves higher performance and citation precision than strong baselines while using fewer LLM tokens. Its gain over EHR-only prediction grows at longer horizons, and its advantage carries over to an external benchmark.

cs.LG

新论文 · v1arXiv:2611.05551

VirtualTrialHarness: Coordinating Agentic Operationalization of Virtual Trial Protocols Across Complex Clinical Schemas

Pengze Li, Jingna Feng, Yue Yu, Yining Wu, Xinyue Hu, Jie Lin, Avanti Bhandarkar, Cui Tao

原文摘要

Virtual trials use routinely collected clinical data to evaluate treatment strategies, but translating a study protocol into an executable analysis requires determining how clinical concepts and study requirements should be represented in the available data and applied consistently across the workflow. These decisions depend on local data representations and operational conventions and can involve source selection, patient and encounter identity, linkage, and temporal interpretation. Here we introduce VirtualTrialHarness (VTHarness), an agent framework that coordinates virtual-trial operationalization by selecting reusable procedural skills for each workflow stage and uses explicit contracts to maintain consistent study decisions across stages. We also introduce VTBenchmark for evaluating source selection and cohort construction. Across three complex synthetic environments, VTHarness successfully produced all required cohort outputs matching the references in 95.1% of workflows after requirement clarification, compared with 60.4% using retrieval from the same procedural corpus. Procedural skills improved source recovery across three language models and increased source overlap with analyst code in 13 Mayo Clinic cases. Site-specific adaptation enabled reference-matched cohort execution across eight MIMIC-IV tasks. Within the Mayo Clinic Virtual Trials Program, the framework supported investigator review of cohort construction and endpoint analysis. These findings support coordinating procedural guidance with workflow decisions to improve virtual-trial implementation across complex clinical schemas.

cs.AI

新论文 · v1arXiv:2611.05549

Whose Transparency is it Anyway? Understanding Generative AI Transparency Needs and Gaps Across Stakeholders

Genevieve Smith, Sahiba Chopra, Natalia Luka, Min Kyung Lee

原文摘要

Transparency has become a central principle in AI governance, yet there is little agreement about what transparency means, for whom, and in what contexts. Drawing on interpretive flexibility within the Social Construction of Technology, this paper examines how different stakeholders understand and experience transparency in generative AI. This study draws from a global survey of 400 end-users, AI builders, and policymakers, complemented by a structured focus group with end-users, grounding the quantitative findings in qualitative insights from the group most underserved by current transparency practice. We present three key findings. First, all three groups share similar understandings of what transparency means and what it should afford, centered on ensuring accuracy and privacy. Second, gaps between the importance of transparency features and their perceived availability are substantially larger for end-users than builders, revealing how power shapes what gets built and who it serves. Only 28% of end-users report that current transparency practices reflect their needs very well, compared to 53% of builders and 49% of policymakers. Third, transparency is situationally constructed, priorities shift with context and task structure, with role-specific frames activating when context demands them and receding when it does not. We argue that meaningful AI transparency requires moving beyond a one-size-fits-all solution, including current emphases on AI disclosure and static documentation, toward pluralistic transparency infrastructures that reflect the needs of diverse users and stakeholders.

cs.AI · cs.CY · cs.HC

新论文 · v1arXiv:2611.05544

A Unified Framework for Training-Dataset Aggregation and Exact Machine Unlearning via Gibbs Probability Measures

Yaiza Bermudez, Samir M. Perlaza, Iñaki Esnaola

原文摘要

In this paper, three operations on Gibbs probability measures are studied: renormalization, normalized log-linear combination, and nesting. The resulting measures are shown to be Gibbs probability measures with explicit expressions for their objective functions, reference measures, and regularization factors. These measures are further characterized as unique solutions to optimization problems involving linear combinations of the original objective functions, subject to either relative entropy regularization or relative entropy constraints. When the reference measures are probability measures, geometric interpretations of these three operations are established involving Pythagorean identities and exponential geodesics.A central result is the equivalence between nesting and normalized log-linear combinations of Gibbs probability measures. These results are then applied to supervised machine learning with Gibbs algorithms, which are represented by Gibbs probability measures. In this context, either through nesting or log-linear combinations, Gibbs algorithms trained on local datasets are used to form new Gibbs algorithms trained upon the aggregation of all local training datasets. Interestingly, the parameters of such operations, determine the weights of each training data point on the aggregated dataset. %Operations on local Gibbs probability measures are shown to control the contributions of training data. This observation is leveraged for achieving: (a) exact machine unlearning in centralized, decentralized, and federated learning systems; and (b) centralized-equivalent performance, in the sense of producing algorithms trained on the aggregation of all local datasets in decentralized and federated learning .

stat.ML · cs.IT · cs.LG

版本更新 · v2arXiv:2610.17590

Revisiting the 16x Pretraining Compute Gap between Diffusion and Autoregressive Language Models

Guanghan Wang, Bing He, Zhan Shi, Benoit Dumoulin, Hanqing Lu, Volodymyr Kuleshov

原文摘要

Diffusion language models (DLMs) have attracted wide attention for their fast, parallel decoding, but they are believed to be far less efficient to train than autoregressive language models (ARMs): a widely cited study reports that a DLM needs roughly 16x the training compute of an ARM to match its likelihood, a figure that has made pretraining DLMs from scratch look prohibitive at scale. We find that the methodology behind this figure has fallen out of step with current DLM practice: it scores the model with its evidence lower bound (ELBO) and trains a full-sequence, decoder-only model. We therefore revisit the scaling laws of DLMs, adopting the exact likelihood under the model's own decoding order, block diffusion training, an encoder-decoder architecture, and a sweep over the block sizes used in practice. Under this new protocol, we study across ten model variants, about 1,700 models in total, and find that pretraining DLMs is far cheaper than previously thought. Concretely, scoring with the exact likelihood reduces the compute multiple to 12.8x; block diffusion training and an encoder-decoder architecture further reduce it to 7.8x at block size 32, and smaller block sizes narrow it to 4.6x at block size 8 and 3.0x at block size 4. We complement these scaling analyses with an empirical rule for the optimal decoder depth of encoder-decoder block diffusion, a held-out compute budget beyond the fitting range at which the gap between variants persists, and downstream benchmark results where likelihood improvements carry over to accuracy. Overall, the 16x figure substantially overstates the pretraining cost gap between DLMs and ARMs, and pretraining DLMs from scratch is far more viable than previously assumed.

cs.LG · cs.AI

新论文 · v1arXiv:2611.05542

Towards Efficient Whole Page Ranking with One-Pass Inference

Qi Xu, Zhigang Hua, Zijie Lei, Yan Xie, Jizhe Zhang, Lynn Lu, Delun Du, Sha Hua 等 13 位作者

原文摘要

Whole-page ranking jointly optimizes advertisements and organic content to balance business outcomes and user engagement under complex layout and business constraints. Existing non-autoregressive (NAR) approaches enable efficient page generation but typically score candidate items independently of previously selected items, limiting their ability to capture order-dependent interactions. Autoregressive (AR) methods address this limitation through sequential conditioning, but incur substantial inference overhead that challenges large-scale deployment. Bridging this quality-efficiency gap remains a challenge in industrial whole-page ranking. We propose Multi-Item Scoring (MIS), a prefix-aware NAR-style framework that incorporates sequential context into efficient multi-item scoring. MIS integrates global candidate interactions, localized prefix conditioning, and position-aware scoring within a shared representation architecture. By computing reusable representations once per request and performing lightweight prefix-conditioned scoring during constrained beam search, MIS captures important sequential dependencies without repeated full-model inference. Experiments on KuaiRand-1K and RL4RS demonstrate that MIS approaches the generation quality of an autoregressive CGA baseline while achieving 4.07x and 3.54x faster CPU decoding, respectively. In a randomized evaluation on a large-scale social-video platform, MIS improves the realization metric by 0.104% and watch time by 0.058%, while reducing ranking-service CPU consumption by 9.73%. These results demonstrate that prefix-aware multi-item scoring can narrow the quality gap between NAR and AR generation while retaining the efficiency required for industrial scalability.

cs.AI · stat.ML

新论文 · v1arXiv:2611.05539

Rewrite, Then Veto: Rewriter-Agnostic Edit Gating for LLM-Based Post-OCR Correction

Jorge Ramón Fonseca Cacho

原文摘要

LLMs can repair noisy OCR transcripts of historical documents, but they also change text that was already correct. We propose EditVeto, a veto gate placed after a full-context LLM rewrite. The rewrite is character-aligned to the OCR input, its differences are split into blocks, and a 0.6B-parameter gate keeps or reverts each block. An oracle analysis motivates the design: given the true error locations, per-span generation is worse than no correction, whereas vetoing a full rewrite's edits helps. Trained on rewrites by two Qwen3 models and evaluated, frozen, on the eight HIPE-OCRepair-2026 test sets, the gate improves all five rewriters tested, two of them unseen in training: weighted cMER falls by 0.0026-0.0044 and the preference score rises by 0.15-0.25 (paired bootstrap, p ~ 0.0002 each). On published competition outputs it lowers cMER for three of four teams but raises it for the winning run (0.0050 to 0.0065). In a second, disclosed test look, a retrained gate still improves LoRA-tuned rewriters (cMER -0.0011 to -0.0021), and an ensemble of their gated edits reaches a cMER of 0.0069 and a preference score of 0.928, mostly through fine-tuning and pooling rather than gating. Built only on public models and data, it is behind the winner (0.0050) and tied with the second-ranked run (0.0071), both from the only team using domain pre-training, and ahead of all other published runs. A third, secondary look shows the unchanged gate improving zero-shot Qwen3.8-27B (cMER 0.0114 to 0.0108) but only the preference score of its LoRA-tuned version.

cs.CL · cs.CV

版本更新 · v2arXiv:2606.09258

Back to the Familiar Future: Failure Recovery for VLA Policies via Pre-Imagined Milestone Selection

Suyeon Shin, Juwon Kim, Hyeonbin Park, Hyunseo Kim, Hyundo Lee, Hyung-Sin Kim, Byoung-Tak Zhang

原文摘要

Vision-language-action (VLA) policies can deviate from nominal trajectories during manipulation, even when tasks remain physically feasible. Recovering from these deviations is challenging, as they push the policy into unfamiliar state spaces where direct re-planning frequently destabilizes action sequences. We propose Back to the Familiar Future (B2FF), a recovery framework for foresight-driven VLAs that leverages future visual conditioning as a recovery interface. Before execution, the VLA generates a milestone bank of familiar future states conditioned on the clean initial observation. At recovery time, a recoverability-aware selector selects a recovery milestone from this bank and enforces it as a fixed visual goal. This enables the VLA to robustly map off-trajectory observations back to a familiar future. On failure-injected LIBERO, under controlled recovery timing aligned with the injected failure, B2FF increases the average success rate of a baseline VLA from 56.3% to 74.0%, demonstrating that pre-imagined milestones can guide recovery without fine-tuning the low-level action generator.

cs.RO

新论文 · v1arXiv:2611.05524

MA-SafeDiffuser: Safe Multi-Agent Planning with Diffusion Probabilistic Models

Kiran Ravish, Ankita Kushwaha, Preeti, Pawan Kumar

原文摘要

We propose MA-SafeDiffuser, a multi-agent extension of SafeDiffuser that equips diffusion-based trajectory planners with finite-time diffusion invariance guarantees for joint-agent safety specifications. Building on the single-agent construction that embeds control barrier function (CBF) constraints into reverse-diffusion updates, we: (i) formalize joint safe sets as intersections of per-agent and pairwise barrier sets; (ii) derive centralized and decentralized (communication-aware) constrained denoising procedures with provable invariance under mild assumptions; (iii) address local-trap and deadlock phenomena via time-varying specifications and liveness CBFs; and (iv) develop a lightweight benchmarking suite including a multi-agent Maze2D domain. Empirically, MA-SafeDiffuser reduces violation counts relative to unconstrained diffusion baselines, while retaining planning quality. We provide algorithms, proofs, and reference implementations.

cs.AI · cs.MA

版本更新 · v2arXiv:2610.32503

Pareto-optimal Non-Clairvoyant Scheduling with Predictions

Ziyad Benomar, Vianney Perchet

原文摘要

We study preemptive single-machine non-clairvoyant scheduling with predictions, where a prediction of the order of the jobs (or of their sizes) is available, and the objective is to minimize the total completion time. An algorithm is $c$-consistent if it is $c$-competitive when the prediction is correct, and $R$-robust if it is $R$-competitive whatever the prediction. Since the introduction of this problem as one of the first examples of learning-augmented algorithms, the best possible trade-off between consistency and robustness has remained open. We determine it exactly for deterministic algorithms. For every $R>2$, we give an $R$-robust algorithm whose consistency is \[ c(R)=R\Big(1-\Big(1-\frac{R+2}{R^2}\Big)^{\frac R{R+2}}\Big), \] and we prove that no deterministic $R$-robust algorithm, with either predicted order or predicted job sizes, has better consistency. In particular, consistency $1+\varepsilon$ is achievable with robustness $\varepsilon^{-1/2}+\frac16+O(\sqrt\varepsilon)$, whereas all previous algorithms required robustness $Θ(1/\varepsilon)$. Our algorithm is greedy: it follows the predicted order as fast as possible, subject to the invariant that the cost paid so far is at most $R$ times the optimum of the instance in which every unfinished job would end immediately. The matching lower bound rests on the observation that every robust deterministic algorithm must satisfy the same invariant along its run on correct predictions. Furthermore, we give a simple randomized algorithm, using predicted sizes, with consistency $1+\varepsilon$ and robustness $(3\varepsilon)^{-1/2}+O(1)$, strictly below the deterministic frontier. The question of determining the Pareto-optimal frontier among randomized algorithms remains open.

cs.DS · cs.GT

版本更新 · v2arXiv:2606.18439

RegimeVGGT: Layer-Wise Spatially Preserving Redundancy Removal for Visual Geometry Grounded Transformer

Jinhao You, Shuo Lyu, Zhuohang Lyu, Tanxuan Li, Zibo Zhao, Jiaxiang Hu, Kai Tang, Yichen Guo

原文摘要

Visual Geometry Grounded Transformer (VGGT) recovers dense 3D scene structure from multi-view images in one forward pass, but quadratic cross-frame attention limits its scalability. Existing training-free accelerators exploit token, frame, or attention redundancy; we investigate how layer-wise functional roles can guide compression. Our spectral, probing, and causal analyses reveal three regimes: shallow layers lack cross-view structure, middle layers drive cross-view alignment, and deep layers are redundant for dense geometry yet their cross-frame attention remains essential for pose. RegimeVGGT applies layer-wise U-shaped compression along two axes: Saliency-Guided Banded Merging protects geometry- and edge-salient tokens, while Selectively Protected K/V Downsampling preserves cross-frame spatial coverage and the pose-critical path through a phase-shifted spatial grid, a reference-frame anchor, and uncompressed camera/register tokens. Without any training, RegimeVGGT achieves a 6.7x speedup over the memory-optimized VGGT* at matched reconstruction quality. Project page: https://tracyou07.github.io/regimevggt/

cs.CV · cs.RO

新论文 · v1arXiv:2611.05517

When to Ask, When to Answer: Strategic Clarification for Ambiguous Reference Resolution in Dialogue

Ibrahim Khebour, Nikhil Krishnaswamy

原文摘要

For humans, referential disambiguation is a collaborative process involving clarification questions asked when they will meaningfully change the outcome. However, large language models (LLMs) have been shown to be biased toward premature answering, preferring definite single-turn responses over more clarification exchanges. In this paper, we study the problem of "strategic clarification" -- asking clarification questions in a reference game when their answers will narrow the set of candidate referents. We construct a controlled test environment from the SIMMC 2.1 dataset that records how many questions each ambiguous reference needs to be successfully resolved, and examine how baseline LLM behavior and common post-training methods ask clarifying questions vs. attempt to answer the referent. We also propose BACE (Belief-Aware Critic with Epistemic tracking), a lightweight action chooser method on top of a frozen LM backbone, and show that BACE more consistently chooses the optimal number of clarifying questions than methods such as GRPO and ArCHer.

cs.CL · cs.AI