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
+63已有论文修订
+93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 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 21:05 — 2026-11-16 21:05(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 13:44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6,921 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 23,827 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 · v3arXiv:2606.08810

What Simple Readouts Miss in Continuous Language Diffusion

Zhicheng Du, Lan Ma

原文摘要

How much of a learned decoder can a simple readout preserve? On generated ELF and AURORA states, token-wise affine maps recover $97.17\%$ and $95.74\%$ of native lexical decisions. Contextual computation has already produced these states; only the terminal readout is simplified. The remaining disagreements matter beyond their count: equal-count rare-first and low-native-margin-first repairs have opposing pooled evaluator effects in both interfaces. On conditional summarization, rare-first improves reference similarity, while source consistency remains unresolved. Score accounting locates part of the benefit on unchanged text despite increased unigram cost, without identifying rarity as a cause. Repeatable repair effects do not ensure prediction transfer: a frozen predictor improves on two ELF checkpoints but fails on a distilled student. A separate task-fitted selector improves BERTScore over random selection by $0.261$ points on 256 fresh articles at a $50\%$ native-call budget; all-native decoding remains higher-scoring and acceleration is unestablished. Compressed and directional interface tests further distinguish fitting-state coverage, native decisions, and soft inputs. Together, the results motivate testing a simplification at three levels: preserved decisions, output consequences, and computational savings. Native decisions are fidelity targets, not semantic truth.

cs.CL · cs.LG

版本更新 · v3arXiv:2607.27287

Alternating Abduction and Planning over Temporal Dynamic Knowledge Graphs

Amir Hossein Sharafi, Alireza Shahbazi

原文摘要

Knowledge graphs change over time, but the effects of actions on them are only partly stated: the ontology entails further consequences, facts that an action needs are often unknown, and an action may make the graph inconsistent. We study these problems for Temporal Dynamic Knowledge Graphs (TDKGs), that is, SROIQ knowledge bases whose actions are rules with delete/insert templates and whose events lie on an intrinsic timeline. We present three tools that use a SROIQ reasoner only through a few operations: temporal projection, which plays the events along the timeline and is the exact test of plans; DDA (Direct-Derivation Abduction), which explains an observation by assuming its negation and negating what the reasoner newly derives; and APT (Abduction and Planning over TDKGs), which plans backwards from a goal, assumes the facts that the plan needs but nobody stated, and lets DDA explain the assumptions, each explanation becoming a new goal for a sub-plan, up to a depth bound. The same machinery synthesises action sequences that end in a chosen contradiction. We prove that projection is decidable and that the indirect effects of an action are exactly the entailments of the updated state; that DDA is sound, terminates and finds every single-assertion explanation; and that APT is sound and terminates, while bounded planning is decidable but 2NExpTime-hard. We compare the tools analytically with hitting-set abduction and classical planning, compare DDA with the abduction solver CATS on shared problems, and run them on six benchmarks. Five reasoners (HermiT, Konclude, Pellet, Openllet, JFact) return identical results. Their incremental modes answered some checks wrongly after removals and gave no speed-up; parallel calls help only when a single call is expensive.

cs.AI · cs.LO

新论文 · v1arXiv:2611.12027

An open source Python code for three-dimensional topology optimization in single precision on a consumer GPU

Leonilson Toffoli Pedrini, Rodolfo G. M. Andrade, Rafael M. Ferro

原文摘要

Three-dimensional topology optimization solves linear systems with millions of unknowns at every design iteration. Consumer graphics cards run far faster in single than in double precision, and open codes for them mostly address minimum compliance. This educational article presents TOF3D, an open source Python code for density-based topology optimization in single precision on one consumer GPU. It solves four classes of problems: stress constrained minimum compliance, robust minimum compliance against manufacturing errors, compliant mechanisms and bone-like porous infill. The stiffness operator is applied without assembly, and the conjugate gradient method is preconditioned by geometric multigrid. Rounding the element matrix to single precision gave rigid body motions a spurious energy and changed compliances by up to 5.4%. Forming the element products from differences of nodal displacements reduced this error to $1.3\times 10^{-5}$ at no cost in time. Adjoint sensitivities agreed with finite differences to within $1.7\times 10^{-6}$, and the solutions agreed with Ansys Mechanical APDL to within $4.1\times 10^{-10}$ with the same element. On an RTX 3060 with 12 GB, one design iteration of a cantilever took 0.46 s with 0.5 million elements and 15 s with 33.5 million. On the same card and problem, an open GPU code that applies its operator in double precision took 3.7 and 21 s with 0.5 and 4.2 million elements and ran out of memory on larger meshes. Eight cases fixed in a protocol before the runs took 9 to 35 minutes each with 4.2 to 5.2 million elements.

cs.CE · cs.MS

新论文 · v1arXiv:2611.12026

MambaPD: Bidirectional Selective State Space Model for Parkinson's Disease Detection from Resting-State EEG

Ayesha Zulfiqar

原文摘要

Typical diagnosis of Parkinson's disease (PD) occurs only after significant dopaminergic loss, while resting-state EEG abnormalities like alpha slowing and reduced coherence occur earlier. While many published EEG-based PD detectors claim accuracy greater than 95%, many use epoch-level splits which leak subject identity. I introduce MambaPD, a bidirectional selective state space model for resting-state EEG-based PD detection, blending the channel mixing, patch tokenization and bidirectional Mamba encoder. It is compared with four baselines (TCN, BiLSTM with attention, EEGNet and a patch Transformer) in two public datasets (UNM, SanDiego) using subject-independent 5-fold cross-validation (checkpoints were selected on the held-out fold, so absolute estimates are optimistic). On UNM the accuracy is between 0.67 and 0.71, and MambaPD (0.714) is not statistically distinguishable from the Transformer (0.715), and TCN (0.708), with the highest sensitivity (0.82), while the lowest specificity (0.52). For the smaller SanDiego cohort, accuracy is in the range of 0.60 to 0.70, with the highest scores (0.703) from TCN and the lowest (0.601) from EEGNet, while MambaPD scores 0.631, with the lowest specificity (0.46) among the five models. The differences among the models on UNM are minor compared to the differences among folds. I report the whole pipeline, per-fold results, and the shortcomings of the protocol.

cs.LG · eess.SP

版本更新 · v2arXiv:2611.01835

ReFrame: Silence-Aware Compute Reclamation for Full-Duplex Speech Models

Zheng Zhou, Guanyi Chen, Jing Wei, Haoyuan Liang, Jian Zhang, Haohuan Fu

原文摘要

Full-duplex speech models execute dense model inference for every audio frame throughout a live interaction. This uniform framewise schedule creates sustained GPU load across dialogue states whose computation has strong, reusable temporal structure. ReFrame formulates full-duplex inference as a silence-aware computation problem. Mutual Silence Speculation (MSS) operates when both participants are silent: it evaluates multi-frame Temporal continuations, verifies text and hidden-state stability, and applies batched Mimi audio-token correction. Listening Frame Folding (LFF) operates while the user speaks and the agent listens: it processes already-arrived user frames through parallel Temporal execution and frame-batched audio-token generation while accepting only the verified prefix. Frame-Budget Reinvestment (FBR) assigns the released frame intervals to resumable external retrieval and language-model workers, then injects timely references through Moshi's conditioning interface. We instantiate ReFrame on five full-duplex models spanning Moshi-family, phase-structured, and flattened autoregressive generation. Across the complete 1,225-conversation FDBench, ReFrame reduces measured GPU execution time by 18.80-31.01% and retains 96.92-100% non-PAD text agreement on five different models. On HaluEval tests, FBR increases the number of correct generated spoken answers from 86 to 205 under the same auxiliary-service budget. ReFrame turns recurring dialogue structure into lower inference cost and higher end-to-end service capability.

cs.LG

新论文 · v1arXiv:2611.12025

Single Image Super-Resolution via Semantic Prompt and Cross-Modal Training on Content Area

Xiao Tan

原文摘要

Enhancing image quality through super-resolution is crucial in image and video processing. While contemporary deep learning models, such as CNNs and Transformers, excel in pixel-level enhancements, they often overlook the rich semantic context within images. To address this, we introduce a novel approach that synergizes pixel intensity with semantic information for superior detail recovery. Our method involves extracting semantic data, including textual descriptors and spatial positioning, and encoding this information. We also present a Cross-Modal Feature Fusion module for generating semantic feature maps via multimodal training, and a Prompt Traction Head to augment the backbone network with semantic insights, thereby refining image details. Our empirical results across various datasets validate the superiority of our approach.

cs.CV

新论文 · v1arXiv:2611.12024

FocusBranch: Combinatorial Branch-and-Bound for $\ell_0$ Neural Network Robustness Verification

Renwei Deng, Yang He, Linyi Li, Yuepeng Wang

原文摘要

Verifying the local robustness of neural networks under $\ell_0$ perturbations is inherently combinatorial, as it must reason over all sparse subsets of $ε$ perturbed pixels. This paper presents FocusBranch, a combinatorial branch-and-bound framework for $\ell_0$ robustness verification. The key insight is to make the $\ell_0$-ball decomposable and branchable using a node abstraction, which consists of a focus pixel set $\mathcal{S}$ and a level $l$, permitting at most $ε-l$ pixels outside $\mathcal{S}$. This abstraction unifies two branching mechanisms: concrete nodes branch through upper shadows to fix additional perturbed locations, while super nodes branch through covering designs to cover many perturbation cases with fewer child nodes. FocusBranch proves node safety by concretizing linear relaxations over node-constrained $\ell_0$-balls and recursively branches on unknown nodes. Rather than relying on a fixed verification plan, it samples nodes across levels to estimate safe rates and costs, then selects a starting level and branching strategy predicted to minimize verification time. Experiments on fully connected and convolutional classifiers for MNIST, Fashion-MNIST, and CIFAR-10 show that FocusBranch verifies $\ell_0$ robustness effectively across architectures and outperforms state-of-the-art verifiers. The code is available at: https://github.com/simpl-group/FocusBranch.

cs.LG

新论文 · v1arXiv:2611.12023

TIRAD: Text-guided Image Residual Learning for Generalist Anomaly Detection

Seongsu Lee, Seunghyun Oh, Seungjae Moon, Youngmin Ro

原文摘要

Recent anomaly detection studies have shown that residual features, which model the discrepancy between normal and abnormal patterns, provide strong generalization to anomalies unseen during training. However, existing residual-based approaches mainly rely on visual discrepancies derived from image representations, while semantic discrepancies that can be explicitly expressed through language remain largely underexplored. To address this problem, we propose TIRAD, Text-guided Image Residual Learning for Generalist Anomaly Detection, a multimodal residual learning framework that defines the discrepancy between textual representations of normal and abnormal states as a Text Residual Feature and uses it to guide the Image Residual Feature. Specifically, a Text Fusion Module converts patch-level text residuals into a gate that modulates the image residual of each patch. The gate retains the visual discrepancies that the text residual identifies as defect-related and attenuates the others, leading to more discriminative anomaly representations. Extensive experiments on industrial benchmarks and industrial-to-medical transfer demonstrate that the proposed method outperforms existing image-centric residual learning methods.

cs.CV

新论文 · v1arXiv:2611.12020

A generalized transition framework for identifying reduction domains in non-binary constituency parsing

Jungyeul Park, Zihao Huang, Eunkyul Leah Jo

原文摘要

Direct non-binary constituency parsing must identify an ordered sequence of children at each phrase-level reduction. We extend our earlier delimiter-guided bottom-up construction to a common calculus for top-down, in-order, and bottom-up parsing. At reduction, the rightmost delimiter marks the left boundary, the nonterminal marker supplies the mother label, and the completed items in the delimited segment determine the children and arity. We use a stack invariant to prove soundness and completeness and derive the exact length of the static oracle's action sequence. A projection-and-lifting theorem shows that each delimiter-guided system and its canonical counterpart generate the same set of trees under both the structural and grammar-licensed transition relations. In controlled experiments on PTB and CTB, the delimiter-guided parsers achieve similar labeled accuracy to their canonical counterparts across all traversal orders. For bottom-up parsing, delimiter guidance reduces the number of action classes and increases the number of supervised decisions per tree.

cs.CL

版本更新 · v3arXiv:2604.01044

CROWD: A global dataset of continuous urban dashcam driving

Md Shadab Alam, Olena Bazilinska, Pavlo Bazilinskyy

原文摘要

We introduce CROWD (City Road Observations With Dashcams), a manually curated dataset of ordinary, variable duration, temporally contiguous, unedited, front facing urban dashcam segments screened and segmented from publicly available YouTube videos. CROWD is designed to support cross-domain robustness and interaction analysis by prioritising routine driving and explicitly excluding crashes, crash aftermath, and other edited or incident-focused content. The release contains 107,407 segment records spanning 36,204.26 hours (82,484 unique uploads), covering 10,538 named inhabited places in 238 countries and territories across all six inhabited continents (Africa, Asia, Europe, North America, South America and Oceania), with segment level manual labels for time of day (day or night) and vehicle type. To lower the barrier for reproducible baseline analysis, we provide per-segment CSV files of automatic detections for all 80 MS-COCO classes produced with YOLOv11x, together with segment-local multi-object tracks generated with BoT-SORT; e.g. person, bicycle, motorcycle, car, bus, truck, traffic light, stop sign, etc. CROWD is distributed as video identifiers with segment boundaries and derived detection and tracking pseudo-labels, enabling reproducible research without redistributing the underlying videos. To support leakage-free evaluation, we also provide canonical splits grouped by source channel or by locality, and weights that balance the contribution of localities and countries.

cs.CV

新论文 · v1arXiv:2611.12019

Feeling Easier, Working Harder: Cognitive Load in AI-Assisted Code Comprehension

Maryangela White, Maximilian Rose, Matthew Buckman, Amy McDonnell, Francisco Ortega, Bianca Trinkenreich

原文摘要

Software developers spend significant time reading and understanding code, increasingly supplemented by generative AI. While these tools aim to reduce the difficulty of reading code, interacting with them introduces a dual-task environment that may impose extraneous cognitive load that is challenging to capture. This study investigates how access to generative AI affects developers' real-time cognitive workload, code comprehension performance, and self-perceived code comprehension strategies. We conducted a 3x2 within-subjects study with 20 novice CS students reviewing Java code snippets of varying lengths with or without AI assistance, followed by an AI-unassisted comprehension quiz. Cognitive workload was continuously captured using a Detection-Response Task (tDRT) during both reading and quiz phases, and compared to post-quiz NASA-TLX and SEQ scores. AI assistance significantly increased objective cognitive workload, raising tDRT reaction times by 11.2%, yet participants' perceived workload remained unchanged. Code comprehension scores were high under both conditions, with no evidence that AI assistance improved comprehension at the difficulty levels evaluated; a ceiling effect limited power to detect benefits on harder tasks. Qualitatively, participants reported trusting the AI conditionally -verifying its output against their own reading for more complex snippets, but directly trusting it for simpler code- and, while many felt their reading process was unchanged, a notable subset shifted toward skimming or reading the AI's explanations in place of the code itself. These findings reveal that developers do not accurately perceive the cognitive resources they expend when managing AI tools. This study provides evidence of added cognitive effort associated with using generative AI, pointing towards a need to account for this dual-task penalty in software engineering tools and education.

cs.SE · cs.AI

新论文 · v1arXiv:2611.12017

Grasp-Taxonomy Conditioning as a Mode Switch for Dexterous Grasping of Climbing Holds

Rumi Loghmani, Abraham George, Amir Barati Farimani

原文摘要

Dexterous grasping in robotics relies on distinct hand configurations depending on object geometry. We introduce BetaGrasp, a 3D diffusion policy that conditions a DP3-style point-cloud policy on a four-class grasp label (crimp, sloper, pinch, and jug), running on a Franka arm with a 16-DoF LEAP hand. We also introduce a climbing-hold benchmark: a spring testbed whose ratchet gives a slip-force reading in newtons. In our analysis the policy's point-cloud encoder did not separate the four holds, so the scan alone gave it little to choose a grasp from. Without the label (a DP3-style baseline), simulated rollouts from the robot's reset pose all end in a jug grasp, whatever the hold (25% correct grasp type, versus 94% for BetaGrasp). The label works as a switch for which grasp the policy performs. On 80 paired hardware trials, BetaGrasp raises average slip force from 9.6 N to 14.3 N, and grasps slipping fully off the hold drop from 44% of trials to 10%.

cs.RO · cs.AI

版本更新 · v2arXiv:2603.29322

VACP: Visual Analytics Context Protocol

Tobias Stähle, Péter Ferenc Gyarmati, Thilo Spinner, Rita Sevastjanova, Dominik Moritz, Mennatallah El-Assady

原文摘要

The rise of AI agents introduces a fundamental shift in Visual Analytics (VA), in which agents act as a new user group. Current agentic approaches - based on computer vision and raw DOM access - fail to perform VA tasks accurately and efficiently. This paper introduces the Visual Analytics Context Protocol (VACP), a framework designed to make VA applications "agent-ready" that extends generic protocols by explicitly exposing application state, available interactions, and mechanisms for direct execution. To support our context protocol, we contribute a formal specification of AI agent requirements and knowledge representations in VA interfaces. We instantiate VACP as a library compatible with major visualization grammars and web frameworks, enabling augmentation of existing systems and the development of new ones. Our evaluation across representative VA tasks demonstrates that VACP-enabled agents achieve higher success rates in interface interpretation and execution compared to current agentic approaches, while reducing token consumption and latency. VACP closes the gap between human-centric VA interfaces and machine perceivability, ensuring agents can reliably act as collaborative users in VA systems.

cs.HC

版本更新 · v2arXiv:2611.02076

Scene-Adaptive Readout and Decoding in Diffusion Driving VLAs

Seungjun Yu, Jiho Choi, Inha Kang, Hojun Choi, Seungwook Kim, Hyunjung Shim

原文摘要

Diffusion driving vision-language-action models repeatedly execute the backbone at every denoising stage, incurring substantial inference cost, while it remains unclear whether all scenes require the same decoding computation. To distinguish when a trajectory becomes readable from how much further refinement it requires, we analyze trajectory readout across network depth and decoding progress. We identify a depth-decoding dissociation in which late-layer representations already support useful trajectory readout after the first forward sweep, whereas early-layer representations benefit more from continued decoding. We further find that both the preferred readout layer and decoding depth vary across scenes. Based on these observations, we propose a scene-adaptive readout and decoding framework. A scene-conditioned readout MoE adaptively weights and combines trajectory predictions from layer-specific late-layer representations after a single backbone sweep, while an adaptive decoding policy applies additional native refinement only when required by the scene. We evaluate our framework on two diffusion driving VLAs across the Waymo E2E and nuScenes benchmarks. Our method improves validation RFS by up to 0.56 while also improving test performance, and achieves an end-to-end speedup of up to $6.0\times$ on Waymo E2E, while consistently reducing trajectory error on nuScenes. These results demonstrate that scene-level readout and decoding allocation improves planning quality while avoiding unnecessary decoding. Our code is available at https://github.com/sjyu001/SARD

cs.CV · cs.AI · cs.RO

新论文 · v1arXiv:2611.12016

Speculative Self-Distillation enables Efficient Knowledge Internalization

Shayan Talaei, Agam Bhatia, Arshia Soltani Moakhar, Jonas Hübotter, Amin Saberi, Azalia Mirhoseini

原文摘要

Many real-world applications require language models to internalize knowledge that was absent from pretraining, to incorporate continually updated facts, or to learn new domain skills. Self-distillation has emerged as a natural approach for this task. A model conditioned on the source material acts as the teacher, and an unconditioned student is trained to reproduce the teacher's behavior closed-book. We propose Speculative Self-Distillation (SSD), an efficient per-token mixed-policy method for self-distillation. The student generates each rollout by default, while the teacher intervenes only at positions where its next-token distribution substantially diverges from the student's. Unlike off-policy distillation with teacher-generated prefixes, this design keeps training rollouts close to the student's test-time behavior, while avoiding the low-signal states that fully on-policy rollouts drift into. In effect, SSD lets the teacher steer the rollout exactly where the privileged context changes the prediction. On three closed-book QA benchmarks measuring fact recall, knowledge updates, and skill acquisition, SSD nearly matches on-policy distillation while using 38-69% fewer supervised tokens and consistently outperforms off-policy distillation on the held-out test set. On a forgetting stress test, SSD retains the most general capability while also achieving the best in-domain accuracy and using less supervision than the on-policy baseline. Overall, SSD establishes a new accuracy-efficiency-forgetting Pareto frontier for self-distillation.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.12014

Benchmarking language models and agents for scientific reasoning in evolving materials laboratories

Xuyu Dong, Yixuan Li, Jianguo Huang, Feng Chen, Yiyun Zhou, Bo An, Zheng Liu, Da Shu

原文摘要

Large language models and the multi-agent systems built around them could accelerate materials discovery by connecting scientific knowledge with experimental decisions. Existing benchmarks establish capabilities in domain knowledge, multimodal interpretation and scientific tool use. As language models increasingly support materials research workflows, their ability to distinguish closely related material states and reason accurately with quantitative evidence remains insufficiently evaluated. These abilities are essential for comparing material responses, assessing mechanisms and maintaining reliable judgements as experimental evidence accumulates. We introduce MatScope to evaluate three connected capabilities. M1 tests unaided, condition-specific reasoning through 200 tasks spanning ten research functions, using aluminium and high-entropy alloys as representative material systems. M2 tests agent-assisted transfer of related knowledge to unresolved materials questions. MatEvoBench-20 tests initial forecasts across scientific dependency chains and revisions of still-hidden responses as observations accumulate. Across eleven model deployments, including GPT-6 Astra and Claude Fable 5.1, given-input calculations and many physical explanations are handled well. Fine-grained response estimates, comparisons between similar states and quantitatively supported choices remain substantially weaker. Related literature improves selected estimates, while condition and baseline mismatches limit transfer. Progressive observations calibrate some downstream responses and destabilize earlier accurate predictions. MatScope establishes measurable targets for developing reliable scientific reasoning in future self-evolving materials laboratories and materials-aware world models.

cs.AI · cond-mat.mtrl-sci · cs.CE · cs.LG

新论文 · v1arXiv:2611.12013

Enhancing Multi-Step Chemical Mechanism Prediction with Graph-Guided Preference Data

Yu Zhang, Ruijie Yu, Xuelin Zhao, Jinming Yang, Feng Zhu, Xiaokang Yang, Yaohui Jin, Yanyan Xu

原文摘要

Predicting multi-step chemical reaction mechanisms requires identifying plausible intermediates and correctly ordering the elementary reaction steps. Existing computational methods focus on single-step elementary reaction prediction, limiting their ability to generalize to unseen reaction spaces. We introduce a graph-guided framework for multi-step chemical mechanism prediction that leverages a chemical mechanism knowledge graph (ChemMechKG) to guide large language models (LLMs). To improve pathway prediction, we develop a graph-aligned reaction mechanism predictor (GRMP) that uses graph neural networks to generate synthetic candidate pathways for pathway optimization. During inference, we design a relation retrieval (RR) module to extract relevant graph evidence from the KG for pathway refinement. Experiments show that GRMP achieves the highest pathway accuracy among all compared methods on ChemMechQA and oMe-Gold, reaching 48.1% and 57.9%, respectively. On a fixed sample of 110 out-of-distribution reactions from ChemMechQA-Hard, GRMP achieves 36.4% top-1 pathway accuracy. LLM-as-Judge and human assessment further demonstrate its ability to generalize to unseen reactions.

cs.AI

新论文 · v1arXiv:2611.12012

Robust Domain-Mixture Scheduling for Multi-Teacher On-Policy Distillation

Yankai Chen, Sida Lin, Yifan Li, Hanjun Luo, Hanrong Zhang, Zhuohan Xie, Bowei He, Wei-Chieh Huang 等 13 位作者

原文摘要

Multi-teacher on-policy distillation (MOPD) merges the capabilities of multiple domain-expert teachers, such as mathematical reasoning, code generation, and instruction following, into a single compact student. Since all domains share a limited training budget, how to allocate it across domains directly determines the quality of distillation. Existing methods allocate the budget by each domain's learning progress, but offer no guarantee for lagging domains. We therefore introduce distributionally robust optimization (DRO) into MOPD to prioritize the worst-performing domain. However, the per-domain training signals are estimated from a few rollouts and are inherently noisy, so directly applying DRO mistakes noise for the worst case, lets occasional spikes hijack the budget, and protects inherently hard domains rather than truly regressing ones. To address these issues, we propose RDS-MOPD, which keeps the DRO objective and redesigns its three parts: it shifts the allocation only when differences clearly exceed the noise, bounds the influence of any single anomaly, and defines the worst case as the regression from each domain's own best level, all with theoretical guarantees. Experiments show that RDS-MOPD outperforms recent competing methods and ranks first on most mathematical reasoning, code generation, and instruction-following benchmarks.

cs.CL

新论文 · v1arXiv:2611.12011

HIST3R: Decomposing and Rectifying State Updates with History for Streaming 3D Reconstruction

Kenneth Yang, Yu-Chiang Frank Wang

原文摘要

Streaming 3D reconstruction with recurrent states enables long-video scene understanding under bounded memory, but turns reconstruction into a state-evolution problem: each incoming frame updates a compact scene memory on which all subsequent predictions depend, so unreliable updates overwrite historical context and accumulate into long-horizon geometric drift. We analyze CUT3R-style recurrent updates through a direction--magnitude decomposition, in which the magnitude sets the update gain, i.e., how strongly an observation is written into the state, and the direction encodes the geometric intent, i.e., where the update drives the state. This decomposition provides a unified view of CUT3R and its variants, revealing that existing training-free extensions perform magnitude-only control: they can attenuate an unreliable update but cannot correct its direction. We propose HIST3R, a training-free framework built on CUT3R that controls both components using history. HIST3R rectifies the update direction using locally consistent historical states, and modulates the update magnitude according to the visual discrepancy between the current observation and its history, suppressing redundant updates while preserving complementary evidence. Across camera pose estimation, 3D reconstruction, and video depth estimation, HIST3R consistently improves long-horizon performance while retaining the memory footprint and inference speed of CUT3R. With 1000 input frames, it reduces ATE by 23.87% on ScanNet and 33.65% on TUM-Dynamics relative to the strongest competing method; with 500 frames, it improves median reconstruction accuracy over the strongest CUT3R-based variant by 56.52% on 7-Scenes and 33.96% on NRGBD.

cs.CV

新论文 · v1arXiv:2611.12010

Scalable Bayesian Optimization for Efficient Exploration of Moire Patterns

Panagiotis Krokidas, Christos Lazaridis, Vassilis Sioros, Efi-Maria Papia, Vassilios Constantoudis, George Giannakopoulos

原文摘要

Large materials design spaces often contain rare high-performing configurations that are difficult to identify through trial-and-error exploration or purely representative machine-learning (ML) sampling. In this work, we present FruBO, a flexible Bayesian Optimization framework for accelerating the discovery of optimal configurations in computationally demanding materials design problems. As a case study, we investigate multilayer Moiré patterns generated by the superposition of six rotated hexagonal lattices, where the objective is to identify the rotational conformation that maximizes pore-size uniformity, quantified using the Jain fairness index. The resulting benchmark contains 600,000 unique configurations and exhibits a highly skewed objective distribution, making the global optimum difficult to locate by random sampling. We compare random exploration, Gaussian Process-based Bayesian Optimization, and Bayesian Optimization using a lightweight CatBoost surrogate with committee-based uncertainty estimation. Random sampling identifies the global optimum only after 533,012 evaluations, requiring approximately 31 hours, while Gaussian Process-based BO becomes impractical due to GPU memory exhaustion after 290 acquired samples. In contrast, FruBO with CatBoost identifies the global optimum after 1,470 acquired samples and approximately 1.15 hours. These results demonstrate that scalable surrogate models can substantially improve the feasibility and efficiency of BO in large nanomaterials design spaces.

cs.LG · physics.app-ph

版本更新 · v3arXiv:2605.06467

No Triangulation Without Representation: Generalization in Topological Deep Learning

Johannes S. Schmidt, Martin Carrasco, Ernst Röell, Guy Wolf, Nello Blaser, Bastian Rieck

原文摘要

Despite an ever-increasing interest in topological deep learning models that target higher-order datasets, there is no consensus on how to evaluate such models. This is exacerbated by the fact that topological objects permit operations, such as structural refinements, that are not appropriate for graph data. In this work, we extend MANTRA, a benchmark dataset containing manifold triangulations, to a larger class of manifolds with more diverse homeomorphism types. We show that, contrary to prior claims, graph neural networks can saturate the benchmark, while higher-order message passing methods lag behind. However, we find that this is contingent on the right representation and feature assignment, emphasizing their importance in baseline models. Hence, we present a novel evaluation protocol based on representational diversity and triangulation refinement. Even when including refinement-like changes in the training data, existing models fail to generalize beyond the combinatorial structure of the data. This points towards a research gap in developing models that understand topological structure independent of scale. Our work thus provides the necessary scaffolding to evaluate future models and enable the development of topology-aware inductive biases.

cs.LG · math.AT

版本更新 · v2arXiv:2606.16897

Contrastive-Difference CKA Reveals Concept-Specific Structural Alignment Across Language Model Architectures

Xueping Gao

原文摘要

Do language models encode the same prompted concepts in structurally compatible ways, beyond generic similarity induced by shared questions? We study contrastive-difference centered kernel alignment ($\mathrm{CKA}_Δ$), which compares per-question activation differences between opposing concept instructions. A matched same-concept versus cross-concept comparison separates the question of concept-conditioned structure from the magnitude of representational similarity. Across four checkpoints and eight personality-related traits, a fixed-final-layer analysis gives mean same- and cross-trait $\mathrm{CKA}_Δ$ of 0.7259 and 0.6828. Trait-label randomization detects correspondence conditional on this model and prompt set ($p=1/10001$, one-sided), but a model-and-trait-weighted 95% interval for the difference is $[-0.0330,0.1017]$, limiting broader generalization. Strict question-group holdouts retain high same-trait linear recoverability. More stringently, maps and preprocessing fitted on seven traits transfer a source polarity classifier for the eighth trait to handwritten test questions: mean affine and orthogonal accuracies are 88.10% and 88.57%, versus 47.70% for shuffled pairing. Performance varies substantially across traits and model directions. Synthetic controls show why moderate CKA and high affine accuracy alone do not establish functional equivalence. The results support a scoped diagnostic of concept-specific structure and held-out linear recoverability; they do not establish universal invariance or a robust advantage over raw CKA across architectures.

cs.CL

新论文 · v1arXiv:2611.12006

Constraining Evidence Strength in Bayesian Tonal-State Inference: A Posterior-Continuity Diagnostic

Chen-Gia Tsai

原文摘要

Effective pitch-evidence strength governs the concentration of tonal-state posteriors. Expert local-key annotations cannot calibrate this strength because they do not specify the posterior distribution over the 24 candidate keys. This study constrains evidence strength through tonal continuity, quantified by a measure $λ$ derived from adjacent-window posterior overlap. Passages with $λ$ > 0.50 exhibit relatively strong tonal continuity. At $λ$ = 0.50, carrying forward the preceding tonal belief is predictively equivalent to starting afresh with a uniform, key-neutral prior. Across 26 subcorpora of the Distant Listening Corpus, median $λ$ remains above 0.50 for changes from major keys to IV, V, and vi throughout the examined range of evidence strengths, whereas changes to i, ii, and iii cross this threshold as evidence strength increases. Because these latter three keys share the departed key's tonic or differ from it by a single key-signature accidental, such changes are expected to retain $λ$ > 0.50 in a substantial proportion of cases. An event share G therefore assesses how often this expectation holds as tonal selectivity increases in 4-bar windows. The resulting high-G region identifies evidence-strength settings that may be appropriate for tonal-state inference. When $λ$ is extended to cross-scale compatibility, the Presto finale of Mozart's Piano Sonata K. 310 shows that, within this region, a 4-bar C-minor interpretation remains compatible with its 16-bar C-major context. The findings establish tonal continuity as a music-theoretical constraint on evidence strength and illustrate how local and prevailing-key interpretations can coexist when pitch evidence is integrated over nested spans.

cs.SD

版本更新 · v2arXiv:2610.27726

Anytime-Valid Runtime Monitoring of Learned Barrier Certificates

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

原文摘要

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

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

版本更新 · v3arXiv:2510.11370

Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers

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

原文摘要

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

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.12000

HyPLM Technical Report

Haowei Lin, Cai Zhou, Xiangxin Zhou

原文摘要

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

cs.LG · q-bio.BM

版本更新 · v2arXiv:2605.30326

RoboWits: Unexpected Challenges for Robotic Creative Problem Solving

Chunru Lin, Hongxin Zhang, Fenghao Yu, Zhehuan Chen, Thomas L. Griffiths, Yejin Choi, David Held, Chuang Gan

原文摘要

The ability to reason, adapt, and creatively solve problems under unexpected challenges is essential for robots operating in real-world environments. However, current robotic benchmarks primarily emphasize skill-level execution and provide limited insight into such cognitive reasoning capabilities. We introduce RoboWits, a bi-manual robotic benchmark designed to systematically evaluate cognitive reasoning, creative tool use, and robustness to unexpected conditions. To enable scalable construction of high-quality reasoning-centric unexpected scenarios, we propose an automated task generation pipeline formulated as a multi-agent cooperative framework, comprising agents for seed task generation and verification, metric generation, scene generation, and task mutation. Using the pipeline, we curated 30 diverse seed tasks and 200 tasks with mutations and graded difficulty across geometry, material, and assembly-based reasoning. We benchmark popular robot policies, pre-trained VLAs, a zero-shot policy built on a frontier VLM, and oracle-state planners. Our results reveal a significant performance gap: while pre-trained VLAs exhibit preliminary success on seed tasks after fine-tuning, they struggle to perform on mutated tasks, implying their brittleness in manipulation tasks requiring reasoning, strategy adaptation, and robustness to deceptive or constrained environments. A zero-shot policy built on GPT-6 Astra outperforms all fine-tuned VLAs, yet still loses about a fifth of its success on mutated tasks, showing that stronger foundation models alone do not close the robustness gap. See our project page https://umass-embodied-agi.github.io/RoboWits/ for videos.

cs.RO · cs.AI

版本更新 · v2arXiv:2603.13389

Logit-Conditioned Diffusion Decoding for Frozen Discrete-Token VLMs

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

原文摘要

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

cs.CV · cs.LG

新论文 · v1arXiv:2611.11998

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

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

原文摘要

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

cs.LG

版本更新 · v2arXiv:2611.03698

Training LLM Agents to Automate LLM Post-Training with RSI-Dojo

Shuzheng Gao, Zhaojian Yu, Penghao Yin, Yuling Shi, Kai Cai, Shilin He, Michael R. Lyu

原文摘要

Recursive Self-Improvement (RSI) aims to enable AI systems to autonomously build and improve AI systems themselves, including models, harnesses, and underlying infrastructure. Within this broader agenda, a central capability is enabling agents to train and improve base models. However, existing studies on automated model training primarily focused on workflow- or harness-level optimizations, rather than internalizing the ability to conduct post-training into the model itself. Developing this capability requires executable model training environments that can produce high-quality trajectories demonstrating how to select data, train models, diagnose failures, and iteratively improve results. In this paper, we introduce RSI-Dojo, a collection of executable model training environments designed to teach LLM agents to conduct post-training. To construct RSI-Dojo, we develop RSI-Craft, an automatic pipeline that converts human research artifacts into executable model training environments. RSI-Craft automatically collects research papers from top venues, instantiates datasets and metrics into a unified interface, and reproduces evaluation dependencies. It then filters tasks by data size, execution reliability, and discriminability, yielding RSI-Dojo with 281 seed model training tasks. Building on RSI-Dojo, we employ a trajectory collection method with an improved harness to collect high-quality model-training trajectories from frontier models, then retain examples through rubric-based and outcome-based filtering. We fine-tune Qwen3.5-9B and Qwen3.6-35B-A3B on these trajectories. The resulting RSI-Dojo-9B and RSI-Dojo-35B-A3B improve over their base models by 8.74 and 16.87 PostTrainBench points, respectively. RSI-Dojo-35B-A3B reaches 29.95 on PostTrainBench and 53.29 on PostTrainBench-Lite, matching the performance of frontier models such as GLM-5.2 and GPT 5.5.

cs.AI