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

+1680新增论文
+1333其中 AI 相关
+187已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-17 23:35各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 11:30 — 2026-11-18 11:30(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:2026-11-18 04:28最近发现新增版本:2026-11-17 23:35库内论文最新更新时间:2026-11-17 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。

25,786 已收录论文21,491 AI 相关7,725 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 19,087 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
版本更新 · v3arXiv:2605.01507

MILD: Mediator Agentic System with Bidirectional Perception and Multi-Layered Alignment for Human-Vehicle Collaboration

Jiyao Wang, Yunbiao Wang, Yubo Jiao, Xiao Yang, Dengbo He, Sasan Jafarnejad, Luis Miranda-Moreno, Raphael Frank 等 9 位作者

原文摘要

Prior studies report that partial driving automation can increase the cognitive demands on human drivers. This effect largely arises from human drivers' lack of transparent insight into the vehicle's intentions and decision logic, as well as from automated systems' limited awareness of the driver's dynamic state and preferences. This bidirectional misalignment undermines shared situational awareness and exacerbates coordination failures in human-vehicle interaction. To address these limitations, we argue for a paradigm shift that elevates the human role from passive supervisor to active manager. We introduce the Mediator-in-the-Loop-Driving system, based on an agentic system architecture to facilitate synergistic human-vehicle collaboration. MILD integrates a perception agent for joint in-cabin and out-of-cabin understanding with a lightweight strategy agent that generates compliant and explainable action suggestions. To ensure these strategies are strictly aligned with safety regulations and human values, we develop Evidence- and Constraint-weighted Policy Optimization. ECPO leverages automatic validators to steer the agent toward behaviors that are not only accurate but also structurally complete, substantiated by evidence, and less prone to constraint violations. Furthermore, a retrieval-augmented generation module dynamically incorporates constraints from traffic regulations, speed recommendations, and driver preferences into the decision loop. Experiments across three open datasets demonstrate that MILD consistently outperforms baselines in both perception accuracy and strategy quality under auditable offline metrics, and yields higher human-rated policy adequacy, comfort, and explanation than baselines.

cs.AI

版本更新 · v2arXiv:2610.31471

Ask About the Right Moment: Training-Free Object Identity Reasoning for Video-Language Models

Di Yang, Xiaochang Li, Muyang Liu, Yufei Wang, Yanhai Xiong

原文摘要

Many questions about a video concern one physical object. Where does the ball end up after the cups are shuffled? Which card is the queen? How often was the mug covered? Open video-language models (Video-LMs) recognise such objects in single frames but do not keep them apart over time. On shuffled shell games, open models from eight families stay near chance, and so do published tool agents. We separate semantic identity binding from temporal identity maintenance. Binding should happen at a moment when the evidence for the object is visible, and maintenance should be left to a tracker. Track, Then Bind implements this principle without training. A promptable video tracker follows every candidate object and draws it with a track number. A frozen vision-language model (VLM) answers one question about the identifying evidence, which binds the target to a track. The answer is then derived from a text description of the tracks. With Qwen3-VL-32B, the agent solves both VET-Bench tasks, where a fine-tuned trajectory model reaches 92% and 90%. On real cup games from the Perception Test, it raises accuracy from 35.5% to 52.3%. Without retuning, the same configuration also solves VET-Bench with Gemma 4 and GPT-5.5. Its track-derived visibility timelines add 8.8-17.9 points on TOC-Bench for open models. GPT-6.1 already answers 92.5% of the real cup games directly but 71.0% through our pipeline, while our timelines still raise its TOC-Bench accuracy from 52.5% to 57.7%. The benefit of external tracking thus depends on the underlying model and the task.

cs.CV

版本更新 · v2arXiv:2608.11810

On the Feasibility of Image-Based Representations for Air Traffic Complexity Estimation

Hyewook Kim, Byul Kang, Seokbin Yoon, Keumjin Lee

原文摘要

Air traffic controllers perceive traffic complexity through the radar display, suggesting that a computer vision model operating on the same imagery may provide a natural architecture for modeling controller-perceived complexity; however, whether radar imagery is a viable input format for deep learning vision models remains unclear. Unlike natural images, radar images are extremely sparse and self-similar, consisting primarily of a black background and a few visually identical aircraft blobs, while small changes in aircraft positions can substantially alter sector-level complexity. To test whether a vision model can capture these operationally important differences, we encode each traffic situation as a position image supplemented by five channels representing aircraft state variables, including heading, speed, and altitude, and train a Vision Transformer (ViT) to regress four intrinsic complexity components derived from pairwise geometric relations among aircraft. The model achieves $R^2 > 0.96$ for all four components on test data, and a one-aircraft removal perturbation study shows that the change in the model's estimate is proportional to how much the removed aircraft contributed to sector complexity, rather than the same for every removal. These results demonstrate that, despite its atypical visual characteristics, the proposed image-based representation is a viable input format for air traffic complexity modeling.

cs.CV · cs.LG

新论文 · v1arXiv:2611.10162

M5-TTS: A Mini-Scale Multilingual and Multi-Dialect Text-to-Speech Language Model with Multi-Token Prediction

Wenhao Li, Jingbin Hu, Shengming Ling, Xiaming Ren, Haoyu Zhang, Jinrui Liang, Hanke Xie, Qirui Zhan 等 23 位作者

原文摘要

We present M5-TTS, a compact text-to-speech system supporting multilingual and Chinese multidialect synthesis, zero-shot voice cloning, speaker-specific multilingual generation, and CPU streaming. Its 50M-parameter language model, excluding the speech codec, combines a temporal backbone with a local multi-token prediction module over 16 codebooks. GRPO post-training combines global speaker-similarity and pause feedback with a token-level CER process advantage. Character-level error comparisons provide local feedback, with negative credit propagated backward within a clause and projected onto audio-token positions. M5-TTS achieves 1.37% CER on Seed-ZH and 2.91% WER on Seed-EN, corresponding to relative error reductions of 62.2% and 35.3% over MOSS-TTS-Nano with half the language-model parameters. It also achieves lower content error rates in five of six evaluated MiniMax languages, while difficult Chinese inputs remain a limitation. On four Intel Xeon Gold 6530 cores, it achieves a real-time factor of 0.653 and a warm first-chunk latency of 225ms. A 10-listener evaluation gives M5-TTS higher speaker-similarity and intelligibility ratings than MOSS-TTS-Nano, with a lower naturalness rating. We will release training, post-training, and inference code, together with voice-cloning and speaker-specific checkpoints, to support reproducible research on compact speech generation for on-device voice interaction.

eess.AS · cs.SD

新论文 · v1arXiv:2611.10160

Improving the Diffusability of Motion Tokenizer

Guanhe Huang, Songqiao Han, Tangzheng Lian, Oya Celiktutan

原文摘要

Latent diffusion models paired with a variational auto-encoder (VAE) tokenizer have shown promising performance for efficient text-driven human motion generation. However, motion latent diffusion suffers from a generation-reconstruction trade-off: simply increasing tokenizer capacity enhances reconstruction but fails to proportionally improve text-conditioned generation quality. We assume this trade-off stems from a spectral mismatch inside the VAE tokenizer: the encoder yields a latent space biased toward high frequencies, and the decoder introduces temporal artifacts. In this paper, we propose the Diffusable Motion Tokenizer (DiMoT) to improve the diffusability of the tokenizer, rather than scaling up the diffusion backbone. To improve text-conditioned optimization, Critic Spectral Adaptation (CSA) leverages a pretrained diffusion model as the critic to suppress high-frequency latent energy. To preserve motion dynamics, the Alpha-Flow Motion Decoder (AMD) performs generative decoding via average-velocity prediction, enabling efficient one-step decoding. Extensive experiments demonstrate that DiMoT achieves state-of-the-art performance across various challenging text-to-motion benchmarks, yielding superior motion fidelity and text-motion alignment. Project page: https://githubhgh.github.io/dimot/.

cs.CV

新论文 · v1arXiv:2611.10157

BACGUARD: Fact-Grounded Runtime Mitigation of Broken Access Control

Moses Ndebugre

原文摘要

Broken Access Control (BAC) has been the foremost category in the OWASP Top Ten since 2021, primarily due to the challenges in enforcing authorization at the application layer. Traditional mechanisms depend on logic embedded in the application, referencing relational database information such as permissions, roles, or ownership. However, missing or incorrect checks can go undetected by external systems, leaving applications vulnerable. This paper presents BACGUARD, a reverse proxy designed to enforce authorization for unmodified applications. BACGUARD reconstructs authorization relations by leveraging authenticated user data from session stores and object ownership from relational schemas. It evaluates whether users are permitted to access resources and blocks unauthorized requests in real time. Unlike existing approaches, BACGUARD bases its authorization on database joins, making the system resilient to forgery. For most requests, decisions are made deterministically. In cases where access control violations are only apparent in response data, such as cross-user data leakage, a language model is used as a fallback. Evaluations on six applications, including those with known vulnerabilities, demonstrate that BACGUARD's hybrid deterministic and language model-based approach blocks all tested attacks with a false-positive rate below 0.7%. Competing solutions like Web Application Firewalls are less effective and more disruptive. The results highlight BACGUARD's primary contribution: the external reconstruction of authorization facts, enabling robust enforcement even when the application itself is flawed.

cs.CR

新论文 · v1arXiv:2611.10156

DeepResearch RewardBench: Evaluating Reward Models for Deep Research Report

Shudong Liu, Yuting Zhong, Guanhua Chen, Xinyi Yang, Junnan Liu, Lidia S. Chao, Jiaheng Liu, Derek F. Wong

原文摘要

Empowered by Large Language Models (LLMs), deep research systems integrate online information into research reports through multi-step web searching and information synthesis. Evaluating these reports presents a significant challenge due to their long context, high information density, and domain specificity, necessitating the use of AI evaluation as a substitute for prohibitively expensive human assessment. However, few studies have examined the effectiveness of existing reward models or LLMs in understanding and evaluating such research reports. To bridge this gap, we introduce DeepResearch RewardBench, the first benchmark dedicated to evaluating reward modeling for research reports. We collect diverse report candidates from multiple agents or tool-augmented LLMs. These candidates are scored using query-specific golden rubrics, and we ensure data quality and difficulty through a combination of multi-round filtering and human verification. Our benchmark comprises preference datasets formatted as pairs, triplets, and quadruplets to test ranking capabilities across varying levels of difficulty. Extensive experiments demonstrate that while current reward models handle general coherence effectively, their performance significantly degrades when evaluating research reports. Generative LLMs acting as judges demonstrate comprehensive superiority in this domain, with comparative evaluation proving more effective than direct scoring methods. We anticipate that this benchmark will serve as a vital testbed for the evaluation and advancement of research agents.

cs.AI · cs.CL

版本更新 · v2arXiv:2611.06348

Flexible Intensities Matter: A Comprehensive Re-evaluation of Hawkes Processes and Neural Temporal Point Processes

Hendrik Mehrtens, Florian Buettner, Oliver Stegle

原文摘要

Temporal point processes (TPPs) are the canonical model class for event sequences in continuous time, with applications ranging from seismology to electronic health records. Recent benchmarks report that neural TPPs substantially outperform their classical counterparts, such as Hawkes processes. However, these comparisons set flexible neural models against Hawkes processes in their most restricted forms and covered only a narrow range of domains. We revisit this comparison under autoregressive next-event prediction, evaluating Poisson and Hawkes processes of increasing flexibility against neural TPPs on five established benchmarks and two large-scale medical tasks derived from UK Biobank disease histories and MIMIC-IV ICU records. First, once Hawkes processes are equipped with flexible, learnable baselines and kernels, the previously reported gap to neural TPPs largely closes. Second, neural TPPs are likewise limited by their intensity parametrization: a Transformer with a spline-based intensity head outperforms previous intensity-based neural TPPs and matches or exceeds the intensity-free model. Decomposing the log-likelihood into time and type terms shows that this gain lies almost entirely in modeling when events occur (log p(t)) rather than which type occurs (log p(d|t)). Third, only on MIMIC-IV do neural TPPs retain an advantage in predicting event types, underscoring the value of complex datasets for evaluating TPPs. We release TorchPP, an open-source PyTorch framework with unified implementations of classical and neural TPPs.

cs.LG · stat.ML

版本更新 · v2arXiv:2611.07847

Computation, not weight access: large language models as auditors of clinical prediction networks

Zhiyu Liu, Xinyu Yang

原文摘要

Frontier large language models (LLMs) have been reported to read, edit and write the weights of small neural networks, raising the prospect of auditing clinical prediction models from their files alone. Public demonstrations, however, mixed reading raw weights with running code. We separated these conditions in internally pre-specified simulation experiments. Tanh networks of 105 to 38,401 weights were trained on simulated cohorts of patients with subarachnoid haemorrhage, each with a planted relationship or none, and one network was trained on labels that under-recorded deaths in a subgroup. GPT-6 Astra and four other GPT models answered single prompts under a default or an explicit system instruction, either with the weights in the prompt and no tools, or with a calculation-only tool that exposed the weights (white box) or only the network's predictions (black box). Without tools, Astra recovered planted relationships in 353-weight networks but became unreliable at 3,457 weights, and under the default instruction it declined 17 of 21 audit and repair tasks as unidentifiable; the explicit instruction removed these refusals. With the tool, it recovered the planted relationship in all 39 runs on networks of up to 38,401 weights, raised no false alarm in 21 runs on null networks, and found the biased subgroup in 6 of 6 runs. Black-box access performed as well as white-box access, and other GPT-6 models read as accurately. A well-designed script matched the comparator models on the audit and the best LLM repair. For auditing these networks, what mattered was computation and elicitation, not access to the weights.

cs.LG · cs.AI

新论文 · v1arXiv:2611.10153

Learning Across Heterogeneous Feature Spaces with Group Robustness

Xenia Konti, Arjun Tschand, Chuan Hong, Nicoleta J. Economou-Zavlanos, Michael M. Zavlanos

原文摘要

In clinical applications, patients undergo different combinations of tests, and machine learning models must therefore ensure accurate predictions across heterogeneous feature spaces. Current approaches upweight the patients with the highest loss, without accounting for the limited predictive information in their features preventing their loss from going any lower. Moreover, when patients' feature spaces are fully disjoint, current methods reduce to training independent models, preventing knowledge transfer across them. We propose a framework for group robust learning across heterogeneous feature spaces, where groups are patients sharing a feature space. Since a high loss may simply reflect uninformative features, we instead optimize for worst-group excess loss, the gap between a group's loss and an estimate of its achievable optimum. To allow collaboration between groups, we use group-specific encoders mapping into a shared latent space in which learnable Gaussian anchors cluster patients by outcome. On tabular and imaging medical datasets, including fully disjoint feature settings, our framework outperforms state-of-the-art methods when groups differ in their optimal losses or cannot train a good model on their own, reducing worst-group loss by up to 79% and excess loss by up to 95% with up to 18$\times$ fewer parameters.

cs.LG

新论文 · v1arXiv:2611.10151

WorldMind: Test-Time Scaling for Visual Spatial Reasoning through Latent World Simulation

Haoming Wang, Yongjian Fu, Ju Ren, Wei Gao

原文摘要

Vision-Language Models (VLMs) have continuous deficiency in spatial reasoning tasks that require \emph{mental spatial transformation}, such as reasoning under hypothetical changes in viewpoint or position, known as perspective-taking tasks. Existing approaches either scale linguistic reasoning or augment VLMs with static geometric representations, but neither directly enables active transformation of the represented scene. World models offer this capability, yet existing systems typically communicate through synthesized RGB images, introducing a latent-to-pixel-to-latent bottleneck. We introduce \emph{WorldMind}, a framework for test-time scaling of spatial reasoning through latent world simulation. Given a query and observation, the VLM selects useful spatial transformations, while a world model executes them and exposes aligned intermediate latent features directly to the VLM. The resulting latent evidence is incorporated into subsequent reasoning steps, enabling iterative spatial simulation without repeatedly decoding imagined states into pixels. To optimize this interaction, WorldMind further employs process-verifiable reinforcement learning that rewards reasoning progress only when the associated action and latent transition are valid. WorldMind thus scales spatial reasoning by allocating additional inference-time computation to active world simulation rather than generating more language or pixels. Across VSI-Bench, MMSI-Bench, and MindCube-Tiny, WorldMind achieves an average improvement of 16.0% over the base VLM and 8.3% over the strongest RGB-based world simulation.

cs.AI

新论文 · v1arXiv:2611.10150

What Is the Value of AI-Involved Art? Evidence From a Juried In-Person Exhibition

Wisdom Obinna, Hexuan Wang, Cecile Duncan, Kristelia Garcia, Nina Grgić-Hlača, Toni-Lee Sangastiano, Elissa M. Redmiles

原文摘要

What is the value of AI-involved art, and to whom does it belong? We begin to answer these questions using data from an in-person, juried AI art exhibition. Our study involved artists, lawyers, and computer scientists (N=209) as either creators or evaluators of AI-involved artworks. We found that nearly half of evaluators reported willingness to buy an artwork, with pricing correlating with perceived artistic value---creativity and visual appeal---as well as the effort necessary to create it. In contrast, three-quarters of creators reported willingness to sell at prices correlating only with effort rather than artistic value. Both groups viewed prompting users and AI developers as deserving rewards and rights, leaving training data artists behind. Disciplinary training shaped these views: participants with legal training favored distributed reward models. These findings have implications for future research on human-AI creative collaboration and policy debates regarding AI-involved works.

cs.AI

版本更新 · v2arXiv:2611.07328

DC-SQEM: Medial Mesh Extraction by Dual Contouring with Spherical Quadric Error Metric

Bingchuan Li, Ruilong Liu, Tianhao Hu, Congyi Zhang, Ningna Wang, Junfeng Yao, Xiaohu Guo

原文摘要

The medial axis, as a compact representation, describes not only the boundary but also the interior of the shape, and has been widely used in analyzing and simplifying shapes. However, approximating feature-preserving medial axis from unstructured data, such as oriented point clouds, remains challenging due to the lack of explicit connectivity and the presence of noise in the source. We propose DC-SQEM, a dual-contouring-based framework that computes medial meshes (an explicit representation of the medial axis) directly from oriented point clouds without relying on watertight manifold surfaces or volumetric structures. With the help of an adaptive octree, our method fits local medial spheres for each cell based on the Spherical Quadric Error Metric (SQEM). We address several long-standing robustness issues in dual-contouring and mesh extraction, including out-of-cell solutions, unstable feature classification, and redundant topological connections. To this end, we introduce virtual nodes, a feature-downgrading strategy, and a geometry-driven topology-aware cleanup procedure, enabling robust SQEM-based medial dual contouring with clean mesh outputs. Unlike prior point-cloud-based methods that produce either only 1D skeletal structures or incomplete medial features, our method preserves sharp geometric features from the input and reconstructs a complete medial structure, including sheets, curves, seams, and junctions. Compared to restricted-power-diagram-based approaches, our algorithm can handle point clouds as input, without having a strong requirement on water-tightness or manifoldness.

cs.GR

新论文 · v1arXiv:2611.10148

BATCH: Behavior Alignment for Cross-Embodiment Learning from Humans

Zeyi Liu, Shuran Song

原文摘要

Human demonstrations provide a scalable source of diverse manipulation data, but leveraging them for robot learning remains challenging due to differences in embodiment, viewpoint, action spaces, and temporal structure. We introduce BATCH, a cross-embodiment learning framework that explicitly aligns human and robot behaviors. BATCH learns self-supervised temporal representations with a cycle-consistency objective to establish cross-embodiment correspondences without manual annotation. We further introduce two complementary training objectives that leverage these correspondences within an autoregressive videoaction diffusion model: behavior-aligned co-training and human-to-robot style transfer. On real-world manipulation tasks, BATCH improves generalization to unseen task configurations compared with training on unaligned data and prior cross-embodiment baselines, with additional gains from the style-transfer objective. Our results demonstrate that explicit behavior alignment enables more effective transfer from human demonstrations to robot policies.

cs.RO · cs.AI · cs.CV

新论文 · v1arXiv:2611.10147

Learning of Tree Automata applied to Neural Language Acceptors

Juan Pedro da Silva, Sergio Yovine

原文摘要

We extract visibly pushdown grammars (VPGs) from neural language models in a fully black-box setting. Our work builds on the VPL* framework, which learns VPGs from recurrent networks by exploiting access to the target's internal state. First, we replace the white-box equivalence oracle with PAC sampling over trees. The resulting algorithm applies unchanged to transformer language models and, more generally, to any acceptor exposing only binary decisions. Second, we further observe that the original framework only ever queries the target on well-formed sequences that can be accepted by the most permissive VPG (called BParse) with the target's ranked alphabet. That is, VPL* is blind to the target's behavior outside BParse. Thus, we propose to sample trees directly instead of sequences and call the target with all the resulting sequences in order to provide an error estimate of how far the target deviates from being a VPG. Last but not least, we develop a learner that captures a tree automaton describing discovered behaviors of the target outside BParse, which results in a larger learnable space. We evaluate the approach on several cases, including transformers trained with Dyck grammars and synthetic targets designed to be outside BParse.

cs.CL · cs.AI

新论文 · v1arXiv:2611.10145

TrialJev: Open-Weight Single Pass Eligibility Scoring for Patient Trial Screening

Omar Ibrahim, Grant Hamblin, Benjamin Haibe-Kains

原文摘要

Clinical trial screening requires assessing large numbers of patient-trial pairs to prioritize candidates for detailed eligibility review, often under restrictions on sharing patient records. We introduce TrialJev, an open-weight eligibility scorer that uses LoRA-adapted Qwen models and a pointer head to score natural-language answer options in a single forward pass, without autoregressive decoding. Trained on TREC Clinical Trials 2021 and evaluated on 6,975 eligible-or-excluded pairs from 50 unseen TREC 2022 synthetic patients, TrialJev achieves 80.97% (Qwen3.5-27B) and 81.84% (Qwen3.8-27B) accuracy, compared with 79.87% and 79.93% for LLMs fine-tuned on the same data to generate verdicts. In matched batch-1 measurements, verdict generation takes 2.45-2.70 times as long as the one-pass inference of TrialJev at 9B-27B. Under a common development-fitted decision correction, the two 27B TrialJev models reach 80.99% and 81.88% accuracy, compared with 81.28% for the proprietary hosted Jev API; paired confidence intervals include zero. TrialJev runs locally on a single GPU, requiring approximately 178 ms per pair at 27B, without transmitting patient text to an external model API. An A/B-logit ablation shows that avoiding decoding, rather than the pointer head alone, accounts for the measured efficiency advantage. TrialJev is intended for first-pass prioritization of candidate trials, complementing rather than replacing explanatory models and clinical review. Evaluation is limited to synthetic patients and implementation-specific timing, and clinical use has not been validated. Adapters, pointer heads, and model cards are released on Hugging Face.

cs.LG

新论文 · v1arXiv:2611.10144

Dataset Collections: Challenges of Large-Scale Data Aggregation in 3D Medical Image Datasets

Yannick Kirchhoff, Saikat Roy, Elisa Stegmeier, Hamideh Haghiri, Constantin Ulrich, Maximilian Rouven Rokuss, Tassilo Wald, Karol Gotkowski 等 33 位作者

原文摘要

The development of deep learning-based medical AI depends on high-quality annotated data. Yet, dataset creation remains constrained by the need for expert radiologist annotations, limiting curated datasets to relatively small cohorts. To overcome this limitation, recent efforts increasingly aggregate disparate public datasets into large-scale dataset collections. However, combining datasets at scale often obscures data provenance, introducing substantial risks of reuse propagation, unintended leakage, bias amplification and distorted data distributions. In this work, we study these problems on a massive collection of 565k 3D radiological images across 1034 public datasets and provide practical resources to address them. Firstly, we formalize dataset collections as a distinct paradigm in medical image analysis and characterize their structural challenges, including reuse propagation, duplication, and provenance fragmentation. Secondly, we perform a large-scale empirical study of duplication on this collection and demonstrate extensive exact and near-duplicate reuse across public datasets via perceptual hashing and manual tracing, identifying a lower bound of 118k duplicate pairs. We make the perceptual hashes publicly accessible for comparison through our website, providing researchers with a standardized reference for identifying potential overlaps and shared provenance. Thirdly, since hashing alone cannot detect all duplicates, we introduce MAP (Metadata for Aggregation and Provenance), a lightweight, portable metadata profile for documenting provenance, known overlaps, and deduplication decisions in dataset collections. Our contributions help dataset collections shift from coarse aggregations to reliable and provenance-aware data scaling mechanisms in medical image analysis. A web tool supporting our work is available at https://mic-dct.dkfz.de/.

eess.IV · cs.CV

版本更新 · v2arXiv:2606.30509

Muon learns balanced solutions in matrix factorization without slow saddle-to-saddle dynamics

Mark Rhee, Jamie Simon, Dhruva Karkada

原文摘要

Matrix factorization (i.e., problems of the form $\min_{\mathbf{P},\mathbf{Q}} \|\mathbf{M}^\star - \mathbf{P}^\top\mathbf{Q}\|_\mathrm{F}^2$) is a minimal learning problem that exhibits both nonlinear parameter dynamics and representation learning. In this setting, we study how parameter trajectories under the Muon optimizer differ from those of gradient descent. We identify three main dynamical differences: (1) Muon avoids the slow saddle-to-saddle dynamics of GD from small initialization. Muon instead learns all the top singular vectors of $\mathbf{M}^\star$ at the same rate, and they saturate in order of increasing (rather than decreasing) singular value. (2) Muon does not diverge even when the learning rate exceeds the critical threshold set by the local loss sharpness. This frees the learning rate from the condition number of the problem, enabling rapid convergence via exponential learning rate annealing. (3) Once the weights are aligned with each other and the target, Muon flow conserves the matrix quantity $\sqrt{\mathbf{P}^\top \mathbf{P}}-\sqrt{\mathbf{Q}^\top \mathbf{Q}}$, while gradient flow is known to conserve the matrix $\mathbf{P}^\top\mathbf{P} - \mathbf{Q}^\top\mathbf{Q}$. Despite having distinct conserved quantities, both optimizers find the so-called balanced solution from vanishing initialization. When training from small random initialization, the weights spontaneously align early in training. We derive the alignment rates in simple settings and show that they predict the empirical alignment rates in general. Finally, we exploit structural properties of Muon to construct a learning rate schedule that achieves near-perfect alignment in only two optimization steps.

cs.LG

版本更新 · v2arXiv:2605.06086

LARGO: Low-Rank Hypernetwork for Handling Missing Modalities

Niels Vyncke, Pooya Ashtari, Aleksandra Pižurica

原文摘要

Addressing missing modalities is an important challenge in multimodal image analysis and often relies on complex architectures that do not transfer easily to different datasets without architectural modifications or hyperparameter tuning. While most existing methods tackle this problem in feature space by engineering representations that are robust to missing inputs, we instead operate in weight space. We propose LARGO, a hypernetwork that compresses the $2^N-1$ dedicated missing-modality models into a single network by modelling the convolutional weights using the Canonical Polyadic (CP) tensor decomposition. Extensive experimental validation on BraTS 2018 (4 modalities, 15 scenarios) and ISLES 2022 (3 modalities, 7 scenarios) shows that our method ranks first in 47 out of 52 configurations, achieving average Dice improvements of +0.68$\%$ and +2.53$\%$ over state-of-the-art baselines (mmFormer, M$^{3}$AE, ShaSpec, SimMLM). A proof-of-concept experiment on avMNIST suggests that LARGO may extend beyond medical imaging to heterogeneous non-medical modalities. Code is available at https://github.com/nielsvyncke/LARGO.

cs.CV

版本更新 · v2arXiv:2604.14886

Cooperate to Compete: Strategic Data Generation and Incentivization Framework for Coopetitive Cross-Silo Federated Learning

Thanh Linh Nguyen, Nguyen Van Huynh, Quoc-Viet Pham

原文摘要

In data-sensitive domains such as finance, cross-silo federated learning (CFL) allows organizations to collaboratively train AI models without sharing raw data. However, many practical CFL deployments are coopetitive, where organizations cooperate during model training while competing in downstream markets. In such settings, training contributions can improve the global model yet inadvertently strengthen rivals, eroding one's competitive advantage. This dilemma is amplified by non-IID data, which leads to asymmetric learning gains and undermines sustained participation. While existing work reward organizations based on marginal training contributions, they fail to account for the implicit costs of strengthening competitors. In this paper, we introduce CoCoGen+, a coopetition-compatible data generation and incentivization framework that jointly models data heterogeneity and inter-organizational competition while endogenizing GenAI-based synthetic data generation as a strategic decision. Specifically, CoCoGen+ formulates each training round as a weighted potential game, where organizations strategically decide how much data to generate by balancing learning gains against computational costs and utility losses caused by competition. We establish the existence and uniqueness of the continuous Nash equilibrium under the adopted model and develop a provably convergent scalar bisection algorithm. We further analyze how bilateral payoff redistribution modifies residual competition and data-generation incentives, and empirically evaluate the social welfare and individual utilities of the resulting allocations. Experiments on FMNIST, CIFAR-10, and CIFAR-100 validate the feasibility of CoCoGen+. The results show how heterogeneity, competition intensity, and incentives shape organizational strategies and social welfare, while CoCoGen+ achieves higher social welfare than competition-aware baselines.

cs.AI · cs.DC · cs.GT

版本更新 · v3arXiv:2601.02322

Environment-Adaptive Covariate Selection: Learning When to Use Spurious Correlations for Out-of-Distribution Prediction

Shuozhi Zuo, Yixin Wang

原文摘要

A common approach to out-of-distribution prediction restricts models to causal or invariant covariates to avoid spurious associations that may change across environments. Despite its theoretical appeal, this strategy can underperform empirical risk minimization when only a subset of the causal parents of the outcome is observed. In such settings, non-causal covariates can serve as proxies for unobserved causal parents and improve prediction when the proxy relationship is stable, but they can hurt when shifts disrupt that relationship. Thus, the optimal covariate set can depend on the specific shift encountered. Because different shifts can leave distinct signatures in the covariate distribution, we propose an environment-adaptive covariate selection algorithm that chooses which covariates to use in each environment based on summaries of its unlabeled covariates. The summaries may be hand-crafted or learned from multi-environment data, and prior causal knowledge can be incorporated as constraints. We give sufficient conditions under which such summaries are informative in linear causal models, and explain when adapting only the covariate set is preferable to letting every coefficient vary with the environment. In simulations and two applications, adapting the covariate set improves prediction over static baselines, including causal and invariant covariate selection.

stat.ME · cs.LG

新论文 · v1arXiv:2611.09894

Video-Coder:强化智能体式编码以生成视频

Video-Coder: Reinforcing Agentic Coding for Video Generation

Chaoyang Wang, Sicheng Gao, Junan Hu, Kunyang Li, Dongyang Chen, Yiyang Zhou, Huaxiu Yao, Yong Jae Lee 等 10 位作者

AI 速读 基于摘要

作者提出并训练一个代码驱动的视频生成智能体,通过自主编写与执行代码构建动态3D场景(Draft Video),为下游视频生成器提供结构与运动信号。

cs.CV

查看原文摘要

Recent years have witnessed remarkable progress in video generation in terms of visual quality and temporal consistency. However, generating videos with precise spatial structure, coherent motion dynamics, and controllable scene composition remains challenging. In this paper, we introduce Video-Coder, the first attempt to train a code-driven video generation agent, which autonomously writes and executes code to construct a dynamic 3D scene (Draft Video) that provides structure and motion signals to downstream video generators. To support this paradigm, we design a dedicated data pipeline and curate two high-quality datasets, Video-Coder-SFT-6k and Video-Coder-RL-2k, which contain diverse prompts and ground-truth reference videos. We further develop the Video- Coder Harness, a unified interactive environment integrating code execution, 3D scene rendering, and execution feedback for agent training and inference. We then train Video-Coder with SFT fol- lowed by harness-native agentic reinforcement learning with dual reward feedback, which combines execution-based and video-based rewards. Additionally, we design an annealing training strategy that gradually reduces the execution reward over time, allowing the model to rely more on the video reward in the later training stages. Experiments show that Video-Coder achieves significant gains, improving Minimax-H3 by approximately 7 points on PhyGenBench and 24 points on VBench-2.0. We hope this work can serve as an open foundation for coding agents in video generation, and we fully open-source our data, models, and code

新论文 · v1arXiv:2611.09892

论智能体式操作策略

On Agentic Manipulation Policies

Chen Chen, Omid Bagherieh, Naveen Nikamanth Appiah Balaji, Jesse T. Gonzalez, Negin Heravi, Fahad Islam, Xueting Li, Jean-Baptiste Regli 等 13 位作者

AI 速读 基于摘要

作者提出并系统分析智能体式操作策略(AMPs),即由通用AI模型直接控制机械臂并随任务进展调整动作,报告其在多个基准和真实试验中优于专用VLA与WAM策略。

cs.RO · cs.AI · cs.CV · cs.LG

查看原文摘要

Recent work on robot manipulation has focused on specialist policies trained on demonstrations. We show that generalist AI models can control manipulators more reliably than specialist policies such as vision-language-action models (VLAs) and world-action models (WAMs). We systematically analyze agentic manipulation policies (AMPs), in which a generalist AI model commands the manipulator directly, adapting its actions as the task unfolds. We present AMP1, a reference harness that runs unchanged across single-arm, bimanual, and mobile manipulation. AMP1 achieves state-of-the-art results on the RoboLab-120 and CaP-Gym benchmarks, with no demonstrations or task-specific training. On RoboLab-120, AMP1 reaches an 85.6\% success rate zero-shot, compared to 49.2\% and 42.9\% for leading VLA and WAM policies. The agent succeeds zero-shot in 104 of 108 real-world trials spanning twelve tasks and three robot instances, reducing failure rates by 20x and 15x relative to strong VLA and WAM baselines. The basic harness supplies no grasping, pushing, or placing skills; the agent develops its own strategies, such as searching for hidden objects, using objects as tools, and calibrating its cameras. With the addition of a persistent memory store, the agent can also learn from experience: an augmented harness with a memory representation that is carried across episodes lowers the failure rate on RoboDojo bimanual manipulation tasks by 4.6x relative to zero-shot deployment. Our analysis suggests that AMPs are substantially more general and robust than specialist manipulation policies, providing a promising foundation for robot manipulation.

新论文 · v1arXiv:2611.09888

面向自动驾驶闭环策略评估的场景编排

Scenario Orchestration for Closed-loop Policy Evaluation of Autonomous Driving

Frieda Rong, Zhaoyue Wang, Veer Kapadia, Vishaka Rajani, Aren A. Babikian, Xujie Si, Mahsa Golchoubian, Raquel Urtasun 等 9 位作者

AI 速读 基于摘要

提出场景编排器,在闭环仿真中持续监测交通状态并动态调整非自车参与者,以可靠实现预设交互意图,从而区分场景是否达成与策略是否失败。

cs.RO

查看原文摘要

Scenario-based simulation is central to evaluating autonomous-driving policies, but a scenario scripted before execution (i.e., with predetermined, fixed actor routes and speeds) may not preserve its intended interaction once the tested ego policy responds in closed loop. Scripted scenarios cannot adapt to unanticipated ego behavior, while learned traffic actors may remain reactive without reliably realizing a particular scenario intent. We introduce a scenario orchestrator that continuously monitors the joint traffic state and adapts non-ego actors through re-timing, re-routing, and role reassignment for creating a specific scenario intent. At each step, the orchestrator solves a constrained optimization problem that preserves the intended interaction while limiting interventions and maintaining traffic feasibility. We further distinguish scenario realization from policy failure, allowing a test to first be judged based on whether the intended interaction occurred and then by how the ego policy responded. Experiments in the CARLA simulator across multiple scenario families and driving policies show that orchestration realizes targeted interactions more reliably than scripted and learned actor-level baselines, particularly under variations in initial conditions and ego behavior. These results support closed-loop scenario orchestration as a tool for controlled and reproducible policy evaluation.

新论文 · v1arXiv:2611.09887

关于 ReLU 网络集合的(非)闭性

On the (non-)closedness of the set of ReLU networks

Eloi Martinet, Leon Bungert

AI 速读 基于摘要

作者证明单隐层 ReLU 网络集合在 Sobolev 空间中是弱闭的,而宽度有界的双隐层 ReLU 网络集合在 Sobolev 空间与连续函数空间中均不闭。

cs.LG · math.CA · math.FA · math.NA · math.OC

查看原文摘要

We prove that the set $\mathcal{N}_N$ of ReLU networks with one hidden layer and at most $N\in\mathbb N$ neurons is weakly closed in $W^{1,p}(Ω)$, for a bounded connected open set $Ω\subset\mathbb R^d$. Consequently, every coercive, weakly lower semicontinuous energy on this space attains its minimum over $\mathcal{N}_N$. This covers the Deep Ritz method with convex integrands, Sobolev training and Lipschitz learning. Moreover, as the weight decay parameter tends to zero, minimizers of the regularized problem converge, up to subsequences, to minimizers with minimal parameter norm. We also prove that the set of ReLU networks with two hidden layers of bounded widths is not closed in $W^{1,p}(Ω)$ or in $C(\overlineΩ)$. This disproves a conjecture of Petersen, Raslan and Voigtlaender.

新论文 · v1arXiv:2611.09882

FlowMoP:随机多人运动预测

FlowMoP: Stochastic Multi-Person Motion Prediction

Aadya Agrawal, Ho Kei Cheng, Alexander Schwing

AI 速读 基于摘要

提出基于条件流匹配的多人三维运动预测框架,联合生成多智能体多样且交互感知的未来运动分布。

cs.CV · cs.LG

查看原文摘要

Predicting the future motion of multiple people is inherently stochastic: the same observed history admits many plausible continuations depending on intent, coordination, and social context. Yet the dominant paradigm in multi-person 3D motion prediction remains deterministic, with existing methods producing a fixed number of outputs per agent. In contrast, we present a conditional flow matching framework that jointly generates diverse future motions for multiple agents, modeling both global trajectories and root-relative poses. A B-spline reparameterization compresses the generative state space while enforcing temporal smoothness, and a dual-stream transformer conditions each agent's predictions on observed neighbor motion for interaction-aware forecasting. Our method achieves state-of-the-art performance on CMU-Mocap (UMPM) and 3DPW, outperforming deterministic baselines on joint position error, pose error, and final displacement error despite producing a full predictive distribution. We additionally establish the first motion prediction baseline on WorldPose, a large-scale professional soccer dataset, where social conditioning demonstrably concentrates predictive uncertainty along interaction-constrained directions.

版本更新 · v2arXiv:2603.04399

SimpliHuMoN:简化人体运动预测

SimpliHuMoN: Simplifying Human Motion Prediction

Aadya Agrawal, Alexander Schwing

AI 速读 基于摘要

作者提出一种简洁的端到端 Transformer 模型,用统一的架构同时处理姿态预测、轨迹预测及二者联合的人体运动预测。

cs.CV · cs.LG

查看原文摘要

Human motion prediction combines the tasks of trajectory forecasting and human pose prediction. For each of the two tasks, specialized models have been developed. Combining these models for holistic human motion prediction is non-trivial, and recent methods have struggled to compete on established benchmarks for individual tasks. To address this, we propose a simple yet effective transformer-based model for human motion prediction. The model employs a stack of self-attention modules to effectively capture both spatial dependencies within a pose and temporal relationships across a motion sequence. This simple, streamlined, end-to-end model is sufficiently versatile to handle pose-only, trajectory-only, and combined prediction tasks without task-specific modifications. We demonstrate that this approach achieves state-of-the-art results across all tasks through extensive experiments on a wide range of benchmark datasets, including Human3.6M, AMASS, ETH-UCY, and 3DPW.

新论文 · v1arXiv:2611.09880

ZeoBench:面向三维沸石表示的自监督学习基准

ZeoBench: A Benchmark for Self-Supervised Learning on 3D Zeolite Representations

Aaron Sun, Yachan Liu, Ping Yang, Peng Bai, Subhransu Maji

AI 速读 基于摘要

作者提出 ZeoBench 基准,在低数据条件下系统比较多种三维沸石表示学习策略,并在六个吸附性质预测任务上评估。

cs.CV

查看原文摘要

Zeolites are an important class of porous crystalline materials with broad applications in gas storage, separations, and catalysis. Although hundreds of thousands of experimentally realized and hypothetical zeolite structures are known, identifying materials optimized for a target application remains challenging because property labels are expensive to obtain and available only for limited structure-molecule pairs. While prior work has demonstrated that 3D neural representations can predict zeolite properties effectively, it remains unclear which representation-learning strategies are most effective in the low-data regime relevant to materials discovery. We present ZeoBench, a benchmark for self-supervised learning on dense 3D representations of all-silica zeolites, and evaluate the resulting features on six existing downstream adsorption-property prediction tasks, across a range of training set sizes. Our study compares self-supervised 3D pretraining on volumetric zeolite data, adaptations of image-pretrained 2D ConvNets and vision transformers to 3D via multiview and channel-inflation strategies, and 3D ConvNets pretrained on out-of-domain volumetric datasets, alongside hand-crafted descriptors and supervised baselines. Using our pretraining and evaluation framework, we find self-supervised 3D representations outperform existing methods and achieve state-of-the-art performance across both in-domain label regimes and for the unseen domain of metal organic frameworks. Learned representations consistently outperform hand-crafted descriptors, and convolutional architectures are generally more effective than vision transformers in this setting. These results establish ZeoBench as a practical benchmark for 3D representation learning in zeolites and provide guidance for data-limited adsorption property prediction.

新论文 · v1arXiv:2611.09879

PhotoFinish:可移植的无定时器微架构延迟探测

PhotoFinish: Portable Timerless Probing of Microarchitectural Latencies

Tristan Hornetz, Eduard Ebert, Lorenz Hetterich, Lukas Gerlach, Michael Schwarz

AI 速读 基于摘要

提出一种仅依赖并行执行与共享内存、无需构造或读取时钟的无定时器探测原语,将延迟差异直接转化为架构可观测值。

cs.CR

查看原文摘要

Timing measurements are a fundamental building block of microarchitectural attacks, enabling software to convert otherwise invisible latency differences into architectural observations. Thus, restricting high-resolution timers is a common defense, especially in constrained environments such as web browsers. Timerless probing primitives provide an alternative approach. Instead of reading or constructing a timer, they observe architectural events that correlate with the microarchitectural state. However, such primitives typically rely on platform-specific behavior, and none generalizes across the wider computing landscape. In this paper, we present PhotoFinish, a portable timerless probing primitive that converts latency differences directly into an architectural value. PhotoFinish races an operation under test against a fixed reference in two parallel threads that then write unique values to the same shared location, resulting in a latency-dependent architectural value. PhotoFinish only requires parallel execution and shared memory, without constructing or reading a clock. We evaluate PhotoFinish on 38 CPUs spanning four ISAs and demonstrate reliable cache state classification across widely different microarchitectures, with comparable fidelity when compiled to WebAssembly and executed inside a browser. We further use PhotoFinish in AES T-table and Evict+Reload attacks, show that it applies beyond caches to TLB and execution-engine latencies, and demonstrate sufficient precision to identify the LLC slice of an address. Our results demonstrate shared-memory races as a generic and precise replacement for explicit timing, showing that restricting timers alone does not prevent software from observing fine-grained microarchitectural latency differences.

新论文 · v1arXiv:2611.09878

分级卷积网络:无需尺度参数的尺度不变性与对未知模糊的鲁棒性

Graded convolutional networks: scale invariance without the scale and robustness to unknown blur

Tanush Shaska

AI 速读 基于摘要

作者提出基于高斯射流加权球面收缩的分级卷积网络,在理论上实现尺度不变性并提升对未知高斯模糊的鲁棒性,并在 MNIST 上报告了对比实验。

cs.CV · cs.LG

查看原文摘要

The Gaussian jet of an image is a graded vector space: a dilation by $λ$ multiplies derivatives of order $k$ by $λ^{-k}$. Local graded convolutions are exactly homogeneous differential operators, and a local feature is dilation-invariant if and only if it factors through the scale-normalized jet or, without the scale, through the retraction onto the weighted sphere of the grading. Under unknown Gaussian blur the retraction changes only by a change of scale, whereas the scale-normalized jet acquires a grading factor that no radial normalization removes. At the zero jet the retraction separates image families that radial normalizations and continuous classifiers cannot. Networks built on the retraction are universal for invariant features. On MNIST such a network keeps 88.4% accuracy under a two-pixel blur, against 66.2% for the same network on scale-normalized derivatives; in Lindeberg's Gaussian derivative network the retraction raises accuracy at that blur from 91.5% to 95.1%.