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

+0新增论文
+0其中 AI 相关
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-15 02:35 · 全站最近入库：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-14 03:21 — 2026-11-15 03:21（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：2026-11-15 02:35最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,729 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 4,254 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-15 02:34（北京时间）
版本更新 · v2arXiv:2607.24984

Automatic Knowledge Graph Construction and Query for Earthquake Catalogs

Yuxin Zhou, Huai Zhang, S. Mostafa Mousavi

原文摘要

In recent years, the number of events in earthquake catalogs has significantly increased due to the utilization of more effective deep learning based detectors and phase pickers but answering open ended questions such as what characterizes this sequence? remains constrained by rigid spatiotemporal windowing and subjective expert interpretation. We present the first systematic application of graph based retrieval augmented generation GraphRAG directly to raw, tabular catalog records across three independently featured catalogs, a reservoir adjacent swarm, the 2019 Ridgecrest tectonic sequence, and the 2021 Maduo Mw7.4 aftershock sequence. Without the need for manual data structuring, the pipeline builds structurally complete, queryable knowledge graphs for all three. Rigorous evaluation individually verified against catalog derived ground truth and a rule based reference graph exposes failure modes, and four seismology informed prompt fixes eliminate all targeted fabrications while sharply improving mechanism reasoning. A vector RAG baseline demonstrates the graph layers distinctive value, catalog wide summarization and temporal stage comparison. In addition, we have identified two main pitfalls that need attention. GraphRAG thus offers a practical, transferable, near zero cost query interface for earthquake catalogs, where careful prompting ensures the results are consistently accurate and trustworthy.

physics.geo-ph · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2406.04428

MoralBench: Moral Evaluation of LLMs

Jianchao Ji, Yutong Chen, Mingyu Jin, Wujiang Xu, Wenyue Hua, Yongfeng Zhang

原文摘要

In the rapidly evolving field of artificial intelligence, large language models (LLMs) have emerged as powerful tools for a myriad of applications, from natural language processing to decision-making support systems. However, as these models become increasingly integrated into societal frameworks, the imperative to ensure they operate within ethical and moral boundaries has never been more critical. This paper introduces a novel benchmark designed to measure and compare the moral reasoning capabilities of LLMs. We present the first comprehensive dataset specifically curated to probe the moral dimensions of LLM outputs, addressing a wide range of ethical dilemmas and scenarios reflective of real-world complexities. The main contribution of this work lies in the development of benchmark datasets and metrics for assessing the moral identity of LLMs, which accounts for nuance, contextual sensitivity, and alignment with human ethical standards. Our methodology involves a multi-faceted approach, combining quantitative analysis with qualitative insights from ethics scholars to ensure a thorough evaluation of model performance. By applying our benchmark across several leading LLMs, we uncover significant variations in moral reasoning capabilities of different models. These findings highlight the importance of considering moral reasoning in the development and evaluation of LLMs, as well as the need for ongoing research to address the biases and limitations uncovered in our study. We publicly release the benchmark at https://drive.google.com/drive/u/0/folders/1k93YZJserYc2CkqP8d4B3M3sgd3kA8W7 and also open-source the code of the project at https://github.com/agiresearch/MoralBench.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16009

JustRUA: A Controlled Study of GPT-6 Robot-Use Agents

Zefan Wang, Yufan Dang, Xuanwei Shi, Mingqi Gao, Cheng Yin, SikYuen Tam, Hanyu Liu, Yasheng Wang 等 12 位作者

原文摘要

GPT-6 Astra can drive a robot arm directly through a fixed harness, and scores of such robot-use agents on RoboDojo have risen quickly since. Reported systems differ in harness and test subset and often change several designs at once, so it is hard to tell which choices produce the gains. We take these designs apart and test them in one framework, along the harness around the model, the action interface, the reuse of experience and the scene geometry given to the model. A lean harness that keeps the full episode history and stops each motion early goes a long way. Reusing experience changes how the model acts but is not a free lunch, and scene geometry helps most, even when depth is predicted from RGB alone. JustRUA starts from the official L3 harness and keeps only what matters most. Even with no learned policy, self-improvement loop or task-specific tuning, this simple harness raises the score on the RoboDojo simulation benchmark substantially, from 29.7 to 50.3.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.29037

Near-Optimal Consistency-Robustness Bounds for Non-Clairvoyant Scheduling

Sizhe Li, Nicolas Christianson, Tongxin Li

原文摘要

We study the problem of characterizing the optimal consistency--robustness tradeoff for single-machine non-clairvoyant scheduling with predicted processing times. For a fixed number of jobs $n$, Wei and Zhang (2020) established a lower bound on the achievable consistency--robustness tradeoff which is known to be tight only in a few restrictive cases, leaving the optimal tradeoff for general $n$ unresolved. A different worst-case-$n$ regime was introduced by Benomar et al. (2025), who applied the former work's construction to show that for $λ\in (0, 1)$, any $(1+λ)$-consistent algorithm must be $1 + Ω(\sqrt{1/λ})$-robust. On the other hand, the best known upper bound gives $(1+λ)$-consistency and $1+O(1/λ)$-robustness, leaving a polynomial gap. In this work, we develop a new lower bound using a multi-stage adversarial construction and a new algorithm that together give a near-optimal characterization of the consistency--robustness tradeoff: for every $n$, our upper bound is within a multiplicative factor $3/2$ of our lower bound, and thus our algorithm is within a multiplicative factor $3/2$ of the online optimal. In particular, our lower bound shows that any $(1+λ)$-consistent algorithm must have robustness at least $1/\sqrtλ$ as $n \to \infty$, while our algorithm achieves robustness at most $\frac{1}{2}+\sqrt{\frac{5}{4}+1/λ}$ for any $n$, matching the lower bound in the leading term as $λ\downarrow 0$; our upper bound also closes the polynomial gap in the worst-case-$n$ regime. We additionally show how our algorithm can be made error-tolerant, preserving the near-optimal consistency-robustness tradeoff while incurring only slightly degraded performance under bounded prediction errors.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2608.28553

Four conditions for composing plugin-based agents without a host agents

Hanzhang Jia, Liheng Zeng, Hao Cheng, Yi Gao, Bo Ma, Guolong Xu

原文摘要

Large language model agents now run long-horizon, multi-tool, autonomous sessions, and the infrastructure must keep the current assembly of capabilities, the progress of execution, and the basis for recovery after a fault. A single-process host holds this information in its own running state, so its death takes the session record and the assembly with it. This paper gives four conditions under which a plugin-based agent needs no host process, one each on state placement, record carriers, recovery coordination, and provider resolution. The store, writer, and delivery disciplines keep the conditions in force, and each carries formal support from the spatiotemporal-composability calculus and from the proofs in the supplementary materials. An agent that meets them can be constructed with its assembly on a bus of peer processes and its record in an append-only carrier owned by no process, and removing any one part makes the assembly need a host again. The conditions themselves are the contribution, and every implementation that meets them inherits the same advantages. Such an agent keeps its session through the death of any process, wastes no calls after a fault, loses no records, recovers locally, changes its capability set while it runs, and carries its undo semantics across processes. This paper builds one SDK of the conditions, Logos, and measures whether it fulfills their promise against the single-process reference and a configuration over MCP under one fault in each of 200 tasks, realized in 197. The reference lost all 197 faulted sessions, the MCP configuration kept its sessions but issued 1,212 wasted calls, and the SDK kept every session, wasted no call, lost no record, and fulfilled the promise of the conditions in every faulted task, with task performance preserved. The conditions give builders a tested route from single-process hosts to peer processes.

cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15983

TRACE: Trajectory Synchronization for Training-Free Resolution Extension in Video Generation

Libo Zhu, Fan Li, Zhixin Wang, Binglu Wang, Weisheng Dong, Yulun Zhang

原文摘要

More text-to-video models are available, but many remain limited to low resolutions. Training them for higher resolutions is costly, while existing training-free methods still struggle with fine detail, scene structure, and efficiency. We propose TRACE, a training-free method that synchronizes low- and high-resolution generation trajectories. During early denoising, TRACE aligns predicted scene content at corresponding noise levels. It computes high-resolution updates from low-resolution predictions and the current high-resolution state, without high-resolution model inference. The high-resolution trajectory retains fine-grained variation for generating new details. Local window attention then refines fine details in a shared high-resolution latent state. TRACE checks suspected duplicate subjects against the corresponding low-resolution layout and corrects selected regions and their solver history while preserving detail elsewhere. Experiments across all kinds of video generation backbones and resolutions show improved perceptual quality and text-video alignment over FreeSwim, a state-of-the-art training-free method, with 2.0-2.9x end-to-end speedups. Our code and models will be released at https://github.com/libozhu03/TRACE.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2602.09297

Laplacian Heads Improve Transformers by Smoothing Token Representations

Yuchong Zhang, Vardan Papyan

原文摘要

Transformers update token representations through multi-head attention and residual connections: $X \leftarrow X + \sum_{i} P^{(i)}\text{Norm}(X)W_{V_i}W_{o_i}$, where $P^{(i)}$ is the softmax probability matrix in head $i$. We propose replacing some $P^{(i)}$'s with $I - P^{(i)}$, giving $X \leftarrow X + \sum_{i \in \mathcal{A}} P^{(i)}\text{Norm}(X)W_{V_i}W_{o_i} + \sum_{i \in \mathcal{L}} (I - P^{(i)})\text{Norm}(X)W_{V_i}W_{o_i}$. We call heads that use $I - P^{(i)}$ Laplacian heads. Our proposal has two motivations. First, it allows attention heads to update the mean of token representations, while Laplacian heads can directly control within-sequence variance. Second, if tokens are viewed as nodes in a graph with normalized edge weights $P^{(i)}$, then $I - P^{(i)}$ is a graph Laplacian operator, and the update can be interpreted as one step of heat diffusion on the graph. We show that this simple modification improves performance across supervised learning, causal language modeling, and vision self-supervised learning tasks. To investigate why, we examine the token representations learned with and without Laplacian heads. In supervised learning, Laplacian heads collapse token representations within the same sequence and align the sequence means with the geometry of Neural Collapse. In language modeling, they increase the separability of token representations that share the same next-token prediction. In vision self-supervised learning, they produce token representations whose top principal components better capture segmentation structure. Across modalities, they also lead to faster-decaying spectra, indicating stronger token smoothing. Overall, our findings challenge the prevailing view that token oversmoothing is inherently harmful, showing instead that certain forms of smoothing can be beneficial.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15966

Subject-Held-Out Evaluation of Deep Ground Reaction Force Estimators Across Two Laboratories: Leakage and Cross-Laboratory Transfer

Hernan David Santos, Yinong Chen, Yu Ding, Xudong Zhang, Jian Tao

原文摘要

Deep networks that estimate ground reaction forces and centers of pressure from motion-capture markers are validated within one laboratory, in a seldom-stated coordinate frame, and sometimes with trial-level splits that put the same person in the training and the test set. We measured what each practice costs, and whether such models transfer between laboratories. Three sequence models (convolutional, convolutional-recurrent, and convolutional-transformer) were evaluated on two independent datasets, locomotion (6 subjects) and occupational patient handling (10 subjects), under one pipeline, one tuning procedure, three seeds, and four protocols: trial-level split, leave-one-subject-out, pooled two-laboratory training with matched held-out subjects, and cross-laboratory transfer. At a fixed configuration, trial-level splits overstated the subject-held-out coefficient of determination by +0.040 to +0.194; on occupational data the overstatement exceeded every difference between architectures. With subjects held out, the three models reached values between 0.583 and 0.804; the leader differed between datasets, and gaps lay within subject-to-subject variability. Pooling the laboratories changed neither dataset on matched subjects. Transfer between laboratories was below chance in both directions, including the vertical force, which no in-plane rotation can affect. Leaving force targets in the plate frame while inputs were heading-aligned cost 0.57 of locomotion anteroposterior-force explained variance, enough to make that force look hardest; a Newton's-law correlation detected the mismatch before training. Split protocol and target frame changed reported accuracy more than architecture did. Learned force estimators should be validated with subjects held out, checked for frame consistency before training, and tested across laboratories before deployment claims are made.

cs.LG · eess.SP · q-bio.QM

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.07594

BiGym 2.0: Benchmarking Learned and Agent-Developed Policies for Humanoid Household Manipulation

Zexi Zhang, Zecheng Zhu, Zidong Chen, Zulkhuu Tuya, Stephen James

原文摘要

Humanoid household manipulation requires the arms to act while the body balances, steps and changes posture. We present BiGym 2.0, an adaptation of BiGym for the Unitree G1 across 20 household tasks using a unified whole-body controller for demonstration and evaluation. The suite provides 60 native human virtual-reality demonstrations per task with synchronised multi-camera views and full-body execution records. We benchmark vision-language-action fine-tuning, imitation learning, demo-driven reinforcement learning, and cold-start coding agents given the interaction budget of online reinforcement learning. With the same onboard views, proprioception and whole-body controller for every method, vision-language-action fine-tuning has the highest nine-task mean, and agent-developed programs outperform every demo-driven reinforcement learning baseline on this mean and lead on bimanual reaching. Cross-workspace stacking remains open, $π_{0.5}$ stays low on pick-box, and multi-object transport is hard for imitation learning, demo-driven reinforcement learning and coding agents. All environments, human demonstrations, and evaluation traces are open-sourced at https://github.com/swirl-uk/BiGym2.

cs.RO · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15928

Runtime Safety and Emergency Stops on a Full-Size Humanoid: Deployment Lessons and a Case for Graduated Force Authority

Max Conway, Yutong Zhang, Allen Devaraj, William Xie, Alessandro Roncone, Nikolaus Correll

原文摘要

Full-size humanoid robots are being considered for hazardous industrial work such as disassembling electric-vehicle batteries. We describe the safety mechanisms of an open-source autonomy stack for the Unitree H1-2 humanoid and what deploying them taught us. All joint commands pass through a safety layer that runs separately from the control software. It enforces joint position, velocity, and torque limits, and it stops the robot when a state estimate becomes stale or when the hard-wired emergency stop (e-stop) is pressed or disconnected. We pushed the standing robot until it lost balance. With a model-predictive lower-body controller it never recovered, and the operator had to press the e-stop in every trial. Pressing it removes balance control, and the robot falls. The safety layer's own limits trigger the same stop, and limits chosen for manipulation were exceeded during normal walking. Near an operator or a battery pack, the fall can be more dangerous than the cause of the stop. Joint limits bound how much force a robot can apply, but not when applying it is appropriate. Drawing on research on responsibility and on child and adolescent development, we therefore make a case for granting robots force authority in stages, with a person or organization explicitly responsible for its use.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.38520

What Hallucinations Have We Measured? Semantic Illusion, Confabulation, and Expressed Uncertainty

Hazel H. Kim, Jakub Binkowski, Ekaterina Fadeeva, Juan David Guerra, Yijie Hao, Zheng Yi Ho, Baixiang Huang, Buyun Liang 等 26 位作者

原文摘要

Hallucination remains one of the most critical challenges in deploying large lan- guage models (LLMs) reliably and safely. Yet the term is used inconsistently across the research community. We argue for a strict definition of hallucinations in LLMs. First, hallucinations should be confident incorrectness, kept separate from expressed uncertainty (UNK). UNK reveals that the model may be wrong, whereas a hallucination does not reveal it and is therefore more dangerous in prac- tice. Conflating the two obscures their distinct behaviors and makes them hard to study. Second, hallucinations should be split by a simple re-elicitation test: does any semantically equivalent prompt recover the correct response? This test probes whether the relevant knowledge is accessible. If none does, the knowledge is likely absent or inaccessible, and the error type is a confabulation (CF) that likely requires external knowledge or retraining; if some does, the knowledge is accessible from the model but applied inconsistently, and the error type is a semantic illusion (SI) that simple prompt or decoding changes can mitigate3. Re-evaluating 14 recent hallucination methods under this taxonomy yields three findings. (1) Mitigation methods are far more effective for SI than for CF. (2) Detection methods flag UNK more often than hallucinated responses (i.e., SI and CF). (3) Latent signals are more informative than output-level signals for CF. An audit of recent hallucination papers shows that most conflate these categories. We recommend reporting CF, SI, and UNK separately, and introduce a practical labeling protocol that needs only a modest number of semantically equivalent prompts.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15834

Where to Generate Touch: Do Image Latents Preserve Material Recognition?

Wanghao Ye, Aarosh Das, Sihan Chen, Yiting Wang, Bowei Tian, Guoheng Sun, Shwai He, Zheyu Shen 等 29 位作者

原文摘要

Generated touch could extend robot learning beyond recorded contacts. A tactile generator needs a latent space, and we choose one by testing whether a material classifier trained on real GelSight presses still works on encode-decode reconstructions from pretrained image models. On ObjectFolder Real, the classifier loses 6.5 to 9.7 points on reconstructions from three 16x discrete tokenizers and 0.3 points on those from the Stable Diffusion VAE (SD-VAE). The 16x tokenizers again lose far more on Touch and Go and on DIGIT object recognition (YCB-Slide). Retraining the classifier on reconstructions, with no new labels, narrows the discrete gap. SD-VAE reconstructions also keep object identity, with 76.7% object-matching accuracy against 78.9% for real touch and 67.0% for MAGVIT-v2. We therefore select SD-VAE latents and show a photo-to-touch generator trained in them. Code will be released upon acceptance.

cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15831

NIBench: benchmarking autonomous AI agents for execution, skill evolution and scientific judgment in neuroimaging

Lujia Zhong, Yihao Xia, Jianwei Zhang, Shuo Huang, Xinyu Nie, Mingyang Xia, Zhiwei Deng, Jiaxin Yue 等 11 位作者

原文摘要

Autonomous AI agents are increasingly used to automate biomedical research, creating a growing need to benchmark their capabilities on real scientific data and workflows. Their reliability in neuroimaging remains insufficiently characterized, where plausible analytical outputs can conceal errors that affect scientific conclusions. Existing studies have advanced scientific question answering and tool-based automation, but provide limited evidence on workflow reconstruction, acquisition of procedural expertise and evidence-based scientific judgment. Here we present NIBench, a neuroimaging benchmark comprising three complementary evaluations of autonomous agents. First, we benchmark execution and workflow reconstruction using 56 tasks across seven tool ecosystems, covering structural, diffusion and functional magnetic resonance imaging, positron emission tomography and multimodal analyses. Second, we examine whether agents can evolve their procedural skills through distillation of execution trajectories, evaluating the resulting skills on previously encountered tasks, unseen tasks and other models. Third, we assess scientific judgment using 36 claims from published Alzheimer's disease studies, requiring agents to analyse raw cohort data and provide reproducible evidence. We evaluate 19 language models within a shared agent framework, with selected models undergoing skill distillation and claim evaluation. Leading agents execute supplied analysis protocols nearly perfectly, whereas withholding procedural guidance widens performance differences. Distilled skills improve performance on acquisition tasks and transfer between models, but benefits on unseen tasks are inconsistent. Agents reproduce their reported results yet sometimes reach conclusions inconsistent with expert-derived answers, and access to data does not always improve judgment.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.25403

A Faster Strongly Polynomial Time Algorithm for Submodular Function Minimization

Alina Ene, Huy L. Nguyen

原文摘要

We give a strongly polynomial time algorithm for submodular function minimization with overall running time $\widetilde{O}(n^{2}\mathsf{EO}+n^{3})$, where $\mathsf{EO}$ is the running time of a single evaluation of the function. Our algorithm improves upon the previously fastest strongly polynomial algorithms of Lee, Sidford, and Wong (FOCS 2015), Dadush, Végh, and Zambelli (SODA 2018), and Jiang, Lee, Song, and Zhang (SODA 2024) that run in time $\widetilde{O}(n^{3}\mathsf{EO}+n^{4})$. Similarly to prior works, our work combines a cutting plane algorithm with the combinatorial arc-finding framework of Iwata, Fleischer, and Fujishige (JACM 2001). We achieve our faster running time by developing an algorithm that runs the cutting plane method end to end, without restarting after discovering arcs and contracting strongly connected components.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.04792

Do More Modalities Always Help? A Geometric Perspective on Missing-Modality Robustness

Songyuan Sui, Zhen Tan, Mohan Zhang, Rana Muhammad Shahroz Khan, Xia Hu, Tianlong Chen

原文摘要

Missing modality remains a longstanding challenge in multimodal learning. Existing methods typically address this issue through modality recovery or adaptive strategies. However, they overlook models' internal cross-modal dependencies formed during multimodal training, which later impair robustness. We systematically characterize a counterintuitive deployment-time failure mode: models trained on full modalities can underperform unimodal models when one modality is missing at inference time. This pattern appears across diverse architectures, such as fusion models, CLIP-style two-tower models, and vision-language models. We show that such degradation is closely associated with learned cross-modal dependencies in the principal parameter subspaces. Multimodal training induces structured rotations of these subspaces, particularly in cross-modal interaction layers. These rotations are associated with reduced task-aligned margins and larger task-aware representation harm under missing-modality inputs. We propose Geodesic Unlearning (GU), a lightweight parameter-editing method that leverages Grassmannian subspace geometry for structured subspace correction to improve missing-modality robustness. It rotates the principal input subspace toward a unimodal reference along a geodesic path. We prove that this correction minimizes the distance to the reference within a fixed subspace-distance budget. Experiments across architectures and datasets show that GU improves performance under missing-modality inference while preserving full-modality accuracy, outperforming strong missing-modality robustness baselines. These findings support a geometric view of deployment-time missing-modality degradation and suggest localized subspace editing as a practical route for robustness correction.

cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15789

VibePrevisBench: Evaluating Agentic Coding for 4D Scene Generation in Blender

Yuzhe Chen, Muxi Diao, Lele Yang, Wenbin Xu, Xuyang Liu, Qile Su, Changyi Liu, Jiankang Chen 等 22 位作者

原文摘要

Controllable real-world video generation models can condition on a rendered graybox proxy video, which fixes layout, motion and camera. Coding agents can build such videos by reconstructing a 4D scene in Blender, yet no benchmark checks both these videos and the long, multi-shot scenes behind them. We introduce VibePrevisBench, a benchmark for 4D scene reconstruction: an agent turns a brief into an executable 4D scene and renders its proxy video. Its 242 tasks span four input kinds, including scripts, photos, continuations, and reference videos. Each delivery is scored along two evaluation dimensions. Rule-based Scene Check re-runs the code and compares the exported 4D scene with hidden ground truth facts in nine dimensions. VLM-based Screen Check asks a VLM judge whether the facts that pass can be recognized in the proxy video. We analyze the evaluation results and trajectories of 11 frontier coding agents and identify three key observations. First, multimodal understanding separates the agents, especially in understanding space and camera motion. Second, all agents seem to already master basic camera work and staging, and fail at challenging requests. Third, agents inspect their own renders but fail to correct their errors. Agents thus need better visual understanding of space and camera, explicit checks for challenging requests, and item-by-item verification of renders against the brief.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15778

From Link Prediction to Linear Community Detection: A Finite-Sample Guarantee for Graph Pretraining

Ying Chen, Zhangyang Wang, Yixuan He

原文摘要

Link prediction (LP) is a standard pretraining objective for graph neural networks (GNNs): hide edges, train an encoder-decoder to predict them, and reuse the node embeddings for downstream node tasks. Despite its empirical success, there is little quantitative theory explaining why an edge-level objective should produce embeddings that are linearly useful for node classification. We study this question in the finite-sample stochastic block model (SBM). For any bounded GNN encoder paired with a symmetric bilinear decoder, we prove a conditional reduction: small population held-out LP excess risk implies small community-classification error for a transductive linear classifier on the learned embeddings. The bound decomposes into an optimization residual, an architectural approximation residual, and explicit statistical terms of order $\tilde{O}(\sqrt{d/n})$ in bounded dense regimes. We further give a constructive few-label classifier: nearest-centroid classification under the positive semidefinite quadratic form $G = W Z^\top Z W$, whose label error is coupled to LP quality. The framework is architecture-agnostic through the approximation residual, and we instantiate this residual as $O(\log n / n)$ for a graph isomorphism network (GIN) with spectral positional encoding and a bilinear decoder. Synthetic SBM experiments validate the theorem chain from LP risk to score error to classification error, and show when the worst-case constants become conservative.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2603.27998

HRIR-Former: Grid-Free Time-Domain Reconstruction of Head-Related Impulse Responses with a Spatially Encoded Transformer

Shaoheng Xu, Chunyi Sun, Jihui Zhang, Amy Bastine, Prasanga N. Samarasinghe, Thushara D. Abhayapala, Hongdong Li

原文摘要

Individualized head-related impulse responses (HRIRs) enable binaural rendering, but dense per-listener measurements are costly. We address HRIR spatial up-sampling from sparse per-listener measurements: given a few measured HRIRs for a listener, predict HRIRs at unmeasured target directions. Prior learning methods often work in the frequency domain, rely on minimum-phase assumptions or separate timing models, and use a fixed direction grid, which can degrade temporal fidelity and spatial continuity. We propose HRIR-Former, a time-domain, grid-free binaural Transformer for reconstructing HRIRs at arbitrary directions from sparse inputs. It uses sinusoidal spatial features, a Conv1D refinement module, and auxiliary interaural time difference (ITD) and interaural level difference (ILD) heads. On SONICOM, it improves normalized mean squared error (NMSE), cosine distance, and ITD/ILD errors over prior methods; ablations validate modules and show minimum-phase preprocessing is unnecessary.

eess.AS · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15764

AIFR: Adaptive Identity Feature Recovery for Diffusion-Based Makeup and Anime Portraits

Linyan Dai, Xinwei Zhang, Yaxin Xiao, Mengyu Sun, Xinwei Liu, Renyang Liu, Qingqing Ye, Haibo Hu

原文摘要

Diffusion-based makeup and anime portraits are increasingly popular in online content creation (e.g., virtual makeup editing and anime avatar generation), but their altered appearances can hinder face recognition (FR) in identity-based content screening. Existing methods mainly adapt FR encoders or restore input images. The former require costly gallery re-encoding, while the latter may be incomplete or distort identity-related facial details. To address these limitations, we aim to correct identity features within a frozen FR model to recover its output embeddings in its original space. Appearance changes vary in strength and affect facial regions differently. To this end, we propose Adaptive Identity Feature Recovery (AIFR), a framework that inserts a lightweight recovery module at a single intermediate layer to predict sample-level correction strength and spatially adaptive residual updates. Module training uses fused identity targets to guide embedding recovery in the original FR space and an identity-shift score to regulate correction strength and limit unnecessary changes. At inference, AIFR processes a single portrait in one forward pass without reference images, producing recovered embeddings that can be directly matched with existing gallery templates without re-encoding. With only 1.22M trainable parameters, AIFR improves the average TAR at FAR=$10^{-4}$ from 66.1\% to 90.2\% over the original ArcFace, and further experiments show improvements across unseen makeup styles, stylization strengths, and generators. Beyond recognition, the recovered embeddings can directly condition a pretrained Arc2Face model to generate faces with improved identity preservation, showing compatibility with embedding-conditioned downstream generation.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15692

CGOcc: Learning Cross-Gaussian Dependencies for 3D Semantic Occupancy Prediction

Zirui Huang, Jiongle He, Yunfan Zeng, Yuanzhi Lu, Guangye Li, Boyan Tang, Weite SU, Pedro V. Sander 等 9 位作者

原文摘要

In Gaussian-based semantic occupancy prediction, overlapping primitives can provide ambiguous class predictions, making their joint interpretation important for voxel classification. However, current methods using spatially weighted mixtures neglect explicit modeling of cross-primitive dependencies, limiting the readout's ability to utilize category-specific relational evidence. Hence, we introduce CGOcc, a supervised multi-camera framework that explicitly models Cross-Gaussian dependencies for 3D semantic Occupancy prediction. CGOcc integrates appearance and geometric observations to refine Gaussian states and encodes cross-Gaussian dependencies in a diagonal-plus-low-rank representation. To incorporate these dependencies into voxel classification, CGOcc uses a class-conditional projection to extract diagonal and signed cross-Gaussian statistics without constructing a dense dependency matrix. The readout then refines occupied-class probabilities using these statistics while preserving a learned reference's occupied mass and free probability. Extensive experiments on nuScenes demonstrate CGOcc achieves state-of-the-art performance, with larger gains at high Gaussian overlap and improved predictions near boundaries. Ablation studies validate the effectiveness of covariance-aware prediction and support its synergy with geometric interaction.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15675

Optimal-Time Independent Subset Sampling over Acyclic Joins

Xuyang Liu, Zijian Zhang, Zhen Li

原文摘要

Join results can greatly exceed their inputs even when applications need only a small random subset. We study sampling that includes each result independently with a prescribed probability given by the product of its input-tuple weights (PRODUCT). For fixed full acyclic joins with static weights, we achieve input-linear preprocessing and index space together with output-linear expected sampling work, eliminating logarithmic factors from previous bounds. A shared join-tree index supports weighted draws over the entire join and locates high-probability results. Direct Bernoulli trials handle high-probability results, allowing Poisson thinning to generate the remaining independent inclusion decisions with bounded overhead. Our exact sampler uses expected $O(N)$ preprocessing, $O(N)$ index space, and expected $O(1+mμ)$ time per call including output construction. Here $N$ is the input size, $m$ counts relation occurrences, and $μ$ is the expected sample size. The guarantees hold on a real random-access machine with unit-cost exact arithmetic and logarithms, continuous uniform randomness, and expected-time hashing. The time bounds are optimal, matching input reading and explicit output writing. Our floating-point prototype has lower sampling latency than the fastest applicable baseline in 17 of 18 PRODUCT settings on three queries over the STATS benchmark. Construction savings on large joins can offset indexed materialization's faster sampling over a limited number of calls. On a real-data path at $μ=100$, our sampler achieves a $20.5\times$ speedup over indexed materialization for construction plus 300 calls, measured after common data preparation and loading.

cs.DB · cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15653

A Mechanistic Interpretability Study of an Astronomy Foundation Model

Rachel C. Zhang, Alberto Bietti, Wes Gurnee, Alessandro Favero, Miles Cranmer

原文摘要

Foundation models are increasingly used across the sciences, but whether their internal computations correspond to known scientific operations or proceed through different mechanisms remains unclear. Understanding these mechanisms is essential for assessing reliability, identifying failure modes, and learning new science from the models. We present, to our knowledge, the first causal mechanistic interpretability study of an astronomy foundation model, AION-1, focusing on its multimodal advantage in redshift prediction, where combining imaging with photometry outperforms photometry alone. We find that this advantage is largest for spatially extended and dust-attenuated galaxies, and that most of it is localized to the first of the encoder's twelve blocks. Within that block, how well a property is linearly decodable does not predict whether it can be localized. Spatial extent is causally used, and one attention head dominates linear probing for it, yet ablating that head has negligible effect on redshift prediction: the information is distributed across heads and is decodable again one layer after we erase it. Dust attenuation shows the opposite pattern: it is only weakly decodable anywhere in the encoder, yet a single head is necessary for most of the multimodal advantage, particularly for the most dust-attenuated galaxies, and keeping that head as the only active head in its block preserves nearly all of the advantage. None of the astrophysically motivated operations we tested explains what this head computes. Whether this reflects a limitation of current interpretability methods or a computation that does not correspond to any known astrophysical operation remains open, and resolving it is a prerequisite for using interpretability as a tool for scientific discovery.

cs.LG · astro-ph.IM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15651

Recover, Don't Just Continue: Learning from Feedback for Physical Failure Understanding and Correction

Miao Pan, Kaixiang Yao, Xiaohe Zhou, Xu Wang, Qinfeng Li, Wenqi Zhang, Xuhong Zhang

原文摘要

Multimodal large language models are regarded as the cognitive foundation of embodied intelligence, but planning from instructions alone cannot make them reliable. During execution, actions deviate from intended effects, constrained by the embodiment and environment. An embodied brain must understand why execution deviates, identify what can be reliably realized, and revise decisions using interaction experience. These correspond to causal failure localization, capability-constrained adaptation, and experience-driven revision. Current embodied foundation models largely lack these capabilities. To address this, we introduce Embodied-Corrector. We construct failure-recovery data by injecting perturbations at subtask boundaries of successful trajectories, replaying affected subtasks, and keeping failures that are observable from public evidence and recoverable from the current state. We align actions, consequences, failure causes, and recoveries into Judge-Cause-Sub-Fine supervision. Training uses evaluation-first SFT: the model learns Judge and Cause first, then Sub and Fine conditioned on accurate prefixes. Since deployment uses self-generated prefixes, evaluation errors propagate into recovery planning, and response-level rewards are too coarse to locate affected planning tokens. We therefore use OPD to internalize the planning distribution under accurate prefixes into that under self-generated ones: the model generates plans from self-generated prefixes, while a contrastive forward pass with accurate prefixes compares token probabilities to reinforce or suppress planning tokens. At deployment, this branch is removed. Experiments show stronger failure analysis and corrective planning: with a frozen VLA, composite task success improves by 6.1 percentage points; with fixed GPT-5.5 execution, manipulation and navigation tasks improve by 13.9 percentage points.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15641

Contour-Assisted Evolutionary Computation: Estimating Peaks From the Contour Lines of Evaluated Solutions

Jun Zhang, Tong Qian, Hua Ding, Zhi-Hui Zhan, Wei-Jie Yu, Jian-Yu Li

原文摘要

Evolutionary algorithms (EAs) evaluate many candidate solutions but use them mainly to rank individuals. This paper treats the evaluated solutions as the spot heights of a topographic survey and draws the contour lines they imply. The contour map decomposes the evaluated region into peaks: in two dimensions a contour tree with persistence separates significant peaks from interpolation ripples, and in more dimensions hill climbing on the interpolated surface locates the peaks and ray-cast level sets describe them. A memory of the explored peaks directs the search to new ones. The data-supported contours of each peak are extrapolated to zero size by an area law, exact for quadratic peaks and second-order accurate for smooth ones, that estimates a peak's location, height and shape before it is sampled. A contour-assisted EA (CA-EA) inserts contour steps with local search and peak memory into a genetic algorithm (GA), differential evolution or particle swarm optimization. A contour-assisted surrogate-assisted EA (CA-SAEA), for expensive problems, spends each evaluation on surrogate-screened offspring or on sampling around a peak, entered at the maximum of the interpolated surface. On 2-D benchmarks, CA-EA reduces the evaluations a plain GA needs by factors of 12 to 112; controls attribute its gain over classical memetic search to restarting local search on distinct peaks. On the CEC 2015 expensive suite in 10 and 30 dimensions, CA-SAEA has the second-best average rank, behind DYCORS and ahead of lq-CMA-ES and the competition winner MVMO, although in 30 dimensions MVMO wins significantly on 9 functions and loses on 6; there the map beats sampling around the best point on 5 of 15 functions and loses on 3. Entering the peaks at their extrapolated locations brought no gain at these budgets, although, with enough samples, it improves the estimated heights on most two-dimensional functions.

cs.NE · cs.AI · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15639

ChJGBench: A Comprehensive Benchmark for Chinese Legal Judgment Generation with Diagnostic Evaluation

Yinghao Hu, Linggang Kong, Qian Xiao, Yuting Huang, Yunlong Zhang, Yujie Zhang, Yiquan Wu, Fei Duan 等 12 位作者

原文摘要

With the rapid development of LLMs, increasing attention has been paid to whether they can reliably generate complete and legally valid judicial documents. This calls for a benchmark capable of evaluating whether models can accurately apply statutes and resolve outcome-critical issues, including claims, charges, penalties, and monetary obligations. However, existing benchmarks typically focus on isolated legal tasks or coarse-grained evaluation. We introduce ChJGBench, a benchmark for generating the reasoning and dispositive sections of Chinese judgments across civil, criminal, and administrative cases. Built from 3,462 real-world judgments, ChJGBench provides a case-type-aware diagnostic evaluation framework comprising 13 metric types and adopts a hybrid paradigm. Experiments reveal no uniform advantage for legal-domain models over general-purpose models, with model strengths varying across diagnostic dimensions. Performance is generally stronger on criminal cases, while civil and administrative cases continue to present substantial challenges.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2609.10947

The Platonic brain bridge hypothesis: brain networks as architectural priors for multimodal large language models

Pengfei Zhang, Biao Tian, Xiangang Li, Li Liu

原文摘要

Multimodal large language models predict brain activity, but alignment has remained a measurement, not a design tool. We propose the Platonic brain bridge hypothesis: omni models, which jointly process video, audio and text, share brain-like representations usable in both directions. From model to brain, seven omni models show stable brain-likeness across participants, and our encoding experts lead the Algonauts 2025 out-of-distribution leaderboard by mean score. From brain to model, we make three contributions. Brain-MoE ties the experts of a frozen model to the seven cortical networks, raises held-out accuracy in all 15 model-benchmark pairs and exceeds capacity-matched random experts in 14. Brain-AVQA, to our knowledge the first audiovisual benchmark with cortical-network labels for every question, supplies the pretraining questions. Brain-Scope finds sparse features that predict brain responses, steer routing and, when removed, weaken brain prediction. Human brain organization is therefore a usable architectural prior for multimodal large language models.

q-bio.NC · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2509.17100

The SAGES Critical View of Safety Challenge: A Global Benchmark for AI-Assisted Surgical Quality Assessment

Deepak Alapatt, Jennifer Eckhoff, Zhiliang Lyu, Yutong Ban, Jean-Paul Mazellier, Sarah Choksi, Kunyi Yang, Po-Hsing Chiang 等 41 位作者

原文摘要

Advances in artificial intelligence (AI) for surgical quality assessment promise to democratize access to expertise, with applications in training, guidance, and accreditation. This study presents the SAGES Critical View of Safety (CVS) Challenge, the first AI competition organized by a surgical society, using the CVS in laparoscopic cholecystectomy, a universally recommended yet inconsistently performed safety step, as an exemplar of surgical quality assessment. A global collaboration across 54 institutions in 24 countries engaged hundreds of clinicians and engineers to curate 1,000 videos annotated by 20 surgical experts according to a consensus-validated protocol. The challenge addressed key barriers to real-world deployment in surgery, including achieving high performance, capturing uncertainty in subjective assessment, and ensuring robustness to clinical variability. To enable this scale of effort, we developed EndoGlacier, a framework for managing large, heterogeneous surgical video and multi-annotator workflows. Thirteen international teams participated, achieving up to a 17% relative gain in assessment performance, over 62% reduction in calibration error, and a 17% relative improvement in robustness over the state-of-the-art. Analysis of results highlighted methodological trends linked to model performance, providing guidance for future research toward robust, clinically deployable AI for surgical quality assessment.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15609

GLCR: Global-Local Collaborative Routing for Multi-Task Electromagnetic Signal Processing

Fang Lu, Yao Lu, Zhuangzhi Chen, Sicheng Zhang, Shanqing Yu, Yun Lin, Qi Xuan, Guan Gui

原文摘要

Deep neural networks for electromagnetic signal processing are typically developed as single-task experts with fixed inputs and objectives, limiting cross-task transferability. Electromagnetic foundation models offer broader task coverage but incur substantial pretraining and inference costs. To balance accuracy and efficiency, we adopt model routing to dynamically dispatch unknown signals to matched experts within a heterogeneous pool. We construct HeteroSignal-7, a multi-task routing benchmark with 140,000 samples from seven datasets covering six task types, paired with seven classification and waveform-recovery experts and a unified evaluation protocol. We then propose GLCR, a two-stage routing method combining global dispatch with local discrimination of similar tasks. First, a lightweight one-dimensional convolutional neural network (CNN) with an additive-margin head predicts one of seven routing classes. Second, a gradient-boosted-tree specialist uses four physical statistics to re-evaluate samples whose top two candidates match a confusion pair automatically identified from validation errors. The pipeline is trained across the full signal-to-noise ratio (SNR) range and requires neither SNR labels nor noise estimation at inference time. GLCR outperforms all 19 baselines, achieving 96.16% routing accuracy and a 76.30% system score, exceeding the respective second-best baselines by 1.16% and 1.14%. It achieves the lowest routing latency among the compared methods at 1.43 ms per sample and reduces expected overall system FLOPs by 5.9 times compared with executing all experts. This work provides a public evaluation platform and an efficient, reproducible baseline for heterogeneous expert routing in electromagnetic signal processing.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15602

CoCode-World: Shared 3D Proxy Representation for Multi-Player World Models

Qirui Li, Xin Zhang, Yabo Chen, Jinkun Hao, Paul L Rosin, Yu-Kun Lai, Haibin Huang, Yin Chen 等 10 位作者

原文摘要

Multiplayer generative world models must produce observations that agree on shared entities despite different camera motions and occlusions. Explicit world representations provide spatial control, but precise modeling of individual game maps limits scene diversity, while shared geometry alone cannot ensure consistent appearance across views. We present CoCode-World, a shared 3D proxy framework that separates structural control from visual synthesis for two-player video generation. Programmable proxies specify scene layout, motion, and occlusion, while RGB references guide character and scene appearance. To coordinate visual details across players, we concatenate paired proxy videos, appearance references, and target views in a consistent spatial layout and generate both views jointly with a pretrained video model. This formulation uses the model's native attention for cross-view communication within a single generation branch, with LoRA adaptation learning proxy adherence and appearance correspondence from paired observations. We construct a two-player GTA~V dataset that pairs synchronized RGB observations with proxy videos derived from shared map geometry and game-engine state. Experiments demonstrate appearance transfer to characters and scene styles unseen during training, with improvements in video quality and cross-view player identity over the evaluated baseline. Ablations further examine how proxy construction and cross-view communication affect generation. Project page: https://iapple233.github.io/CCW/.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15600

MemCredit: From Relevance to Utility for Decision-Time Memory in Long-Horizon Web Agents

Quanjiang Guo, Sijie Wang, Qianyang Zhu, Ben Zhang, Jinchuan Zhang, Ke Yan, Zhao Kang

原文摘要

Large language model (LLM) agents increasingly operate over long Web interaction histories, making memory management critical for reliable and efficient decision making. Existing methods primarily optimize storage, retrieval, or compression, but the memories most semantically relevant to the current state are not necessarily those that most improve the agent's action. We introduce MemCredit, a decision-centric memory framework that shifts memory selection from semantic relevance to decision utility. MemCredit estimates the state-, reference-context-, and policy-conditional marginal contribution of individual memories through controlled counterfactual interventions, and distills these intervention-derived credits into a lightweight utility estimator. At inference time, semantic relevance is used only for high-recall candidate generation, while predicted utility arbitrates which memories are retained under a fixed token budget, without modifying the underlying agent policy or requiring additional environment interaction. We evaluate MemCredit on ALFWorld and WebShop against representative memory baselines. On ALFWorld, MemCredit achieves 86.57 SR@50 under a 500-token historical-memory budget, compared with 65.67% for BM25 retrieval. Counterfactual analysis further shows that memory utility is sparse, strongly state dependent, and poorly captured by semantic relevance. These results suggest that decision utility provides a more effective principle than relevance alone for long-horizon agent memory management.

cs.AI

查看论文
arXiv ↗PDF ↗