跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 22:53 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 23:29 — 2026-11-08 23:29（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：2026-11-08 22:53最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,057 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 14,661 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 22:48（北京时间）
新论文 · v1arXiv:2611.06585

Signed, Sealed, Leaked: Trust Beyond Signature for MCP Toolchains

Yichiet Aun, Mohammed A. Alhartomi, Jing Jie Tan, Waqas Nadeem, Adeb Salh, Shankar Karuppayah, Sin Chee Tan

原文摘要

AI agents rely on third-party tools, such as Model Context Protocol (MCP) servers, whose publishers can be authenticated and whose execution can be restricted by runtime security policies. Yet authenticity does not guarantee benign behaviour: a legitimately signed tool may perform its advertised function while concealing malicious code that leaks confidential information. We demonstrate this trust failure with a signed MCP tool that embeds sensitive data in requests to a policy-allowed destination. Meta's MCPGuard-Dynamic, a state-of-the-art runtime defence, blocks a direct exfiltration attempt in the same run, yet fails to prevent this attack in every trial. We introduce germline execution, which limits information disclosure without inspecting or trusting tool implementations. Each tool invocation runs in ephemeral copies forked from a data-free germline process, each receiving only information authorised for its destination. Even if malicious code executes, what it can disclose is bounded by the data available to its copy. Under explicit assumptions on copy confinement and a data-free germline, we prove sink noninterference for every signed release and, for releases deterministic within our replay model, show that a verified witness establishes a flow violation. Across 153 attack runs, no unauthorised disclosure was detected under germline execution, compared with 5.9-74.5% of runs under baseline defences and an ablation. Invocations served by a single copy completed in 10-49 ms, 2-28x faster than restarting the tool for every invocation, the conventional way to clear state. These results show that data-isolated execution protects agent toolchains against malicious code concealed within authenticated software.

cs.CR · cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06582

Finite-width shift of the edge of chaos in deep neural networks

Arn Caesar

原文摘要

Deep neural networks train best when they are initialised at the edge of chaos, the critical line in the plane of weight and bias variances on which the distance between two inputs neither grows nor shrinks with depth. The line is known for infinitely wide networks; at finite width it moves, and how it moves has been disputed. We treat the logarithm of the distance between two inputs through a network of width $N$ as a random walk and compute its drift and variance to order $1/N$. The edge of chaos moves to a larger weight variance, by $Δσ_w^2=-a_1/(N\,\partial_{σ_w^2}\lnχ_1)$, about $8/N$ for $\tanh$ networks at a bias variance of $0.05$, confirmed by simulations of the exact finite-width recursion. The shift describes a typical network; the average over many networks is dominated by rare networks in which the distance grows, and its critical point moves the other way, which explains why calculations and simulations have disagreed. Backpropagation follows the same random walk, so the shift applies to gradients unchanged. Along the edge of chaos, the information about the similarity of two inputs is constant until the compression over the depth exceeds about one nat, which fixes where to sit on the line. The results give an initialisation rule, Crinit, that places a network on its finite-width edge of chaos without a search. On MNIST and Fashion-MNIST at width $64$ it is more accurate than the standard rules at their usual settings, by a small margin in shallow networks and a large one in deep networks, where most standard rules fail; it trains in fewer steps, and it matches or beats the standard rules with a tuned gain.

cond-mat.dis-nn · cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.39913

TokenRepel: Generating Diverse Image Sets Without Compromising Quality

Qingtao Yu, Zhen Wang, Ning Lai, Boyang Hu, Hongdong Li, Dylan Campbell

原文摘要

We present an inference-time approach that enhances the visual diversity of image sets generated by text-to-image models, without compromising the average image quality. Our method leverages the intrinsic geometry of hidden representations in pretrained models to diversify images generated from the same prompt. First, we introduce a token repulsion mechanism that increases the angle between feature tokens across samples. It takes a negative Riemannian gradient step on a von Mises-Fisher mixture distribution of tokens on the unit hypersphere. Second, to preserve the quality of each output image, we propose a token density preservation mechanism that projects the repulsion-induced prediction change onto a half-space aligned with the model's score direction. This encourages the updates to remain within the high-density regions learned by the generative model. We further extend this mechanism to the output of each intermediate layer, enabling finer-grained iterative guidance. We evaluate our method on three types of pretrained text-to-image models. Experiments show substantial gains in visual diversity under identical prompts, while maintaining a comparable level of image fidelity.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.16601

Quantifying Error Propagation and Model Collapse in Diffusion Models

Nail B. Khelifa, Richard E. Turner, Ramji Venkataramanan

原文摘要

Machine learning models are increasingly trained or fine-tuned on synthetic data. Recursively training on such data has been observed to significantly degrade performance in a wide range of tasks, often characterized by a progressive drift away from the target distribution. In this work, we theoretically analyze this phenomenon in the setting of score-based diffusion models. For a realistic pipeline where each training round uses a combination of synthetic data and fresh samples from the target distribution, we obtain upper and lower bounds on the accumulated divergence between the generated and target distributions. Notably, to the best of our knowledge, this is the first lower bound on the divergence between the learned and target distributions, even for standard diffusion models. Our results allow us to characterize different regimes of drift, depending on the score estimation error and the proportion of fresh data used in each generation. In a certain regime, the accumulated divergence after several retraining rounds can be expressed as a discounted sum of score estimation errors made at each generation. We also provide empirical results on synthetic data and images to illustrate the theory.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2401.08739

EgoGen: An Egocentric Synthetic Data Generator

Gen Li, Kaifeng Zhao, Siwei Zhang, Xiaozhong Lyu, Mihai Dusmanu, Yan Zhang, Marc Pollefeys, Siyu Tang

原文摘要

Understanding the world in first-person view is fundamental in Augmented Reality (AR). This immersive perspective brings dramatic visual changes and unique challenges compared to third-person views. Synthetic data has empowered third-person-view vision models, but its application to embodied egocentric perception tasks remains largely unexplored. A critical challenge lies in simulating natural human movements and behaviors that effectively steer the embodied cameras to capture a faithful egocentric representation of the 3D world. To address this challenge, we introduce EgoGen, a new synthetic data generator that can produce accurate and rich ground-truth training data for egocentric perception tasks. At the heart of EgoGen is a novel human motion synthesis model that directly leverages egocentric visual inputs of a virtual human to sense the 3D environment. Combined with collision-avoiding motion primitives and a two-stage reinforcement learning approach, our motion synthesis model offers a closed-loop solution where the embodied perception and movement of the virtual human are seamlessly coupled. Compared to previous works, our model eliminates the need for a pre-defined global path, and is directly applicable to dynamic environments. Combined with our easy-to-use and scalable data generation pipeline, we demonstrate EgoGen's efficacy in three tasks: mapping and localization for head-mounted cameras, egocentric camera tracking, and human mesh recovery from egocentric views. EgoGen will be fully open-sourced, offering a practical solution for creating realistic egocentric training data and aiming to serve as a useful tool for egocentric computer vision research. Refer to our project page: https://ego-gen.github.io/.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2601.20476

In-Context Learning for Diagram Code Generation: What is the Effect on Faithfulness and Quality?

Evanfiya Logacheva, Arto Hellas, Tsvetomila Mihaylova, Juha Sorva, Ava Heinonen, Juho Leinonen

原文摘要

We investigate how provision of in-context examples based on discourse similarity affects quality and hallucination in diagram code generation from educational materials. Using a sample of texts as sources for diagram generation, we test two methods using a conventional text-to-diagram task format, instruction-based zero-shot generation and ICL with text-to-diagram examples, and an unconventional ICL method with a discourse analysis-to-diagram example, which requires a model to generate a diagram from a discourse analysis. We evaluate AI-generated diagrams for faithfulness to provided context and their quality outcomes using both human and automated evaluation. Bayesian data analysis of the human diagram evaluation shows that there is significant evidence that the unconventional task format improves context faithfulness in diagram generation compared to the zero-shot instruction with reducing the odds of context faithfulness hallucination by nearly $70\%$; however, we do not find the ICL having a significant effect on the diagram aesthetic presentation and superficial coherence. Evaluation with the LLM-as-a-judge G-Eval metric shows nearly 4.5-fold increased odds of the perfect faithfulness outcome for the novel ICL task. Our study provides a novel insight into ICL format effect on superficial fluency and faithfulness in context-grounded structured diagram code generation.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06569

One Scale, Four Texts: Gaps, Overlaps and Silent Repairs in Published Grading Schemes

Elisa Rovai, Fabio Rovai

原文摘要

Category systems often reach their users as text, and readers apply them with tacit repairs. We ask what such a text determines once the repairs are removed, using diabetic retinopathy grading, where one international scale circulates in several documents. We transcribe four texts (the English screening definitions of 2025, the international scale as tabulated in 2017 and as published in 2003, and an Italian guideline of 2015) into one rule language over 24 finding variables, and make every point a text leaves open a named precisification. Exhaustive enumeration of 1,425,807,360 finding profiles, re-derived by an SMT solver and spot-checked by an OWL reasoner, shows that every text that assigns actions leaves some eyes without a category under every reading; that the 2017 tabulation has a proliferative class that is empty when read literally and a macular gap that the 2003 text lacks, so that no function maps the 2003 grades onto the 2017 grades; and that on image findings alone the English and Italian texts order some pairs of eyes in opposite ways. On 927 annotated photographs from three public datasets, with retinal thickening assumed absent, the English text and the 2017 tabulation disagree on referral for 26.8% of the eyes of one dataset (DDR) on which both decide, and in a pre-registered experiment classifiers trained on each text's labels side with their own text. Thickening cannot be seen on a colour photograph; left free, every disagreement involving England becomes undecidable, so it rests on what the camera cannot show. In a second pre-registered study, language models that answered without deliberating repaired most gap and overlap items even when told to read literally, while Claude Sonnet 5.5 and Claude Opus 5.5 reported the defects far more often; within two models, deliberation reduced silent repair without removing it.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06564

Playing Soccer Like Humans Do: Learning Versatile and Agile Humanoid Soccer via Latent Motion Priors

Haoyu Shao, Yunshen Wang, Jingze Zhang, Shaohang Zhu, Yong-Lu Li, Tianzhu Zhang, Baoxiong Jia, Siyuan Huang

原文摘要

Humanoid soccer requires a robot to seamlessly combine agile locomotion, ball manipulation, and impact-rich contact dynamics across a continuous, dynamic behavioral spectrum. Yet existing approaches either cover only a limited set of skills, or forego motion priors entirely and produce unnatural behaviors, leaving the combination of a unified skill set and human-like motion quality unaddressed. We present soccerbot, a hierarchical reinforcement learning framework that resolves both limitations through a structured latent motion prior distilled from large-scale human soccer motion capture data. By constraining policy learning within this dynamically plausible motion manifold, a single skill-conditioned policy naturally learns to perform moving, dribbling, trapping, and kicking in a unified formulation, while inherently producing human-like motion and fluid transitions during commanded skill switching. Augmented by robustness-oriented simulation design, soccerbot transfers zero-shot to the Unitree G1 humanoid robot, demonstrating agile, natural, and robust execution of the full soccer skill repertoire under real-world conditions.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.29845

Bricker to BRACE: A Bracket Exposure RAW Dataset and Restoration Model for Flicker-Banding

Zihan Zhou, Libo Zhu, Jue Gong, Zhiyi Zhou, Jiezhang Cao, Yong Guo, Yulun Zhang

原文摘要

Flicker-Banding (FB) arises from temporal aliasing between a camera's rolling shutter and a display's brightness modulation, degrading screen-captured image readability with color shifts and jagged patterns. Existing single-frame methods with simplified parametric stripe models cannot reliably distinguish these artifacts from genuine texture. To address this, we conduct a systematic analysis of complex FB morphologies and reveal their significant variation across exposure settings, motivating a multi-frame bracketed RAW restoration paradigm. We construct Bricker, a synthetic-real bracketed RAW dataset built via ray-tracing-based physical simulation and an automated multi-exposure capture tool. We further propose BRACE: Bracketed RAW Flicker-Banding Removal, a multi-frame restoration model that utilizes a frequency-aware banding prior and a multi-scale spatial cross-attention modulator (MSCAM) for cross-exposure spatial fusion. We also introduce the Stripe Frequency Consistency (SFC) metric to evaluate banding removal. Experiments demonstrate state-of-the-art performance on both synthetic and real benchmarks. Our dataset and code are available at: https://github.com/ZZH-qwq/BRACE

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.16512

Medial Axis Aware Learning of Signed Distance Functions

Samuel Weidemaier, Christoph Norden-Smoch, Martin Rumpf

原文摘要

We propose a novel variational method to compute a highly accurate global signed distance function (SDF) to a given point cloud. To this end, the jump set of the gradient of the SDF, which coincides with the medial axis of the surface, is explicitly taken into account through a higher-order variational formulation that enforces linear growth along the gradient direction away from this discontinuity set. The eikonal equation and the zero-level set of the SDF are enforced as constraints. To make this variational problem computationally tractable, a phase field approximation of Ambrosio-Tortorelli type is employed. The associated phase field function implicitly describes the medial axis. The method is implemented for surfaces represented by unoriented point clouds using neural network approximations of both the SDF and the phase field. Experiments demonstrate the method's accuracy both in the near field and globally. Quantitative and qualitative comparisons with other approaches show the advantages of the proposed method.

cs.CV · cs.CG · cs.GR · cs.LG · math.NA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06556

LungMend: A Healthy-Only Latent Diffusion Shape Prior for Lung Mask Correction in Severe Tuberculosis CT

Rezkellah Noureddine Khiat, Pierre-Yves Brillet, Catalin Fetita

原文摘要

Lung segmentation models such as R231 are widely used, but they fail on severe tuberculosis (TB) CT: cavities and consolidations look like non-lung tissue and are left out of the mask. We present LungMend, a post-processing model that corrects such masks using only healthy anatomy. A latent diffusion model, trained on healthy lungs with synthetically corrupted masks, learns to recover the complete lung from the faulty mask and the bone anatomy, without any pathological data or CT intensities. LungMend recovers cavities and consolidations that R231 misses and improves accuracy on expert-annotated slices. Code: https://github.com/noureddinekhiati/LungMend

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06554

RAGAM-AI: A Hybrid Reinforcement Learning based Agentic approach powered by Generative AI for Edge Resource Management

Shreya K. Chari, John S. Vardakas, Kostas Ramantas, Christos Verikoukis

原文摘要

Resource management for distributed edge networks hosting different services has been handled efficiently using Reinforcement learning (RL). Reward generalization in complex workflows is still an open issue within the RL realm. Therefore, this work proposes RAGAM-AI, a hybrid framework that combines the capabilities of RL algorithms and Generative-AI (Gen-AI) for powering an Agentic AI workflow that optimizes resource allocation at the Multi-access Edge Computing (MEC) units. This framework further resolves the reward generalization issue by utilizing Large Language Model (LLM) for feedback. A Multi- Agent Soft-Actor Critic (MASAC) using MathΣtral as a reward oracle is implemented for managing resource allocations at the MEC. RAGAM-AI interprets system state information and evaluates multi-objective trade-offs guiding the resource orchestration loop over distributed edge server agents. The complexity of the framework is further brought down by incorporating surrogate reward model. The overall performance is evaluated against the single agent SAC, REINFORCE and random policies for benchmarking. On using RAGAM-AI, lower allocation deviations for CPU, memory and bandwidth resources are reported while minimizing the latency and data rate costs. A scalable AI as a feedback (AIAF) solution optimizing network resources with significant performance improvement is thus presented.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06553

Addition by Subtraction: Toward Mitigating Fragile Safety Alignment in Large Language Models

Hamid Dashtbani, Alexandra Dmitrienko

原文摘要

Large language models (LLMs) undergo safety alignment to prevent harmful generations, yet they remain vulnerable to jailbreak attacks. Recent work reveals a deeper structural weakness: safety alignment can be highly sparse, such that pruning a small number of safety-critical neurons or ablating a single refusal direction can substantially undermine aligned behavior. In this work, we take the first steps toward strengthening safety alignment such that it is less dependent on sparse model components. We propose Addition by Subtraction, which gradually removes identified safety-critical neurons during finetuning and uses preference optimization to re-establish safety-aligned behavior through other parts of the model. Our results show that the resulting models are substantially more robust to pruning-based attacks. Remarkably, these benefits generalize beyond the white-box attacks motivating our design: Addition by Subtraction improves robustness against other sparsity-based interventions, including refusal-direction ablation, as well as a broad range of black-box jailbreak attacks. The finetuned models also exhibit improved truthfulness while largely preserving general capabilities. Comprehensive experiments across four models from three vendors demonstrate consistent improvements in safety robustness, reducing attack success rates by up to 90% for some attacks.

cs.AI · cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.00986

Sparse Reward Subsystem in Large Language Models

Guowei Xu, Mert Yuksekgonul, James Zou

原文摘要

Recent studies show that LLM hidden states encode reward-related information, such as answer correctness and model confidence. However, existing approaches typically fit black-box probes on the full hidden states, offering little insight into how this information is structured across neurons. In this paper, we show that reward-related information is concentrated in a sparse subset of neurons. Using simple probing, we identify two types of neurons: value neurons, whose activations predict state value, and dopamine neurons, whose activations encode step-level temporal difference (TD) errors. Together, these neurons form a sparse reward subsystem within LLM hidden states. These names are drawn by analogy with neuroscience, where value neurons and dopamine neurons in the biological reward subsystem also encode value and reward prediction errors, respectively. We demonstrate that value neurons are robust and transferable across diverse datasets and models, and provide causal evidence that they encode reward-related information. Finally, we show applications of the reward subsystem: value neurons serve as effective predictors of model confidence, and dopamine neurons can function as a process reward model (PRM) to guide inference-time search. Our code is available at https://github.com/zou-group/reward_subsystem.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2107.12636

Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers

Wen Wang, Yang Cao, Jing Zhang, Fengxiang He, Zheng-Jun Zha, Yonggang Wen, Dacheng Tao

原文摘要

Detection transformers have recently shown promising object detection results and attracted increasing attention. However, how to develop effective domain adaptation techniques to improve its cross-domain performance remains unexplored and unclear. In this paper, we delve into this topic and empirically find that direct feature distribution alignment on the CNN backbone only brings limited improvements, as it does not guarantee domain-invariant sequence features in the transformer for prediction. To address this issue, we propose a novel Sequence Feature Alignment (SFA) method that is specially designed for the adaptation of detection transformers. Technically, SFA consists of a domain query-based feature alignment (DQFA) module and a token-wise feature alignment (TDA) module. In DQFA, a novel domain query is used to aggregate and align global context from the token sequence of both domains. DQFA reduces the domain discrepancy in global feature representations and object relations when deploying in the transformer encoder and decoder, respectively. Meanwhile, TDA aligns token features in the sequence from both domains, which reduces the domain gaps in local and instance-level feature representations in the transformer encoder and decoder, respectively. Besides, a novel bipartite matching consistency loss is proposed to enhance the feature discriminability for robust object detection. Experiments on three challenging benchmarks show that SFA outperforms state-of-the-art domain adaptive object detection methods. Code has been made available at: https://github.com/encounter1997/SFA.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06546

Adapting Sleep Foundation Models for Dense Sleep Spindle Localization

Alexis Bollengier, Abel Díaz Berenguer, Olivier Pallanca, André Anjos, Hichem Sahli

原文摘要

Adapting sleep foundation models to dense electroencephalography (EEG) event localization is challenging because multi-second representations may not preserve sufficient temporal detail for precise boundary recovery. We address sleep spindle localization by adapting a frozen SleepFM encoder with a local time-frequency pathway that preserves spindle-relevant spectral content and intra-token position. The local representation drives localization, while residual cross-attention incorporates SleepFM temporal context. Dense predictions are obtained through localized token-to-sample reconstruction and temporal refinement. Tested on the Massive Online Data Annotation (MODA), the proposed model achieves an event-level $F_1$ of $0.8080 \pm 0.0040$ at IoU 0.2 across six folds. Ablations show that localization primarily depends on local spectral and sub-token temporal information, while the pretrained representation provides complementary context. These results indicate that dense adaptation benefits from preserving information below the pretrained token scale. Code will be released upon acceptance.

eess.SP · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06545

When Do Summaries Become Instructions? Unsupported Policy in LLM Agents' Self-Written Handoff Summaries

Wenhui Chu

原文摘要

Long-running LLM agents compact their context, replacing most history with a summary. We ask whether handoff summaries state permissions or requirements the record does not support, whether such sentences change what the next instance (the successor) does, and where they come from. Synthetic tool-use tasks carry a ground-truth permission ledger; same-snapshot replay reruns the successor with those whole sentences replaced by neutral filler. Two AI readers, reading only rule-flagged held-out summaries, confirmed unsupported restrictions in 1.2% and 2.4% of all readable summaries from two open-weight models, and unsupported authorizations in 0.1% and 1.3%. For restrictions, a pre-specified replay test was not significant (p = 0.58); a follow-up, planned after it, found a fragile effect (p = 0.027). Neutralizing false approvals cut unauthorized actions from 24 to 7 of 120 held-out runs (post hoc; later set: 17 to 11 of 48). Most development restrictions followed the agent's earlier reasoning that an action needs approval (post hoc). In pre-specified tests, replacing the system prompt's "Some actions need approval." with one saying where requirements come from cut unsupported restrictions from 5.0% to 1.8% of development summaries and, on held-out templates, from 1.8% to 0.3% (both p < 10^-9), while requests for approvals the ledger requires barely changed. Code and data: https://github.com/Chuw1/handoff-audit

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06544

MKD2World: A Typed Spatial MarkDown World Model For Web Agents

Zhihao Nan, Sifan Zhou, Yiming Cheng, Jinkai Zheng, Zheng Zhu, Si Shi, Ming Li, Fei Yu

原文摘要

Graphical user interface (GUI) agents can improve decision-making with world-model foresight, provided that predicted states accurately reflect post-action interfaces. Existing state representations fail to jointly capture interface layout, UI semantics, and explicit locations. We introduce Typed Spatial Markdown (TSM), a Markdown-style textual state representation for desktop web interfaces. TSM serializes block-level and atomic-level UI elements according to their spatial relationships, jointly encoding their types, visual semantics, explicit locations, optional control states, and hierarchical membership. To train a screenshot-to-TSM renderer, we construct AtomBlock-WebUI, a dataset with precise annotations at both granularities. By injecting element-type labels into HTML and directly extracting bounding boxes after rendering, we avoid annotation errors caused by post-hoc inference from webpage structures. Building on TSM, we propose MKD2World, a desktop web world model trained in two stages for current-state description and action-conditioned next-state prediction. During inference, the web agent queries MKD2World as needed and performs a ``digest'' step, in which it interprets each predicted state and extracts task-relevant evidence for selecting the best action. Experiments show that MKD2World-9B achieves an EleF1 score of 26.50 on the out-of-domain test set, outperforming GPT-5.6-Sol(14.98) by 11.52 points. Across Online-Mind2Web tasks, MKD2World-9B improves the success rate of the Qwen3.5-35B web agent from 22.94% to 37.61%, achieving competitive performance among leading open-source GUI world models. Code is available at https://github.com/OmniAI-Lab-CUHKSZ/MKD2World.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.00064

The minimal width of universal $p$-adic ReLU neural networks

Sándor Z. Kiss, Ambrus Pál

原文摘要

We determine the minimal width of $p$-adic neural networks with the universal approximation property for continuous $\mathbb Q_p$-valued functions on compact open subsets with respect to the $L_q$ norms and the $C_1$ norm, where the activation function is a natural $p$-adic analogue of the ReLU function.

math.NT · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06542

EvoOPD: Evolving Privileged Information Strategies for Black-Box On-Policy Distillation

Ximo Zhu, Ruiqi Liu, Yi Han, Zhengan Wu, Gengsheng Li, ZiAn Wang, Zhu Yuantian, Jin Jiang 等 9 位作者

原文摘要

Proprietary language models exhibit strong reasoning and coding capabilities, but their output distributions are inaccessible, making fine-grained distillation methods that rely on teacher logits difficult to apply directly to black-box models. We observe that rich textual feedback from a black-box teacher can be treated as privileged information (PI) and converted, through a PI-conditioned privileged teacher, into dense supervision signals on the student's own trajectories. However, what PI should be acquired from the teacher to most effectively support student learning remains unclear. PI strategies that differ in where they focus, what information they request, and how much detail they provide can have substantially different effects on the current student, and their relative effectiveness can further change as training progresses. Based on this observation, we propose Evolving Privileged Information Strategies for Black-Box On-Policy Distillation (EvoOPD), which treats PI acquisition itself as an optimization problem and maintains a PI Strategy Bank that evolves with the student state. EvoOPD uses the measured repair utility of PI on the current student to adapt the focus, information type, and granularity of teacher feedback, allowing the acquired information to continually match the student's learning needs. We systematically evaluate EvoOPD on mathematical reasoning and code generation with Qwen3-1.7B, 4B, and 8B students. EvoOPD achieves the best overall performance in all six model-task settings, improving over the strongest baseline in each setting by an average of 2.14 percentage points in mathematics and 1.30 points in code. Further analysis shows that the relative effectiveness of PI acquisition strategies changes with student state, making a fixed strategy difficult to sustain as the best choice throughout distillation.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06540

Spatially and Compositionally Controlled Multimodal Glioblastoma MRI Synthesis with Latent Diffusion

Steven Glass, Max Van Puyvelde, Marija Pizurica, Mia Meyer, Olivier Gevaert, Willie Brink

原文摘要

Glioblastoma exhibits substantial heterogeneity in tumour morphology and composition across MRI modalities, often making available clinical datasets highly unbalanced in terms of patient pathologies. We propose a two-stage latent diffusion model (LDM) framework for the generation of explicitly controllable 2D glioblastoma MRI scans. First, a segmentation LDM generates tumour maps conditioned on location, spatial extent, axial position, and subregion composition. Second, a modality-conditioned LDM with ControlNet generates T1, T1Gd, T2, and FLAIR images adhering to the requested segmentation. On a held-out test set, generated segmentations achieved a mean centroid error of 0.842 pixels and a subregion proportion error of 0.795 percentage points. ControlNet improved Fréchet inception distance (FID) across all four modalities, reducing pooled FID from 42.59 to 36.12. An expert reader study yielded mean quality ratings of 6.60 for real images, 6.83 for ControlNet-generated images, and 6.77 for fully synthetic images.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2505.07413

Learning Penalty for Changepoint Detection via Automatic Feature Extraction

Tung L Nguyen, Toby Hocking

原文摘要

Changepoint detection identifies significant shifts in data sequences, making it important in areas like finance, genetics, and healthcare. The Optimal Partitioning algorithms efficiently detect these changes, using a penalty parameter to limit the changepoints count. Determining the optimal value for this penalty can be challenging. Traditionally, this process involved manually extracting statistical features, such as sequence length or variance to make the prediction. This study proposes a novel approach that uses recurrent networks to learn this penalty directly from raw sequences by automatically extracting features. Experiments conducted on 20 benchmark genomic datasets show that this novel method generally outperforms traditional ones in changepoint detection accuracy.

cs.LG · stat.AP

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.10334

The Alpha Blending Hypothesis: Compositing Shortcut in Deepfake Detection

Andrii Yermakov, Jan Cech, Mario Fritz, Jiri Matas

原文摘要

Recent deepfake detection methods demonstrate improved cross-dataset generalization, yet the underlying mechanisms remain underexplored. We introduce the Alpha Blending Hypothesis, positing that state-of-the-art frame-based detectors primarily function as alpha blending searchers; rather than learning semantic anomalies or specific generative neural fingerprints, they localize low-level compositing artifacts introduced during the integration of manipulated faces into target frames. We experimentally validate the hypothesis, demonstrating that deepfake detectors exhibit high sensitivity to the so-called self-blended images (SBI) and non-generative manipulations. We propose the method BlenD that leverages a large-scale, diverse dataset of real-only facial images augmented with SBI. This approach achieves the best average cross-dataset generalization on 15 compositional deepfake datasets released between 2019 and 2025 without utilizing explicitly generated deepfakes during training. Furthermore, we show that predictions from explicit blending searchers and models resilient to blending shortcuts are highly complementary, yielding a state-of-the-art AUROC of 94.0% in an ensemble configuration. The code with experiments and the trained model will be publicly released.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02897

PhotoGuider: Composition-Aware Cropping and 360° View Framing with Explainable Photographic Assessments

Yuan-Kang Lee, Kuan-Lin Chen, Chia-Che Chang, Yu-Lun Liu

原文摘要

Traditional image cropping assumes the photograph already contains the composition worth keeping, and asks only where to crop. A full 360$^{\circ}$ scene offers no such guarantee: the viewing direction in a scene has to be discovered before anything can be framed. We present PhotoGuider, a measure-then-frame method that answers both questions with compact learned scorers over one shared set of composition-aware features. The designed features are extracted using foundation and task-specific vision models and structured into four photographic tokens: Subject, Composition, Aesthetics, and Integrity. Our MLLM explainer is fine-tuned to generate composition-related explanations conditioned on images and measured token assessments. To our knowledge, PhotoGuider is the first method to combine explicit composition-based direction selection in 360$^{\circ}$ panoramas with refined framing, camera-parameter output for native re-rendering, and measurement-conditioned explanations. On two standard 2D cropping benchmarks, PhotoGuider achieves the highest average mIoU performance against ground-truth crops. In a blind ranking study, 120 participants ranked three cropping methods over 100 panoramic scenes from the public Poly Haven HDRI library, placing our framings first in 53.2% of cases, against 27.3% and 19.5% for two strong alternatives. Project page: https://ntuneillee.github.io/research/photoguider/

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.16586

When Is Complex Chunking Worth It? A Multi-Objective Evaluation of Chunking Methods at Scale

Laura Caspari, Kanishka Ghosh Dastidar, Michael Dinzinger, Jelena Mitrović, Michael Granitzer

原文摘要

Dense retrieval is commonly evaluated on benchmarks that represent each document with a single embedding, even though real-world retrieval systems often index long documents that require chunking. In these settings, the chosen chunking method not only affects retrieval quality, but also indexing throughput, query latency, and memory usage. Prior comparisons of chunking strategies have mainly focused on retrieval performance, leaving operational trade-offs underexplored. To address these issues, we evaluate eight representative chunking strategies across two scalable corpora, three embedding models, and multiple corpus sizes, measuring both retrieval effectiveness and system-level costs. Our results show that computationally expensive methods rarely provide consistent gains over simpler chunking. Instead, the best performing strategy depends on the embedding model, dataset, corpus size, and target retrieval metric. Methods with similar performance can also differ substantially in operational cost, showing that chunking should be seen as a multi-objective design decision.

cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2411.16119

Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression

Xi Zhang, Xiaolin Wu

原文摘要

It is customary to deploy uniform scalar quantization in the end-to-end optimized Neural image compression methods, instead of more powerful vector quantization, due to the high complexity of the latter. Lattice vector quantization (LVQ), on the other hand, presents a compelling alternative, which can exploit inter-feature dependencies more effectively while keeping computational efficiency almost the same as scalar quantization. However, traditional LVQ structures are designed/optimized for uniform source distributions, hence nonadaptive and suboptimal for real source distributions of latent code space for Neural image compression tasks. In this paper, we propose a novel learning method to overcome this weakness by designing the rate-distortion optimal lattice vector quantization (OLVQ) codebooks with respect to the sample statistics of the latent features to be compressed. By being able to better fit the LVQ structures to any given latent sample distribution, the proposed OLVQ method improves the rate-distortion performances of the existing quantization schemes in neural image compression significantly, while retaining the amenability of uniform scalar quantization. Code is available at: https://github.com/xzhang9308/OLVQ.

eess.IV · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02474

Gnomon4D: Learning Where and When to Focus for Geometric Motion-Grounded World-Action Modeling

Lingwei Dang, Yan Zhou, Juntong Li, Zhenhao Zhang, Yiteng Chen, Xiaoqiang Liu, Liang An, Hongwen Zhang 等 13 位作者

原文摘要

World-action models (WAMs) predict scene changes to guide robot actions, yet their RGB futures entangle state changes with appearance and lack 3D geometry. Recent WAMs add geometry as a training signal or a control interface, or build native 3D models, but decide what geometry to model rather than how the action should read it. Intuitively, control-relevant cues lie at embodiment--object interactions and their transitions, yet probing existing WAMs reveals that their action attention underweights these interactions in favor of the rest of the embodiment. To focus the action on these interactions, we present Gnomon4D, a WAM that jointly generates future video, robot actions, and GeoDelta, a video-aligned 4D geometric motion field recording the image-plane displacement and depth change of embodiment and object points. With the embodiment and objects in one field, their relative motion, which marks an interaction, can be read off. Guided by this motion and the task, Interaction-Salient Attention (InSAttn) selects where the action reads, and Transition-Anchored Aggregation (TransAgg) selects when, around grasp and release. As GeoDelta encodes surface motion rather than embodiment-specific controls, it serves as a human--robot quasi-action that links action-free pretraining on EgoManip-5000H, which we curate, to robot mid-training on Robot-30H. Gnomon4D leads on RoboTwin~2.0, VLABench, and RoboDojo, and outperforms real-robot baselines, especially under visual shifts. Project page: https://droliven.github.io/Gnomon4D.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.29300

MusTBench: Benchmarking and Advancing Temporal Grounding in Music LLMs

Daeyong Kwon, Qiyu Wu, Shinobu Kuriya, Junghyun Koo, Shuyang Cui, Zhi Zhong, Wei-Hsiang Liao, Hiromi Wakaki 等 9 位作者

原文摘要

Recent Large Audio-Language Models (LALMs) have demonstrated promising abilities in understanding musical content. However, whether their responses are grounded in the correct temporal regions of the audio remains underexplored. This limitation is particularly critical for music understanding, where key information often occurs as temporally localized events, such as instrument entries and rhythmic transitions. To address this gap, we introduce MusTBench, a reliable benchmark with stem-wise data and music-expert validation designed to evaluate temporal grounding in LALMs through five temporally grounded question-answering tasks. To further improve temporal grounding in existing models, we propose MusT, a novel four-stage temporal optimization recipe spanning music encoder adaptation, LLM adaptation, LLM supervised fine-tuning, and RL-based optimization. Experiments on MusTBench show that existing LALMs face challenges in precise temporal grounding, while MusT consistently improves performance across different LALM backbones and scales. These results highlight temporal grounding as an important challenge in current LALMs and provide a benchmark and training recipe that may support future research on temporally grounded music understanding.

cs.CL · cs.AI · cs.SD

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.16828

Prediction-Intervention Games and Invariant Sets

Linus Kühne, Felix Schur, Jonas Peters

原文摘要

We consider the following two-player game: using observational data, the leader chooses a prediction function for a response variable $Y$ from given covariates. The follower then reacts with an intervention on some covariates in the underlying structural causal model to maximize their own objective. The leader knows the intervention targets, but may have limited knowledge of the follower's objective. We call this setup a prediction-intervention game, a special case of a Stackelberg game. Finding an optimal strategy for the leader is generally difficult. To avoid severe performance loss, the leader may base their prediction on the causal parents of $Y$, or more generally on an invariant subset of covariates. We prove, for two common classes of follower objectives, that predictors based on the stable blanket, an invariant subset, are at least as good as those based on the causal parents. We further upper bound the leader's post-intervention risk by a worst-case risk over allowed interventions and strengthen existing distribution generalization results to analyze this bound: we give sufficient conditions under which stable-blanket predictors are worst-case optimal, and show by examples that these conditions cannot in general be dropped. Finally, we discuss practical strategies for settings with known and unknown graph, and test them on simulated and real-world data.

stat.ML · cs.AI · cs.LG · stat.ME

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.39329

PatchKV: Weight-Space Compensation of KV Cache

Chanryeol Lee, Chanhyuk Lee, Yeonwoo Choi, Donggyun Kim, Seunghoon Hong

原文摘要

Long-context inference with Large Language Models (LLMs) is bottlenecked by the linearly growing memory of the key-value (KV) cache. Existing compression methods reduce the cache through token eviction or approximation, but degrade sharply at aggressive compression budgets. We propose PatchKV, a training-free framework that compensates KV cache compression methods by carrying part of the context in the model's weights. PatchKV pairs an off-the-shelf compressed KV cache with a context-specific weight patch, which is computed once at context-loading time and served for downstream queries for the context. The weight patch is derived in closed form via ridge regression, by aligning the block-wise activations of context-derived reference query tokens under the full cache and the compressed cache. Once merged into the model, the patch leaves the forward graph and per-query inference cost unchanged in the single-context, multi-query setting. Across long-context QA (SCBench with up to 170K tokens, SQuAD, NIAH) and math (GSM8K) benchmarks on three model architectures, PatchKV consistently improves cache compression methods, suggesting an alternative direction to compensate them at aggressive budgets.

cs.LG

查看论文
arXiv ↗PDF ↗