cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5258, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

20
MemInStream: Memorizing or Merely Recognizing? Rethinking Streaming Video Memory Evaluation
📄 Paper HF Daily Papers 9 ngày trước

Streaming video understanding aims to continuously process incoming visual observations, making the retention and retrieval of relevant information increasingly important as the video history grows. Although existing benchmarks include memory-related questions, question-answering…

🅲 hạng C
20
DataPraxis: Scaling Analytics Tasks via Verified Workspace Evolution
📄 Paper arXiv cs.AI 29 ngày trước

arXiv:2610.26924v1 Announce Type: new Abstract: General-purpose agents are increasingly expected to perform professional analytics work, which requires sustained reasoning, iterative investigation, and reliable evidence. Training these capabilities requires diverse and challengi…

🅲 hạng C
20
Fix, Not Just Resample: Bounded Compiler-Guided Repair in Lean 4
📄 Paper arXiv cs.AI 29 ngày trước

arXiv:2610.26942v1 Announce Type: new Abstract: Automated theorem provers often rely on sampling language models, but proof assistants like Lean reject each failed step with a precise error message --- information that pure sampling discards. To overcome this, we introduce a bou…

🅲 hạng C
20
LightCRS: Lightweight Multi-Domain Conversational Recommendation System
📄 Paper arXiv cs.AI 29 ngày trước

arXiv:2610.26948v1 Announce Type: new Abstract: Conversational recommender systems have recently adopted vision-language models to match user dialogue intents with multimodal product information. However, extending these methods to many product domains faces a dilemma: deploying…

🅲 hạng C
20
Physical AI: Concepts, Techniques, and Challenges
📄 Paper arXiv cs.AI 29 ngày trước

arXiv:2610.27045v1 Announce Type: new Abstract: In recent years, physical artificial intelligence (physical AI) has experienced rapid development, capturing significant attention in academia and industry. However, the field has yet to reach consensus on its definition, technical…

🅲 hạng C
20
EDMA: Entropy-Driven Multimodal Answering
📄 Paper arXiv cs.AI 29 ngày trước

arXiv:2610.27120v1 Announce Type: new Abstract: Multimodal question answering (MMQA) is based on integrating heterogeneous data sources, selectively leveraging relevant modalities, and ignoring distractors. Existing approaches based on Multimodal Large Language Models (MLLMs) im…

🅲 hạng C
20
MoSAIK: Motion Search with Artificial Intelligence in K-space
📄 Paper arXiv cs.AI 29 ngày trước

arXiv:2610.27156v1 Announce Type: new Abstract: Object: Motion artefacts remain a major limitation of routine two-dimensional T2-weighted turbo spin-echo (TSE) brain MRI, reducing diagnostic confidence and often necessitating repeated acquisitions. MoSAIK (Motion Search with A…

🅲 hạng C
20
A latent control model for realistic rodent motion
📄 Paper arXiv cs.AI 29 ngày trước

arXiv:2610.27279v1 Announce Type: new Abstract: The development of embodied models of animal behavior is a major goal of the neuro-AI community. Embodied models will enhance our ability to make direct comparisons between biological and artificial agents. To make such comparisons…

🅲 hạng C
20
Evolving Self-tuning Benchmarks for Long-Horizon Tool Use
📄 Paper arXiv cs.AI 29 ngày trước

arXiv:2610.27307v1 Announce Type: new Abstract: For AI assistants to move beyond simple chat interfaces and reliably assist users with applications like Gmail, Venmo, and Slack, we need to improve their tool-use capabilities. However, existing tool use benchmarks are still limit…

🅲 hạng C
20
Modeling Authentic Research Trajectories: A Graph View of Research Ideation
📄 Paper arXiv cs.AI 29 ngày trước

arXiv:2610.27337v1 Announce Type: new Abstract: The research idea in a published paper is rarely the project's initial idea. Between the two lies a closed-loop process in which researchers run experiments, derive insights, identify challenges, explore the literature, and revise …

🅲 hạng C
20
Correcting Attribution Patching with a Few Exact Measurements
📄 Paper arXiv cs.AI 29 ngày trước

arXiv:2610.27393v1 Announce Type: new Abstract: Mechanistic interpretability asks which language model components matter for a behavior, and activation patching answers by changing one component's activation and measuring its effect, at a cost growing with components and prompts…

🅲 hạng C
20
Evidence-Grounded LLM-Assisted Android Mobile Forensic Reporting
📄 Paper arXiv cs.CR 29 ngày trước

arXiv:2610.26946v1 Announce Type: new Abstract: Large language models can assist forensic report drafting, but fluent output does not ensure evidentiary reliability. This study presents an evidence-grounded framework for evaluating LLM-assisted Android forensic reports at the at…

🅲 hạng C
20
Reliable Estimation of Differential Privacy under Selection Bias
📄 Paper arXiv cs.CR 29 ngày trước

arXiv:2610.27021v1 Announce Type: new Abstract: Statistical privacy audits are essential for verifying the theoretical privacy guarantees of differentially private (DP) mechanisms. Auditors typically use Membership Inference Attacks (MIAs) to estimate a lower bound on the true p…

🅲 hạng C
20
BR-MoE: Budgeted Semantic Release for Privacy-Preserving Traffic Analytics
📄 Paper arXiv cs.CR 29 ngày trước

arXiv:2610.27026v1 Announce Type: new Abstract: Traffic cameras support useful analysis, but their outputs can reveal private information. Replacing images with text reduces direct visual exposure. It does not place a formal bound on disclosure. The published reinforcement learn…

🅲 hạng C
20
ECHO: Revealing Review-to-Submission Linkage in Anonymous Peer Review
📄 Paper arXiv cs.CR 29 ngày trước

arXiv:2610.27044v1 Announce Type: new Abstract: Anonymous peer review protects reviewers from retaliation, yet reviewer anonymity may also be weakened by artifacts released through the review process itself. This risk is growing as many venues require submitting authors to revie…

🅲 hạng C
20
Guided Diffusion for Trustworthy Synthetic Text Generation
📄 Paper arXiv cs.CR 29 ngày trước

arXiv:2610.27259v1 Announce Type: new Abstract: The rapid evolution of Large Language Models is fueled by massive datasets, yet this reliance poses severe privacy risks, as models can inadvertently memorize and even directly output sensitive training data. Synthetic text generat…

🅲 hạng C
20
Scrambled Multiply-with-Carry Pseudorandom Number Generators
📄 Paper arXiv cs.CR 29 ngày trước

arXiv:2610.27313v1 Announce Type: new Abstract: Multiply-with-carry (MWC) generators are very fast pseudorandom number generators whose quality depends on the choice of a multiplier, and is usually assessed by applying the spectral test to an associated multiplicative congruenti…

🅲 hạng C
20
Privacy-Preserving Robustness-Guided Testing
📄 Paper arXiv cs.CR 29 ngày trước

arXiv:2610.27441v1 Announce Type: new Abstract: In industries like semi-conductors and aerospace, it is common for the design company to contract out part of the testing process to a Testing-as-a-Service (TaaS) company. In such a setup, both parties want to keep their intellectu…

🅲 hạng C