cập nhật 54 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.3 giờ sau khi CVE được công bố (n = 5300, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

29
ALIoTh: Orchestrating Multi-Agent LLMs for Autonomous IoT Penetration Testing
📄 Paper arXiv cs.CR 2 ngày trước

arXiv:2611.25809v1 Announce Type: new Abstract: Penetration testing in Internet of Things (IoT) environments, especially those composed of various different devices, e.g., smart plugs, smart cameras, and smart doors, presents great challenges across the phases of information gat…

🅲 hạng C
28
DSFlow: A Neuro-Symbolic Data Workflow Agent with Statistical Diagnostic Guardrails
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.25111v1 Announce Type: new Abstract: Data science workflows often require tools that presume non-trivial technical knowledge. Large language models (LLMs) reduce this barrier, but a gap remains between flexible general-purpose agents and statistically controlled pipel…

🅲 hạng C
28
Mem2Fair: Online Fairness Control for Text-to-Video Generation via Fair Memory
📄 Paper arXiv cs.AI 5 ngày trước

arXiv:2611.19215v1 Announce Type: new Abstract: Text-to-video (T2V) generation models can produce systematically unfair demographic outcomes when prompts leave protected attributes unspecified. For example, prompts describing nurses without specifying gender may disproportionate…

🅲 hạng C
23
GUARD: Stabilizing Recursive Self-Improvement with Regret Guidance
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.23476v1 Announce Type: new Abstract: Autonomous AI agents pair a frozen base model with an editable harness of prompts, skills, tool rules, and memory. Recursive self-improvement (RSI) adapts this harness from experience without weight updates, yet self-editing withou…

🅲 hạng C
23
A CPU Inside an LLM: Zero-Gradient Compilation of Exact Circuits into Pretrained Weights
📄 Paper HF Daily Papers 3 ngày trước

Pretrained language models (LMs) remain unreliable on exact multi-digit arithmetic without gradient fine-tuning or external tool interpreters. We introduce closed-form, zero-gradient circuit-grafting primitives that compile deterministic computation directly into pretrained LM we…

🅲 hạng C
23
From Sorry to QED: Refining LLM Math Proofs via Angelic Execution
📄 Paper arXiv cs.AI 4 ngày trước

arXiv:2611.22103v1 Announce Type: new Abstract: Large language models (LLMs) can now generate Lean proof scripts that capture the high-level structure of many mathematical arguments. However, these scripts frequently fail on complex theorems: a single missing side condition or m…

🅲 hạng C
22
Steering Automated Scientific Discovery via Audited Epistemic Exploration
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.25214v1 Announce Type: new Abstract: Scientific discovery requires revisiting the hypotheses in light of new evidence and identifying promising directions beyond those already explored. However, research agents often make claims that are not supported by their observa…

🅲 hạng C
22
Learning Networked Dynamical Systems via Neural ODE-based Graph Structure Inference
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.25586v1 Announce Type: new Abstract: Inferring the latent interaction graph from multivariate time series is fundamental to understanding complex dynamical systems in neuroscience, biology, and physics. Despite recent progress in neural relational inference, most meth…

🅲 hạng C
21
Playing the SMR Game with Existential Honesty
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.24586v1 Announce Type: new Abstract: State machine replication protocols are usually proven secure in the honest-Byzantine setting, which requires an honest supermajority of validators. Deployed systems offer no such guarantee: validators participate for profit and ma…

🅲 hạng C
21
DNeo: Your Parallel Draft Model Needs Better Target Feature Encoding
📄 Paper arXiv cs.AI 4 ngày trước cũng có trên: HF Daily Papers

arXiv:2611.21925v1 Announce Type: new Abstract: Speculative-diffusion decoding uses a small parallel drafter model to generate b draft tokens in one forward pass, which then undergo parallel verification via a larger target model. Faster inference can be achieved when multiple d…

🅲 hạng C
21
Suppressing the Shortcut Hidden Behind the Gains of VideoLLM Fine-Tuning
📄 Paper HF Daily Papers 3 ngày trước

Supervised fine-tuning (SFT) is the stage in which Video Large Language Models (VideoLLMs) advance their capability to reason over video. However, the VideoLLM also learns to answer from textual regularities of its training data, a shortcut that bypasses the video. The regulariti…

🅲 hạng C
20
Replay, Don't Resample: Off-Policy Consolidation of Long-Horizon RL Experts
📄 Paper HF Daily Papers 4 ngày trước

Frontier post-training follows a common recipe: train one expert per domain with reinforcement learning (RL), then consolidate the experts into one model via multi-teacher on-policy distillation (MOPD). Such consolidation is expensive: the student samples in every environment aga…

🅲 hạng C
20
Match and Correct: A Repeated Computational Motif in Evoformer Layers
📄 Paper arXiv cs.AI 5 ngày trước

arXiv:2611.19016v1 Announce Type: new Abstract: Triangle attention and triangle multiplicative updates form key components of the Evoformer, and were introduced specifically to encourage consistency with the triangle inequality. Yet whether representational changes over layers r…

🅲 hạng C
20
Policy Optimization With Multiple Verifiers via Pareto Rankings
📄 Paper arXiv cs.AI 5 ngày trước

arXiv:2611.19064v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become an important approach to improving the reasoning capabilities of large language models. In tasks such as code generation and instruction following, multiple verifiers…

🅲 hạng C
20
Out of Sight, Still in Mind: Token Compression for Omni-LLMs
📄 Paper HF Daily Papers 5 ngày trước

The goal of this paper is to reduce the input token cost of Omni-modal large language models (Omni-LLMs) at inference time. Omni-LLMs reason jointly over audio, video and text, but the cost of the three streams is highly unbalanced: visual tokens account for the vast majority of …

🅲 hạng C
20
Tractable Importance Sampling for Monte Carlo Privacy Accounting
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.17596v1 Announce Type: new Abstract: Evaluating tight Differential Privacy (DP) parameters for DP matrix factorization with privacy amplification by sampling requires analyzing high-dimensional, correlated Gaussian mixtures. Because integrating these mixture distribut…

🅲 hạng C
20
On the Same Track: Privacy Leaks in Electric Rail Transport via Magnetic Fields
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.18312v1 Announce Type: new Abstract: Inertial sensors of smartphones are a well-known privacy risk, as they allow inferring sensitive user movements and activity without explicit permissions. Among these sensors, the magnetometer has received little attention, as it i…

🅲 hạng C