cập nhật 52 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5464, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

24
Robust & Scalable Website Fingerprinting via Minimal DRAM Traffic
📄 Paper arXiv cs.CR 10 ngày trước

arXiv:2611.09422v1 Announce Type: new Abstract: Website fingerprinting attacks infer websites visited by users and threaten their privacy. These attacks are classified as on-path, which monitor network traffic, and co-located, which exploit shared system resources. Existing co-l…

🅲 hạng C
24
A Case Study of a Phishing Cluster Targeting German Universities
📄 Paper arXiv cs.CR 9 ngày trước

arXiv:2611.10698v1 Announce Type: new Abstract: In light of recent ransomware attacks, this study analyzes and measures the impact of cyberattacks against academic institutions in German-speaking areas. First, we provide an overview of 25 confirmed cyberattacks against universit…

🅲 hạng C
24
Coding Agents Propagate Vulnerabilities in Code Bases
📄 Paper arXiv cs.CR 9 ngày trước

arXiv:2611.11455v1 Announce Type: new Abstract: LLM-based coding agents are widely used to develop critical production software. Even though coding agents are known to occasionally write vulnerable code, there has not been any investigation into how code base vulnerabilities evo…

🅲 hạng C
24
Shortcuts and Boundaries: Verifiable RL Misalignment and Contextual Safety Learning
📄 Paper HF Daily Papers 10 ngày trước

Reinforcement learning (RL) can improve an agent's task capability while reinforcing behavior that violates contextual execution requirements. We study this reward-driven misalignment, including reward hacking, through verifiable reward--context conflicts, where compliant task co…

🅲 hạng C
24
Embodied Science Agents: Making Embodied Experimental Design Learnable
📄 Paper arXiv cs.AI 8 ngày trước

arXiv:2611.12958v1 Announce Type: new Abstract: Recent advances in large models have accelerated AI for Science toward agentic science, where AI agents autonomously conduct scientific discovery. Realising this vision requires closing the loop between computational reasoning and …

🅲 hạng C
24
Seeing Is Not Believing: Counterfactual Lesion Erasure Teaches a Small Medical Vision-Language Agent to Report Only What the Image Shows
📄 Paper arXiv cs.AI 8 ngày trước

arXiv:2611.13006v1 Announce Type: new Abstract: Medical vision-language models (VLMs) often report a finding because the question names it; standard benchmarks miss this. From public segmentation datasets we build counterfactual views without manual annotation: the lesion erased…

🅲 hạng C
24
Veritas: A Verifier Generation Harness for Agent Tasks
📄 Paper arXiv cs.CR 8 ngày trước

arXiv:2611.13336v1 Announce Type: cross Abstract: The effectiveness of a self-improving system relies heavily on the quality of its verifier, which judges the outcome of each improvement round. However, the verifiers of most tasks are written by hand, which is expensive and does…

🅲 hạng C
24
A Cross-Scenario Survey and Analysis of Self-Evolving Multimodal Agents
📄 Paper HF Daily Papers 9 ngày trước

Recent work shows that multimodal agents increasingly self-improve without recurring human annotation. However, each self-improvement mechanism is designed and evaluated within a single scenario, leaving its preconditions unverified under cross-scenario transfer. This survey inve…

🅲 hạng C
24
Termination Lag: Coding Agents Solve Early but Stop Late
📄 Paper HF Daily Papers 8 ngày trước

Coding agents can solve a task well before they stop working on it. We characterize termination lag--the number of steps between an agent's first correct patch and the end of its run--across five models, two agent frameworks, and three SWE-bench datasets by recording and testing …

🅲 hạng C
24
VoxLock: Target-Speaker Extraction for Voice Agents Without an Enrollment Step
📄 Paper HF Daily Papers 21 ngày trước

A voice agent's speech recognizer transcribes everyone near the microphone, including people other than the caller. I fine-tuned a public causal target-speaker extraction model (REAL-TSE, 27M parameters) on one GPU to work from a voice sample cut from the call itself, and release…

🅲 hạng C
24
Why Pay for Long Reasoning When Rewrite Do Trick? Causal Effects of Reasoning History Compaction on Future Generation and Agent Cost
📄 Paper HF Daily Papers 17 ngày trước

Reasoning substantially improves language models' ability to solve difficult problems, but long reasoning traces make these gains expensive. Efficient reasoning should express useful analysis in fewer tokens by reducing repetition and text that adds little value to solving the pr…

🅲 hạng C
24
Skill^{infty}: Recursive Self-Improvement for Agent Skill Optimization
📄 Paper HF Daily Papers 24 ngày trước

Recursive self-improvement (RSI), in which a system also improves the way it improves, is a long-standing aspiration on the path to AGI. Language agents increasingly store procedural knowledge in reusable skills. Optimizing skills offers a direct way to achieve RSI, because the o…

🅲 hạng C
24
Learning to Act with World Models by Valuing What Comes Next
📄 Paper HF Daily Papers 10 ngày trước

A sparse terminal reward tells an agent little about its steps. Much of the missing information is implicit in the environment's dynamics, because each state transition can change the conditions for success long before the reward arrives. A world model trained on real transitions…

🅲 hạng C
24
rTaste: Do Research Agents Have Taste? Evaluating Early Stage Research Judgment
📄 Paper HF Daily Papers 20 ngày trước

Do research agents have taste, the judgment of which experiments are worth running before their outcomes are known? We give six frontier models seven recent NLP papers. Each model, working as a research agent alone or as a team, proposes minimum viable experiments (MVEs), forecas…

🅲 hạng C
24
Coding or Cheating? An Investigation of Frontier Coding LLMs
📄 Paper HF Daily Papers 12 ngày trước

Frontier agentic LLMs are trained on verifiable rewards in reinforcement learning (RL) environments built from real software repositories. A passing test suite is treated as the reward for solving the task. We show that, on hard problems, frontier models often satisfy these rewar…

🅲 hạng C
24
DRAP: Dynamics-Risk Adaptive Plasticity for Continual Learning in Physical AI
📄 Paper HF Daily Papers 15 ngày trước

Continual learning in physical AI differs from conventional continual learning because small per-step policy errors can accumulate over a trajectory. Each deviation may move the agent outside the training distribution, increase subsequent prediction errors, and ultimately cause c…

🅲 hạng C
24
AscendGYM: A Cost-Aware Kernel Optimization Benchmark for Real-World Workloads on Ascend NPUs
📄 Paper arXiv cs.AI 3 ngày trước cũng có trên: HF Daily Papers

arXiv:2611.17621v1 Announce Type: new Abstract: Kernel optimization is essential for efficient large language model (LLM) training and inference on Ascend NPUs. Existing Ascend kernel benchmarks primarily focus on kernel generation, with less emphasis on the ability of agents to…

🅲 hạng C
24
DNeo: Your Parallel Draft Model Needs Better Target Feature Encoding
📄 Paper arXiv cs.AI 1 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
24
Calpha: Toward Native Biomolecular Intelligence in a General-Purpose Language Model
📄 Paper HF Daily Papers 3 ngày trước

Biomolecular foundation models predict the structures of proteins and their complexes accurately, and large language models (LLMs) reason in natural language, but the two remain separate: the abilities of the former are not part of a general-purpose LLM, and the reasoning of the …

🅲 hạng C
23
Co-Sight Harness: Externalized Control Assets and Deterministic Enforcement for Long-Horizon Business Agents
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.17696v1 Announce Type: new Abstract: Long-horizon business workflows fail in two ways: errors accumulate as a chain of activities lengthens, and the knowledge an activity needs is written in a different vocabulary from the user's request. We study whether such workflo…

🅲 hạng C
23
LLMs are Vulnerable to Malicious Requests with Indistinguishable Intent
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.17818v1 Announce Type: new Abstract: Jailbreak attacks can circumvent the safety mechanisms of Large Language Models (LLMs) and lead to the generation of harmful or policy-violating content. We first examine eight jailbreak methods against an LLM-based filter and obse…

🅲 hạng C
23
Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2510.10140v3 Announce Type: replace-cross Abstract: Deep learning-based weather forecasting (DLWF) models leverage past weather observations to generate future forecasts, supporting a wide range of downstream applications, including tropical cyclone (TC) prediction. In thi…

🅲 hạng C
23
A Foundation Model to Measure and Predict Human Behaviour
📄 Paper HF Daily Papers 1 ngày trước

Large language models (LLMs) are increasingly used to infer psychological attributes, predict individual behaviour, and simulate human populations. However, despite generating plausible responses, they often misrepresent individuals and distort population statistics. Here we intr…

🅲 hạng C
23
Abstention Direction in Large Language Models: Mechanistic Interpretability of Abstention Across Query Ambiguity, Knowledge Limits, and Safety Alignment
📄 Paper HF Daily Papers 3 ngày trước

Abstention, the withholding of a response by a large language model (LLM) under uncertainty or safety risks, is essential for trustworthy models. The causes of abstention fall into three perspectives: ambiguity in the Query (Q), limits of Model Knowledge (MK), and misalignment wi…

🅲 hạng C
23
WorldRuler: Interactive World Modeling under Configurable Rules
📄 Paper HF Daily Papers 1 ngày trước

Rules govern how player actions change interactive worlds. Different rules create distinct gameplay experiences within similar scenes and action spaces. For customizable gameplay, generative world models must follow user-defined rules beyond real-world behaviors. However, realizi…

🅲 hạng C
23
VoxMel TTS Technical Report
📄 Paper HF Daily Papers 4 ngày trước

Continuous autoregressive TTS relies on an acoustic target that enables stable next-latent modeling while preserving fine-grained acoustic details. While existing approaches employ learned compressed representations (e.g., continuous VAE latents) to render prediction tractable, t…

🅲 hạng C
23
Why is AI generated language so hard to understand?
📄 Paper Hacker News 25 ngày trước ▲ 244 · 💬 197 thảo luận

Nghiên cứu về lý do tại sao văn bản do AI tạo ra lại khó hiểu hoặc thiếu tự nhiên đối với con người. Giúp cải thiện cách viết prompt hoặc tinh chỉnh mô hình ngôn ngữ lớn (LLM).

🅲 hạng C
23
Invariant-Aware Harness Enforcement to Protect LLM Agents from Silent API Failures
📄 Paper HF Daily Papers 3 ngày trước

LLM agents answer questions by calling APIs and trusting the results. An API can fail silently. It ignores part of a request, such as a misnamed filter, yet returns HTTP 200 and a plausible but wrong result. Current fixes, such as checklists, reviewer models and LLM judges, ask t…

🅲 hạng C
23
VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding
📄 Paper HF Daily Papers 14 ngày trước

Models for physical AI tasks, such as robotics and autonomous driving, need not reason solely in language. They can use visual plans--points, bounding boxes, and trajectories--to represent spatial goals and anticipate motion. However, autoregressive vision-language models generat…

🅲 hạng C