cập nhật 59 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5418, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

23
META-IR: Meta-Introspective Reasoning for Adaptive Safety Alignment in LLM
📄 Paper arXiv cs.AI 9 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
23
SIRIS: Can LLMs Tell When Simulation Errors Matter in AI-Driven Systems Research
📄 Paper arXiv cs.AI 9 ngày trước

arXiv:2611.10329v1 Announce Type: new Abstract: LLM agents increasingly drive systems research and rely on simulators to evaluate candidate designs at scale. Simulators are imperfect by design: their modeling limitations can distort predictions yet leave the recommended design c…

🅲 hạng C
23
Beyond Query Similarity: Safety-Conditioned Cache Routing for LLM Response Reuse
📄 Paper arXiv cs.AI 9 ngày trước

arXiv:2611.10418v1 Announce Type: new Abstract: Semantic response caching reuses a cached response for a semantically similar query to improve LLM inference efficiency. However, query similarity alone can lead to unsafe reuse when safety conditions change. Existing approaches im…

🅲 hạng C
23
An Empirical Study on CVE-based Vulnerabilities Propagation from one System to another System (IntraProject vs InterProject)
📄 Paper arXiv cs.CR 8 ngày trước

arXiv:2611.14164v1 Announce Type: new Abstract: Vulnerabilities in applications, including browsers, media players, online services and document readers, etc. are often exploited and cause a serious damage. The vulnerabilities could exist in your system maybe because of some cod…

🅲 hạng C
23
Model-Based Authoring of SOC Simulation Exercises for Cybersecurity Education
📄 Paper arXiv cs.CR 8 ngày trước

arXiv:2611.14227v1 Announce Type: new Abstract: Cybersecurity training and classroom exercises with a virtual Security Operations Center (SOC) combine alerts, evidence, timeline entries, learner tasks, and assessment items that must remain consistent across an evolving incident.…

🅲 hạng C
23
SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs
📄 Paper HF Daily Papers 28 ngày trước

Policy enforcement for LLM agents has shifted from single-turn content moderation to compound, application-specific policies evaluated over multi-turn transcripts and tool-call trajectories. Fine-tuned guardrail models are efficient but degrade on compound policies, and while LLM…

🅲 hạng C
23
Beyond Benchmarks: Can Small Open-Weight Models Get Real Coding Work Done?
📄 Paper HF Daily Papers 25 ngày trước

Making an open-weight language model generate text is not the same as making it finish coding work. This retrospective empirical systems experience report follows my engineering work from July to October 2026 across coding clients, model-specific serving recipes, vLLM, SGLang, ll…

🅲 hạng C
23
LLM2Cert: LLM Synthesis of Certificates with SMT/Lean Verification
📄 Paper HF Daily Papers 29 ngày trước

Lyapunov functions and barrier certificates give state-space guarantees of stability and safety, but synthesizing and verifying them---especially for nonlinear, high-dimensional systems---remains an open challenge. Existing pipelines verify candidates with numerical solvers (sum-…

🅲 hạng C
23
EmoHarness: Boosting Multimodal Emotion Understanding with Meta-Harness Evolving
📄 Paper HF Daily Papers 11 ngày trước

Small multimodal models can misjudge emotion when words, voice, and visual cues conflict. We present EmoHarness, which runs such a model, the frozen student, inside a harness: the prompts, settings, and verification code around its calls. A human-written starting harness, the sca…

🅲 hạng C
23
On the Token Collapse Phenomenon in Textual Graph Soft Prompting
📄 Paper HF Daily Papers 28 ngày trước

Recent methods for injecting graph structure into LLM prompts include graph soft prompting, in which a graph neural network (GNN) learns graph-specific tokens that capture relational information among entities in textual prompts. G-Retriever combines graph soft prompts with a ver…

🅲 hạng C
23
Enhancing Stock Market Information Retrieval with Retrieval-Augmented Generation
📄 Paper HF Daily Papers 18 ngày trước

Natural Language Processing (NLP) has been widely applied in financial domains, enabling automated analysis and retrieval of stock market information. However, traditional NLP-based systems often struggle with maintaining contextual accuracy and generating relevant responses in d…

🅲 hạng C
22
Late Entry in Looped Language Models
📄 Paper HF Daily Papers 2 ngày trước

Looped language models deepen reasoning at a compact parameter count by iterating a shared layer stack T times per token, turning recurrence depth directly into sequential decoding latency. Conventional early-exit decoding halts after initial passes without cache completion, trun…

🅲 hạng C
22
RoughCut-Bench: A Benchmark for Automatic Video Rough-Cut with Large Vision-Language Models
📄 Paper HF Daily Papers 2 ngày trước

Video rough-cut is a core stage in media production workflows, organizing raw media materials into an initial video cut. Despite recent advances in large vision-language models (LVLMs) for video-related tasks, automatic rough-cut remains underexplored, without a comprehensive ben…

🅲 hạng C
22
NEBench R1: a Reasoning Benchmark for Evaluating Nuclear Domain Competence in Large Language Models
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.21682v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly being explored for knowledge-intensive and safety-critical applications in nuclear engineering. However, existing nuclear-domain benchmarks provide limited content coverage or focus pri…

🅲 hạng C
22
Chain-of-Thought Controllability Can Reduce Chain-of-Thought Monitorability
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.21799v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is a promising tool for detecting hidden goals, off-task behavior, and other failures in AI agents. One risk is that models could deliberately shape their reasoning to make it opaque to monitors. W…

🅲 hạng C
22
Auditors Struggle to Catch Sabotage In End-to-End Transcripts of AI Safety Research
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.21832v1 Announce Type: new Abstract: As AI systems are increasingly used to automate AI R&D, misaligned systems could sabotage research intended to improve model safety and alignment. To stress-test defenses against such sabotage, we use a human expert as a proxy sabo…

🅲 hạng C
22
Language Models Can Rewrite Their Own Weights
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.21885v1 Announce Type: new Abstract: Language models are trained once, frozen and deployed: improving one again takes another training run, and a prompt, a scaffold or extra computation at inference is gone once the task ends. A frontier model has been shown to edit t…

🅲 hạng C