arXiv:2508.00910v3 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success in software engineering tasks when trained with executable runtime environments, particularly in resolving GitHub issues. However, such runtime environments are ofte…
⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5486, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.19299v1 Announce Type: new Abstract: Staged LLM agents make market and social simulators realistic, but one 102-day run of a 200-agent, ten-index market simulator issues 203,100 language-model calls and returns one realization. Conventional low-compute distillation dr…
🧩 Chức năng: Sinh video bằng AI (text/ảnh → video)
SDK Python không chính thức hỗ trợ toàn bộ dòng mô hình video Seedance (2.0, 2.5, 2.5 Flash, Mini) của ByteDance. Cung cấp API Text-to-Video, Image-to-Video chuẩn 1080p và tính năng duy trì khuôn mặt, nhân vật nhất quán.
arXiv:2611.22085v1 Announce Type: new Abstract: Professional work involves under-specified assignments, where relevant information is spread across workplace applications and may conflict or change over time. To evaluate how well frontier agents can perform economically valuable…
arXiv:2611.22589v1 Announce Type: new Abstract: Large Language Models (LLMs) enable honeypots to generate responses and deceptive artefacts on demand, yet existing approaches evaluate generated content one reply at a time and leave open whether artefacts that jointly describe a …
🧩 Chức năng: Sinh video bằng AI (text/ảnh → video) · Hậu kỳ & ghép (ComfyUI, upscale, nội suy khung, phụ đề)
Every video model ranked by price per second, with a realistic workflow budget.
arXiv:2611.21923v1 Announce Type: cross Abstract: Published face-privacy methods report protection above 90% against black-box recognition models. That number comes from an evaluation protocol with two independent defects, reported in a measure that cannot size either one. The i…
arXiv:2611.20459v1 Announce Type: new Abstract: AI models can exhibit deceptive behaviors such as strategically underperforming on evaluations (sandbagging), faking alignment, or covertly acting on behalf of a hidden principal. Safe deployment therefore requires auditing techniq…
Technical Write-up: https://www.justinchavez.com/blog/isometric-sf-how/ Hi HN! Showcasing this fun project. I took 1300 square miles of the SF Bay Area from Google Photorealistic 3D Tiles and transformed them into a cohesive pixel map. It's really fun to explore and stumble upon …
Web agents powered by large language and vision-language models are increasingly applied to realistic browser work that spans heterogeneous applications, multimodal content, and stateful workflows. However, existing reproducible web-agent benchmarks cover only a small number of w…
arXiv:2611.14769v1 Announce Type: new Abstract: Arena-style rankings of language models are a widely used evaluation framework in online leaderboards, research papers, and model evaluation in production. These rankings aim to realistically assess model performance using pairwise…
arXiv:2611.15316v1 Announce Type: new Abstract: Building and evaluating security tools for IoT firmware requires targets whose weaknesses are known in ad- vance and can be reproduced in a running device. Two problems remain: (1) firmware collected from real-world products provid…
Posted by info on Nov 16 Hi oss-security, I maintain BenchProctor, an Apache-2.0 corpus for evaluating static application security scanners. Release 2026.11.16 replaces the July corpus, which I withdrew after finding bad safe labels and cases whose modeled flow was unrealis…