HuggingFace
MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation
Recent advances in video diffusion models (VDMs) have enabled high-fidelity video synthesis. However, generating mirr...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Business Arena: Benchmarking LLM Agents in a Realistic Marketplace
Running a business is a challenging form of intelligent work. Operators must infer opportunities from partial signals...
HuggingFace
Cultivar: A Contrastive and Locale-Oriented Translation Benchmark for Investigating Contamination and Localisation Robustness
Multilingual translation benchmarks are typically sourced in English and translated into other languages, treating la...
HuggingFace
On-Policy Self-Distillation without Any Supervision
On-policy (Self-)Distillation (OPD / OPSD) has shown strong potential for post-training large language models (LLMs)....
HuggingFace
Beyond Starry Night: Shortcut-Aware Control-State Planning for Artist-Grounded Text to Image Generation
Artist-grounded image generation requires more than appending an artist name to a prompt. Image models often respond ...
HuggingFace
Beyond Sequence Order: Syntax-Informed Positional Embeddings for Transformers
Positional embeddings (PE) in Transformers encode token distance and order but are largely agnostic to syntactic stru...
HuggingFace
The Next Screenshot Knows: Gated Hindsight Distillation for Mobile GUI Agents
GUI agents are commonly trained offline from successful interaction trajectories. Standard training decomposes each t...
arXiv
Agentic Auto-Research is Fuzz Testing
Autonomous research agents can generate experiments faster than researchers can validate them. Researchers have respo...
arXiv
Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy
Advances in advanced artificial intelligence tools have sparked research in robot autonomy, but the development of su...
arXiv
Towards Expert-level Medical AI for Real-time Video Consultations
Audio-visual interaction is the standard for patient-physician consultations, enabling natural communication and effe...
arXiv
Stealing Reasoning Traces from Proprietary LLM APIs
Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to prot...
arXiv
Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains
We introduce Sci-VBench, a comprehensive benchmark for evaluating knowledge- and reasoning-intensive video generation...