HuggingFace
ISO: An RLVR-Native Optimization Stack
Reinforcement learning with verifiable rewards (RLVR) is rapidly advancing the reasoning capabilities of language mod...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers
Text-to-image diffusion transformers (DiTs) jointly process text and image tokens, yet their internal computation dur...
HuggingFace
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents
LLM agent failures are difficult to debug because the step where an error surfaces is often not the one that caused i...
HuggingFace
Generative World Renderer at the Speed of Play
Generative world renderer AlayaRenderer receives structured world states exported from physics engines and synthesize...
HuggingFace
EduPanel: A Three-Agent LLM Judge for Teaching Videos -- Reliability, Complementarity, and Human Trust Calibration
Teaching videos are becoming a major medium for education, creating a growing need for scalable evaluation of their p...
HuggingFace
Where Should Optimizer State Live? Tiered State Allocation for Memory-Efficient Mixture-of-Experts Training
Optimizer state is the largest single line item in the memory budget of mixture-of-experts (MoE) training: on a 6.78B...
HuggingFace
Delineate Anything v2: A Global Foundation Model for Field Delineation
Accurate agricultural field boundary delineation at large scale is a foundational task for food security, supply chai...
HuggingFace
Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges
Multimodal humor in memes, cartoons, and comics remains difficult for AI systems because intended meaning depends on ...
HuggingFace
Can Multimodal Large Language Models Understand OCT?
Optical coherence tomography (OCT) imaging is essential for the diagnosis and treatment of retinal diseases. Although...
HuggingFace
ShotPlan: Cinematic Video Generation with Learnable Planning Token
Current video generation models achieve impressive results in single-shot generation, yet remain limited in cinematic...
HuggingFace
Diagnosing and Calibrating Tool-Call Boundary Drift in Multi-Teacher On-Policy Distillation
Agentic language models must learn when to call tools, when to consume tool responses, and when to answer directly. T...
HuggingFace
Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning
Egocentric videos of human manipulation provide scalable supervision for embodied intelligence, yet existing resource...