HuggingFace
Qwen-Image-2.0-RL Technical Report
We present Qwen-Image-2.0-RL, a post-training pipeline that applies reinforcement learning from human feedback (RLHF)...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning
Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications....
HuggingFace
NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning
Reinforcement learning (RL) post-training improves the reward alignment of flow-based generators, but often degrades ...
HuggingFace
Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents
Web-agent benchmarks overwhelmingly measure depth -- pinning one obscure answer behind a chain of constraints -- whil...
HuggingFace
ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering
Knowledge-based Visual Question Answering (KB-VQA) requires models to combine image understanding with external knowl...
HuggingFace
Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots
We study whether we can learn novel manipulation skills from human actions to a bi-manual robot with parallel gripper...
HuggingFace
Boundary-Aware Context Grounding for A Low-Channel EEG Agent
Large language models (LLMs) can make scientific software easier to use. However, a general model does not automatica...
HuggingFace
Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)
I describe my solution to the LeHome Challenge 2026, an ICRA 2026 competition on bimanual garment folding. The system...
HuggingFace
Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement
Vision-Language-Action (VLA) models can generalize across diverse manipulation tasks, but their imitation-learning-ba...
HuggingFace
GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems
Multi-agent systems (MAS) built on large language models (LLMs) provide a promising framework for solving complex tas...
HuggingFace
Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents
Voice agents face a fundamental tension: the reasoning, retrieval, and tool use that make foundation models capable a...
HuggingFace
When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models
Multi-model LLM systems such as routing, voting, cascades, fusion, and mixture-of-agents are used to beat single-mode...