MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification
Paper • 2603.15726 • Published • 186
Zuhao Yang
mwxely
AI & ML interests
Large Multimodal Models
Recent Activity
authored a paper about 6 hours ago
MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification authored a paper about 6 hours ago
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning upvoted a paper about 15 hours ago
Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic SimulationOrganizations
authored 2
papers about 6 hours ago
authored a
paper 9 days ago
authored a
paper 10 days ago
authored a
paper 18 days ago
authored a
paper 5 months ago
authored 7
papers 6 months ago
FACE: Evaluating Natural Language Generation with Fourier Analysis of Cross-Entropy
Paper • 2305.10307 • Published
LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
Paper • 2511.20785 • Published • 188
TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding
Paper • 2508.01699 • Published
AI-Generated Images as Data Source: The Dawn of Synthetic Era
Paper • 2310.01830 • Published
ToDRE: Visual Token Pruning via Diversity and Task Awareness for Efficient Large Vision-Language Models
Paper • 2505.18757 • Published
Versatile Transition Generation with Image-to-Video Diffusion
Paper • 2508.01698 • Published
OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe
Paper • 2511.16334 • Published • 96