AI.info
Xiaobin Hu
Explore Xiaobin Hu on AI.info.
- Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning
- Towards Generalized Multi-Image Editing for Unified Multimodal Models
- Guiding a Diffusion Transformer with the Internal Dynamics of Itself
- The devil is in the details: Enhancing Video Virtual Try-On via Keyframe-Driven Details Injection
- Med-CMR: A Fine-Grained Benchmark Integrating Visual Evidence and Clinical Logic for Medical Complex Multimodal Reasoning
- Boosting Reasoning in Large Multimodal Models via Activation Replay
- DiP: Taming Diffusion Models in Pixel Space
- VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
- Towards One-step Causal Video Generation via Adversarial Self-Distillation
- IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment