AI.info
Hao Zhang
Explore Hao Zhang on AI.info.
- OSWorld-Pro: Process-based Evaluation for Computer Use Agents
- DRACO: a Cross-Domain Benchmark for Deep Research Accuracy, Completeness, and Objectivity
- Kimi K2.5: Visual Agentic Intelligence
- MagicFuse: Single Image Fusion for Visual and Semantic Reinforcement
- Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning
- ShieldedCode: Learning Robust Representations for Virtual Machine Protected Code
- Video-KTR: Reinforcing Video Reasoning via Key Token Attribution
- FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction
- Multimodal Multi-Agent Empowered Legal Judgment Prediction
- d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation
- HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation
- PTalker: Personalized Speech-Driven 3D Talking Head Animation via Style Disentanglement and Modality Alignment
- Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed
- Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench
- CREward: A Type-Specific Creativity Reward Model
- Real Deep Research for AI, Robotics and Beyond
- Scaling Language-Centric Omnimodal Representation Learning