AI.info
Fei Huang
Explore Fei Huang on AI.info.
- DevicesWorld: Benchmarking Cross-Device Agents in Heterogeneous Environments
- P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling
- CorpusQA: A 10 Million Token Benchmark for Corpus-Level Analysis and Reasoning
- Understanding Generalization in Role-Playing Models via Information Theory
- IterResearch: Rethinking Long-Horizon Agents with Interaction Scaling
- LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability
- OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents
- Tongyi DeepResearch Technical Report
- Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model
- ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling