Picture for Haifeng Wang

Haifeng Wang

Can Understanding and Generation Truly Benefit Together -- or Just Coexist?

Add code
Sep 11, 2025
Viaarxiv icon

An U-Net-Based Deep Neural Network for Cloud Shadow and Sun-Glint Correction of Unmanned Aerial System (UAS) Imagery

Add code
Sep 10, 2025
Viaarxiv icon

RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models

Add code
Sep 04, 2025
Viaarxiv icon

Semantic Energy: Detecting LLM Hallucination Beyond Entropy

Add code
Aug 20, 2025
Viaarxiv icon

BEE-RAG: Balanced Entropy Engineering for Retrieval-Augmented Generation

Add code
Aug 07, 2025
Viaarxiv icon

Advantageous Parameter Expansion Training Makes Better Large Language Models

Add code
May 30, 2025
Viaarxiv icon

Reinforced Informativeness Optimization for Long-Form Retrieval-Augmented Generation

Add code
May 27, 2025
Viaarxiv icon

HomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple Devices

Add code
May 26, 2025
Viaarxiv icon

TransBench: Breaking Barriers for Transferable Graphical User Interface Agents in Dynamic Digital Environments

Add code
May 23, 2025
Viaarxiv icon

ToolSpectrum : Towards Personalized Tool Utilization for Large Language Models

Add code
May 19, 2025
Viaarxiv icon