AI.info

Kai-Wei Chang

Explore Kai-Wei Chang on AI.info.

• From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop
• OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks
• MotionEdit: Benchmarking and Learning Motion-Centric Image Editing
• FronTalk: Benchmarking Front-End Development as Conversational Code Generation with Multi-Modal Feedback
• LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training
• BRIEF-Pro: Universal Context Compression with Short-to-Long Synthesis for Fast and Accurate Multi-Hop Reasoning
• HoneyBee: Data Recipes for Vision-Language Reasoners
• Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy
• Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models