AI.info

Jiaqi Wang

Explore Jiaqi Wang on AI.info.

• In-Context Robot Learning with VLM Agents
• Context-Adaptive Inference: A Unified Statistical and Foundation-Model View
• Encode Once, Decode Never: Reusing Audio LM Internals for Efficient Temporal Localization
• GenArena: How Can We Achieve Human-Aligned Evaluation for Visual Generation Tasks?
• SS4D: Native 4D Generative Model via Structured Spacetime Latents
• VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?
• WearVQA: A Visual Question Answering Benchmark for Wearables in Egocentric Authentic Real-world scenarios
• Think Visually, Reason Textually: Vision-Language Synergy in ARC
• CRAG-MM: Multi-modal Multi-turn Comprehensive RAG Benchmark