AI.info

Serena Yeung-Levy

Explore Serena Yeung-Levy on AI.info.

• UniT: Unified Multimodal Chain-of-Thought Test-time Scaling
• Seeing Is Believing? A Benchmark for Multimodal Large Language Models on Visual Illusions and Anomalies
• PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVR
• RadDiff: Describing Differences in Radiology Image Sets with Natural Language
• Transductive Visual Programming: Evolving Tool Libraries from Experience for Spatial Reasoning
• CryoHype: Reconstructing a thousand cryo-EM structures with transformer-based hypernetworks
• Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models
• Data or Language Supervision: What Makes CLIP Better than DINO?