3 papers
cs.CV2026
FigEx2: Visual-Conditioned Panel Detection and Captioning for Scientific Compound Figures
Jifeng Song, Arun Das, Pan Wang +3
Scientific compound figures combine multiple labeled panels into a single image. However, in a PMC-scale crawl of 346,567 compound figures, 16.3% have no caption and 1.8% only have…
cs.LG2026
HERO: Hierarchical Evidential Reasoning Optimization for Radiology Report Generation via Reason-then-Summarize
Kun Zhao, Siyuan Dai, Guodong Liu +6
Multimodal Large Language Models (MLLMs) have substantially advanced Radiology Report Generation (RRG), yet aligning them through reinforcement learning (RL) remains challenging du…
cs.CL2024
Achieving Sparse Activation in Small Language Models
Jifeng Song, Kai Huang, Xiangyu Yin +2
Sparse activation, which selectively activates only an input-dependent set of neurons in inference, is a useful technique to reduce the computing cost of Large Language Models (LLM…