2 papers
cs.AI2026
Let Credit Follow Computation: Architecture-Aware Credit Transport for Large Language Model Reinforcement Learning
Qifan Shi, Zhaolu Kang, Chenghua Zhu
Credit assignment in large-language-model reinforcement learning (LLM RL) can be separated into three objects: evidence about success, a transport operator that converts this evide…
cs.CV2026
COMET: Contrastive Motion-Enhanced Temporal Reasoning for Video Multimodal Large Language Models
Chenghua Zhu, Zhaolu Kang, Qifan Shi +8
Video multimodal large language models have advanced significantly, yet fine-grained motion-temporal understanding remains fragile. The core bottleneck is not only sparse frame sam…