3 papers
cs.AI2026
Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization
Yunhan Bu, Quan Zhang, Huaping Zhang +9
Multi-Hop Fact Verification requires complex reasoning across disparate evidence, posing significant challenges for Large Language Models , which may suffer from hallucinations and…
cs.CV2026
Beyond Perceptual Shortcuts: Causal-Inspired Debiasing Optimization for Generalizable Video Reasoning in Lightweight MLLMs
Jingze Wu, Quan Zhang, Hongfei Suo +2
Although reinforcement learning (RL) has significantly advanced reasoning capabilities in large multimodal language models (MLLMs), its efficacy remains limited for lightweight mod…
cs.LG2025
Explainable Benchmarking through the Lense of Concept Learning
Quannian Zhang, Michael Röder, Nikit Srivastava +2
Evaluating competing systems in a comparable way, i.e., benchmarking them, is an undeniable pillar of the scientific method. However, system performance is often summarized via a s…