4 papers
CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning
Yongxin Wang, Zhicheng Yang, Meng Cao +5
Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures. When all rollouts are wrong, gradients stal…
Seeing through Imagination: Learning Scene Geometry via Implicit Spatial World Modeling
Meng Cao, Haokun Lin, Haoyuan Li +6
Spatial reasoning, the ability to understand and interpret the 3D structure of the world, is a critical yet underdeveloped capability in Multimodal Large Language Models (MLLMs). C…
PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly
Liang Ma, Jiajun Wen, Min Lin +12
While vision-language models (VLMs) have demonstrated promising capabilities in reasoning and planning for embodied agents, their ability to comprehend physical phenomena, particul…
EACO: Enhancing Alignment in Multimodal LLMs via Critical Observation
Yongxin Wang, Meng Cao, Haokun Lin +5
Multimodal large language models (MLLMs) have achieved remarkable progress on various visual question answering and reasoning tasks leveraging instruction fine-tuning specific data…