5 papers
ReMAP: Restoring the Perceptual Cycle with Reasoning-Time Latent Visual Memory
Hao Jiang, Zhanyu Guo, Chenwei Wu +11
As multimodal large language models (MLLMs) reason for longer, attention to the initial visual input diminishes, weakening visual grounding. Visual memory reintroduces visual evide…
MiCo: Mutual Information Coverage Optimization through Semantic Erasure Modeling for Efficient MLLM Inference
Tinghao Wang, Yichen Guo, Qizhe Zhang +11
Multimodal large language models (MLLMs) have demonstrated impressive performance in multimodal understanding, but processing large numbers of visual tokens results in high computa…
STAR-Pro: Stage-Wise Token Adaptive Reduction with Progressive Refinement for Efficient Large Vision-Language Models
Yichen Guo, Tinghao Wang, Qizhe Zhang +15
Large vision-language models (LVLMs) achieve strong multimodal understanding, but the hundreds to thousands of visual tokens they process impose substantial computational overhead,…
Do Robotic World Models Really Follow Actions? Diagnosing and Aligning Action-Conditioned Generation for Policy Learning
Sixiang Chen, Jiaming Liu, Jixian Wu +11
Action-conditioned world models increasingly serve as learned simulators for robotic policy improvement, yet their reliability rests on an unverified assumption: generated futures…
TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference
Tinghao Wang, Yichen Guo, Rui Huang +13
Multimodal large language models (MLLMs) have achieved strong multimodal reasoning capabilities, but their efficiency is limited by the large number of visual tokens, which introdu…