8 papers
X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining
Miracle Kang, Lights Shi, Lucy Liang +10
Modern Vision-Language-Action (VLA) models must bridge pretrained vision-language reasoning and precise continuous robot control. Existing action tokenizers discretize actions prim…
Cascaded Sparse Autoencoders Learn Multi-Level Visual Concepts in Multimodal LLMs
Yusong Zhao, Hengyi Wang, Tanuja Ganu +2
Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language tasks, yet their internal visual representations remain difficult to interpret. Spa…
CLEAR-HPV: Interpretable concept discovery for human-papillomavirus-associated morphology in whole-slide histology
Weiyi Qin, Yingci Liu-Swetz, Shiwei Tan +1
Human papillomavirus (HPV) status is a critical determinant of prognosis and treatment response in head and neck and cervical cancers. Although attention-based multiple instance le…
OTPrune: Distribution-Aligned Visual Token Pruning via Optimal Transport
Xiwen Chen, Wenhui Zhu, Gen Li +9
Multi-modal large language models (MLLMs) achieve strong visual-language reasoning but suffer from high inference cost due to redundant visual tokens. Recent work explores visual t…
Causal Decoding for Hallucination-Resistant Multimodal Large Language Models
Shiwei Tan, Hengyi Wang, Weiyi Qin +3
Multimodal Large Language Models (MLLMs) deliver detailed responses on vision-language tasks, yet remain susceptible to object hallucination (introducing objects not present in the…
Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading
Hanfei Yu, Xingqi Cui, Hong Zhang +1
Large Language Models (LLMs) have gained immense success in revolutionizing various applications, including content generation, search and recommendation, and AI-assisted operation…