7 papers
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
Sudong Wang, Weiquan Huang, Xiaomin Yu +9
The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiab…
A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models
Duo Li, Zuhao Yang, Xiaoqin Zhang +2
Discrete diffusion-based multimodal large language models (dMLLMs) have emerged as a promising alternative to autoregressive MLLMs thanks to their advantages in parallel decoding a…
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
Keming Wu, Zuhao Yang, Kaichen Zhang +24
Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning…
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
Zuhao Yang, Kaichen Zhang, Sudong Wang +7
Training large multimodal models (LMMs) via reinforcement learning (RL) to natively invoke video-processing tools (e.g., cropping) has become a promising route to long-video unders…
ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance
Duo Li, Zuhao Yang, Xiaoqin Zhang +2
Visual token pruning aims to compress and prune redundant visual tokens which play a critical role in efficient inference with large vision-language models (LVLMs). However, most e…
TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding
Zuhao Yang, Yingchen Yu, Yunqing Zhao +2
Video Temporal Grounding (VTG) aims to precisely identify video event segments in response to textual queries. The outputs of VTG tasks manifest as sequences of events, each define…