5 papers · 1 filter
AR-GRPO: Training Autoregressive Image Generation Models via Reinforcement Learning
Shihao Yuan, Yahui Liu, Yang Yue +5
Inspired by the success of reinforcement learning (RL) in refining large language models (LLMs), we propose AR-GRPO, an approach to integrate online RL training into autoregressive…
TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos
Fanheng Kong, Jingyuan Zhang, Hongzhi Zhang +7
Videos are unique in their integration of temporal elements, including camera, scene, action, and attribute, along with their dynamic relationships over time. However, existing ben…
Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval
Fanheng Kong, Jingyuan Zhang, Yahui Liu +8
Multimodal information retrieval (MIR) faces inherent challenges due to the heterogeneity of data sources and the complexity of cross-modal alignment. While previous studies have i…
Guiding the Experts: Semantic Priors for Efficient and Focused MoE Routing
Chengxi Min, Wei Wang, Yahui Liu +4
Mixture-of-Experts (MoE) models have emerged as a promising direction for scaling vision architectures efficiently. Among them, Soft MoE improves training stability by assigning ea…
Clapper: Compact Learning and Video Representation in VLMs
Lingyu Kong, Hongzhi Zhang, Jingyuan Zhang +4
Current vision-language models (VLMs) have demonstrated remarkable capabilities across diverse video understanding applications. Designing VLMs for video inputs requires effectivel…