74 citations · 448 across the 40 of their papers we have counts for
Showing 2025Show all
3 papers · 1 filter
cs.LG2025
VADE: Variance-Aware Dynamic Sampling via Online Sample-Level Difficulty Estimation for Multimodal RL
Zengjie Hu, Jiantao Qiu, Tianyi Bai +5
Group-based policy optimization methods like GRPO and GSPO have become standard for training multimodal models, leveraging group-wise rollouts and relative advantage estimation. Ho…
cs.LG2025
WavefrontDiffusion: Dynamic Decoding Schedule for Improved Reasoning
Haojin Yang, Rui Hu, Zequn Sun +3
Diffusion Language Models (DLMs) have shown strong potential for text generation and are becoming a competitive alternative to autoregressive models. The denoising strategy plays a…
cs.CV2025
Image Tokens Matter: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing
Weixing Wang, Zifeng Ding, Jindong Gu +4
Large Vision-Language Models (LVLMs) with discrete image tokenizers unify multimodal representations by encoding visual inputs into a finite set of tokens. Despite their effectiven…