5 papers
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…
UltraLLaDA: Scaling the Context Length to 128K for Diffusion Large Language Models
Guangxin He, Shen Nie, Fengqi Zhu +6
Diffusion LLMs have attracted growing interest, with plenty of recent work emphasizing their great potential in various downstream tasks; yet the long-context behavior of diffusion…
Local Success Does Not Compose: Benchmarking Large Language Models for Compositional Formal Verification
Xu Xu, Xin Li, Xingwei Qu +2
We introduce DafnyCOMP, a benchmark for evaluating large language models (LLMs) on compositional specification generation in Dafny. Unlike prior benchmarks that focus on single-fun…
Multi-Step Visual Reasoning with Visual Tokens Scaling and Verification
Tianyi Bai, Zengjie Hu, Fupeng Sun +7
Multi-modal large language models (MLLMs) have achieved remarkable capabilities by integrating visual perception with language understanding, enabling applications such as image-gr…
Hallucination at a Glance: Controlled Visual Edits and Fine-Grained Multimodal Learning
Tianyi Bai, Yuxuan Fan, Jiantao Qiu +7
Multimodal large language models (MLLMs) have achieved strong performance on vision-language tasks but still struggle with fine-grained visual differences, leading to hallucination…