collaborators

5 papers

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.CL2025

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…

cs.PL2025

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…

cs.CV2025

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…

cs.CV2025

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…