7 papers
An LMM for Precisely Grounding Elements in Documents
Yijian Lu, Chuangxin Zhao, Kai Sun +3
Visual grounding in documents is a crucial ability for Large Multimodal Models (LMMs) in areas such as document understanding, deep research and document error detection. However,…
HG-Bench: A Benchmark for Multi-Page Handwritten Answer-Region Grounding in Automated Homework Assessment
Chuangxin Zhao, Boyan Shi, Yanling Wang +7
Automated homework assessment depends not only on recognizing student answers, but also on accurately locating where each answer and each intermediate reasoning step appears in noi…
Attention-Spectrum Regularization for Replay-Free Continual Multimodal LLMs
Chuangxin Zhao, Canran Xiao, Siyuan Ma +5
Multimodal large language models (MLLMs) are increasingly required to adapt to non-stationary streams of visual domains, question types, and user instructions, yet continual fine-t…
Reasoning emerges from constrained inference manifolds in large language models
Yanbiao Ma, Fei Luo, Linfeng Zhang +10
Reasoning in large language models is predominantly evaluated through labeled benchmarks, conflating task performance with the quality of internal inference. Here we study reasonin…
ScDiVa: Masked Discrete Diffusion for Joint Modeling of Single-Cell Identity and Expression
Mingxuan Wang, Cheng Chen, Gaoyang Jiang +4
Single-cell RNA-seq profiles are high-dimensional, sparse, and unordered, causing autoregressive generation to impose an artificial ordering bias and suffer from error accumulation…
Curiosity Meets Cooperation: A Game-Theoretic Approach to Long-Tail Multi-Label Learning
Canran Xiao, Chuangxin Zhao, Zong Ke +1
Long-tail imbalance is endemic to multi-label learning: a few head labels dominate the gradient signal, while the many rare labels that matter in practice are silently ignored. We…
-GRPO: Unifying the GRPO Frameworks with Learnable Token Preferences
Yining Wang, Jinman Zhao, Chuangxin Zhao +3
Reinforcement Learning with Human Feedback (RLHF) has been the dominant approach for improving the reasoning capabilities of Large Language Models (LLMs). Recently, Reinforcement L…