6 papers
CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
Congmin Zheng, Jiachen Zhu, Jianghao Lin +6
Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially for mathematical problem solving. Howeve…
Investigating Data Pruning for Pretraining Biological Foundation Models at Scale
Yifan Wu, Jiyue Jiang, Xichen Ye +9
Biological foundation models (BioFMs), pretrained on large-scale biological sequences, have recently shown strong potential in providing meaningful representations for diverse down…
EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuning
Jing-Cheng Pang, Liu Sun, Chang Zhou +10
Domain-specific large language models (LLMs), typically developed by fine-tuning a pre-trained general-purpose LLM on specialized datasets, represent a significant advancement in a…
Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs
Hao Fang, Changle Zhou, Jiawei Kong +3
Large Vision-Language Models (LVLMs) are susceptible to hallucinations, where generated responses seem semantically plausible yet exhibit little or no relevance to the input image.…
Group Relative Knowledge Distillation: Learning from Teacher's Relational Inductive Bias
Chao Li, Changhua Zhou, Jia Chen
Knowledge distillation typically transfers knowledge from a teacher model to a student model by minimizing differences between their output distributions. However, existing distill…
Text-Guided Coarse-to-Fine Fusion Network for Robust Remote Sensing Visual Question Answering
Zhicheng Zhao, Changfu Zhou, Yu Zhang +3
Remote Sensing Visual Question Answering (RSVQA) has gained significant research interest. However, current RSVQA methods are limited by the imaging mechanisms of optical sensors,…