13 citations · 36 across the 27 of their papers we have counts for
29 papers
Train4Merge: RL or SFT---Which Yields Better Teachers for OPD-Based Model Merging?
Jingyuan Huang, Zuming Huang, Yucheng Shi +4
Domain experts trained from a shared checkpoint can transfer their specialized capabilities to a single student through on-policy distillation (OPD). Existing research primarily fo…
OPERA: Aligning Open-Ended Reasoning via Objective Perplexity-based Reinforcement Learning
Wenxuan Jiang, Zining Fan, Zijian Zhang +6
Reinforcement Learning (RL) has enabled LLMs to excel in objective reasoning tasks such as mathematics and code generation. However, applying RL to open-ended tasks, such as creati…
SAERec: Constructing Fine-grained Interpretable Intents Priors via Sparse Autoencoders for Recommendation
Jiangnan Xia, Xuansheng Wu, Yu Yang +2
Intent-based recommender systems have gained significant attention for improving accuracy and interpretability by modeling the underlying motivations behind user behaviors. Most ex…
Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding
Jingyuan Huang, Zuming Huang, Yucheng Shi +4
GUI grounding requires vision-language models (VLMs) to identify small target elements in high-resolution screenshots and predict precise screen coordinates. On-policy self-distill…
Learnable Assessment Skills for LLM-based Automated Scoring: Rubric Construction via Iterative Optimization
Yun Wang, Xin Xia, Xuansheng Wu +2
LLM-based automated scoring approaches near-human performance, but scaling to new tasks remains bottlenecked by the per-item human configuration of upstream stages such as rubric c…
TR-ICRL: Test-Time Rethinking for In-Context Reinforcement Learning
Wenxuan Jiang, Yuxin Zuo, Zijian Zhang +8
In-Context Reinforcement Learning (ICRL) enables Large Language Models (LLMs) to learn online from external rewards directly within the context window. However, a central challenge…
BRIDGE the Gap: Mitigating Bias Amplification in Automated Scoring of English Language Learners via Inter-group Data Augmentation
Yun Wang, Xuansheng Wu, Jingyuan Huang +3
In the field of educational assessment, automated scoring systems increasingly rely on deep learning and large language models (LLMs). However, these systems face significant risks…
Enhancing LLM Steering through Sparse Autoencoder-Based Vector Refinement
Anyi Wang, Xuansheng Wu, Dong Shu +2
Steering has emerged as a promising approach in controlling large language models (LLMs) without modifying model parameters. However, most existing steering methods rely on large-s…
AutoSCORE: Enhancing Automated Scoring with Multi-Agent Large Language Models via Structured Component Recognition
Yun Wang, Zhaojun Ding, Xuansheng Wu +3
Automated scoring plays a crucial role in education by reducing the reliance on human raters, offering scalable and immediate evaluation of student work. While large language model…
LMOD+: A Comprehensive Multimodal Dataset and Benchmark for Developing and Evaluating Multimodal Large Language Models in Ophthalmology
Zhenyue Qin, Yang Liu, Yu Yin +13
Vision-threatening eye diseases pose a major global health burden, with timely diagnosis limited by workforce shortages and restricted access to specialized care. While multimodal…
Common Inpainted Objects In-N-Out of Context
Tianze Yang, Tyson Jordan, Ruitong Sun +2
We present Common Inpainted Objects In-N-Out of Context (COinCO), a novel dataset addressing the scarcity of out-of-context examples in existing vision datasets. By systematically…
Concept-Centric Token Interpretation for Vector-Quantized Generative Models
Tianze Yang, Yucheng Shi, Mengnan Du +4
Vector-Quantized Generative Models (VQGMs) have emerged as powerful tools for image generation. However, the key component of VQGMs -- the codebook of discrete tokens -- is still n…
Artificial Intelligence Bias on English Language Learners in Automatic Scoring
Shuchen Guo, Yun Wang, Jichao Yu +7
This study investigated potential scoring biases and disparities toward English Language Learners (ELLs) when using automatic scoring systems for middle school students' written re…
Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
Haiyan Zhao, Xuansheng Wu, Fan Yang +3
Linear concept vectors effectively steer LLMs, but existing methods suffer from noisy features in diverse datasets that undermine steering robustness. We propose Sparse Autoencoder…
Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders
Dong Shu, Xuansheng Wu, Haiyan Zhao +2
Sparse Autoencoders (SAEs) have recently emerged as powerful tools for interpreting and steering the internal representations of large language models (LLMs). However, conventional…
Towards Trustworthy GUI Agents: A Survey
Yucheng Shi, Wenhao Yu, Jingyuan Huang +3
Graphical User Interface (GUI) agents extend large language models from text generation to action execution in real-world digital environments. Unlike conversational systems, GUI a…
A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
Dong Shu, Xuansheng Wu, Haiyan Zhao +4
Large Language Models (LLMs) have transformed natural language processing, yet their internal mechanisms remain largely opaque. Recently, mechanistic interpretability has attracted…
Interpreting and Steering LLMs with Mutual Information-based Explanations on Sparse Autoencoders
Xuansheng Wu, Jiayi Yuan, Wenlin Yao +2
Large language models (LLMs) excel at handling human queries, but they can occasionally generate flawed or unexpected responses. Understanding their internal states is crucial for…
Self-Regularization with Sparse Autoencoders for Controllable LLM-based Classification
Xuansheng Wu, Wenhao Yu, Xiaoming Zhai +1
Modern text classification methods heavily rely on contextual embeddings from large language models (LLMs). Compared to human-engineered features, these embeddings provide automati…
LMOD: A Large Multimodal Ophthalmology Dataset and Benchmark for Large Vision-Language Models
Zhenyue Qin, Yu Yin, Dylan Campbell +6
The prevalence of vision-threatening eye diseases is a significant global burden, with many cases remaining undiagnosed or diagnosed too late for effective treatment. Large vision-…
Leveraging Large Language Models with Chain-of-Thought and Prompt Engineering for Traffic Crash Severity Analysis and Inference
Hao Zhen, Yucheng Shi, Yongcan Huang +2
Harnessing the power of Large Language Models (LLMs), this study explores the use of three state-of-the-art LLMs, specifically GPT-3.5-turbo, LLaMA3-8B, and LLaMA3-70B, for crash s…
Unveiling Scoring Processes: Dissecting the Differences between LLMs and Human Graders in Automatic Scoring
Xuansheng Wu, Padmaja Pravin Saraf, Gyeonggeon Lee +3
Large language models (LLMs) have demonstrated strong potential in performing automatic scoring for constructed response assessments. While constructed responses graded by humans a…
Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models
Yili Wang, Kaixiong Zhou, Ninghao Liu +2
Sharpness-aware minimization (SAM) has received increasing attention in computer vision since it can effectively eliminate the sharp local minima from the training trajectory and m…
Rethinking Independent Cross-Entropy Loss For Graph-Structured Data
Rui Miao, Kaixiong Zhou, Yili Wang +3
Graph neural networks (GNNs) have exhibited prominent performance in learning graph-structured data. Considering node classification task, based on the i.i.d assumption among node…