1 citations · 1 across the 9 of their papers we have counts for
10 papers
From Copying to Composition: How Language Models Develop In-Context Learning
Minglai Yang, Xinyu Guo, Renxiong Wang +3
In-context learning (ICL) allows language models to adapt their behavior from instructions and demonstrations in a prompt, but accuracy alone does not reveal how contextual informa…
Rubric Dropout: A Simple Way to Mitigate Reward Hacking in Rubric-Based RL
Minglai Yang, Xinyu Guo, Zhengliang Shi +8
Rubric-based reinforcement learning, in which an LLM judge scores responses against prompt-specific criteria, has become a standard way to post-train language models on tasks witho…
TrackNetV5: Residual-Driven Spatio-Temporal Refinement and Motion Direction Decoupling for Fast Object Tracking
Haonan Tang, Yanjun Chen, Lezhi Jiang +2
The TrackNet series has established a strong baseline for fast-moving small object tracking in sports. However, existing iterations face significant limitations: V1-V3 struggle wit…
AlignSAE: Concept-Aligned Sparse Autoencoders
Minglai Yang, Xinyu Guo, Zhengliang Shi +4
Large Language Models (LLMs) encode factual knowledge within hidden parametric spaces that are difficult to inspect or control. While Sparse Autoencoders (SAEs) can decompose hidde…
Deep Research: A Systematic Survey
Zhengliang Shi, Yiqun Chen, Haitao Li +23
Large language models (LLMs) have rapidly evolved from text generators into powerful problem solvers. Yet, many open tasks demand critical thinking, multi-source, and verifiable ou…
AVFakeBench: A Comprehensive Audio-Video Forgery Detection Benchmark for AV-LMMs
Shuhan Xia, Peipei Li, Xuannan Liu +3
The threat of Audio-Video (AV) forgery is rapidly evolving beyond human-centric deepfakes to include more diverse manipulations across complex natural scenes. However, existing ben…
The Answer Lies Within: Self-Derived Rewards Enable Explainable Relation Extraction
Xinyu Guo, Zhengliang Shi, Minglai Yang +2
Despite the remarkable reasoning capabilities of large language models, they still struggle with one-shot relation extraction without predefined relation labels. We identify two pi…
QUEST: Query Optimization in Unstructured Document Analysis
Zhaoze Sun, Qiyan Deng, Chengliang Chai +6
Most recently, researchers have started building large language models (LLMs) powered data systems that allow users to analyze unstructured text documents like working with a datab…
Automated Loss function Search for Class-imbalanced Node Classification
Xinyu Guo, Kai Wu, Xiaoyu Zhang +1
Class-imbalanced node classification tasks are prevalent in real-world scenarios. Due to the uneven distribution of nodes across different classes, learning high-quality node repre…
View Transition based Dual Camera Image Fusion
Tiantian Cao, Xuan Dong, Chunli Peng +3
The dual camera system of wide-angle () and telephoto () cameras has been widely adopted by popular phones. In the overlap region, fusing the and …