13 citations · 44 across the 37 of their papers we have counts for
15 papers · 1 filter
EEGChaT: A Transformer-Based Modular Channel Selector for SEEG Analysis
Chen Wang, Yansen Wang, Dongqi Han +2
Analyzing stereoelectroencephalography (SEEG) signals is critical for brain-computer interface (BCI) applications and neuroscience research, yet poses significant challenges due to…
Hybrid OCR-LLM Framework for Enterprise-Scale Document Information Extraction Under Copy-heavy Task
Zilong Wang, Xiaoyu Shen
Information extraction from copy-heavy documents, characterized by massive volumes of structurally similar content, represents a critical yet understudied challenge in enterprise d…
A Tale of LLMs and Induced Small Proxies: Scalable Small Language Models for Knowledge Mining
Sipeng Zhang, Longfei Yun, Zilong Wang +2
At the core of Deep Research is knowledge mining, the task of extracting structured information from massive unstructured text in response to user instructions. Large language mode…
DermINO: Hybrid Pretraining for a Versatile Dermatology Foundation Model
Jingkai Xu, De Cheng, Xiangqian Zhao +27
Skin diseases impose a substantial burden on global healthcare systems, driven by their high prevalence (affecting up to 70% of the population), complex diagnostic processes, and a…
SoM-1K: A Thousand-Problem Benchmark Dataset for Strength of Materials
Qixin Wan, Zilong Wang, Jingwen Zhou +5
Foundation models have shown remarkable capabilities in various domains, but their performance on complex, multimodal engineering problems remains largely unexplored. We introduce…
A Disease-Centric Vision-Language Foundation Model for Precision Oncology in Kidney Cancer
Yuhui Tao, Zhongwei Zhao, Zilong Wang +17
The non-invasive assessment of increasingly incidentally discovered renal masses is a critical challenge in urologic oncology, where diagnostic uncertainty frequently leads to the…
Agent Lightning: Train ANY AI Agents with Reinforcement Learning
Xufang Luo, Yuge Zhang, Zhiyuan He +5
We present Agent Lightning, a flexible and extensible framework that enables Reinforcement Learning (RL)-based training of Large Language Models (LLMs) for any AI agent. Unlike exi…
GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models
Zilong Wang, Xiang Zheng, Xiaosen Wang +3
Text-to-image (T2I) models such as Stable Diffusion have advanced rapidly and are now widely used in content creation. However, these models can be misused to generate harmful cont…
Training Language Models to Generate Quality Code with Program Analysis Feedback
Feng Yao, Zilong Wang, Liyuan Liu +7
Code generation with large language models (LLMs), often termed vibe coding, is increasingly adopted in production but fails to ensure code quality, particularly in security (e.g.,…
RRO: LLM Agent Optimization Through Rising Reward Trajectories
Zilong Wang, Jingfeng Yang, Sreyashi Nag +5
Large language models (LLMs) have exhibited extraordinary performance in a variety of tasks while it remains challenging for them to solve complex multi-step tasks as agents. In pr…
The Price of Format: Diversity Collapse in LLMs
Longfei Yun, Chenyang An, Zilong Wang +2
Instruction-tuned large language models (LLMs) employ structured templates, such as role markers and special tokens, to enforce format consistency during inference. However, we ide…
Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs
Zhihe Yang, Xufang Luo, Zilong Wang +4
Reinforcement learning (RL) has become a cornerstone for enhancing the reasoning capabilities of large language models (LLMs), with recent innovations such as Group Relative Policy…
Exploring Interpretability for Visual Prompt Tuning with Cross-layer Concepts
Yubin Wang, Xinyang Jiang, De Cheng +4
Visual prompt tuning offers significant advantages for adapting pre-trained visual foundation models to specific tasks. However, current research provides limited insight into the…
Evaluating Harmful Memorization in LLM Code Generation
Lizhe Zhang, Wentao Chen, Li Zhong +3
Assessing memorization in LLM code generation is challenging because code reuse is not inherently harmful. Correct programs often share APIs, templates, and algorithmic idioms, so…
Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLM's Nest
Letian Peng, Zilong Wang, Feng Yao +1
Massive high-quality data, both pre-training raw texts and post-training annotations, have been carefully prepared to incubate advanced large language models (LLMs). In contrast, f…