14 papers
Generative Skill Composition for LLM Agents
Xinyu Zhao, Zhen Tan, Vaishnav Tadiparthi +5
Recent LLM agents benefit from skills for solving complex tasks. Skills encapsulate modular packages of procedural knowledge and instructions for performing specialized tasks, such…
Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer Review
Xinyu Zhao, Rana Muhammad Shahroz Khan, Zhen Xu +2
The integration of Large Language Models (LLMs) and Multimodal LLMs (MLLMs) into scientific peer-review workflows introduces novel and significant risks for adversarial manipulatio…
S2Aligner: Pair-Efficient and Transferable Pre-Training for Sparse Text-Attributed Graphs
Yuhan Wang, Haopeng Zhang, Yibo Ding +6
Pre-training on text-attributed graphs (TAGs) is central to building transferable graph foundation models, where LLM-as-Aligner methods align graph and text representations through…
FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning
Xu Shen, Song Wang, Zhen Tan +5
Large language models (LLMs) increasingly rely on Chain-of-Thought (CoT) prompting to improve problem-solving and provide seemingly transparent explanations. However, growing evide…
Dialogue is Better Than Monologue: Instructing Medical LLMs via Strategical Conversations
Zijie Liu, Xinyu Zhao, Jie Peng +5
Current medical AI systems often fail to replicate real-world clinical reasoning, as they are predominantly trained and evaluated on static text and question-answer tasks. These tu…
Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints
Guanjie Chen, Xinyu Zhao, Yucheng Zhou +3
Diffusion Transformers (DiT) have emerged as a powerful architecture for image and video generation, offering superior quality and scalability. However, their practical application…