8 citations · 16 across the 16 of their papers we have counts for
17 papers
Harnessing Image Question Dependence for Better VLM Test-time Reinforcement Learning
Xinrui He, Ting-Wei Li, Junting Wang +4
Test-time reinforcement learning can adapt vision-language models (VLMs) to unlabeled target data, but its effectiveness is fundamentally limited by the reliability of self-generat…
Does Accuracy Equal Evidence? Reasoning Faithfulness under KV Cache Compression
Mengting Ai, Jingrui He, Yue Guo
KV cache compression is commonly evaluated by final-answer accuracy, implicitly assuming that preserving the answer also preserves the reasoning that supports it. We test this assu…
SafeImpute: Reliable Clinical Data Imputation via Conformal Selection
Xinrui He, Mengting Ai, Junting Wang +2
Clinical care often relies on key laboratory indicators, yet real-world patient visits are sparse and tests are ordered irregularly, leading to pervasive missingness. While many im…
Harnessing Generalist Agents for Contextualized Time Series
Zihao Li, Kaifeng Jin, Yuanchen Bei +8
Time series are often embedded in rich contexts that are essential for holistic modeling. Moreover, real-world practitioners often require end-to-end workflows for analyzing tempor…
Code as Agent Harness
Xuying Ning, Katherine Tieu, Dongqi Fu +39
Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineerin…
Heterogeneous Scientific Foundation Model Collaboration
Zihao Li, Jiaru Zou, Feihao Fang +6
Agentic large language model systems have demonstrated strong capabilities. However, their reliance on language as the universal interface fundamentally limits their applicability…
MedConceal: A Benchmark for Clinical Hidden-Concern Reasoning Under Partial Observability
Yikun Han, Joey Chan, Jingyuan Chen +3
Patient-clinician communication is an asymmetric-information problem: patients often do not disclose fears, misconceptions, or practical barriers unless clinicians elicit them skil…
MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains
Xuying Ning, Dongqi Fu, Tianxin Wei +7
With the increasing demand for step-wise, cross-modal, and knowledge-grounded reasoning, multimodal large language models (MLLMs) are evolving beyond the traditional fixed retrieve…
Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning
Sirui Chen, Yunzhe Qi, Mengting Ai +4
Supervised fine-tuning (SFT) relies critically on selecting training data that most benefits a model's downstream performance. Gradient-based data selection methods such as TracIn…
Competing Visions of Ethical AI: A Case Study of OpenAI
Melissa Wilfley, Mengting Ai, Madelyn Rose Sanfilippo
Introduction. AI Ethics is framed distinctly across actors and stakeholder groups. We report results from a case study of OpenAI analysing ethical AI discourse. Method. Research ad…
A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents
Tianxin Wei, Ting-Wei Li, Zhining Liu +26
Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilitie…
AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning
Jiaru Zou, Ling Yang, Yunzhe Qi +5
Agentic reinforcement learning has advanced large language models (LLMs) to reason through long chain-of-thought trajectories while interleaving external tool use. Existing approac…
Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
Tianxin Wei, Noveen Sachdeva, Benjamin Coleman +12
Statefulness is essential for large language model (LLM) agents to perform long-term planning and problem-solving. This makes memory a critical component, yet its management and ev…
NIRVANA: Structured Pruning Reimagined for Large Language Model Compression
Mengting Ai, Tianxin Wei, Sirui Chen +1
While structured pruning presents a highly effective pathway for accelerating Large Language Model (LLM) inference, existing methods frequently suffer from significant performance…
ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration
Mengting Ai, Tianxin Wei, Yifan Chen +7
Mixture-of-Experts (MoE) Transformer, the backbone architecture of multiple phenomenal language models, leverages sparsity by activating only a fraction of model parameters for eac…
PyG-SSL: A Graph Self-Supervised Learning Toolkit
Lecheng Zheng, Baoyu Jing, Zihao Li +9
Graph Self-Supervised Learning (SSL) has emerged as a pivotal area of research in recent years. By engaging in pretext tasks to learn the intricate topological structures and prope…
APEX: Adaptive and Extreme Summarization for Personalized Knowledge Graphs
Zihao Li, Dongqi Fu, Mengting Ai +1
Knowledge graphs (KGs), which store an extensive number of relational facts, serve various applications. Recently, personalized knowledge graphs (PKGs) have emerged as a solution t…