1 citations · 2 across the 19 of their papers we have counts for
20 papers
Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops
Yubo Li, Ramayya Krishnan, Rema Padman
System One models choose an agent's next action by scoring a supplied set of options in a single pass. This makes them fast and cheap, but when they choose wrongly there is nothing…
LLMs Know the Constraint But Do Not Use It: Activation Bottlenecks in Pragmatic Constraint Reasoning
Yubo Li, Ramayya Krishnan, Rema Padman
When a salient surface cue competes with an implicit feasibility constraint, LLMs often fail -- but aggregate accuracy conflates genuine constraint inference with conservative defa…
Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries
Yubo Li
Large language model agents increasingly store reusable procedures outside the model. These reusable procedures are often called \emph{skills}: they may be code functions, natural-…
Auditing Institutional Heterogeneity for Generative AI in Patient Education: A Large-Scale Study of 102 US Transplant Handbooks
Yubo Li, Rema Padman, Ramayya Krishnan
Health systems are rapidly deploying generative-AI assistants that answer patient questions from institution-authored education materials, on the premise that grounding in local co…
The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure
Yubo Li, Ramayya Krishnan, Rema Padman
Reasoning models are evaluated on single-turn benchmarks but deployed in multi-turn dialogue, where users push back on correct answers. Under sustained adversarial pressure we find…
Same Question, Different Source, Different Answer: Auditing Source-Dependence in Medical Multi-Source RAG
Yubo Li, Rema Padman, Ramayya Krishnan
A retrieval-augmented generation (RAG) system deployed over a multi-author institutional corpus can give a different answer to the same question depending on which source it retrie…
PANDO: Efficient Multimodal AI Agents via Online Skill Distillation
Yubo Li, Yidi Miao, Yuntian Shen +1
Recent advances in multimodal web agents often rely on increased inference-time computation, including rollout search, verifier passes, offline skill discovery, and specialist mode…
CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon LLM
Yubo Li, Yidi Miao
Long-horizon LLM inference turns the key--value (KV) cache into the dominant GPU memory consumer and makes per-token attention increasingly expensive. Many common eviction policies…
When Documents Disagree: Measuring Institutional Variation in Transplant Guidance with Retrieval-Augmented Language Models
Yubo Li, Ramayya Krishnan, Rema Padman
Patient education materials for solid-organ transplantation vary substantially across U.S. centers, yet no systematic method exists to quantify this heterogeneity at scale. We intr…
Consistency of Large Reasoning Models Under Multi-Turn Attacks
Yubo Li, Ramayya Krishnan, Rema Padman
Large reasoning models with reasoning capabilities achieve state-of-the-art performance on complex tasks, but their robustness under multi-turn adversarial pressure remains underex…
The Model Says Walk: Measuring whether LLMs Condition on Hidden Constraints
Yubo Li, Lu Zhang, Tianchong Jiang +2
Asked whether to walk or drive to a car wash 50 m away, most language models say walk, forgetting that the car has to be there. Such failures are usually measured by accuracy on qu…
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
Xiangyi Li, Yimin Liu, Wenbo Chen +75
Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to m…
Chain-of-Influence: Tracing Interdependencies Across Time and Features in Clinical Predictive Modelings
Yubo Li, Rema Padman
Modeling clinical time-series data is hampered by the challenge of capturing latent, time-varying dependencies among features. State-of-the-art approaches often rely on black-box m…
Time-To-Inconsistency: A Survival Analysis of Large Language Model Robustness to Adversarial Attacks
Yubo Li, Ramayya Krishnan, Rema Padman
Large Language Models (LLMs) have revolutionized conversational AI, yet their robustness in extended multi-turn dialogues remains poorly understood. Existing evaluation frameworks…
Co-Alignment: Rethinking Alignment as Bidirectional Human-AI Cognitive Adaptation
Yubo Li, Weiyi Song
Current AI alignment through RLHF follows a single directional paradigm that AI conforms to human preferences while treating human cognition as fixed. We propose a shift to co-alig…
Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models
Yubo Li, Xiaobin Shen, Yidi Miao +4
Recent advances in large language models (LLMs) have substantially improved single-turn task performance, yet real-world applications increasingly demand sophisticated multi-turn i…
Firm or Fickle? Evaluating Large Language Models Consistency in Sequential Interactions
Yubo Li, Yidi Miao, Xueying Ding +2
Large Language Models (LLMs) have shown remarkable capabilities across various tasks, but their deployment in high-stake domains requires consistent and coherent behavior across mu…
No Black Box Anymore: Demystifying Clinical Predictive Modeling with Temporal-Feature Cross Attention Mechanism
Yubo Li, Xinyu Yao, Rema Padman
Despite the outstanding performance of deep learning models in clinical prediction tasks, explainability remains a significant challenge. Inspired by transformer architectures, we…
Towards Interpretable End-Stage Renal Disease (ESRD) Prediction: Utilizing Administrative Claims Data with Explainable AI Techniques
Yubo Li, Saba Al-Sayouri, Rema Padman
This study explores the potential of utilizing administrative claims data, combined with advanced machine learning and deep learning techniques, to predict the progression of Chron…
Enhancing End Stage Renal Disease Outcome Prediction: A Multi-Sourced Data-Driven Approach
Yubo Li, Rema Padman
Objective: To improve prediction of Chronic Kidney Disease (CKD) progression to End Stage Renal Disease (ESRD) using machine learning (ML) and deep learning (DL) models applied to…