19 citations · 19 across the 5 of their papers we have counts for
9 papers
Don't Repeat Yourself: Self-Supervised Fine-Tuning for Coverage
Eric Fithian, Kirill Skobelev, X. Y. Han
In verifiable domains such as math and coding, finding one correct solution among many attempts can matter more than the pass rate of each attempt. Post-training can concentrate la…
Fine-Tuning Fixes Mode Collapse and Over-Dispersion in LLMs
Kirill Skobelev, Eric Fithian, X. Y. Han
Recent work by Doshi and Hauser (2024), Bisbee et al. (2024), and Xie et al. (2026) raises concerns that outputs from large language models (LLMs) tend to be under-diverse: they re…
Rank-Efficient LoRA via Joint Tangent-Space Optimization under Isotropic Curvature
Zihan Zhu, Zhehang Du, Xuyang Chen +5
Low-Rank Adaptation (LoRA) is an effective approach for adapting large pretrained models by learning low-rank weight updates. In practice, the LoRA rank is used to control an adapt…
SurgPhase: Time efficient pituitary tumor surgery phase recognition via an interactive web platform
Yan Meng, Jack Cook, X. Y. Han +12
Accurate surgical phase recognition is essential for analyzing procedural workflows, supporting intraoperative decision-making, and enabling data-driven improvements in surgical ed…
A Comparative Study in Surgical AI: Potential and Limitations of Data, Compute, and Scaling
Kirill Skobelev, Eric Fithian, Yegor Baranovski +9
Recent Artificial Intelligence (AI) models have matched or exceeded human experts in several benchmarks of biomedical task performance, but surgical benchmarks in particular are of…
Enhancing Model Context Protocol (MCP) with Context-Aware Server Collaboration
Meenakshi Amulya Jayanti, X. Y. Han
The Model Context Protocol (MCP) (MCP Community, 2025) has emerged as a widely used framework for enabling LLM-based agents to communicate with external tools and services. The ori…
A Theoretical Framework for Auxiliary-Loss-Free Load Balancing of Sparse Mixture-of-Experts in Large-Scale AI Models
X. Y. Han, Yuan Zhong
In large-scale AI training, Sparse Mixture-of-Experts (s-MoE) layers enable scaling by activating only a small subset of experts per token. An operational challenge in this design…
Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path
X. Y. Han, Vardan Papyan, David L. Donoho
The recently discovered Neural Collapse (NC) phenomenon occurs pervasively in today's deep net training paradigm of driving cross-entropy (CE) loss towards zero. During NC, last-la…
Disk matrices and the proximal mapping for the numerical radius
X. Y. Han, Adrian S. Lewis
Optimal matrices for problems involving the matrix numerical radius often have fields of values that are disks, a phenomenon associated with partial smoothness. Such matrices are h…