Kai Xu

Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning

Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling

Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling

TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning

CosyCPT: Coreness-Aware Synthetic Continued Pretraining

Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods

SQuat: Subspace-orthogonal KV Cache Quantization

Practical Epistemic Uncertainty Quantification for View Synthesis

Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs

Preference Data Annotation with Guided Density Ratios

Narcissus: Leveraging Early Training Dynamics for Unsupervised Anomaly Detection