collaborators

10 papers

cs.LG2026

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon

Huaqing Zhang, Jingchu Gai, Juno Kim +2

Online imitation learning (IL), particularly on-policy distillation, has emerged as a strong LLM post-training approach, often outperforming offline supervised fine-tuning (SFT). Y…

cs.LG2026

A computational phase transition for learning-to-sample from Ising models

Andrej Risteski, Thuy-Duong Vuong

We study \emph{learning-to-sample} -- a basic algorithmic task underlying generative modeling -- for Ising models, a standard testbed for algorithmic ideas in both theoretical comp…

cs.AI2026

Understanding and Mitigating Premature Confidence for Better LLM Reasoning

Jingchu Gai, Guanning Zeng, Christina Baek +4

Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute. Improving rea…

cs.LG2026

The tractability landscape of diffusion alignment: regularization, rewards, and computational primitives

Ankur Moitra, Andrej Risteski, Dhruv Rohatgi

Inference-time reward alignment asks how to turn a pre-trained diffusion model with base law into a sampler that favors a reward while remaining close to . Since there i…

cs.LG2026

CodePDE: An Inference Framework for LLM-driven PDE Solver Generation

Shanda Li, Tanya Marwah, Junhong Shen +4

Partial differential equations (PDEs) are fundamental to modeling physical systems, yet solving them remains a complex challenge. Traditional numerical solvers rely on expert knowl…

cs.LG2026

Steering diffusion models with quadratic rewards: a fine-grained analysis

Ankur Moitra, Andrej Risteski, Dhruv Rohatgi

Inference-time algorithms are an emerging paradigm in which pre-trained models are used as subroutines to solve downstream tasks. Such algorithms have been proposed for tasks rangi…