activity
20242026
collaborators

9 papers

cs.LG2026

Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference

Noah Golowich, Fan Chen, Dhruv Rohatgi +4

Inference-time methods that aggregate and prune multiple samples have emerged as a powerful paradigm for steering large language models, yet we lack any principled understanding of…

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…

cs.LG2025

To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning

Yuda Song, Dhruv Rohatgi, Aarti Singh +1

Partial observability is a notorious challenge in reinforcement learning (RL), due to the need to learn complex, history-dependent policies. Recent empirical successes have used pr…

cs.LG2025

Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking

Dhruv Rohatgi, Abhishek Shetty, Donya Saless +4

Test-time algorithms that combine the generative power of language models with process verifiers that assess the quality of partial generations offer a promising lever for elicitin…

cs.LG2025

Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration

Dylan J. Foster, Zakaria Mhammedi, Dhruv Rohatgi

Language model alignment (or, reinforcement learning) techniques that leverage active exploration -- deliberately encouraging the model to produce diverse, informative responses --…

cs.LG2025

Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification

Dhruv Rohatgi, Adam Block, Audrey Huang +2

Next-token prediction with the logarithmic loss is a cornerstone of autoregressive sequence modeling, but, in practice, suffers from error amplification, where errors in the model…