Tarun Suresh

SWERank: Software Issue Localization with Code Ranking

InvBench: Can LLMs Accelerate Program Verification with Invariant Synthesis?

SuperCoder: Assembly Program Superoptimization with Large Language Models

Fun2spec: Code Contract Synthesis At Scale

Pessimistic Reward Modeling in RLHF against Reward Hacking

DINGO: Constrained Inference for Diffusion LLMs

CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis

IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking

CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking

CRANE: Reasoning with constrained LLM generation

Tamper-Resistant Safeguards for Open-Weight LLMs

Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actions