3 citations · 7 across the 10 of their papers we have counts for
13 papers
ThunderSyncRL: Lossless Acceleration of Agentic Reinforcement Learning
Seil Kang, Hangoo Kang, Tarun Suresh +4
Language models are moving beyond generating answers to pursuing long-horizon goals in interactive environments. Post-training these agents requires long, heterogeneous trajectorie…
Block Parallelism For Efficient Distributed Long-Context Diffusion Language Model Training
Tarun Suresh, Pranshu Chaturvedi, Hangoo Kang +4
Block diffusion language models (BDLMs) combine autoregressive dependencies across blocks with parallel denoising within blocks, but long-context training is constrained by distrib…
Training Hybrid Block Diffusion Language Models with Partial Bidirectionality
Pranshu Chaturvedi, Parth Shroff, Tarun Suresh +2
High-throughput long-context generation is one of the central challenges for large language models. Generation is typically memory-bandwidth-bound rather than compute-bound: each d…
Unsupervised Diffusion Solver for Combinatorial Optimization via Combinatorial Adjoint Matching
Shengyu Feng, Tarun Suresh, Yiming Yang
Diffusion-based neural solvers have shown strong promise for combinatorial optimization (CO), but existing methods typically rely on supervised training with large collections of n…
BEAVER: An Efficient Deterministic LLM Verifier
Tarun Suresh, Nalin Wadhwa, Debangshu Banerjee +1
As large language models (LLMs) transition from research prototypes to production systems, practitioners often need reliable methods to verify model outputs and characterize tail r…
DINGO: Constrained Inference for Diffusion LLMs
Tarun Suresh, Debangshu Banerjee, Shubham Ugare +2
Diffusion LLMs have emerged as a promising alternative to conventional autoregressive LLMs, offering significant potential for improved runtime efficiency. However, existing diffus…
Learning a Pessimistic Reward Model in RLHF
Yinglun Xu, Hangoo Kang, Tarun Suresh +2
This work proposes `PET', a novel pessimistic reward fine-tuning method, to learn a pessimistic reward model robust against reward hacking in offline reinforcement learning from hu…
CRANE: Reasoning with constrained LLM generation
Debangshu Banerjee, Tarun Suresh, Shubham Ugare +2
Code generation, symbolic math reasoning, and other tasks require LLMs to produce outputs that are both syntactically and semantically correct. Constrained LLM generation is a prom…
IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking
Shubham Ugare, Rohan Gumaste, Tarun Suresh +2
Large Language Models (LLMs) are widely used for tasks such as natural language and code generation, but their outputs often suffer from issues like hallucination, toxicity, and in…
Is The Watermarking Of LLM-Generated Code Robust?
Tarun Suresh, Shubham Ugare, Gagandeep Singh +1
We present the first in depth study on the robustness of existing watermarking techniques applied to code generated by large language models (LLMs). As LLMs increasingly contribute…
SynCode: LLM Generation with Grammar Augmentation
Shubham Ugare, Tarun Suresh, Hangoo Kang +2
LLMs are widely used in complex AI applications. These applications underscore the need for LLM outputs to adhere to a specific format, for their integration with other components…
Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actions
Yinglun Xu, Tarun Suresh, Rohan Gumaste +10
Preference-based reinforcement learning (PBRL) in the offline setting has succeeded greatly in industrial applications such as chatbots. A two-step learning framework where one app…
Incremental Randomized Smoothing Certification
Shubham Ugare, Tarun Suresh, Debangshu Banerjee +2
Randomized smoothing-based certification is an effective approach for obtaining robustness certificates of deep neural networks (DNNs) against adversarial attacks. This method cons…