activity
20242026
collaborators

6 papers

cs.LG2026

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…

cs.AI2026

TRACE: Capability-Targeted Agentic Training

Hangoo Kang, Tarun Suresh, Jon Saad-Falcon +1

Models often fail to complete agentic tasks because they lack core capabilities required by the target environment. However, mainstream approaches for addressing these failures typ…

cs.AI2025

TRAP: Targeted Redirecting of Agentic Preferences

Hangoo Kang, Jehyeok Yeon, Gagandeep Singh

Autonomous agentic AI systems powered by vision-language models (VLMs) are rapidly advancing toward real-world deployment, yet their cross-modal reasoning capabilities introduce ne…

cs.LG2025

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…

cs.LG2024

Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment

Jason Vega, Junsheng Huang, Gaokai Zhang +3

Safety alignment of Large Language Models (LLMs) has recently become a critical objective of model developers. In response, a growing body of work has been investigating how safety…

cs.LG2024

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…