Bhuwan Dhingra

When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training

Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models

How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning

Interleaved Reasoning for Large Language Models via Reinforcement Learning

Think Deep, Think Fast: Investigating Efficiency of Trained-verifier-free Inference-time-scaling Methods

Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining

Language Models (Mostly) Know When to Stop Reading

To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts

Improving Model Alignment Through Collective Intelligence of Open-Source Models

Improving Model Alignment Through Collective Intelligence of Open-Source Models

Backoff Decoding: A Language Model Inference Acceleration Framework with a Tunable Efficiency-Performance Tradeoff