7 papers
Solving Physics Olympiad via Reinforcement Learning on Physics Simulators
Mihir Prabhudesai, Aryan Satpathy, Yangmin Li +6
We have witnessed remarkable advances in LLM reasoning capabilities with the advent of DeepSeek-R1. However, much of this progress has been fueled by the abundance of internet ques…
Iterative Refinement Improves Compositional Image Generation
Shantanu Jaiswal, Mihir Prabhudesai, Nikash Bhardwaj +5
Text-to-image (T2I) models have achieved remarkable progress, yet they continue to struggle with complex prompts that require simultaneously handling multiple objects, relations, a…
Diffusion Beats Autoregressive in Data-Constrained Settings
Mihir Prabhudesai, Mengning Wu, Amir Zadeh +2
Autoregressive (AR) models have long dominated the landscape of large language models, driving progress across a wide range of tasks. Recently, diffusion-based language models have…
Self-Questioning Language Models
Lili Chen, Mihir Prabhudesai, Katerina Fragkiadaki +2
Can large language models improve without external data -- by generating their own questions and answers? We hypothesize that a pre-trained language model can improve its reasoning…
Can LLMs Lie? Investigation beyond Hallucination
Haoran Huan, Mihir Prabhudesai, Mengning Wu +2
Large language models (LLMs) have demonstrated impressive capabilities across a variety of tasks, but their increasing autonomy in real-world applications raises concerns about the…
Maximizing Confidence Alone Improves Reasoning
Mihir Prabhudesai, Lili Chen, Alex Ippoliti +3
Reinforcement learning (RL) has enabled machine learning models to achieve significant advances in many fields. Most recently, RL has empowered frontier language models to solve ch…