13 citations · 34 across the 15 of their papers we have counts for
17 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…
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…
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…
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…
Unified Multimodal Discrete Diffusion
Alexander Swerdlow, Mihir Prabhudesai, Siddharth Gandhi +2
Multimodal generative models that can understand and generate across multiple modalities are dominated by autoregressive (AR) approaches, which process tokens sequentially from lef…
Video Diffusion Alignment via Reward Gradients
Mihir Prabhudesai, Russell Mendonca, Zheyang Qin +2
We have made significant progress towards building foundational video diffusion models. As these models are trained using large-scale unsupervised data, it has become crucial to ad…
Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback
Mihir Prabhudesai, Tsung-Wei Ke, Alexander C. Li +2
The advancements in generative modeling, particularly the advent of diffusion models, have sparked a fundamental question: how can these models be effectively used for discriminati…
Aligning Text-to-Image Diffusion Models with Reward Backpropagation
Mihir Prabhudesai, Anirudh Goyal, Deepak Pathak +1
Text-to-image diffusion models have recently emerged at the forefront of image generation, powered by very large-scale unsupervised or weakly supervised text-to-image training data…
Your Diffusion Model is Secretly a Zero-Shot Classifier
Alexander C. Li, Mihir Prabhudesai, Shivam Duggal +2
The recent wave of large-scale text-to-image diffusion models has dramatically increased our text-based image generation abilities. These models can generate realistic images for a…
Test-time Adaptation with Slot-Centric Models
Mihir Prabhudesai, Anirudh Goyal, Sujoy Paul +6
Current visual detectors, though impressive within their training distribution, often fail to parse out-of-distribution scenes into their constituent entities. Recent test-time ada…
CoCoNets: Continuous Contrastive 3D Scene Representations
Shamit Lal, Mihir Prabhudesai, Ishita Mediratta +2
This paper explores self-supervised learning of amodal 3D feature representations from RGB and RGB-D posed images and videos, agnostic to object and scene semantic content, and eva…
3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators
Hsiao-Yu Fish Tung, Zhou Xian, Mihir Prabhudesai +2
We propose an action-conditioned dynamics model that predicts scene changes caused by object and agent interactions in a viewpoint-invariant 3D neural scene representation space, i…
Disentangling 3D Prototypical Networks For Few-Shot Concept Learning
Mihir Prabhudesai, Shamit Lal, Darshan Patil +3
We present neural architectures that disentangle RGB-D images into objects' shapes and styles and a map of the background scene, and explore their applications for few-shot 3D obje…
3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations
Mihir Prabhudesai, Shamit Lal, Hsiao-Yu Fish Tung +3
We propose a system that learns to detect objects and infer their 3D poses in RGB-D images. Many existing systems can identify objects and infer 3D poses, but they heavily rely on…
Embodied Language Grounding with 3D Visual Feature Representations
Mihir Prabhudesai, Hsiao-Yu Fish Tung, Syed Ashar Javed +3
We propose associating language utterances to 3D visual abstractions of the scene they describe. The 3D visual abstractions are encoded as 3-dimensional visual feature maps. We inf…