40 citations · 93 across the 31 of their papers we have counts for
35 papers
AssemblyWorld: Rethinking 3D Assembly with General-Purpose Agents
Jiahao Zhang, Yeying Fan, Moitreya Chatterjee +5
The task of 3D assembly requires translating an understanding of parts and their relationships into precise spatial arrangements. Can pretrained general-purpose agents assemble obj…
AssemblyBench: Physics-Aware Assembly of Complex Industrial Objects
Danrui Li, Jiahao Zhang, Bernhard Egger +4
Assembling objects from parts requires understanding multimodal instructions, linking them to 3D components, and predicting physically plausible 6-DoF motions for each assembly ste…
Understanding Dynamic Compute Allocation in Recurrent Transformers
Ibraheem Muhammad Moosa, Suhas Lohit, Ye Wang +2
Token-level adaptive computation seeks to reduce inference cost by allocating more computation to harder tokens and less to easier ones. However, prior work is primarily evaluated…
Auto-Vocabulary 3D Object Detection
Haomeng Zhang, Kuan-Chuan Peng, Suhas Lohit +1
Open-vocabulary 3D object detection methods are able to localize 3D boxes of classes unseen during training. Despite the name, existing methods rely on user-specified classes both…
WISE: Weighted Iterative Society-of-Experts for Robust Multimodal Multi-Agent Debate
Anoop Cherian, River Doyle, Eyal Ben-Dov +2
Recent large language models (LLMs) are trained on diverse corpora and tasks, leading them to develop complementary strengths. Multi-agent debate (MAD) has emerged as a popular way…
Towards Open-Vocabulary Multimodal 3D Object Detection with Attributes
Xinhao Xiang, Kuan-Chuan Peng, Suhas Lohit +2
3D object detection plays a crucial role in autonomous systems, yet existing methods are limited by closed-set assumptions and struggle to recognize novel objects and their attribu…
Programmatic Video Prediction Using Large Language Models
Hao Tang, Kevin Ellis, Suhas Lohit +2
The task of estimating the world model describing the dynamics of a real world process assumes immense importance for anticipating and preparing for future outcomes. For applicatio…
FreBIS: Frequency-Based Stratification for Neural Implicit Surface Representations
Naoko Sawada, Pedro Miraldo, Suhas Lohit +2
Neural implicit surface representation techniques are in high demand for advancing technologies in augmented reality/virtual reality, digital twins, autonomous navigation, and many…
Multimodal Diffusion Bridge with Attention-Based SAR Fusion for Satellite Image Cloud Removal
Yuyang Hu, Suhas Lohit, Ulugbek S. Kamilov +1
Deep learning has achieved some success in addressing the challenge of cloud removal in optical satellite images, by fusing with synthetic aperture radar (SAR) images. Recently, di…
Time-Series U-Net with Recurrence for Noise-Robust Imaging Photoplethysmography
Vineet R. Shenoy, Shaoju Wu, Armand Comas +3
Remote estimation of vital signs enables health monitoring for situations in which contact-based devices are either not available, too intrusive, or too expensive. In this paper, w…
Recovering Pulse Waves from Video Using Deep Unrolling and Deep Equilibrium Models
Vineet R Shenoy, Suhas Lohit, Hassan Mansour +2
Camera-based monitoring of vital signs, also known as imaging photoplethysmography (iPPG), has seen applications in driver-monitoring, perfusion assessment in surgical settings, af…
Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling
Xinhang Liu, Yu-Wing Tai, Chi-Keung Tang +3
Extensions of Neural Radiance Fields (NeRFs) to model dynamic scenes have enabled their near photo-realistic, free-viewpoint rendering. Although these methods have shown some poten…
Evaluating Large Vision-and-Language Models on Children's Mathematical Olympiads
Anoop Cherian, Kuan-Chuan Peng, Suhas Lohit +3
Recent years have seen a significant progress in the general-purpose problem solving abilities of large vision and language models (LVLMs), such as ChatGPT, Gemini, etc.; some of t…
TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models
Haomiao Ni, Bernhard Egger, Suhas Lohit +5
Text-conditioned image-to-video generation (TI2V) aims to synthesize a realistic video starting from a given image (e.g., a woman's photo) and a text description (e.g., "a woman is…
Multimodal 3D Object Detection on Unseen Domains
Deepti Hegde, Suhas Lohit, Kuan-Chuan Peng +2
LiDAR datasets for autonomous driving exhibit biases in properties such as point cloud density, range, and object dimensions. As a result, object detection networks trained and eva…
Equivariant Spatio-Temporal Self-Supervision for LiDAR Object Detection
Deepti Hegde, Suhas Lohit, Kuan-Chuan Peng +2
Popular representation learning methods encourage feature invariance under transformations applied at the input. However, in 3D perception tasks like object localization and segmen…
G-RepsNet: A Fast and General Construction of Equivariant Networks for Arbitrary Matrix Groups
Sourya Basu, Suhas Lohit, Matthew Brand
Group equivariance is a strong inductive bias useful in a wide range of deep learning tasks. However, constructing efficient equivariant networks for general groups and domains is…
Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis
Nithin Gopalakrishnan Nair, Anoop Cherian, Suhas Lohit +4
Conditional generative models typically demand large annotated training sets to achieve high-quality synthesis. As a result, there has been significant interest in designing models…
Tensor Factorization for Leveraging Cross-Modal Knowledge in Data-Constrained Infrared Object Detection
Manish Sharma, Moitreya Chatterjee, Kuan-Chuan Peng +2
The primary bottleneck towards obtaining good recognition performance in IR images is the lack of sufficient labeled training data, owing to the cost of acquiring such data. Realiz…
Pixel-Grounded Prototypical Part Networks
Zachariah Carmichael, Suhas Lohit, Anoop Cherian +2
Prototypical part neural networks (ProtoPartNNs), namely PROTOPNET and its derivatives, are an intrinsically interpretable approach to machine learning. Their prototype learning sc…
Are Deep Neural Networks SMARTer than Second Graders?
Anoop Cherian, Kuan-Chuan Peng, Suhas Lohit +2
Recent times have witnessed an increasing number of applications of deep neural networks towards solving tasks that require superior cognitive abilities, e.g., playing Go, generati…
Cross-Modal Knowledge Transfer Without Task-Relevant Source Data
Sk Miraj Ahmed, Suhas Lohit, Kuan-Chuan Peng +2
Cost-effective depth and infrared sensors as alternatives to usual RGB sensors are now a reality, and have some advantages over RGB in domains like autonomous navigation and remote…
Learning Partial Equivariances from Data
David W. Romero, Suhas Lohit
Group Convolutional Neural Networks (G-CNNs) constrain learned features to respect the symmetries in the selected group, and lead to better generalization when these symmetries app…
Rotation-Invariant Autoencoders for Signals on Spheres
Suhas Lohit, Shubhendu Trivedi
Omnidirectional images and spherical representations of shapes cannot be processed with conventional 2D convolutional neural networks (CNNs) as the unwrapping leads to large d…