Kembhavi, A.
Co Author Listing * Are You Smarter Than a Sixth Grader? Textbook Question Answering for Multimodal Machine Comprehension
* Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks, A
* Diagram is Worth a Dozen Images, A
* Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering
* ELASTIC: Improving CNNs With Dynamic Scaling Policies
* Eval3D: Interpretable and Fine-Grained Evaluation for 3D Generation
* EXCALIBUR: Encouraging and Evaluating Embodied Exploration
* GridToPix: Training Embodied Agents with Minimal Supervision
* Grounded Situation Recognition
* Holodeck: Language Guided Generation of 3D Embodied AI Environments
* Human Detection Using Partial Least Squares Analysis
* I can't believe there's no images!: Learning Visual Tasks Using Only Language Supervision
* Imagine This! Scripts to Compositions to Videos
* Incremental Multiple Kernel Learning for Object Recognition
* IQA: Visual Question Answering in Interactive Environments
* Iterated Learning Improves Compositionality in Large Vision-Language Models
* ManipulaTHOR: A Framework for Visual Object Manipulation
* MIMIC: Masked Image Modeling with Image Correspondences
* Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
* Motion segmentation and activity representation in crowds
* Objaverse: A Universe of Annotated 3D Objects
* Object Manipulation via Visual Target Localization
* Observing Human-Object Interactions: Using Spatial and Functional Compatibility for Recognition
* One Diffusion to Generate Them All
* Phone2Proc: Bringing Robust Robots into Our Chaotic World
* Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences
* Resource Allocation for Tracking Multiple Targets Using Particle Filters
* ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams
* RoboTHOR: An Open Simulation-to-Real Embodied AI Platform
* RobustNav: Towards Benchmarking Robustness in Embodied Navigation
* SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding
* Scene Graph Contrastive Learning for Embodied Navigation
* Seeing the Unseen: Visual Common Sense for Semantic Placement
* Simple but Effective: CLIP Embeddings for Embodied AI
* SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World
* Structured Set Matching Networks for One-Shot Part Labeling
* Towards General Purpose Vision Systems: An End-to-End Task-Agnostic Vision-Language Architecture
* Tracking Down Under: Following the Satin Bowerbird
* Two Body Problem: Collaborative Visual Task Completion
* Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action
* Vehicle Detection Using Partial Least Squares
* Visual Programming: Compositional visual reasoning without training
* Visual Room Rearrangement
* Visual Semantic Role Labeling for Video Understanding
* Webly Supervised Concept Expansion for General Purpose Vision Models
* What do navigation agents learn about their environment?
* What's Hidden in a Randomly Weighted Neural Network?
* Why Did the Person Cross the Road (There)? Scene Understanding Using Probabilistic Logic Models and Common Sense Reasoning
Includes: Kembhavi, A. Kembhavi, A.[Aniruddha]
48 for Kembhavi, A.
Kemboi, B.
Co Author Listing * User-assisted Object Detection by Segment Based Similarity Measures in Mobile Laser Scanner Data