2.4k citations · 8.4k across the 129 of their papers we have counts for
13 papers · 1 filter
ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding
Le Xue, Mingfei Gao, Chen Xing +6
The recognition capabilities of current state-of-the-art 3D models are limited by datasets with a small number of annotated data and a pre-defined set of categories. In its 2D coun…
Best- Search Algorithm for Neural Text Generation
Jiacheng Xu, Caiming Xiong, Silvio Savarese +1
Modern natural language generation paradigms require a good decoding strategy to obtain quality sequences out of the model. Beam search yields high-quality but low diversity output…
Online Distribution Shift Detection via Recency Prediction
Rachel Luo, Rohan Sinha, Yixiao Sun +5
When deploying modern machine learning-enabled robotic systems in high-stakes applications, detecting distribution shift is critical. However, most existing methods for detecting d…
Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
Anthony Meng Huat Tiong, Junnan Li, Boyang Li +2
Visual question answering (VQA) is a hallmark of vision and language reasoning and a challenging task under the zero-shot setting. We propose Plug-and-Play VQA (PNP-VQA), a modular…
Retrospectives on the Embodied AI Workshop
Matt Deitke, Dhruv Batra, Yonatan Bisk +36
We present a retrospective on the state of Embodied AI research. Our analysis focuses on 13 challenges presented at the Embodied AI Workshop at CVPR. These challenges are grouped i…
LAVIS: A Library for Language-Vision Intelligence
Dongxu Li, Junnan Li, Hung Le +3
We introduce LAVIS, an open-source deep learning library for LAnguage-VISion research and applications. LAVIS aims to serve as a one-stop comprehensive library that brings recent a…
Minkowski Tracker: A Sparse Spatio-Temporal R-CNN for Joint Object Detection and Tracking
JunYoung Gwak, Silvio Savarese, Jeannette Bohg
Recent research in multi-task learning reveals the benefit of solving related problems in a single neural network. 3D object detection and multi-object tracking (MOT) are two heavi…
CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning
Hung Le, Yue Wang, Akhilesh Deepak Gotmare +2
Program synthesis or code generation aims to generate a program that satisfies a problem specification. Recent approaches using large-scale pretrained language models (LMs) have sh…
Masked Unsupervised Self-training for Label-free Image Classification
Junnan Li, Silvio Savarese, Steven C. H. Hoi
State-of-the-art computer vision models are mostly trained with supervised learning using human-labeled images, which limits their scalability due to the expensive annotation cost.…
OmniXAI: A Library for Explainable AI
Wenzhuo Yang, Hung Le, Tanmay Laud +2
We introduce OmniXAI (short for Omni eXplainable AI), an open-source Python library of eXplainable AI (XAI), which offers omni-way explainable AI capabilities and various interpret…
Long Document Summarization with Top-down and Bottom-up Inference
Bo Pang, Erik Nijkamp, Wojciech Kryściński +3
Text summarization aims to condense long documents and retain key information. Critical to the success of a summarization model is the faithful inference of latent representations…
CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
Erik Nijkamp, Bo Pang, Hiroaki Hayashi +5
Program synthesis strives to generate a computer program as a solution to a given problem specification, expressed with input-output examples or natural language descriptions. The…
ACID: Action-Conditional Implicit Visual Dynamics for Deformable Object Manipulation
Bokui Shen, Zhenyu Jiang, Christopher Choy +4
Manipulating volumetric deformable objects in the real world, like plush toys and pizza dough, bring substantial challenges due to infinite shape variations, non-rigid motions, and…