activity
20122023
most citedSkip-Thought Vectors

722 citations · 2k across the 47 of their papers we have counts for

collaborators
Showing 2022Show all

10 papers · 1 filter

cs.CV20227 cited

Composing Ensembles of Pre-trained Models via Iterative Consensus

Shuang Li, Yilun Du, Joshua B. Tenenbaum +2

Large pre-trained models exhibit distinct and complementary capabilities dependent on the data they are trained on. Language models such as GPT-3 are capable of textual reasoning b…

cs.CV2022

Totems: Physical Objects for Verifying Visual Integrity

Jingwei Ma, Lucy Chai, Minyoung Huh +4

We introduce a new approach to image forensics: placing physical refractive objects, which we call totems, into a scene so as to protect any photograph taken of that scene. Totems…

cs.CV2022

Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction

Yining Hong, Kaichun Mo, Li Yi +4

This paper studies the problem of fixing malfunctional 3D objects. While previous works focus on building passive perception models to learn the functionality from static 3D object…

cs.CV202214 cited

ComPhy: Compositional Physical Reasoning of Objects and Events from Videos

Zhenfang Chen, Kexin Yi, Yunzhu Li +4

Objects' motions in nature are governed by complex interactions and their properties. While some properties, such as shape and material, can be identified via the object's visual a…

cs.RO20224 cited

Correcting Robot Plans with Natural Language Feedback

Pratyusha Sharma, Balakumar Sundaralingam, Valts Blukis +5

When humans design cost or goal specifications for robots, they often produce specifications that are ambiguous, underspecified, or beyond planners' ability to solve. In these case…

cs.CV20221 cited

Learning Program Representations for Food Images and Cooking Recipes

Dim P. Papadopoulos, Enrique Mora, Nadiia Chepurko +3

In this paper, we are interested in modeling a how-to instructional procedure, such as a cooking recipe, with a meaningful and rich high-level representation. Specifically, we prop…