activity
20162026
most citedRevisiting Unreasonable Effectiveness of Data in Deep Learning Era

304 citations · 708 across the 22 of their papers we have counts for

collaborators
Showing 2023Show all

10 papers · 1 filter

cs.CV2023

Analyzing Modular Approaches for Visual Question Decomposition

Apoorv Khandelwal, Ellie Pavlick, Chen Sun

Modular neural networks without additional training have recently been shown to surpass end-to-end neural networks on challenging vision-language tasks. The latest such methods sim…

cs.LG2023

Emergence of Abstract State Representations in Embodied Sequence Modeling

Tian Yun, Zilai Zeng, Kunal Handa +4

Decision making via sequence modeling aims to mimic the success of language models, where actions taken by an embodied agent are modeled as tokens to predict. Despite their promisi…

cs.CV2023

AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?

Qi Zhao, Shijie Wang, Ce Zhang +5

Can we better anticipate an actor's future actions (e.g. mix eggs) by knowing what commonly happens after his/her current action (e.g. crack eggs)? What if we also know the longer-…

cs.CV2023

Does Visual Pretraining Help End-to-End Reasoning?

Chen Sun, Calvin Luo, Xingyi Zhou +2

We aim to investigate whether end-to-end learning of visual reasoning can be achieved with general-purpose neural networks, with the help of visual pretraining. A positive result w…

cs.LG2023

Goal-Conditioned Predictive Coding for Offline Reinforcement Learning

Zilai Zeng, Ce Zhang, Shijie Wang +1

Recent work has demonstrated the effectiveness of formulating decision making as supervised learning on offline-collected trajectories. Powerful sequence models, such as GPT or BER…

cs.CV2023

How can objects help action recognition?

Xingyi Zhou, Anurag Arnab, Chen Sun +1

Current state-of-the-art video models process a video clip as a long sequence of spatio-temporal tokens. However, they do not explicitly model objects, their interactions across th…