no code implementations • 23 Feb 2024 • Yuejiang Liu, Alexandre Alahi
Steering the behavior of a strong model pre-trained on internet-scale data can be difficult due to the scarcity of competent supervisors.
no code implementations • 7 Dec 2023 • Yuejiang Liu, Ahmad Rahimi, Po-Chien Luan, Frano Rajič, Alexandre Alahi
Modeling spatial-temporal interactions among neighboring agents is at the heart of multi-agent problems such as motion forecasting and crowd navigation.
1 code implementation • 6 Jun 2023 • Hao Zhao, Yuejiang Liu, Alexandre Alahi, Tao Lin
Test-Time Adaptation (TTA) has recently emerged as a promising approach for tackling the robustness challenge under distribution shifts.
1 code implementation • 12 Jan 2023 • Yuejiang Liu, Alexandre Alahi, Chris Russell, Max Horn, Dominik Zietlow, Bernhard Schölkopf, Francesco Locatello
Recent years have seen a surge of interest in learning high-level causal representations from low-level image pairs under interventions.
1 code implementation • 6 Nov 2022 • Parth Kothari, Danya Li, Yuejiang Liu, Alexandre Alahi
To this end, we introduce two components that exploit our prior knowledge of motion style shifts: (i) a low-rank motion style adapter that projects and adjusts the style features at a low-dimensional bottleneck; and (ii) a modular adapter strategy that disentangles the features of scene context and motion history to facilitate a fine-grained choice of adaptation layers.
1 code implementation • NeurIPS 2021 • Yuejiang Liu, Parth Kothari, Bastien Van Delft, Baptiste Bellot-Gurlet, Taylor Mordan, Alexandre Alahi
In this work, we first provide an in-depth look at its limitations and show that TTT can possibly deteriorate, instead of improving, the test-time performance in the presence of severe distribution shifts.
2 code implementations • CVPR 2022 • Yuejiang Liu, Riccardo Cadei, Jonas Schweizer, Sherwin Bahmani, Alexandre Alahi
Learning behavioral patterns from observational data has been a de-facto approach to motion forecasting.
4 code implementations • ICCV 2021 • Yuejiang Liu, Qi Yan, Alexandre Alahi
Learning socially-aware motion representations is at the core of recent advances in multi-agent problems, such as human motion forecasting and robot navigation in crowds.
Ranked #1 on Trajectory Prediction on TrajNet++
1 code implementation • 2 Feb 2019 • Yuejiang Liu, Parth Kothari, Alexandre Alahi
The standard practice in Generative Adversarial Networks (GANs) discards the discriminator during sampling.
6 code implementations • 24 Sep 2018 • Changan Chen, Yuejiang Liu, Sven Kreiss, Alexandre Alahi
We propose to (i) rethink pairwise interactions with a self-attention mechanism, and (ii) jointly model Human-Robot as well as Human-Human interactions in the deep reinforcement learning framework.