no code implementations • ICML 2020 • Somdeb Majumdar, Shauharda Khadka, Santiago Miret, Stephen Mcaleer, Kagan Tumer
Training policies solely on the team-based reward is often difficult due to its sparsity.
no code implementations • 9 May 2024 • Uday Mallappa, Hesham Mostafa, Mikhail Galkin, Mariano Phielipp, Somdeb Majumdar
As novel machine learning (ML) approaches emerge to tackle such problems, there is a growing need for a modern benchmark that comprises a large training dataset and performance metrics that better reflect real-world constraints and objectives compared to existing benchmarks.
2 code implementations • 15 Jul 2022 • Kyle Min, Sourya Roy, Subarna Tripathi, Tanaya Guha, Somdeb Majumdar
Active speaker detection (ASD) in videos with multiple speakers is a challenging task as it requires learning effective audiovisual features and spatial-temporal correlations over long temporal windows.
Ranked #1 on Node Classification on AVA
1 code implementation • CVPR 2022 • Shaowei Liu, Subarna Tripathi, Somdeb Majumdar, Xiaolong Wang
To tackle this task, we first provide an automatic way to collect trajectory and hotspots labels on large-scale data.
1 code implementation • 18 Dec 2021 • Shengyu Feng, Subarna Tripathi, Hesham Mostafa, Marcel Nassar, Somdeb Majumdar
Dynamic scene graph generation from a video is challenging due to the temporal dynamics of the scene and the inherent temporal fluctuations of predictions.
no code implementations • 2 Dec 2021 • Sourya Roy, Kyle Min, Subarna Tripathi, Tanaya Guha, Somdeb Majumdar
We address the problem of active speaker detection through a new framework, called SPELL, that learns long-range multimodal graphs to encode the inter-modal relationship between audio and visual data.
no code implementations • 15 Jun 2021 • Varun Kumar Vijay, Hassam Sheikh, Somdeb Majumdar, Mariano Phielipp
With these techniques, we show that we can reduce communication by 75% with no loss of performance.
no code implementations • 14 Jun 2021 • Santiago Miret, Vui Seng Chua, Mattias Marder, Mariano Phielipp, Nilesh Jain, Somdeb Majumdar
In this work, we present a flexible and scalable framework for automated mixed-precision quantization that concurrently optimizes task performance, memory compression, and compute savings through multi-objective evolutionary computing.
no code implementations • 6 Jun 2021 • Hesham Mostafa, Marcel Nassar, Somdeb Majumdar
We also show that homophily is a poor measure of the information in a node's local neighborhood and propose the Neighborhood Information Content(NIC) metric, which is a novel information-theoretic graph metric.
1 code implementation • 19 Oct 2020 • Anurag Koul, Varun V. Kumar, Alan Fern, Somdeb Majumdar
Learning and planning with latent space dynamics has been shown to be useful for sample efficiency in model-based reinforcement learning (MBRL) for discrete and continuous control tasks.
no code implementations • 8 Oct 2020 • Hassam Sheikh, Shauharda Khadka, Santiago Miret, Somdeb Majumdar
We show that the discovered dense rewards are an effective signal for an RL policy to solve the benchmark tasks.
no code implementations • 6 Oct 2020 • Santiago Miret, Somdeb Majumdar, Carroll Wainwright
Since the safe agent effectively abstracts a task-independent notion of safety via its action probabilities, it can be ported to modulate multiple policies solving different tasks within the given environment without further training.
no code implementations • ICLR 2021 • Shauharda Khadka, Estelle Aflalo, Mattias Marder, Avrech Ben-David, Santiago Miret, Shie Mannor, Tamir Hazan, Hanlin Tang, Somdeb Majumdar
For deep neural network accelerators, memory movement is both energetically expensive and can bound computation.
no code implementations • 18 Jun 2019 • Shauharda Khadka, Somdeb Majumdar, Santiago Miret, Stephen Mcaleer, Kagan Tumer
Training policies solely on the team-based reward is often difficult due to its sparsity.
1 code implementation • 2 May 2019 • Shauharda Khadka, Somdeb Majumdar, Tarek Nassar, Zach Dwiel, Evren Tumer, Santiago Miret, Yinyin Liu, Kagan Tumer
Deep reinforcement learning algorithms have been successfully applied to a range of challenging control tasks.
1 code implementation • 7 Feb 2019 • Łukasz Kidziński, Carmichael Ong, Sharada Prasanna Mohanty, Jennifer Hicks, Sean F. Carroll, Bo Zhou, Hongsheng Zeng, Fan Wang, Rongzhong Lian, Hao Tian, Wojciech Jaśkowski, Garrett Andersen, Odd Rune Lykkebø, Nihat Engin Toklu, Pranav Shyam, Rupesh Kumar Srivastava, Sergey Kolesnikov, Oleksii Hrinchuk, Anton Pechenko, Mattias Ljungström, Zhen Wang, Xu Hu, Zehong Hu, Minghui Qiu, Jun Huang, Aleksei Shpilman, Ivan Sosin, Oleg Svidchenko, Aleksandra Malysheva, Daniel Kudenko, Lance Rane, Aditya Bhatt, Zhengfei Wang, Penghui Qi, Zeyang Yu, Peng Peng, Quan Yuan, Wenxin Li, Yunsheng Tian, Ruihan Yang, Pingchuan Ma, Shauharda Khadka, Somdeb Majumdar, Zach Dwiel, Yinyin Liu, Evren Tumer, Jeremy Watson, Marcel Salathé, Sergey Levine, Scott Delp
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector.