Search Results - "Debnath, Shoubhik"

Influence of an Intermediate Option on the Description-Experience Gap and Information Search by Sharma, Neha, Debnath, Shoubhik, Dutt, Varun

“…Research shows that people tend to overweight small probabilities in description and underweight them in experience, thereby leading to a different pattern of…”
Get full text

Analysing Predictability in Indian Monsoon Rainfall: A Data Analytic Approach by Azad, Sarita, Debnath, Shoubhik, Rajeevan, M.

“…This paper examines monthly and annual data to analyse predictability in the Indian monsoon rainfall. The periodic structure in the time series data is…”
Get full text

ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders by Woo, Sanghyun, Debnath, Shoubhik, Hu, Ronghang, Chen, Xinlei, Liu, Zhuang, Kweon, In So, Xie, Saining

“…Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance…”
Get full text

RGB-D Local Implicit Function for Depth Completion of Transparent Objects by Zhu, Luyang, Mousavian, Arsalan, Xiang, Yu, Mazhar, Hammad, Eenbergen, Jozef van, Debnath, Shoubhik, Fox, Dieter

“…Majority of the perception methods in robotics require depth information provided by RGB-D cameras. However, standard 3D sensors fail to capture depth of…”
Get full text

Solving Markov Decision Processes with Reachability Characterization from Mean First Passage Times by Debnath, Shoubhik, Liu, Lantao, Sukhatme, Gaurav

“…A new mechanism for efficiently solving the Markov decision processes (MDPs) is proposed in this paper. We introduce the notion of reachability landscape where…”
Get full text

Accelerating Goal-Directed Reinforcement Learning by Model Characterization by Debnath, Shoubhik, Sukhatme, Gaurav, Liu, Lantao

“…We propose a hybrid approach aimed at improving the sample efficiency in goal-directed reinforcement learning. We do this via a two-step mechanism where…”
Get full text

Self-Supervised Real-to-Sim Scene Generation by Prakash, Aayush, Debnath, Shoubhik, Lafleche, Jean-Francois, Cameracci, Eric, State, Gavriel, Birchfield, Stan, Law, Marc T.

“…Synthetic data is emerging as a promising solution to the scalability issue of supervised deep learning, especially when real data are difficult to acquire or…”
Get full text

Exploring Long-Sequence Masked Autoencoders by Hu, Ronghang, Debnath, Shoubhik, Xie, Saining, Chen, Xinlei

“…Masked Autoencoding (MAE) has emerged as an effective approach for pre-training representations across multiple domains. In contrast to discrete tokens in…”
Get full text

PointInfinity: Resolution-Invariant Point Diffusion Models by Huang, Zixuan, Johnson, Justin, Debnath, Shoubhik, Rehg, James M., Wu, Chao-Yuan

“…We present PointInfinity, an efficient family of point cloud diffusion models. Our core idea is to use a transformer-based architecture with a fixed-size,…”
Get full text

PointInfinity: Resolution-Invariant Point Diffusion Models by Huang, Zixuan, Johnson, Justin, Debnath, Shoubhik, Rehg, James M, Wu, Chao-Yuan

“…We present PointInfinity, an efficient family of point cloud diffusion models. Our core idea is to use a transformer-based architecture with a fixed-size,…”
Get full text

ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders by Woo, Sanghyun, Debnath, Shoubhik, Hu, Ronghang, Chen, Xinlei, Liu, Zhuang, Kweon, In So, Xie, Saining

“…Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance…”
Get full text

Solving Markov Decision Processes with Reachability Characterization from Mean First Passage Times by Debnath, Shoubhik, Liu, Lantao, Sukhatme, Gaurav

“…A new mechanism for efficiently solving the Markov decision processes (MDPs) is proposed in this paper. We introduce the notion of reachability landscape where…”
Get full text

Accelerating Goal-Directed Reinforcement Learning by Model Characterization by Debnath, Shoubhik, Sukhatme, Gaurav, Liu, Lantao

“…We propose a hybrid approach aimed at improving the sample efficiency in goal-directed reinforcement learning. We do this via a two-step mechanism where…”
Get full text

Reachability and Differential based Heuristics for Solving Markov Decision Processes by Debnath, Shoubhik, Liu, Lantao, Sukhatme, Gaurav

“…The solution convergence of Markov Decision Processes (MDPs) can be accelerated by prioritized sweeping of states ranked by their potential impacts to other…”
Get full text

Extending cortical-basal inspired reinforcement learning model with success-failure experience by Debnath, Shoubhik, Nassour, John

“…Neurocognitive studies showed that neurons of the orbitofrontal cortex get activated for expectation of immediate reward. Therefore they are the key reward…”
Get full text

RGB-D Local Implicit Function for Depth Completion of Transparent Objects by Zhu, Luyang, Mousavian, Arsalan, Xiang, Yu, Mazhar, Hammad, van Eenbergen, Jozef, Debnath, Shoubhik, Fox, Dieter

“…Majority of the perception methods in robotics require depth information provided by RGB-D cameras. However, standard 3D sensors fail to capture depth of…”
Get full text

Self-Supervised Real-to-Sim Scene Generation by Prakash, Aayush, Debnath, Shoubhik, Lafleche, Jean-Francois, Cameracci, Eric, State, Gavriel, Birchfield, Stan, Law, Marc T

“…Synthetic data is emerging as a promising solution to the scalability issue of supervised deep learning, especially when real data are difficult to acquire or…”
Get full text

Learning diverse motor patterns with a single multi-layered multi-pattern CPG for a humanoid robot by Debnath, Shoubhik, Nassour, John, Cheng, Gordon

“…This paper presents a Multi-Layered Multi-Pattern Central Pattern Generator (CPG) that provides humanoid robots the ability to generate motor patterns in order…”
Get full text

Semi-Supervised StyleGAN for Disentanglement Learning by Nie, Weili, Karras, Tero, Garg, Animesh, Debnath, Shoubhik, Patney, Anjul, Patel, Ankit B, Anandkumar, Anima

“…Disentanglement learning is crucial for obtaining disentangled representations and controllable generation. Current disentanglement methods face several…”
Get full text