no code implementations • ICML 2020 • Soham Dan, Bhaswar B. Bhattacharya
Hypothesis testing of random networks is an emerging area of modern research, especially in the high-dimensional regime, where the number of samples is smaller or comparable to the size of the graph.
no code implementations • Findings (EMNLP) 2021 • Soham Dan, Osbert Bastani, Dan Roth
This way the concept learning problem is naturally a program synthesis problem and our algorithm learns from a few examples to synthesize a program representing the novel concept.
no code implementations • Findings (EMNLP) 2021 • Soham Dan, Xinran Han, Dan Roth
Executing natural language instructions in a physically grounded domain requires a model that understands both spatial concepts such as “left of” and “above”, and the compositional language used to identify landmarks and articulate instructions relative to them.
no code implementations • Findings (EMNLP) 2021 • Soham Dan, Dan Roth
To reduce the cost of training such large models, prior work has developed smaller, more compact models which achieves a significant speedup in training time while maintaining competitive accuracy to the original model on downstream tasks.
no code implementations • 15 Apr 2024 • Mauricio Gruppi, Soham Dan, Keerthiram Murugesan, Subhajit Chaudhury
Moreover, we describe the occurrence of semantic degeneration as a consequence of inappropriate fine-tuning of language models in text-based reinforcement learning (TBRL).
no code implementations • 18 Mar 2024 • Payel Das, Subhajit Chaudhury, Elliot Nelson, Igor Melnyk, Sarath Swaminathan, Sihui Dai, Aurélie Lozano, Georgios Kollias, Vijil Chenthamarakshan, Jiří, Navrátil, Soham Dan, Pin-Yu Chen
Efficient and accurate updating of knowledge stored in Large Language Models (LLMs) is one of the most pressing research challenges today.
no code implementations • 5 Mar 2024 • Hitesh Golchha, Sahil Yerawar, Dhruvesh Patel, Soham Dan, Keerthiram Murugesan
Real-world sequential decision making is characterized by sparse rewards and large decision spaces, posing significant difficulty for experiential learning systems like $\textit{tabula rasa}$ reinforcement learning (RL) agents.
no code implementations • 28 Feb 2024 • Amit Dhurandhar, Tejaswini Pedapati, Ronny Luss, Soham Dan, Aurelie Lozano, Payel Das, Georgios Kollias
Transformer-based Language Models have become ubiquitous in Natural Language Processing (NLP) due to their impressive performance on various tasks.
1 code implementation • 23 Feb 2024 • Kinjal Basu, Ibrahim Abdelaziz, Subhajit Chaudhury, Soham Dan, Maxwell Crouse, Asim Munawar, Sadhana Kumaravel, Vinod Muthusamy, Pavan Kapanipathi, Luis A. Lastras
There is a growing need for Large Language Models (LLMs) to effectively use tools and external Application Programming Interfaces (APIs) to plan and complete tasks.
1 code implementation • 26 Jan 2024 • Takuya Ito, Soham Dan, Mattia Rigotti, James Kozloski, Murray Campbell
On the other hand, neither of these architectural features led to productive generalization, suggesting fundamental limitations of existing architectures for specific types of multimodal generalization.
no code implementations • 15 Nov 2023 • Yahan Yang, Soham Dan, Dan Roth, Insup Lee
We also conduct several ablation experiments to study the effect of language distances, language corpus size, and model size on calibration, and how multilingual models compare with their monolingual counterparts for diverse tasks and languages.
no code implementations • 12 Oct 2023 • Maxwell Crouse, Ibrahim Abdelaziz, Ramon Astudillo, Kinjal Basu, Soham Dan, Sadhana Kumaravel, Achille Fokoue, Pavan Kapanipathi, Salim Roukos, Luis Lastras
We demonstrate how the proposed framework can be used to implement recent LLM-based agents (e. g., ReACT), and show how the flexibility of our approach can be leveraged to define a new agent with more complex behavior, the Plan-Act-Summarize-Solve (PASS) agent.
1 code implementation • 28 Sep 2023 • Tim Klinger, Luke Liu, Soham Dan, Maxwell Crouse, Parikshit Ram, Alexander Gray
Compositional generalization is a key ability of humans that enables us to learn new concepts from only a handful examples.
no code implementations • 18 Jun 2023 • Keerthiram Murugesan, Sarathkrishna Swaminathan, Soham Dan, Subhajit Chaudhury, Chulaka Gunasekara, Maxwell Crouse, Diwakar Mahajan, Ibrahim Abdelaziz, Achille Fokoue, Pavan Kapanipathi, Salim Roukos, Alexander Gray
In this work, we propose a new evaluation scheme to model human judgments in 7 NLP tasks, based on the fine-grained mismatches between a pair of texts.
1 code implementation • 18 May 2023 • Tom Silver, Soham Dan, Kavitha Srinivas, Joshua B. Tenenbaum, Leslie Pack Kaelbling, Michael Katz
We investigate whether LLMs can serve as generalized planners: given a domain and training tasks, generate a program that efficiently produces plans for other tasks in the domain.
no code implementations • 20 Dec 2022 • Yahan Yang, Soham Dan, Dan Roth, Insup Lee
Recently it has been shown that state-of-the-art NLP models are vulnerable to adversarial attacks, where the predictions of a model can be drastically altered by slight modifications to the input (such as synonym substitutions).
no code implementations • 26 Oct 2022 • Pierre Gaillard, Aadirupa Saha, Soham Dan
We address the problem of \emph{`Internal Regret'} in \emph{Sleeping Bandits} in the fully adversarial setup, as well as draw connections between different existing notions of sleeping regrets in the multiarmed bandits (MAB) literature and consequently analyze the implications: Our first contribution is to propose the new notion of \emph{Internal Regret} for sleeping MAB.
no code implementations • 19 Jul 2022 • Harsha Kokel, Mayukh Das, Rakibul Islam, Julia Bonn, Jon Cai, Soham Dan, Anjali Narayan-Chen, Prashant Jayannavar, Janardhan Rao Doppa, Julia Hockenmaier, Sriraam Natarajan, Martha Palmer, Dan Roth
We consider the problem of human-machine collaborative problem solving as a planning task coupled with natural language communication.
1 code implementation • CVPR 2022 • Georgios Georgakis, Karl Schmeckpeper, Karan Wanchoo, Soham Dan, Eleni Miltsakaki, Dan Roth, Kostas Daniilidis
We consider the problem of Vision-and-Language Navigation (VLN).
no code implementations • 20 Feb 2022 • Soham Dan, Osbert Bastani, Dan Roth
Currently, deep neural networks struggle to generalize robustly to such shifts in the data distribution.
1 code implementation • 1 Nov 2021 • Soham Dan, Anirbit Mukherjee, Avirup Das, Phanideep Gampa
On various state-of-the-art neural network training on SVHN, CIFAR-10 and CIFAR-100 we demonstrate how our new proposal of $S_{\rm rel}$, as opposed to the original definition, much more sharply detects the property of the weight updates preferring to make prediction changes within the same class as the sampled data.
no code implementations • NAACL 2021 • Soham Dan, Michael Zhou, Dan Roth
Understanding and executing natural language instructions in a grounded domain is one of the hallmarks of artificial intelligence.
no code implementations • COLING 2020 • Soham Dan, Hagai Taitelbaum, Jacob Goldberger
We propose a natural extension of the PA algorithm that uses multiple orthogonal translation matrices to model the mapping and derive an algorithm to learn these multiple matrices.
no code implementations • LREC 2020 • Soham Dan, Hangfeng He, Dan Roth
Recognizing spatial relations and reasoning about them is essential in multiple applications including navigation, direction giving and human-computer interaction in general.
no code implementations • LREC 2020 • Soham Dan, Parisa Kordjamshidi, Julia Bonn, Archna Bhatia, Jon Cai, Martha Palmer, Dan Roth
To exhibit the applicability of our representation scheme, we annotate text taken from diverse datasets and show how we extend the capabilities of existing spatial representation languages with the fine-grained decomposition of semantics and blend it seamlessly with AMRs of sentences and discourse representations as a whole.
no code implementations • 3 Feb 2020 • Soham Dan, Han Bao, Masashi Sugiyama
We perform a detailed investigation of this problem under two realistic noise models and propose two algorithms to learn from noisy S-D data.
no code implementations • 8 Nov 2019 • Soham Dan, Dushyant Sahoo
To combat this issue, several variance reduced methods have been proposed with faster convergence guarantees than vanilla stochastic gradient descent.
no code implementations • 10 Sep 2017 • Mayank Singh, Soham Dan, Sanyam Agarwal, Pawan Goyal, Animesh Mukherjee
We also categorize individual research articles based on their application areas and the techniques proposed/improved in the article.
no code implementations • WS 2017 • Anjali Narayan-Chen, Colin Graber, Mayukh Das, Md. Rakibul Islam, Soham Dan, Sriraam Natarajan, Janardhan Rao Doppa, Julia Hockenmaier, Martha Palmer, Dan Roth
Agents that communicate back and forth with humans to help them execute non-linguistic tasks are a long sought goal of AI.
no code implementations • 23 Aug 2016 • Soham Dan, Sanyam Agarwal, Mayank Singh, Pawan Goyal, Animesh Mukherjee
Every field of research consists of multiple application areas with various techniques routinely used to solve problems in these wide range of application areas.