84 citations · 147 across the 13 of their papers we have counts for
16 papers
RLPE: Teaching LLMs to Prompt with Reinforcement Learning
Rahul Singhal, Karime Maamari, Pradyumna Tambwekar
Prompting is a widely used method for adapting general-purpose LLMs to domain-specific tasks. Effective prompts can be tedious to create manually, so prompt writing is increasingly…
HARDEN: Constrained Evolutionary Search for Harder, Answer-Preserving Evaluation Cases
Aditya Kumaran, Rahul Singhal, Karime Maamari +2
Language models are often evaluated on curated benchmarks that underrepresent the complexity of enterprise deployments. We introduce HARDEN, a constrained evolutionary search metho…
Proxifield: Decentralized Multi-Agent Communication through Semantic Proximity
Pradyumna Tambwekar, Yenchia Feng, Deep Patel +1
As LLM capabilities have expanded, multi-agent communication has emerged as an increasingly active area of research. Prevailing protocols often adopt rigid structures that introduc…
PrefPO: Pairwise Preference Prompt Optimization
Rahul Singhal, Pradyumna Tambwekar, Karime Maamari
Prompt engineering is effective but labor-intensive, motivating automated optimization methods. Existing methods typically require labeled datasets, which are often unavailable, an…
On the Strengths and Weaknesses of Data for Open-set Embodied Assistance
Pradyumna Tambwekar, Andrew Silva, Deepak Gopinath +3
Embodied foundation models are increasingly performant in real-world domains such as robotics or autonomous driving. These models are often deployed in interactive or assistive set…
Constraints-of-Thought: A Framework for Constrained Reasoning in Language-Model-Guided Search
Kamel Alrashedy, Vriksha Srihari, Zulfiqar Zaidi +3
While researchers have made significant progress in enabling large language models (LLMs) to perform multi-step planning, LLMs struggle to ensure that those plans align with high-l…
Towards Balancing Preference and Performance through Adaptive Personalized Explainability
Andrew Silva, Pradyumna Tambwekar, Mariah Schrum +1
As robots and digital assistants are deployed in the real world, these agents must be able to communicate their decision-making criteria to build trust, improve human-robot teaming…
Generating CAD Code with Vision-Language Models for 3D Designs
Kamel Alrashedy, Pradyumna Tambwekar, Zulfiqar Zaidi +3
Generative AI has transformed the fields of Design and Manufacturing by providing efficient and automated methods for generating and modifying 3D objects. One approach involves usi…
Towards the design of user-centric strategy recommendation systems for collaborative Human-AI tasks
Lakshita Dodeja, Pradyumna Tambwekar, Erin Hedlund-Botti +1
Artificial Intelligence is being employed by humans to collaboratively solve complicated tasks for search and rescue, manufacturing, etc. Efficient teamwork can be achieved by unde…
Towards Reconciling Usability and Usefulness of Explainable AI Methodologies
Pradyumna Tambwekar, Matthew Gombolay
Interactive Artificial Intelligence (AI) agents are becoming increasingly prevalent in society. However, application of such systems without understanding them can be problematic.…
FedPC: Federated Learning for Language Generation with Personal and Context Preference Embeddings
Andrew Silva, Pradyumna Tambwekar, Matthew Gombolay
Federated learning is a training paradigm that learns from multiple distributed users without aggregating data on a centralized server. Such a paradigm promises the ability to depl…
A Computational Interface to Translate Strategic Intent from Unstructured Language in a Low-Data Setting
Pradyumna Tambwekar, Lakshita Dodeja, Nathan Vaska +2
Many real-world tasks involve a mixed-initiative setup, wherein humans and AI systems collaboratively perform a task. While significant work has been conducted towards enabling hum…
Natural Language Specification of Reinforcement Learning Policies through Differentiable Decision Trees
Pradyumna Tambwekar, Andrew Silva, Nakul Gopalan +1
Human-AI policy specification is a novel procedure we define in which humans can collaboratively warm-start a robot's reinforcement learning policy. This procedure is comprised of…
Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptions
Upol Ehsan, Pradyumna Tambwekar, Larry Chan +2
Automated rationale generation is an approach for real-time explanation generation whereby a computational model learns to translate an autonomous agent's internal state and action…
Controllable Neural Story Plot Generation via Reward Shaping
Pradyumna Tambwekar, Murtaza Dhuliawala, Lara J. Martin +3
Language-modeling--based approaches to story plot generation attempt to construct a plot by sampling from a language model (LM) to predict the next character, word, or sentence to…
On Optimizing Human-Machine Task Assignments
Andreas Veit, Michael Wilber, Rajan Vaish +48
When crowdsourcing systems are used in combination with machine inference systems in the real world, they benefit the most when the machine system is deeply integrated with the cro…