← Search

Karthik Gopalakrishnan

7 accepted papers

2024

Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments

NeurIPS 2024poster

The ability of Language Models (LMs) to understand natural language makes them a powerful tool for parsing human instructions into task plans for autonomous robots. Unlike traditional planning methods that rely on domain-specific knowledge and handcrafted rules, LMs generalize from diverse data and…

2023

Online Learning for Traffic Routing under Unknown Preferences

AISTATS 2023poster

In transportation networks, road tolling schemes are a method to cope with the efficiency losses due to selfish user routing, wherein users choose routes to minimize individual travel costs. However, the efficacy of tolling schemes often relies on access to complete information on users’ trip attrib…

2023

Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale

ACL 2023long

Language models have been shown to perform better with an increase in scale on a wide variety of tasks via the in-context learning paradigm. In this paper, we investigate the hypothesis that the ability of a large language model to in-context learn-perform a task is not uniformly spread across all o…

2023

Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation

ICML 2023poster

We consider the problem of multi-agent navigation and collision avoidance when observations are limited to the local neighborhood of each agent. We propose InforMARL, a novel architecture for multi-agent reinforcement learning (MARL) which uses local information intelligently to compute paths for al…

2022

Analyzing the Limits of Self-Supervision in Handling Bias in Language

EMNLP 2022finding

Prompting inputs with natural language task descriptions has emerged as a popular mechanism to elicit reasonably accurate outputs from large-scale generative language models with little to no in-context supervision. This also helps gain insight into how well language models capture the semantics of…

Cited by 3SourcePDFScholar
2022

Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generation

ACL 2022long

Implicit knowledge, such as common sense, is key to fluid human conversations. Current neural response generation (RG) models are trained to generate responses directly, omitting unstated implicit knowledge. In this paper, we present Think-Before-Speaking (TBS), a generative approach to first extern…

2022

VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator

ACL 2022findings

Interactive robots navigating photo-realistic environments need to be trained to effectively leverage and handle the dynamic nature of dialogue in addition to the challenges underlying vision-and-language navigation (VLN). In this paper, we present VISITRON, a multi-modal Transformer-based navigator…