← Search

Siddharth Karamcheti

18 accepted papers

2026

ReSteer: Quantifying and Refining the Steerability of Multitask Robot Policies

RSS 2026poster

Despite strong multi-task pretraining, existing policies often exhibit poor task steerability. For example, a robot may fail to respond to a new instruction “put the bowl in the sink” when moving towards the oven, executing “close the oven”, even though it can complete both tasks when executed separ…

Cited by 0SourceScholar
2025

ProVox: Personalization and Proactive Planning for Situated Human-Robot Collaboration

RA-L 2025

Collaborative robots must quickly adapt to their partner's intent and preferences to proactively identify helpful actions. This is especially true in situated settings where human partners can continually teach robots new high-level behaviors, visual concepts, and physical skills (e.g., through demo

Cited by 4SourceScholar
2024

DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset

RSS 2024poster

The creation of large, diverse, high-quality robot manipulation datasets is an important stepping stone on the path toward more capable and robust robotic manipulation policies. However, creating such datasets is challenging: collecting robot manipulation data in diverse environments poses logistica…

Cited by 216SourcePDFScholar
2024

Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration

ICRA 2024

Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for man

Cited by 910SourcecodeScholar
2024

Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration0

ICRA 2024poster

Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for man…

Cited by 259SourcecodeScholar
2024

OpenVLA: An Open-Source Vision-Language-Action Model

CoRL 2024poster

Large policies pretrained on a combination of Internet-scale vision-language data and diverse robot demonstrations have the potential to change how we teach robots new skills: rather than training new behaviors from scratch, we can fine-tune such vision-language-action (VLA) models to obtain robust,…

Cited by 437SourceScholar
2024

Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models

ICML 2024poster

Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning; adoption that has fueled a wealth of new models such as LLaVa, InstructBLIP, and PaLI-3. Despite the volume of new releases, key design deci…

Cited by 102SourcePDFScholar
2024

Toward Grounded Commonsense Reasoning

ICRA 2024poster

Consider a robot tasked with tidying a desk with a meticulously constructed Lego sports car. A human may recognize that it is not appropriate to disassemble the sports car and put it away as part of the "tidying." How can a robot reach that conclusion? Although large language models (LLMs) have rece…

Cited by 23SourcecodeScholar
2024

Vocal Sandbox: Continual Learning and Adaptation for Situated Human-Robot Collaboration

CoRL 2024poster

We introduce Vocal Sandbox, a framework for enabling seamless human-robot collaboration in situated environments. Systems in our framework are characterized by their ability to *adapt and continually learn* at multiple levels of abstraction from diverse teaching modalities such as spoken dialogue, o…

Cited by 0SourcecodeScholar
2023

Language-Driven Representation Learning for Robotics

RSS 2023poster

Recent work in visual representation learning for robotics demonstrates the viability of learning from large video datasets of humans performing everyday tasks. Leveraging methods such as masked autoencoding and contrastive learning, these representations exhibit strong transfer to policy learning f…

2023

OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents

NeurIPS 2023poster

Large multimodal models trained on natural documents, which interleave images and text, outperform models trained on image-text pairs on various multimodal benchmarks. However, the datasets used to train these models have not been released, and the collection process has not been fully specified. W…

2022

Eliciting Compatible Demonstrations for Multi-Human Imitation Learning

CoRL 2022poster

Imitation learning from human-provided demonstrations is a strong approach for learning policies for robot manipulation. While the ideal dataset for imitation learning is homogenous and low-variance - reflecting a single, optimal method for performing a task - natural human behavior has a great deal…

Cited by 22SourceScholar
2021

ELLA: Exploration through Learned Language Abstraction

NeurIPS 2021poster

Building agents capable of understanding language instructions is critical to effective and robust human-AI collaboration. Recent work focuses on training these agents via reinforcement learning in environments with synthetic language; however, instructions often define long-horizon, sparse-reward t…

2021

Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering

ACL 2021long

Active learning promises to alleviate the massive data needs of supervised machine learning: it has successfully improved sample efficiency by an order of magnitude on traditional tasks like topic classification and object recognition. However, we uncover a striking contrast to this promise: across…

2021

Targeted Data Acquisition for Evolving Negotiation Agents

ICML 2021spotlight

Successful negotiators must learn how to balance optimizing for self-interest and cooperation. Yet current artificial negotiation agents often heavily depend on the quality of the static datasets they were trained on, limiting their capacity to fashion an adaptive response balancing self-interest an…

Cited by 11SourcePDFScholar
2017

Accurately and Efficiently Interpreting Human-Robot Instructions of Varying Granularities

RSS 2017poster

Humans can ground natural language commands to tasks at both abstract and fine-grained levels of specificity. For instance, a human forklift operator can be instructed to perform a high-level action, like 'grab a pallet' or a low-level action like 'tilt back a little bit.' While robots are also capa…