paper-with-me

Papers

Distilling Internet-Scale Vision-Language Models into Embodied Agents

2023-01-29 · Theodore Sumers, Kenneth Marino, Arun Ahuja, Rob Fergus, Ishita Dasgupta

Instruction-following agents must ground language into their observation and action spaces. Learning to ground language is challenging, typically requiring domain-specific engineering or large quantities of human interaction data. To address this challenge, we propose using pretrained vision-language models (VLMs) to supervise embodied agents. We combine ideas from model distillation and hindsight experience replay (HER), using a VLM to retroactively generate language describing the agent's behavior. Simple prompting allows us to control the supervision signal, teaching an agent to interact with novel objects based on their names (e.g., planes) or their features (e.g., colors) in a 3D rendered environment. Fewshot prompting lets us teach abstract category membership, including pre-existing categories (food vs toys) and ad-hoc ones (arbitrary preferences over objects). Our work outlines a new and effective way to use internet-scale VLMs, repurposing the generic language grounding acquired by such models to teach task-relevant groundings to embodied agents.

📄 PDF Abstract BibTeX arXiv:2301.12507

Code (0)

등록된 구현이 없습니다.

Tasks

Instruction Following

Methods 이 논문이 사용한 방법론

Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…

Similar Papers 제목 키워드 기반

RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

2023-07-28 · Anthony Brohan, Noah Brown, Justice Carbajal, Yevgen Chebotar 외

We study how vision-language models trained on Internet-scale data can be incorporated directly into end-to-end robotic control to boost generalization and enable emergent semantic reasoning. Our goal is to enable a sing…

ObjectQuestion AnsweringRobot ManipulationVision-Language-Action+1

YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from YouTube Videos

2025-06-23 · Haoming Chen, Lichen Yuan, Tianfang Sun, Jingyu Gong 외

3D semantic occupancy prediction in the past was considered to require precise geometric relationships in order to enable effective training. However, in complex indoor environments, the large-scale and widespread collec…

3D Semantic Occupancy PredictionRepresentation LearningSuperpixels

Mind's Mirror: Distilling Self-Evaluation Capability and Comprehensive Thinking from Large Language Models

2023-11-15 · Weize Liu, Guocong Li, Kai Zhang, Bang Du 외

Large language models (LLMs) have achieved remarkable advancements in natural language processing. However, the massive scale and computational demands of these models present formidable challenges when considering their…

Transfer Learning

Distilling Knowledge Learned in BERT for Text Generation

2019-11-10 · ACL 2020 6 · Yen-Chun Chen, Zhe Gan, Yu Cheng, Jingzhou Liu 외

Large-scale pre-trained language model such as BERT has achieved great success in language understanding tasks. However, it remains an open question how to utilize BERT for language generation. In this paper, we present …

Language ModelingLanguage ModellingMachine TranslationMasked Language Modeling+4

Ambient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B Model

2026-09-10 · Logesh Kumar Umapathi hf

We describe our entry to the EgoLongQA track of the Wearable-AI Challenge in ECCV 2026, which placed first in the <=2B parameter division with 0.8279 on the held-out test set. Our system is a single 2B vision-language mo…