GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents | Paper Citation Record

Observation f50f39f2-e052-4655-b5da-a369fe0d3d19 · outbound

This paper cites write newline.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:44.943729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28369869-51de-4e3f-b658-9b9c64591727 · outbound

This paper cites Multi-objective latent space optimization of generative molecular design models.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Multi-objective latent space optimization of generative molecular design models

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:46.001240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 14e1e029-8980-4bd3-a986-8f2bf97615fc · outbound

This paper cites Imitating Interactive Intelligence.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Imitating Interactive Intelligence

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:44.960832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 218ff899-930d-4e8f-a422-d73ca4dcb064 · outbound

This paper cites An optimistic perspective on offline reinforcement learning.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents An optimistic perspective on offline reinforcement learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:44.965648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7a7730c-45b8-4919-b357-713eb95f3b6b · outbound

This paper cites OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:44.970264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5edea55d-0b14-4aca-a234-78064cce8fe4 · outbound

This paper cites Flamingo: a Visual Language Model for Few-Shot Learning.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Flamingo: a Visual Language Model for Few-Shot Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:44.976022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8744f31c-5e5a-4fa7-9fa7-7aaeed675001 · outbound

This paper cites Fixing a broken elbo.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Fixing a broken elbo

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:44.981536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69ca765b-5454-4b5d-9ab9-0dba13e472d5 · outbound

This paper cites Hindsight Experience Replay.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Hindsight Experience Replay

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:44.985917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c984fe0-9b1a-41e1-9940-fc603d54ba1f · outbound

This paper cites Agent57: Outperforming the atari human benchmark.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Agent57: Outperforming the atari human benchmark

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:45.972738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 06676397-6534-4398-8f3b-c47ad9508a58 · outbound

This paper cites Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:44.993876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 500ce3f9-1759-4886-9837-0aaeff9386bb · outbound

This paper cites The arcade learning environment: An evaluation platform for general agents.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents The arcade learning environment: An evaluation platform for general agents

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:44.999032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cf34361-3637-4dd8-8133-e34fa7774007 · outbound

This paper cites RT-1: Robotics Transformer for Real-World Control at Scale.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents RT-1: Robotics Transformer for Real-World Control at Scale

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.003192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1732c799-21f6-4b38-b370-1f9ef5864090 · outbound

This paper cites RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.013831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8da9e833-c68d-4395-b509-f4bd10d0700b · outbound

This paper cites Language Models are Few-Shot Learners.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Language Models are Few-Shot Learners

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.021602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70444ac8-ee54-4e16-946a-323d725855cd · outbound

This paper cites Open-world multi-task control through goal-aware representation learning and adaptive horizon prediction.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Open-world multi-task control through goal-aware representation learning and adaptive horizon prediction

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:45.950291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f24ea4a2-6aa5-4c12-90fb-e4beb55d40b1 · outbound

This paper cites Groot: Learning to follow instructions by watching gameplay videos.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Groot: Learning to follow instructions by watching gameplay videos

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:45.937746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 83b80df0-fc92-467f-b030-94ed50058ad0 · outbound

This paper cites Abbeel, A.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Abbeel, A

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:45.923865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 18ad4ab7-8f55-4320-bc0c-aa46bd7932f0 · outbound

This paper cites Transformer-xl: Attentive language models beyond a fixed-length context.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Transformer-xl: Attentive language models beyond a fixed-length context

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.042834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f7cf927-0b2e-4ad3-abc6-6678d4951c82 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.046948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc4d0dcc-4b45-404c-bb45-3bccd86d4211 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.049894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c6542bb-2217-4c5d-8b02-0beca396f1c0 · outbound

This paper cites One-shot imitation learning.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents One-shot imitation learning

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:45.911107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d26f0261-4177-45a8-8f12-8f61498869d1 · outbound

This paper cites Implicit Deep Latent Variable Models for Text Generation.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Implicit Deep Latent Variable Models for Text Generation

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-08-11T20:41:45.530666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 293ec0b5-6d0c-43aa-8f62-93c0d783b7d5 · outbound

This paper cites Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.061059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13f6abe7-be3c-4463-8429-2a2b75e76ab5 · outbound

This paper cites Guss, Brandon Houghton, Nicholay Topin, Phillip Wang, Cayden Codel, Manuela M.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Guss, Brandon Houghton, Nicholay Topin, Phillip Wang, Cayden Codel, Manuela M

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.064991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02419236-e53b-41a7-8067-4f6d8b769539 · outbound

This paper cites Vln-bert: A recurrent vision-and-language bert for navigation.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Vln-bert: A recurrent vision-and-language bert for navigation

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:45.891844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 14dc7441-235e-4a76-a095-56bdd444ded0 · outbound

This paper cites An Embodied Generalist Agent in 3D World.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents An Embodied Generalist Agent in 3D World

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.074200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fafca65-a57c-47b7-ab54-a0b2091c12a5 · outbound

This paper cites Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.078763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61b1740d-0afc-4bfd-9177-f8d85f0c2d28 · outbound

This paper cites BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.083397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0352c213-bfdc-4930-bc33-46e87ae24b0f · outbound

This paper cites The malmo platform for artificial intelligence experimentation.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents The malmo platform for artificial intelligence experimentation

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:45.878744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1b0a3218-9245-42d3-960d-a904105392fc · outbound

This paper cites Auto-Encoding Variational Bayes.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Auto-Encoding Variational Bayes

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.092438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f602080-664e-463e-a314-8bd7086f9af2 · outbound

This paper cites Multi-game decision transformers.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Multi-game decision transformers

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.096021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3daa7d74-c326-499c-82d9-52b066f61ea0 · outbound

This paper cites Evaluating Real-World Robot Manipulation Policies in Simulation.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Evaluating Real-World Robot Manipulation Policies in Simulation

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.100715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 158adb09-896f-45fb-9640-3dd60c27624c · outbound

This paper cites STEVE-1: A Generative Model for Text-to-Behavior in Minecraft.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents STEVE-1: A Generative Model for Text-to-Behavior in Minecraft

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.105155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bb96c3a-44ef-4fd2-8a33-8135c6256bc9 · outbound

This paper cites Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.116529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 151077ff-6bb6-4603-adb4-be779ff5523e · outbound

This paper cites Language Conditioned Imitation Learning over Unstructured Data.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Language Conditioned Imitation Learning over Unstructured Data

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.120926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b7ab2c4-e7d8-40eb-acd9-3de1f078aaf5 · outbound

This paper cites Learning latent plans from play.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Learning latent plans from play

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:45.854733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8f0b4f59-1616-491c-9527-c1e1dc268d6d · outbound

This paper cites Learning latent plans from play.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Learning latent plans from play

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:45.841767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 85dae5c4-4642-4d51-9bf8-e5e2390ec52a · outbound

This paper cites Learning latent plans from play.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Learning latent plans from play

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:45.827698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 53c39c27-ffb2-4a5c-a38b-200f01ec7b37 · outbound

This paper cites Interactive language: Talking to robots in real time.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Interactive language: Talking to robots in real time

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.136889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c85f61f-d6cc-400c-9029-c29b0d88694e · outbound

This paper cites ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.140755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee0692f7-bc58-4de7-9fd4-0870847b5b14 · outbound

This paper cites What matters in language conditioned robotic imitation learning over unstructured data.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents What matters in language conditioned robotic imitation learning over unstructured data

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:45.807648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f5b071b7-f4f6-432b-978a-2fe318553e90 · outbound

This paper cites Rusu, Joel Veness, Marc G.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Rusu, Joel Veness, Marc G

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.149036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58d8e0f2-56fc-4a86-b104-0c53e31d9b77 · outbound

This paper cites Goal representations for instruction following: A semi-supervised language interface to control.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Goal representations for instruction following: A semi-supervised language interface to control

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:45.787144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f89879f9-987a-4a0c-99f1-cc009537a33d · outbound

This paper cites Octo: An open-source generalist robot policy.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Octo: An open-source generalist robot policy

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.156190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 152c4e05-a8ed-4815-983d-9f22f37cce05 · outbound

This paper cites Open X-Embodiment: Robotic Learning Datasets and RT-X Models.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Open X-Embodiment: Robotic Learning Datasets and RT-X Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.159279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bb8bfe7-c9e8-4958-aef8-a31f933bc552 · outbound

This paper cites Conditional Variational Autoencoder for Neural Machine Translation.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Conditional Variational Autoencoder for Neural Machine Translation

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.162510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84e935d3-5426-47a3-b218-c758916988de · outbound

This paper cites Episodic transformer for vision-and-language navigation.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Episodic transformer for vision-and-language navigation

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:45.766547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 87dd3bdf-20cf-41ee-badf-f7e0df4ffe25 · outbound

This paper cites Accelerating reinforcement learning with learned skill priors.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Accelerating reinforcement learning with learned skill priors

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:45.749383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b0412b2c-a674-4c5b-812e-05dd181154cb · outbound

This paper cites Scaling Instructable Agents Across Many Simulated Worlds.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Scaling Instructable Agents Across Many Simulated Worlds

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.173544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea1ff3cd-f5d9-45a3-b93d-d96a13eb9d6c · outbound

This paper cites Improving language understanding by generative pre-training.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Improving language understanding by generative pre-training

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.177377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35cf3de0-21f3-4e86-848e-2cd6bc0f9f24 · outbound

This paper cites Language models are unsupervised multitask learners.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Language models are unsupervised multitask learners

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.181411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c021881-6925-4123-a7b0-f3c5c08f3fee · outbound

This paper cites Learning transferable visual models from natural language supervision.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Learning transferable visual models from natural language supervision

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.186191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 407263d1-4278-4042-b2b2-63265791bec9 · outbound

This paper cites A Generalist Agent.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents A Generalist Agent

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.191304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e417dc5c-f1c3-4089-a3b8-ec46ce4657ab · outbound

This paper cites Habitat: A platform for embodied ai research.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Habitat: A platform for embodied ai research

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.195401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c31d09c1-597f-45b4-a07a-4debc3ede1aa · outbound

This paper cites Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.198736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5f0f9ab-0452-4a05-859e-96f9a2094da0 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Gemini: A Family of Highly Capable Multimodal Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.203599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b518a75-3d8d-4552-bceb-8f71998c5f2b · outbound

This paper cites Describe, explain, plan and select: interactive planning with llms enables open-world multi-task agents.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Describe, explain, plan and select: interactive planning with llms enables open-world multi-task agents

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:45.706557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e80437eb-59ba-462c-83a0-4a437aeed3ba · outbound

This paper cites JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.217706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b12a3f0-374d-4c8a-91ef-fbd89547d5b3 · outbound

This paper cites Xskill: Cross embodiment skill discovery.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Xskill: Cross embodiment skill discovery

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:45.695643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cdb9dadc-fcbe-496d-b6d0-89fe6d0c414c · outbound

This paper cites Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.228028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5e56cbd-a5b0-421b-bd47-db18e53ca0e6 · outbound

This paper cites Learning to drive by watching youtube videos: Action-conditioned contrastive policy pretraining.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Learning to drive by watching youtube videos: Action-conditioned contrastive policy pretraining

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:41:45.685235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6a3966b8-a3b1-4ae6-b34e-daebfa857382 · outbound

This paper cites Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.236842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09bb8d68-c8de-434a-bcf7-6a0cf4209639 · outbound

This paper cites @esa (Ref.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents @esa (Ref

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.240583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83a22687-78ff-4f75-b957-fa99edf90c46 · outbound

This paper cites an unresolved cited work.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents Unresolved cited work

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.245534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b90dc01-faa4-4423-835c-a6af1e088068 · outbound

This paper cites MCU: An Evaluation Framework for Open-Ended Game Agents.

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents MCU: An Evaluation Framework for Open-Ended Game Agents

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-11T20:41:45.249886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers