Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence | Paper Citation Record

Observation 192c2629-4c58-4c29-b2ae-2a7586f78c84 · outbound

This paper cites Cosmos World Foundation Model Platform for Physical AI.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Cosmos World Foundation Model Platform for Physical AI

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08c61e75-b593-46e7-b578-2d559fd8b6f8 · outbound

This paper cites Qwen3-VL Technical Report.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Qwen3-VL Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4e7b323-e807-4ff5-b318-d9872fbb9196 · outbound

This paper cites All are worth words: A vit backbone for diffusion models.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence All are worth words: A vit backbone for diffusion models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac914cc8-773e-430a-ad58-95cb105f6045 · outbound

This paper cites Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be33e499-e20d-49ac-be51-92cf7a4a9a06 · outbound

This paper cites Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a89c811b-c73d-4697-b215-18e91ac12ed0 · outbound

This paper cites Pix2video: Video editing using image diffusion.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Pix2video: Video editing using image diffusion

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b020702-8eba-4d81-97f0-0122d24b5898 · outbound

This paper cites GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 022aa9c7-cea1-4c40-93e5-c62503f3b919 · outbound

This paper cites Spa- tialvlm: Endowing vision-language models with spatial reasoning capabilities.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Spa- tialvlm: Endowing vision-language models with spatial reasoning capabilities

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e0fd127-037a-4154-9468-d349cc052d74 · outbound

This paper cites Topreward: Token probabilities as hidden zero-shot rewards for robotics.arXiv preprint arXiv:2602.19313, 2026.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Topreward: Token probabilities as hidden zero-shot rewards for robotics.arXiv preprint arXiv:2602.19313, 2026

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0e4eda5-31b0-4a47-8581-0b1962d306c2 · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78ff9c17-3c63-4ffa-8565-99ca5cfa304c · outbound

This paper cites Video Language Planning.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Video Language Planning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac52ae1f-39b4-4a05-a641-ef71810bb1b8 · outbound

This paper cites Learning universal policies via text-guided video generation.Advances in neural information processing systems, 36:9156–9172, 2023.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Learning universal policies via text-guided video generation.Advances in neural information processing systems, 36:9156–9172, 2023

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7a92b01-d2b5-4d81-a199-b009fea7e531 · outbound

This paper cites Diffusion Guidance Is a Controllable Policy Improvement Operator.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Diffusion Guidance Is a Controllable Policy Improvement Operator

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fe34d5c-ad09-4ac2-b1e7-2593499aa524 · outbound

This paper cites Self-improving embodied foundation models.arXiv preprint arXiv:2509.15155, 2025.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Self-improving embodied foundation models.arXiv preprint arXiv:2509.15155, 2025

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea91d723-9389-46d6-a35f-a9721eeda47f · outbound

This paper cites CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cbaca3b-31a6-4c48-bf17-041233e5a866 · outbound

This paper cites Language models as zero-shot planners: Extracting actionable knowledge for embodied agents.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Language models as zero-shot planners: Extracting actionable knowledge for embodied agents

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa38d91c-7794-46a2-a4ea-787c90f77b9c · outbound

This paper cites $\pi^{*}_{0.6}$: a VLA That Learns From Experience.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence $\pi^{*}_{0.6}$: a VLA That Learns From Experience

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b66f9c5f-0174-4aa5-897a-dc804425f7d0 · outbound

This paper cites $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6b492f4-738d-4494-842a-f1141f375caf · outbound

This paper cites Scalable deep reinforcement learning for vision-based robotic manipulation.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Scalable deep reinforcement learning for vision-based robotic manipulation

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7834cbb0-c567-4b64-933a-763828bb9d4f · outbound

This paper cites Emergence of human to robot transfer in vision-language-action models.arXiv preprint arXiv:2512.22414, 2025.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Emergence of human to robot transfer in vision-language-action models.arXiv preprint arXiv:2512.22414, 2025

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dbbb35a-e6fa-4533-98c4-6080f93764e8 · outbound

This paper cites OpenVLA: An Open-Source Vision-Language-Action Model.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence OpenVLA: An Open-Source Vision-Language-Action Model

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fde82f6-a70d-46a4-89ad-66656776ed21 · outbound

This paper cites HunyuanVideo: A Systematic Framework For Large Video Generative Models.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence HunyuanVideo: A Systematic Framework For Large Video Generative Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07f739f2-67c1-4d5d-b63a-94d25c060cf7 · outbound

This paper cites Mastering stacking of diverse shapes with large-scale iterative reinforcement learning on real robots.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Mastering stacking of diverse shapes with large-scale iterative reinforcement learning on real robots

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a373dd7-b962-4f43-ad12-48e207303235 · outbound

This paper cites Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9ab1981-4d04-4afb-bbab-53f2aad27238 · outbound

This paper cites LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfe11aac-4bb4-4ccf-921c-573478b4986d · outbound

This paper cites CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47278cb0-48a2-47ec-ad15-ccf043e9d3dd · outbound

This paper cites CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eea69f1f-8645-4d90-8c2f-cb3034870d90 · outbound

This paper cites What matters in building vision–language–action models for generalist robots.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence What matters in building vision–language–action models for generalist robots

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf4e33a8-3dd7-409e-81ac-2c7b803f4039 · outbound

This paper cites Video Generators are Robot Policies.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Video Generators are Robot Policies

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 381d345e-c32d-4001-af81-3c0defaf30f8 · outbound

This paper cites RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 463ddde7-5e29-46b5-9a94-ce0bbd66cd83 · outbound

This paper cites Serl: A software suite for sample-efficient robotic reinforcement learning.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Serl: A software suite for sample-efficient robotic reinforcement learning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7177b8d-ac45-42ce-88f2-a153d4f0d4ce · outbound

This paper cites Liv: Language- image representations and rewards for robotic control.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Liv: Language- image representations and rewards for robotic control

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecca57a0-477e-4ad3-ae79-794766af8939 · outbound

This paper cites Vision language models are in-context value learners.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Vision language models are in-context value learners

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cabc2c1-7d0b-45e0-9ee1-dd5339fc59b4 · outbound

This paper cites Vision language models are in-context value learners.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Vision language models are in-context value learners

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a7cc0f8-9a9d-4e3d-aae0-51c45bb82a21 · outbound

This paper cites Iris: Implicit reinforcement without interaction at scale for learning control from offline robot manipulation data.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Iris: Implicit reinforcement without interaction at scale for learning control from offline robot manipulation data

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faa66cf9-2786-4468-a2e2-d7018133b633 · outbound

This paper cites SmolVLM: Redefining small and efficient multimodal models.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence SmolVLM: Redefining small and efficient multimodal models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cac720eb-4606-43bc-8c22-af189cf78ff0 · outbound

This paper cites ALAN: Autonomously Exploring Robotic Agents in the Real World.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence ALAN: Autonomously Exploring Robotic Agents in the Real World

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d635b52-2d60-4d51-9cd6-cc7985d5307d · outbound

This paper cites Open x-embodiment: Robotic learning datasets and rt-x models: Open x-embodiment collaboration 0.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Open x-embodiment: Robotic learning datasets and rt-x models: Open x-embodiment collaboration 0

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91c3a209-dd3c-4256-88cc-8819b8b1da48 · outbound

This paper cites Scalable diffusion models with transformers.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Scalable diffusion models with transformers

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91a6d654-774a-408c-8c36-79d5ae138793 · outbound

This paper cites Diffdance: Cascaded human motion diffusion model for dance generation.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Diffdance: Cascaded human motion diffusion model for dance generation

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d151e19a-dbc2-45bd-aacd-0266b27d5fcf · outbound

This paper cites A reduction of imitation learning and structured prediction to no-regret online learning.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence A reduction of imitation learning and structured prediction to no-regret online learning

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a438a1f3-be06-4788-a622-f41b3dd4436b · outbound

This paper cites Vision-language-action (vla) models: Concepts, progress, applications and challenges.arXiv preprint arXiv:2505.04769, 2025.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Vision-language-action (vla) models: Concepts, progress, applications and challenges.arXiv preprint arXiv:2505.04769, 2025

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b52f1d98-2a82-4d4b-9351-362aef7d8bde · outbound

This paper cites Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 283492b3-b7b8-43b2-9604-24c154efa646 · outbound

This paper cites Make-A-Video: Text-to-Video Generation without Text-Video Data.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Make-A-Video: Text-to-Video Generation without Text-Video Data

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b456db00-1d39-4382-8d54-47f0178c615f · outbound

This paper cites MIT press Cambridge, 1998.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence MIT press Cambridge, 1998

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e681eb57-6a85-4939-8bcb-f5ee86acab04 · outbound

This paper cites Gigabrain-0: A world model-powered vision-language-action model.arXiv preprint arXiv:2510.19430, 2025.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Gigabrain-0: A world model-powered vision-language-action model.arXiv preprint arXiv:2510.19430, 2025

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16105e39-8cbb-474c-a267-9e91c9a101fc · outbound

This paper cites Gigabrain-0.5 m*: a vla that learns from world model-based reinforcement learning.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Gigabrain-0.5 m*: a vla that learns from world model-based reinforcement learning

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7856bc57-294d-46c2-b953-daf365bdca26 · outbound

This paper cites Octo: An Open-Source Generalist Robot Policy.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Octo: An Open-Source Generalist Robot Policy

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 240cdc55-7d52-4d19-a064-a2e730cb613e · outbound

This paper cites Phenaki: Variable Length Video Generation From Open Domain Textual Description.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Phenaki: Variable Length Video Generation From Open Domain Textual Description

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 893b1e18-c560-4f50-9eda-65d027598cad · outbound

This paper cites Wan: Open and Advanced Large-Scale Video Generative Models.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Wan: Open and Advanced Large-Scale Video Generative Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17387227-7efd-44a3-8fd8-e577754b91f8 · outbound

This paper cites Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 893ac9f3-8441-4ad9-b69b-e70019a4874b · outbound

This paper cites Learning Interactive Real-World Simulators.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Learning Interactive Real-World Simulators

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd7cf4e2-9e4b-46c4-9f6a-7d5e001cf0ea · outbound

This paper cites CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f91f77bc-9ca3-4473-aaea-9e398ba23518 · outbound

This paper cites Gigaworld-policy: An efficient action-centered world–action model.arXiv preprint arXiv:2603.17240, 2026.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Gigaworld-policy: An efficient action-centered world–action model.arXiv preprint arXiv:2603.17240, 2026

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42bdcb8e-9641-4727-9860-d04a6200acbd · outbound

This paper cites World Action Models are Zero-shot Policies.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence World Action Models are Zero-shot Policies

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b369509e-1dc7-4464-943b-e2e2834d0aa0 · outbound

This paper cites A vision-language-action-critic model for robotic real-world reinforcement learning.arXiv preprint arXiv:2509.15937, 2025.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence A vision-language-action-critic model for robotic real-world reinforcement learning.arXiv preprint arXiv:2509.15937, 2025

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f67b77d5-8a4c-40e6-812b-b7c05a25c1c6 · outbound

This paper cites Sigmoid loss for language image pre- training.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Sigmoid loss for language image pre- training

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d59cccbf-895e-41a3-8114-d4b88fc4a3f7 · outbound

This paper cites an unresolved cited work.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Unresolved cited work

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dab481a5-713d-4ec9-b353-a4d72be0babf · outbound

This paper cites GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a2e234f-903c-495f-8cdf-83c364051301 · outbound

This paper cites Taste- rob: Advancing video generation of task-oriented hand-object interaction for generalizable robotic manipulation.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Taste- rob: Advancing video generation of task-oriented hand-object interaction for generalizable robotic manipulation

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd07d209-1066-44be-8de7-b883e8c74efb · outbound

This paper cites Open-Sora: Democratizing Efficient Video Production for All.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Open-Sora: Democratizing Efficient Video Production for All

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fc75366-c9f5-46c2-9048-078a4f502bce · outbound

This paper cites RoboDreamer: Learning Compositional World Models for Robot Imagination.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence RoboDreamer: Learning Compositional World Models for Robot Imagination

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dedbefd9-37be-4c08-819b-8b89a281dba8 · outbound

This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bac59cd-d759-4e47-a132-93e883a6549d · outbound

This paper cites Rt-2: Vision-language-action models transfer web knowledge to robotic control.

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Rt-2: Vision-language-action models transfer web knowledge to robotic control

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-13T00:03:53.609175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers