Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T13:43:04.537493Z
Paper Citation Record · LEDGER
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
As of 18 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 19 inbound Pith citation observations for arXiv:2505.21200.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-15T20:26:09.074689Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z
Reference resolution
47 of 47 outbound references displayed
- verified exact1
- verified fuzzy4
- unresolved42
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z
Outbound references
Observation 42200279-e32f-4538-8d46-af1268e082e5 · outbound
This paper cites Do As I Can, Not As I Say: Grounding Language in Robotic Affordances.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:42:58.620579Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 220d2467-d9a8-4f82-af99-bfdd8cdf092a · outbound
This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:42:58.759097Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f040c164-af62-4b84-a709-3bca321d088b · outbound
This paper cites $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:42:58.929949Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b33ab496-7c76-4034-bbbe-d09dfbaccd17 · outbound
This paper cites RT-1: Robotics Transformer for Real-World Control at Scale.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models RT-1: Robotics Transformer for Real-World Control at Scale
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:42:59.076821Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b38532cb-ba0d-403a-a6c3-4d68fef0db36 · outbound
This paper cites GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:42:59.173764Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 262519e2-caa4-4cbf-b62e-00dbd37ca820 · outbound
This paper cites an unresolved cited work.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Unresolved cited work
Reference 6
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T13:43:06.768722Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 5552c08d-1b32-43ac-aee0-2431f622ec04 · outbound
This paper cites an unresolved cited work.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Unresolved cited work
Reference 8
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T13:43:06.651756Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation ef69b40b-65a0-4648-8698-b9ac0637225c · outbound
This paper cites an unresolved cited work.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Unresolved cited work
Reference 9
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T13:43:06.466170Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 2e7eda50-524d-4190-a527-f414ba586b84 · outbound
This paper cites an unresolved cited work.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Unresolved cited work
Reference 10
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T13:43:06.302972Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 14bfbcab-b152-44de-b9fe-5e4af94d01e5 · outbound
This paper cites an unresolved cited work.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Unresolved cited work
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:42:59.879271Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation af051aea-0e19-4b7f-96ae-f55f54d1c16c · outbound
This paper cites an unresolved cited work.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Unresolved cited work
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:00.008350Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8df6e184-76dd-4822-a79d-9717c2273671 · outbound
This paper cites Manipulate-Anything: Automating Real-World Robots using Vision-Language Models.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Manipulate-Anything: Automating Real-World Robots using Vision-Language Models
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:00.230985Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e6e1485c-b068-44a3-b2bd-e5fe14d36143 · outbound
This paper cites RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:00.431971Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 55fea985-5ab4-45d7-ae53-ef1212805730 · outbound
This paper cites Diffusion Transformer Policy.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Diffusion Transformer Policy
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:00.597211Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9e645849-c1fb-48f3-96b6-e46d5bcf4fe1 · outbound
This paper cites an unresolved cited work.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Unresolved cited work
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:00.735532Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5f2091d7-02ca-4580-a627-db9cc2403b6e · outbound
This paper cites Jiang, X.
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T13:43:06.120893Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 9d404b8d-14f8-44d9-86af-fd0f71ed1923 · outbound
This paper cites DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:01.083162Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4050d5a9-723a-4ca2-aeaf-cabc24b5d3b5 · outbound
This paper cites Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:01.279474Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9b4c248c-1307-4904-93bb-016fe5ee8e86 · outbound
This paper cites OpenVLA: An Open-Source Vision-Language-Action Model.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models OpenVLA: An Open-Source Vision-Language-Action Model
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:01.351486Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 664d0ca2-60ca-40e3-9239-9fe0ecb9f715 · outbound
This paper cites Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters
Reference 21
- Resolution
- verified exact
- local_arxiv, observed 2026-08-07T13:43:05.160857Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation f06cc0f4-5215-4d09-866f-98dd11e095e7 · outbound
This paper cites CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:01.480814Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 34ebeda1-0fb0-4921-8ac1-4c0902d3e029 · outbound
This paper cites Evaluating Real-World Robot Manipulation Policies in Simulation.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Evaluating Real-World Robot Manipulation Policies in Simulation
Reference 23
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:01.638742Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a517b294-5f40-42d8-90fe-a0e1c789012c · outbound
This paper cites Vision-Language Foundation Models as Effective Robot Imitators.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Vision-Language Foundation Models as Effective Robot Imitators
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:01.760587Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 83926484-51c0-4457-93df-48ae6ccede47 · outbound
This paper cites an unresolved cited work.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Unresolved cited work
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:01.916518Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d0bc70a6-f547-44cb-8a61-00668dc6b4f8 · outbound
This paper cites RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:02.033013Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8e3fbcf7-60c1-4579-bac9-cf9dbd6b82d4 · outbound
This paper cites RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:02.178483Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6ba2346a-6f98-45c9-a41c-80c1c81e0659 · outbound
This paper cites Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:02.340523Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bede8346-9c03-4645-b231-b8d865439650 · outbound
This paper cites Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling
Reference 29
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:02.506958Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7b4e0d74-7f2c-4ab2-8c46-f9f0c3947d2c · outbound
This paper cites R3M: A Universal Visual Representation for Robot Manipulation.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models R3M: A Universal Visual Representation for Robot Manipulation
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:02.629364Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 47a2d80b-83af-4431-8303-138fafda7b9b · outbound
This paper cites Oquab, T.
Reference 31
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:02.739636Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation be8158a6-1d9b-4d35-af86-66d8b09a0150 · outbound
This paper cites O’Neill, A.
Reference 32
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:02.744927Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d8b20428-4c1d-403e-9387-b86e1b507580 · outbound
This paper cites Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control
Reference 33
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:02.750457Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bae20548-c5b9-4c76-a6e5-58533845c6b4 · outbound
This paper cites FAST: Efficient Action Tokenization for Vision-Language-Action Models.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models FAST: Efficient Action Tokenization for Vision-Language-Action Models
Reference 34
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:02.850761Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5cc97333-604b-4e29-9a59-121840267127 · outbound
This paper cites Singh, V.
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T13:43:05.924852Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation bc2b18de-deae-4f08-ad3f-df8ae4ddf3ed · outbound
This paper cites an unresolved cited work.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Unresolved cited work
Reference 36
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:03.201022Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 849551f8-8e3d-41bb-8fd4-fde8f3c680d5 · outbound
This paper cites LLaMA: Open and Efficient Foundation Language Models.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models LLaMA: Open and Efficient Foundation Language Models
Reference 37
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:03.323929Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d9b01b24-1d17-4365-b681-446034d39b78 · outbound
This paper cites Diffusion-VLA: Generalizable and Interpretable Robot Foundation Model via Self-Generated Reasoning.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Diffusion-VLA: Generalizable and Interpretable Robot Foundation Model via Self-Generated Reasoning
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:03.455619Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0fc3c282-6fd8-4637-930c-58cea05178ab · outbound
This paper cites an unresolved cited work.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Unresolved cited work
Reference 39
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:03.601909Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d9482747-4466-46a6-ae62-9b5a24e150ee · outbound
This paper cites an unresolved cited work.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Unresolved cited work
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:03.749499Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f8fc4f28-c74a-48c7-881f-8a7e7109521e · outbound
This paper cites DNAct: Diffusion Guided Multi-Task 3D Policy Learning.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models DNAct: Diffusion Guided Multi-Task 3D Policy Learning
Reference 41
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:03.817109Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation abffa18c-c2c1-47ef-8a27-82f0e2f3eccf · outbound
This paper cites an unresolved cited work.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Unresolved cited work
Reference 42
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:03.910286Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8c50a432-9f19-4125-981f-ee77a805da2e · outbound
This paper cites an unresolved cited work.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Unresolved cited work
Reference 43
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T13:43:05.796712Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation c769917f-87c4-458b-bc29-fa86fccecb79 · outbound
This paper cites an unresolved cited work.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Unresolved cited work
Reference 44
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:04.147405Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4e812d10-ea7d-45f4-80f4-3e28783cfb9e · outbound
This paper cites LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
Reference 45
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:04.258730Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 87e0c8c6-c14a-4a5f-9e62-32f80e215ed9 · outbound
This paper cites Zhang, Z.
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T13:43:05.638348Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 549af06b-7b60-4c27-9aa4-e09d009bb627 · outbound
This paper cites SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference.
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
Reference 47
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T13:43:04.407246Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5de09fb8-0c6e-4ec0-b728-13a0d27c0ed1 · outbound
This paper cites Zitkovich, T.
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T13:43:05.434319Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Pith citing papers
Observation 27e0a52e-db45-4355-a05b-7d132211f3f4 · inbound
RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models cites this paper.
RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T19:10:14.854316Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e9ad02eb-0de1-4f98-89bb-7bfaae0e40a2 · inbound
Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey cites this paper.
Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 115
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-17T20:28:16.251395Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 5cc907b8-c95a-409f-af39-091b8910feed · inbound
Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey cites this paper.
Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 56
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T09:08:12.680018Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c7669fec-08b0-4352-868d-3ff350b648b3 · inbound
ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models cites this paper.
ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 23
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T06:09:09.433198Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation d75ee6f8-1593-40a5-aff7-9f64f760f4ba · inbound
TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Control cites this paper.
TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Control Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T09:07:39.309018Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cdeed0c5-557e-4128-8df2-49523da42a74 · inbound
KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models cites this paper.
KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 24
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T18:40:14.434166Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 566736a1-5b5a-44d2-9456-127d74258f25 · inbound
OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism cites this paper.
OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 37
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T11:50:03.934133Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation ebda3e5c-1bb5-4920-babb-7c268ddb6849 · inbound
VLA-InfoEntropy: A Training-Free Vision-Attention Information Entropy Approach for Vision-Language-Action Models Inference Acceleration and Success cites this paper.
VLA-InfoEntropy: A Training-Free Vision-Attention Information Entropy Approach for Vision-Language-Action Models Inference Acceleration and Success Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 10
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T00:25:50.142804Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation a65763df-9030-4369-a569-943e7c27f4f5 · inbound
Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models cites this paper.
Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 49
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T02:22:06.687892Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 2a3220a9-f94f-44ad-8e8d-4501e7d6aa96 · inbound
Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models cites this paper.
Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 49
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T06:15:07.104557Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 346d9813-74f7-4774-a93f-75f41c53f5bf · inbound
AttenA+: Rectifying Action Inequality in Robotic Foundation Models cites this paper.
AttenA+: Rectifying Action Inequality in Robotic Foundation Models Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 24
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T18:47:37.220705Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 012a3ec7-7c05-4075-a2b5-c77670f3a936 · inbound
AttenA+: Rectifying Action Inequality in Robotic Foundation Models cites this paper.
AttenA+: Rectifying Action Inequality in Robotic Foundation Models Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 24
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T14:25:45.902573Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 207fda53-dc32-48a8-a34f-e553e199d3a8 · inbound
ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models cites this paper.
ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 18
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-06-29T07:23:13.041269Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 43146e1b-4c59-4bc5-a8d3-d2e9ed35e07b · inbound
GeoSem-WAM: Geometry- and Semantic-Aware World Action Models cites this paper.
GeoSem-WAM: Geometry- and Semantic-Aware World Action Models Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 22
- Resolution
- verified exact
- arxiv_id, observed 2026-07-02T03:16:34.619734Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 10a0d5dd-2dfe-427d-b614-7934d9e4435a · inbound
UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models cites this paper.
UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 41
- Resolution
- verified exact
- arxiv_id, observed 2026-07-04T10:19:47.661540Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 8bdac25c-b34c-4d14-943d-f0123da50301 · inbound
Improving Robotic Imitation Learning via Trajectory Standardization cites this paper.
Improving Robotic Imitation Learning via Trajectory Standardization Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-04T10:39:45.564349Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation c89b7deb-90ab-4cc3-b7c5-789c8b0edc79 · inbound
Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models? cites this paper.
Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models? Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 43
- Resolution
- verified exact
- arxiv_id, observed 2026-06-29T19:03:52.300386Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 6ee57c48-dd03-412e-ba93-5ae81aa47fbb · inbound
Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation cites this paper.
Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 27
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T10:45:42.864902Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 9426d060-5cdb-4d25-b5cc-493c87fc90f6 · inbound
FlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving cites this paper.
FlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:26:09.074689Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.