Paper Citation Record · LEDGER

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

As of 10 August 2026, this Paper Citation Record lists 100 of 121 outbound references and 12 inbound Pith citation observations for arXiv:2604.18486.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2604.18486 v3

Coverage vector

measured 100 of 121 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-12T00:54:23.508845Z

measured 112 of 112 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 12 of 12 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T19:56:57.482174Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-07-02T16:57:10.319204Z

Reference resolution

100 of 121 outbound references displayed

verified exact49
verified fuzzy50
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation afe21470-a494-48dc-97f9-e6a16805d14c · outbound

This paper cites Claude 3.7 Sonnet and Claude Code.https://www.anthropic.com/news/claude-3-7-sonnet.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Claude 3.7 Sonnet and Claude Code.https://www.anthropic.com/news/claude-3-7-sonnet

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:26.956782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ff616f81-e00f-4a4e-8134-d1475698d7bd · outbound

This paper cites Self-supervised learning from images with a joint-embedding predictive architecture.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Self-supervised learning from images with a joint-embedding predictive architecture

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.146836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3627fa32-91d8-45b1-8876-bba15b85d603 · outbound

This paper cites Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:47:10.348602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cb490e54-c2fb-4f2b-921b-d4dbcdf5a3da · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:36:25.958151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 53e59826-aefe-43c2-809c-72c9aa545c43 · outbound

This paper cites Qwen3-VL Technical Report.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Qwen3-VL Technical Report

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:36:26.145301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 885fe00b-5b3f-4ad9-8230-102eb2512c51 · outbound

This paper cites Qwen2.5-VL Technical Report.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Qwen2.5-VL Technical Report

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:36:26.005487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 64fbd631-b097-441b-ac7b-26de69cc7a57 · outbound

This paper cites Dynamiccity: Large-scale 4d oc- cupancy generation from dynamic scenes.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Dynamiccity: Large-scale 4d oc- cupancy generation from dynamic scenes

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:26.114624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b816d1b3-3b7e-4592-9b40-00e4523b8b45 · outbound

This paper cites nuscenes: A multimodal dataset for autonomous driving.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation nuscenes: A multimodal dataset for autonomous driving

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:26.948035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9dc12a58-83f3-49b9-adcf-dbafa8bd9fad · outbound

This paper cites Maplm: A real-world large-scale vision-language benchmark for map and traffic scene understanding.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Maplm: A real-world large-scale vision-language benchmark for map and traffic scene understanding

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.102138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7ea35755-2bd2-4cd7-9e3b-2514ce54b21d · outbound

This paper cites arXiv preprint arXiv:2510.25122 (2025).

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation arXiv preprint arXiv:2510.25122 (2025)

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:25.952483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1938e40b-b0f9-4977-a83d-a2cf3c406a3e · outbound

This paper cites M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:36:26.135572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6f6069d0-72d4-4e34-aaa0-6e99044706f0 · outbound

This paper cites Automated evaluation of large vision-language models on self-driving corner cases.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Automated evaluation of large vision-language models on self-driving corner cases

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.130709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 41071d63-b645-49a3-9130-b66678e30519 · outbound

This paper cites Driving with llms: Fusing object-level vector modality for explainable autonomous driving.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Driving with llms: Fusing object-level vector modality for explainable autonomous driving

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.081174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3a5e2368-0cbf-46a5-ac7b-06088f13084f · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Evaluating Large Language Models Trained on Code

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:36:26.082150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 112f04bb-3a77-45e8-b544-4996b1204386 · outbound

This paper cites Vilta: A vlm-in-the-loop adversary for enhancing driving policy robustness.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Vilta: A vlm-in-the-loop adversary for enhancing driving policy robustness

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:25.994615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 47737d8e-5862-4011-bebb-f6469cdb3ff9 · outbound

This paper cites Compressed Chain of Thought: Efficient Reasoning Through Dense Representations.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Compressed Chain of Thought: Efficient Reasoning Through Dense Representations

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-17T04:47:40.470022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e7693050-a7ed-4eb9-a224-00b35724fa7f · outbound

This paper cites Impromptu VLA: Open weights and open data for driving vision-language-action models.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Impromptu VLA: Open weights and open data for driving vision-language-action models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.122045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 19177e61-0370-4e00-b196-c64d4bda4c92 · outbound

This paper cites Emu3.5: Native Multimodal Models are World Learners.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Emu3.5: Native Multimodal Models are World Learners

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-18T01:12:13.931083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b46d9a9d-4e92-4705-9491-c54b7881db37 · outbound

This paper cites Navsim: Data-driven non-reactive autonomous vehicle simulation and benchmarking.Advancesin Neural Information Processing Systems, 37:28706–28719.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Navsim: Data-driven non-reactive autonomous vehicle simulation and benchmarking.Advancesin Neural Information Processing Systems, 37:28706–28719

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:26.993180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8ac4bf0a-0f8b-4089-a5d3-767c35939e5c · outbound

This paper cites Language Modeling Is Compression.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Language Modeling Is Compression

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-17T22:36:13.497932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1b9bba79-0104-4460-a111-fe205e9fbb16 · outbound

This paper cites From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-16T11:44:32.634190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c8166422-dbb3-4821-a7d7-ed67d279e2bf · outbound

This paper cites Holistic autonomous driving understanding by bird’s-eye-view injected multi-modal large models.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Holistic autonomous driving understanding by bird’s-eye-view injected multi-modal large models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:26.933883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f61d2ea3-f73d-4c45-acf4-5c9aec3bc003 · outbound

This paper cites Hauptmann, and Zhi-Qi Cheng.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Hauptmann, and Zhi-Qi Cheng

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:26.067131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 545c5e5d-ef61-4ce5-8580-1ecc29d9dd02 · outbound

This paper cites Language-conditioned world modeling for visual navigation.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Language-conditioned world modeling for visual navigation

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:25.942926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2780ccca-bd98-4ccc-8173-eb91a5d33c86 · outbound

This paper cites Large scale interactive motion forecasting for autonomous driving: The waymo open motion dataset.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Large scale interactive motion forecasting for autonomous driving: The waymo open motion dataset

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.000828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 54e96c37-84ae-46f7-a65d-ae63c24a258d · outbound

This paper cites Advancing sequential numerical prediction in autoregressive models.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Advancing sequential numerical prediction in autoregressive models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:26.980942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f1ba7fa9-8fde-4ebd-a3d6-2d641ca8e39e · outbound

This paper cites Dolphin: Document image parsing via heterogeneous anchor prompting.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Dolphin: Document image parsing via heterogeneous anchor prompting

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:26.977003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cc7d6ea5-f360-4445-afc6-a084108778b6 · outbound

This paper cites A Survey of World Models for Autonomous Driving.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation A Survey of World Models for Autonomous Driving

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:25.917007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 236f4343-fad7-49f7-87d5-8d519b6f4cde · outbound

This paper cites Orion: A holistic end-to-end autonomous driving framework by vision-language instructed action generation.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Orion: A holistic end-to-end autonomous driving framework by vision-language instructed action generation

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.031896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e5a188c7-178f-4979-96f9-2b79aac3b7fc · outbound

This paper cites MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-07-20T02:18:22.862599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8198289c-3a26-4a1f-b16b-00bf42971b9e · outbound

This paper cites Vision meets robotics: The KITTI dataset.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Vision meets robotics: The KITTI dataset

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.004571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 085ff846-a7ce-4fad-933e-735946f9a7ea · outbound

This paper cites Driving in Corner Case: A Real-World Adversarial Closed-Loop Evaluation Platform for End-to-End Autonomous Driving.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Driving in Corner Case: A Real-World Adversarial Closed-Loop Evaluation Platform for End-to-End Autonomous Driving

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:36:26.025230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ba9f214d-e395-417a-9c21-2f59262bfd37 · outbound

This paper cites Narasimhan.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Narasimhan

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.035456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0deda81c-23b1-4b65-92e2-67a27e86957d · outbound

This paper cites Gemini 2.5 Pro preview: even better coding performance.https://developers.googleblog.com/en/ gemini-2-5-pro-io-improved-coding-performance.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Gemini 2.5 Pro preview: even better coding performance.https://developers.googleblog.com/en/ gemini-2-5-pro-io-improved-coding-performance

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:26.972718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation dcb3504d-5c72-4a43-9cf2-69b471620150 · outbound

This paper cites World models for autonomous driving: An initial survey.IEEE Transactionson Intelligent Vehicles, pages 1–17.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation World models for autonomous driving: An initial survey.IEEE Transactionson Intelligent Vehicles, pages 1–17

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.117978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 982ffee2-ddec-4146-8e38-ea7f991d2168 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:36:26.045917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1298f9e2-02e3-458a-af07-8c4ef8c99a56 · outbound

This paper cites Seed1.5-VL Technical Report.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Seed1.5-VL Technical Report

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:36:25.937007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d06f0d02-d1db-45ea-b128-a8d00e9bcfcd · outbound

This paper cites World Models.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation World Models

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:36:25.974962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d69e091e-0f6d-4ec1-bd80-73ae172fc2ba · outbound

This paper cites Dream to Control: Learning Behaviors by Latent Imagination.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Dream to Control: Learning Behaviors by Latent Imagination

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:36:26.020489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6b8688fd-4d23-4e64-9556-f587ef618d05 · outbound

This paper cites Training Large Language Models to Reason in a Continuous Latent Space.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Training Large Language Models to Reason in a Continuous Latent Space

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:36:26.108770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e8132dd7-4299-41ac-8c75-432621e774e7 · outbound

This paper cites MiMo-Embodied: X-Embodied Foundation Model Technical Report.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation MiMo-Embodied: X-Embodied Foundation Model Technical Report

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:36:26.119384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 90ab0c2e-c23b-4c66-bf27-d0b1e8da0585 · outbound

This paper cites DriveMRP: Enhancing Vision-Language Models with Synthetic Motion Data for Motion Risk Prediction.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation DriveMRP: Enhancing Vision-Language Models with Synthetic Motion Data for Motion Risk Prediction

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:26.150807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f0455a59-ab08-4d7a-8771-7bc65ef14683 · outbound

This paper cites GAIA-1: A Generative World Model for Autonomous Driving.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation GAIA-1: A Generative World Model for Autonomous Driving

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:36:26.160483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation add2c6a1-1e1d-426a-8654-d2e3493891c2 · outbound

This paper cites Vision-language-action models for autonomous driving: Past, present, and future.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Vision-language-action models for autonomous driving: Past, present, and future

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:25.979896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b47ebd11-2c33-49f0-b3c9-80650a543b56 · outbound

This paper cites NavThinker: Action-conditioned world models for coupled prediction and planning in social navigation.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation NavThinker: Action-conditioned world models for coupled prediction and planning in social navigation

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:25.989888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e9d6a343-9e18-47e9-9d52-25a48fc86a22 · outbound

This paper cites Fuller: Unified multi-modality multi-task 3D perception via multi-level gradient calibration.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Fuller: Unified multi-modality multi-task 3D perception via multi-level gradient calibration

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.012473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5e3ee279-4a83-439c-bbd2-d9bdaa1a2ab2 · outbound

This paper cites Making large language models better planners with reasoning-decision alignment.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Making large language models better planners with reasoning-decision alignment

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.052531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cbeb9ec0-be71-4d1d-8835-4b1049b6e960 · outbound

This paper cites RoboTron-Drive: All-in-one large multimodal model for autonomous driving.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation RoboTron-Drive: All-in-one large multimodal model for autonomous driving

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.026950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6927d97a-b8b8-4ca1-932c-ca107d61b1e0 · outbound

This paper cites GPT-4o System Card.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation GPT-4o System Card

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:36:25.984468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 722e832f-126e-4e72-896f-a079bb27268f · outbound

This paper cites DriveLMM-o1: A Step-by-Step Reasoning Dataset and Large Multimodal Model for Driving Scenario Understanding.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation DriveLMM-o1: A Step-by-Step Reasoning Dataset and Large Multimodal Model for Driving Scenario Understanding

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:26.000557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 50bed8ca-bb2c-49d5-86e7-7465238af746 · outbound

This paper cites OpenAI o1 System Card.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation OpenAI o1 System Card

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:36:26.154997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f9ab1206-fe37-469a-b28a-96803dcd9022 · outbound

This paper cites Meml-grpo: Heterogeneous multi-expert mutual learning for rlvr advancement.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Meml-grpo: Heterogeneous multi-expert mutual learning for rlvr advancement

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.068710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7f35206e-1553-408e-b54e-36717c420eb4 · outbound

This paper cites Towards learning- based planning: The nuPlan benchmark for real-world autonomous driving.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Towards learning- based planning: The nuPlan benchmark for real-world autonomous driving

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:26.922400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8f759bc3-d470-441e-9ab4-9a5b191998a6 · outbound

This paper cites The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:26.010977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e9739e53-cc52-4c1f-8a49-a9d343ed6b9d · outbound

This paper cites Multi-modal data-efficient 3D scene understanding for autonomous driving.IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(5):3748–3765.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Multi-modal data-efficient 3D scene understanding for autonomous driving.IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(5):3748–3765

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:26.918393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 244fed89-f186-451a-a330-46bdeb84d43b · outbound

This paper cites 3D and 4D World Modeling: A Survey.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation 3D and 4D World Modeling: A Survey

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-07-21T03:22:29.733321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9534465d-35cf-4059-a05c-1760ba4fe1f5 · outbound

This paper cites LargeAD: Large-scale cross-sensor data pretraining for autonomous driving.IEEE Transactionson Pattern Analysis and Machine Intelligence, 48(2):1291–1308.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation LargeAD: Large-scale cross-sensor data pretraining for autonomous driving.IEEE Transactionson Pattern Analysis and Machine Intelligence, 48(2):1291–1308

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.155138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 671dee57-d1f4-4b40-a601-7272c70ae337 · outbound

This paper cites Universal intelligence: A definition of machine intelligence.Minds and Machines, 17(4):391–444.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Universal intelligence: A definition of machine intelligence.Minds and Machines, 17(4):391–444

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.048217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 113837ec-0886-4220-9ede-9672b07a86b7 · outbound

This paper cites Enhancing end- to-end autonomous driving with latent world model.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Enhancing end- to-end autonomous driving with latent world model

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.039632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 59a1dff2-a1c9-4ce8-aa54-1f5aba3c953a · outbound

This paper cites End-to-end driving with online trajectory evaluation via BEV world model.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation End-to-end driving with online trajectory evaluation via BEV world model

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.023303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 99fe55d7-c1ef-4ccb-b1c4-456f6bc51bca · outbound

This paper cites DriveVLA-W0: World models amplify data scaling law in autonomous driving.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation DriveVLA-W0: World models amplify data scaling law in autonomous driving

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.139153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1030d577-5b2a-4a88-b885-20bb80d20d79 · outbound

This paper cites ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:36:24.555133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b9fde2de-5229-4987-b210-c34141b1e6a4 · outbound

This paper cites Lidarcrafter: Dynamic 4d world modeling from lidar sequences.Proceedings of the AAAI Conference on Artificial Intelligence, 40(22):18406–18414, Mar.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Lidarcrafter: Dynamic 4d world modeling from lidar sequences.Proceedings of the AAAI Conference on Artificial Intelligence, 40(22):18406–18414, Mar

Reference 63

Resolution: verified exact; doi, observed 2026-05-12T00:56:13.429159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9b11874e-ae5d-42d1-8860-e69e1c4f8220 · outbound

This paper cites Cottereau, Changxin Gao, Liang Pan, Wei Tsang Ooi, and Ziwei Liu.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Cottereau, Changxin Gao, Liang Pan, Wei Tsang Ooi, and Ziwei Liu

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.113849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8abcd7b0-e6d1-45fa-93ae-13363e14d86e · outbound

This paper cites Let’s verify step by step.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Let’s verify step by step

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:26.913878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 23119ec1-5e0a-42ea-a692-29b98f360b55 · outbound

This paper cites Visual instruction tuning.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Visual instruction tuning

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:26.988446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5018f948-4b49-487f-978e-7e0315496a61 · outbound

This paper cites Improved baselines with visual instruction tuning.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Improved baselines with visual instruction tuning

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:26.937629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5520fd27-c576-483a-b886-bd67562cff5a · outbound

This paper cites Guideflow: Constraint-guided flow matching for planning in end-to-end autonomous driving.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Guideflow: Constraint-guided flow matching for planning in end-to-end autonomous driving

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:26.056267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 460b551d-9731-412b-8413-a7f793b171f6 · outbound

This paper cites Driveworld-vla: Unified latent-space world modeling with vision-language-action for au- tonomous driving.ArXiv, abs/2602.06521.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Driveworld-vla: Unified latent-space world modeling with vision-language-action for au- tonomous driving.ArXiv, abs/2602.06521

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:25.923214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 71739495-92fe-4d76-926f-37b578189c94 · outbound

This paper cites ReasonPlan: Unified scene prediction and decision reasoning for closed-loop autonomous driving.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation ReasonPlan: Unified scene prediction and decision reasoning for closed-loop autonomous driving

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:26.926123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 16f167f0-0d6f-4e38-bdbf-8ec01025f4af · outbound

This paper cites A rationale-centric framework for human-in-the-loop machine learning.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation A rationale-centric framework for human-in-the-loop machine learning

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.105989Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b6af7b92-b15e-4d71-9c87-0214aa6f91fe · outbound

This paper cites Punifiedner: a prompting-based unified ner system for diverse datasets.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Punifiedner: a prompting-based unified ner system for diverse datasets

Reference 72

Resolution: verified exact; doi, observed 2026-05-12T00:56:13.432442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3005b26f-07ac-4b60-ae7c-c22cf75f3a93 · outbound

This paper cites What makes pre-trained language models better zero-shot learners? InAnnual Meeting of the Association for Computational Linguistics, pages 2288–2303.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation What makes pre-trained language models better zero-shot learners? InAnnual Meeting of the Association for Computational Linguistics, pages 2288–2303

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.097798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1cf21f5a-3921-4256-b9a6-abd6b2426cb8 · outbound

This paper cites PaDeLLM-NER: Parallel decoding in large language models for named entity recognition.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation PaDeLLM-NER: Parallel decoding in large language models for named entity recognition

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.093495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5be4e1d5-51ab-4b3a-b53e-481f8ef7ab7e · outbound

This paper cites A bounding box is worth one token - interleaving layout and text in a large language model for document understanding.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation A bounding box is worth one token - interleaving layout and text in a large language model for document understanding

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.085499Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6fb73279-136c-4dbe-acc9-dcd487444f67 · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Learn to explain: Multimodal reasoning via thought chains for science question answering

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:26.984854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3565fb29-e396-4de8-9929-aa45e3dad758 · outbound

This paper cites Last-vla: Thinking in latent spatio-temporal space for vision-language-action in autonomous driving.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Last-vla: Thinking in latent spatio-temporal space for vision-language-action in autonomous driving

Reference 77

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:25.903632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 391d1782-8dd5-487c-adfc-baa6fd312bca · outbound

This paper cites Adathinkdrive: Adaptive thinking via reinforcement learning for autonomous driving.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Adathinkdrive: Adaptive thinking via reinforcement learning for autonomous driving

Reference 78

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:25.910801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 291a81bb-1f12-4e16-b88e-edb540f16845 · outbound

This paper cites Unleashing vla potentials in autonomous driving via explicit learning from failures.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Unleashing vla potentials in autonomous driving via explicit learning from failures

Reference 79

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:26.051200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 98cf6bc8-3244-4b8e-8c2d-f27aecb19e8f · outbound

This paper cites MTRDrive: Memory-tool synergistic reasoning for robust autonomous driving in corner cases.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation MTRDrive: Memory-tool synergistic reasoning for robust autonomous driving in corner cases

Reference 80

Resolution: verified exact; arxiv_id, observed 2026-05-12T00:56:14.430355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 733ad1f3-1b83-4b2f-9dfe-252b148f3a1f · outbound

This paper cites DRAMA: Joint risk localization and captioning in driving.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation DRAMA: Joint risk localization and captioning in driving

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.076819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b47adb1f-d950-4cc1-928a-956fd29128e1 · outbound

This paper cites One Million Scenes for Autonomous Driving: ONCE Dataset.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation One Million Scenes for Autonomous Driving: ONCE Dataset

Reference 82

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:25.931211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 600053ac-8981-4a6c-a56d-15215dc29816 · outbound

This paper cites LingoQA: Visual question answering for autonomous driving.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation LingoQA: Visual question answering for autonomous driving

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.008416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 214dbcf6-5d3f-462c-a6a9-3e4b4f8afef3 · outbound

This paper cites The Mapillary Vistas dataset for semantic understanding of street scenes.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation The Mapillary Vistas dataset for semantic understanding of street scenes

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.150957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3663ab44-5b14-4ae8-810a-d62c23301983 · outbound

This paper cites DynVLA: Learning world dynamics for action reasoning in autonomous driving.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation DynVLA: Learning world dynamics for action reasoning in autonomous driving

Reference 85

Resolution: verified exact; arxiv_id, observed 2026-05-12T00:56:14.434052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d1d00094-37b6-426c-b03e-a1f5e829b847 · outbound

This paper cites CODI: Compressing chain-of- thought into continuous space via self-distillation.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation CODI: Compressing chain-of- thought into continuous space via self-distillation

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.109975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f8304efd-5119-48ac-b378-b8122ecca706 · outbound

This paper cites Scalableimagetokenizationwith index backpropagation quantization.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Scalableimagetokenizationwith index backpropagation quantization

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.064985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6f0abdb4-c447-443b-aab4-e40daedde74a · outbound

This paper cites DriveLM: Driving with graph visual question answering.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation DriveLM: Driving with graph visual question answering

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.043786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0a79c90d-afd3-4cab-ba58-fcd97b15a62b · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 89

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:36:26.093692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 39c8e822-17f8-415c-a770-5d479634be57 · outbound

This paper cites Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning

Reference 90

Resolution: verified exact; arxiv_id, observed 2026-05-12T00:56:14.437815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5f8407aa-2f0d-434f-98f2-8281dd1c6aaf · outbound

This paper cites MTVQA: Benchmarking multilingual text-centric visual question answering.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation MTVQA: Benchmarking multilingual text-centric visual question answering

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.072718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1bbfb0b5-56c6-4d27-9c4a-d245529bf937 · outbound

This paper cites What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?

Reference 92

Resolution: verified exact; arxiv_id, observed 2026-05-20T00:04:20.071030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 17a0933a-0ce5-4828-ae43-65e7eeeef114 · outbound

This paper cites SimScale: Learning to Drive via Real-World Simulation at Scale.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation SimScale: Learning to Drive via Real-World Simulation at Scale

Reference 93

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:36:26.062231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 067b5e6b-a2b7-4d3d-874a-9372da15e125 · outbound

This paper cites Deep learning and the information bottleneck principle.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Deep learning and the information bottleneck principle

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.056894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e8a6840c-f5d1-4add-9ac5-4920faf1c7bb · outbound

This paper cites The information bottleneck method.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation The information bottleneck method

Reference 95

Resolution: metadata mismatch; local_arxiv, observed 2026-05-12T08:36:25.947345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 951ca6c9-148f-41f2-8ae5-843ccaf433da · outbound

This paper cites Cambrian-1: A fully open, vision-centric exploration of multimodal LLMs.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Cambrian-1: A fully open, vision-centric exploration of multimodal LLMs

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.143052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b755d325-b7f4-46b6-9a6e-32772f023871 · outbound

This paper cites IDD: A dataset for exploring problems of autonomous navigation in unconstrained environments.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation IDD: A dataset for exploring problems of autonomous navigation in unconstrained environments

Reference 97

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.089472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ed3c0551-9ba4-47ff-b39b-92fc18c2c410 · outbound

This paper cites Attention is all you need.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Attention is all you need

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:26.940888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 900348eb-cf57-4efa-927b-84fc5448bae2 · outbound

This paper cites Vision as LoRA.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Vision as LoRA

Reference 99

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:26.103976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 81cfff75-923f-4a2c-914e-a7cdeca2dc19 · outbound

This paper cites VGGT: Visual geometry grounded transformer.

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation VGGT: Visual geometry grounded transformer

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:28:27.016154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

Observation 331997d7-08e6-4ca7-b2bb-4b05796870be · inbound

Is Your Driving World Model an All-Around Player? cites this paper.

Is Your Driving World Model an All-Around Player? Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:01:24.008567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4e6f403d-8549-477d-ac75-a963e1c621a3 · inbound

OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation cites this paper.

OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-14T19:22:50.653700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 86600751-4c2f-497e-9562-608bea60a07d · inbound

Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives cites this paper.

Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Reference 31

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T05:33:04.352441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0f008b2a-8686-49db-9bf1-fe950c51d477 · inbound

OneVLA: A Unified Framework for Embodied Tasks cites this paper.

OneVLA: A Unified Framework for Embodied Tasks Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-07-01T21:26:14.122300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9eab05e9-a088-4b20-8431-84405cf6c45c · inbound

WALL-WM: Carving World Action Modeling at the Event Joints cites this paper.

WALL-WM: Carving World Action Modeling at the Event Joints Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-07-01T23:36:22.326219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8ac20d96-80fe-467f-a21d-417dbc8bd2eb · inbound

Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction cites this paper.

Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Reference 69

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T11:56:55.429542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e1259f2f-b0cd-40ce-9d3d-f39e2bf1ad4b · inbound

Dash2Sim: Closed-Loop Driving Simulation from in-the-wild Dashcam Videos cites this paper.

Dash2Sim: Closed-Loop Driving Simulation from in-the-wild Dashcam Videos Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-07-02T16:57:10.321628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ddd72e8b-ce8b-4d34-a859-27ce4e0d5e0e · inbound

FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation cites this paper.

FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-06-30T15:44:49.434536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7eb48b8a-c4c7-4953-925b-e620c9234984 · inbound

DriveVer: Lightweight Trajectory Evaluator as Test-Time Verifier for Autonomous Driving cites this paper.

DriveVer: Lightweight Trajectory Evaluator as Test-Time Verifier for Autonomous Driving Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-02T15:07:04.053954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 09405c93-1edd-42bc-b8c0-98cd78597ea7 · inbound

Token-Wise Latent Streaming from Slow Reasoners to Fast Planners for Dynamic Vision Language Navigation cites this paper.

Token-Wise Latent Streaming from Slow Reasoners to Fast Planners for Dynamic Vision Language Navigation Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-01T19:56:57.482174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90980c78-0455-40f7-b57c-a88828014828 · inbound

HyWorldVLA: A Vision-Language-Action Model with Hybrid World Modeling for Autonomous Driving cites this paper.

HyWorldVLA: A Vision-Language-Action Model with Hybrid World Modeling for Autonomous Driving Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T08:49:48.309380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23dbe812-28cd-4331-b7eb-82aea1231cb7 · inbound

Data Pyramid for Embodied Manipulation cites this paper.

Data Pyramid for Embodied Manipulation Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Reference 255

Resolution: unresolved; no resolver link, observed 2026-07-31T06:18:55.846788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.