Paper Citation Record · LEDGER

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving

As of 5 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 3 inbound Pith citation observations for arXiv:2512.14044.

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

pith.paper-citation-record.v1
2512.14044 v3

Coverage vector

measured 65 of 65 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-16T22:34:00.895252Z

measured 68 of 68 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T01:19:54.962342Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

65 of 65 outbound references displayed

verified exact23
verified fuzzy41
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a8999727-9998-438f-961f-991172fb01ca · outbound

This paper cites Flamingo: a visual language model for few-shot learning.Advances in neural information processing systems, 35:23716–23736.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Flamingo: a visual language model for few-shot learning.Advances in neural information processing systems, 35:23716–23736

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.655689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3b0257e3-60d7-4e64-b889-cba02aca093f · outbound

This paper cites Mitigating object hallucinations in large vision-language models with assembly of global and local attention.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Mitigating object hallucinations in large vision-language models with assembly of global and local attention

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.659776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b5e19163-2e6e-4ba9-b324-2e4522965f61 · outbound

This paper cites Qwen2.5-VL Technical Report.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Qwen2.5-VL Technical Report

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-16T22:38:37.809618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 25ae90c6-53c6-4ffd-a325-30f00c2f838d · outbound

This paper cites Spatialbot: Pre- cise spatial understanding with vision language models.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Spatialbot: Pre- cise spatial understanding with vision language models

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.651036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fcbcc38e-4071-433d-a3aa-9c59cd0287c4 · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-16T22:38:37.820176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 38dd5e2d-78e1-41c2-8ce7-fbcb21262aa5 · outbound

This paper cites Spa- tialrgpt: Grounded spatial reasoning in vision-language mod- els.Advances in Neural Information Processing Systems, 37: 135062–135093.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Spa- tialrgpt: Grounded spatial reasoning in vision-language mod- els.Advances in Neural Information Processing Systems, 37: 135062–135093

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.641354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f9d7b09a-88d0-486d-9790-2d79807b6402 · outbound

This paper cites Visual thoughts: A unified perspective of understanding multimodal chain-of-thought.arXiv preprint arXiv:2505.15510.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Visual thoughts: A unified perspective of understanding multimodal chain-of-thought.arXiv preprint arXiv:2505.15510

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:38:37.864781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d9250d5b-7e5a-4ded-8e83-f71d72219f86 · outbound

This paper cites Talk2bev: Language-enhanced bird’s-eye view maps for autonomous driving.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Talk2bev: Language-enhanced bird’s-eye view maps for autonomous driving

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.646807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f7b6ac57-9991-47a6-a0a8-920044a279fd · outbound

This paper cites Retrieval-Based Interleaved Visual Chain-of-Thought in Real-World Driving Scenarios.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Retrieval-Based Interleaved Visual Chain-of-Thought in Real-World Driving Scenarios

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:38:37.815554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f622c574-0cca-4142-8a67-3835f0c6b501 · outbound

This paper cites Virgo: A Preliminary Exploration on Reproducing o1-like MLLM.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Virgo: A Preliminary Exploration on Reproducing o1-like MLLM

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:38:37.799187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 564b4a28-4b2b-4793-88ca-9f99dc93fefa · outbound

This paper cites Drive like a human: Rethinking autonomous driving with large language models.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Drive like a human: Rethinking autonomous driving with large language models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.534764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7449410f-6457-4048-a8a8-a6799a105b49 · outbound

This paper cites SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:38:37.804166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5fc2333f-29a0-4742-bad0-d3f68cee926c · outbound

This paper cites Cogagent: A visual language model for gui agents.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Cogagent: A visual language model for gui agents

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.596818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a85cfac5-4c9c-4517-8d1b-6ad9964ba702 · outbound

This paper cites Visual sketchpad: Sketching as a visual chain of thought for mul- timodal language models.Advances in Neural Information Processing Systems, 37:139348–139379.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Visual sketchpad: Sketching as a visual chain of thought for mul- timodal language models.Advances in Neural Information Processing Systems, 37:139348–139379

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.527675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c43a34f0-d07f-492c-adaa-5a1efc4ab763 · outbound

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

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving DriveLMM-o1: A Step-by-Step Reasoning Dataset and Large Multimodal Model for Driving Scenario Understanding

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:38:37.834021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0fc9ffd2-80b0-4962-adc2-2f7310766ce1 · outbound

This paper cites Gpt-4o: The cutting-edge advance- ment in multimodal llm.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Gpt-4o: The cutting-edge advance- ment in multimodal llm

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.636959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6b6f1835-d10b-4e24-ae05-668478a595b6 · outbound

This paper cites VLM-R$^3$: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving VLM-R$^3$: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:38:37.829832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b4225f2d-f860-4ad9-9a66-e2375c4d7868 · outbound

This paper cites Imagine while Reasoning in Space: Multimodal Visualization-of-Thought.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Imagine while Reasoning in Space: Multimodal Visualization-of-Thought

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-16T23:09:34.995208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6ba9468c-03ce-428e-8273-939cc7b96e70 · outbound

This paper cites Let’s verify step by step.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Let’s verify step by step

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.613542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f2ec3220-6993-45e7-afe4-3c0d2f6efae1 · outbound

This paper cites Ovis: Structural Embedding Alignment for Multimodal Large Language Model.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Ovis: Structural Embedding Alignment for Multimodal Large Language Model

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:38:37.851700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1e36752f-b7ee-425b-abb5-f51d4bf94c52 · outbound

This paper cites Multi-task collaborative network for joint referring expression comprehension and segmentation.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Multi-task collaborative network for joint referring expression comprehension and segmentation

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.545563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d8c4ef7e-50ba-450a-b859-78162166a43d · outbound

This paper cites Compositional chain-of-thought prompting for large multimodal models.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Compositional chain-of-thought prompting for large multimodal models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.570785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6836b733-779b-4a40-b565-ab87d298e1bd · outbound

This paper cites Reason2drive: Towards 9 interpretable and chain-based reasoning for autonomous driv- ing.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Reason2drive: Towards 9 interpretable and chain-based reasoning for autonomous driv- ing

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.584144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e2e20f1b-d2c2-44f1-afe6-ad9fd9f22a31 · outbound

This paper cites Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:38:37.843547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 27d5bed9-c990-4b7d-bc7a-506ff9028bdf · outbound

This paper cites Kosmos-2: Grounding Multimodal Large Language Models to the World.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Kosmos-2: Grounding Multimodal Large Language Models to the World

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-16T22:38:37.847515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7ed99d0c-44d5-4e0c-acab-272436ffcb01 · outbound

This paper cites Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers

Reference 26

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T22:38:37.782622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1f895ce6-d123-4730-af20-68e3a7d0c3f4 · outbound

This paper cites Agentthink: A unified framework for tool-augmented chain-of-thought reasoning in vision-language models for autonomous driving.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Agentthink: A unified framework for tool-augmented chain-of-thought reasoning in vision-language models for autonomous driving

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:38:37.838915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b1496d82-5aa3-4121-bd5b-91d42061e7a1 · outbound

This paper cites Nuscenes-qa: A multi-modal visual question answering benchmark for autonomous driving scenario.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Nuscenes-qa: A multi-modal visual question answering benchmark for autonomous driving scenario

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.616933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 796c6162-006a-427b-8054-22d5d255bd9e · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Learning transferable visual models from natural language supervi- sion

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.610463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0ac72360-876e-43b6-b64a-9355f6083418 · outbound

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

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving A re- duction of imitation learning and structured prediction to no-regret online learning

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.538085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 576284b4-18ff-4459-8c11-2ee8401f9887 · outbound

This paper cites Visual cot: Advancing multi-modal language models with a comprehen- sive dataset and benchmark for chain-of-thought reasoning.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Visual cot: Advancing multi-modal language models with a comprehen- sive dataset and benchmark for chain-of-thought reasoning

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.593907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 420aeb95-a930-453a-9458-c2d39ba4d45b · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-16T22:38:37.787587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f3e7f2e0-f35c-443c-b62a-4bfc073645f3 · outbound

This paper cites VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-16T22:38:37.859935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 130f7f11-fe50-4878-a24d-315f3df4f5b1 · outbound

This paper cites DriveLM: Driving with Graph Visual Question Answering.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving DriveLM: Driving with Graph Visual Question Answering

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:38:37.855821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4fba5927-37cc-447c-b704-b4f8d23d638e · outbound

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

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-16T22:38:37.760388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation db83a0d1-2549-4ae9-9fd5-74de9ad7cb6b · outbound

This paper cites Visual Agents as Fast and Slow Thinkers.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Visual Agents as Fast and Slow Thinkers

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:38:37.777037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0f425a24-b209-4cc5-9266-1079a6b21814 · outbound

This paper cites MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:38:37.764312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1bc3df45-86b4-4ddd-9b40-1aec6c4e8f53 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-05-16T22:38:37.772489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 32e78463-99d1-445e-80d2-2ed4ff4e647b · outbound

This paper cites Llamav-o1: Rethinking step-by-step visual reasoning in llms.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Llamav-o1: Rethinking step-by-step visual reasoning in llms

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.607170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 446efc04-e94b-44c4-b7e2-3b8c8ae20c1d · outbound

This paper cites Llamav-o1: Rethinking step-by-step visual reasoning in llms.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Llamav-o1: Rethinking step-by-step visual reasoning in llms

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.552301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e2100763-cd79-493e-9e2e-8af1e1eed853 · outbound

This paper cites Om- nidrive: A holistic vision-language dataset for autonomous driving with counterfactual reasoning.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Om- nidrive: A holistic vision-language dataset for autonomous driving with counterfactual reasoning

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.604048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7e6c7e1c-b8ef-4da5-bbe4-0e89317a201e · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-05-16T22:38:37.869206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4ec048b3-0182-41a3-bd39-1310f8f6c5ea · outbound

This paper cites Chain-of- thought prompting elicits reasoning in large language models.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Chain-of- thought prompting elicits reasoning in large language models

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.560448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3a9ee09b-52ed-4712-95f2-88e04e92af92 · outbound

This paper cites V?: Guided visual search as a core mechanism in multimodal llms.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving V?: Guided visual search as a core mechanism in multimodal llms

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.587293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5bdcf2d9-0f88-491e-a97b-7ec865a5f00b · outbound

This paper cites Llava-cot: Let vision language models reason step-by-step.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Llava-cot: Let vision language models reason step-by-step

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.541770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b2ba822c-5688-4be4-a143-01c8472bc63d · outbound

This paper cites Llava-cot: Let vision language models reason step-by-step.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Llava-cot: Let vision language models reason step-by-step

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.581112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 81d9e5a5-a3e2-4769-812b-6a52ed018297 · outbound

This paper cites Drivegpt4: Interpretable end-to-end autonomous driving via large language model.IEEE Robotics and Automation Letters.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Drivegpt4: Interpretable end-to-end autonomous driving via large language model.IEEE Robotics and Automation Letters

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.601007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 06be3bcc-8d74-4ced-b42d-4ba96826ed5f · outbound

This paper cites Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:38:37.768730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7e8fe309-d0af-4a50-87a4-d32b5717e7ad · outbound

This paper cites What makes good examples for visual in-context learning?Advances in Neural Information Processing Systems, 36:17773–17794.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving What makes good examples for visual in-context learning?Advances in Neural Information Processing Systems, 36:17773–17794

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.524038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 13849400-eff2-4142-ae61-9293662ee7f7 · outbound

This paper cites Prompt highlighter: Interactive control for multi- modal llms.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Prompt highlighter: Interactive control for multi- modal llms

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.590402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7b84bc3a-c88c-40c8-86a7-2406634d6c31 · outbound

This paper cites Ddcot: Duty-distinct chain-of-thought prompting for multimodal reasoning in language models.Advances in Neu- ral Information Processing Systems, 36:5168–5191.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Ddcot: Duty-distinct chain-of-thought prompting for multimodal reasoning in language models.Advances in Neu- ral Information Processing Systems, 36:5168–5191

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.498122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f95b8e37-6aec-401d-94c5-ebcea50c7a13 · outbound

This paper cites Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:38:37.792767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 395d273a-5215-4e19-ab6f-c238982726c1 · outbound

This paper cites Seqtr: A simple yet universal network for visual grounding.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Seqtr: A simple yet universal network for visual grounding

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.518728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8a88a8c1-d623-400f-897d-384a0de0dc56 · outbound

This paper cites • 9-10:All steps correctly match or closely reflect the reference.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving • 9-10:All steps correctly match or closely reflect the reference

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.574587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 71831751-c947-4cf1-91e0-96c823804e5e · outbound

This paper cites •9-10:Captures almost all critical information.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving •9-10:Captures almost all critical information

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.567273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8a2421e4-0b27-421a-90c0-310092a27082 · outbound

This paper cites •9-10:Correctly identifies and prioritizes key dangers.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving •9-10:Correctly identifies and prioritizes key dangers

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.556444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d85d5b7c-caa5-4507-a844-58fb8535f620 · outbound

This paper cites • 9-10:Fully compliant with legal and safe driving prac- tices.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving • 9-10:Fully compliant with legal and safe driving prac- tices

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.578203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4026a917-dc60-4afd-8753-23ca76186f42 · outbound

This paper cites • 9-10:Clearly understands all relevant objects and their relationships.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving • 9-10:Clearly understands all relevant objects and their relationships

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.623230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d08ac08e-a689-4aca-98bf-16841a61984b · outbound

This paper cites •9-10:No redundancy, very concise.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving •9-10:No redundancy, very concise

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.563912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a43057d9-d6c0-4000-aa5c-d0d573fd6f0a · outbound

This paper cites •9-10:No hallucinations, all reasoning is grounded.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving •9-10:No hallucinations, all reasoning is grounded

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.633307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c4accc52-a18c-4455-904b-b14c47b6037b · outbound

This paper cites •9-10:Nearly complete semantic coverage.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving •9-10:Nearly complete semantic coverage

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.626788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b2904002-0484-421d-8e39-c5a2de645692 · outbound

This paper cites •9-10:Displays strong commonsense understanding.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving •9-10:Displays strong commonsense understanding

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.629954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1aa9d7e0-6bef-429b-9e42-7afedfea4b22 · outbound

This paper cites •9-10:No critical steps missing.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving •9-10:No critical steps missing

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.620021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 78080660-7de0-445c-97da-39a46522218f · outbound

This paper cites • 9-10:Highly specific and directly relevant to the driv- ing scenario.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving • 9-10:Highly specific and directly relevant to the driv- ing scenario

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.548923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 278b306b-a501-4b82-9e54-59bf62e1b649 · outbound

This paper cites • 9-10:No significant details are missing; response is comprehensive and complete.

OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving • 9-10:No significant details are missing; response is comprehensive and complete

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T00:13:44.531263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

Observation b0ae1149-9339-4a00-a69a-5f07d44c1aa4 · inbound

CritiqueDriveVLM: From Verifier-Guided Reinforcement Learning to Latent Thought Distillation for Autonomous Driving cites this paper.

CritiqueDriveVLM: From Verifier-Guided Reinforcement Learning to Latent Thought Distillation for Autonomous Driving OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-11T21:09:01.431209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f4670d0-8c52-4ed1-8de4-ab39b50d4d4c · inbound

WorkDrive: Roadwork Chain of Causation for Autonomous Driving cites this paper.

WorkDrive: Roadwork Chain of Causation for Autonomous Driving OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T01:19:54.962342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77a7e98e-5784-4616-913c-0a6729d7b04b · inbound

ObsDriveBench: Benchmarking Multimodal Understanding under Adverse Weather with Observability Awareness cites this paper.

ObsDriveBench: Benchmarking Multimodal Understanding under Adverse Weather with Observability Awareness OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-30T19:51:03.671252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.