Paper Citation Record · LEDGER

MTA: Multimodal Task Alignment for BEV Perception and Captioning

As of 15 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 1 inbound Pith citation observation for arXiv:2411.10639.

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

pith.paper-citation-record.v1
2411.10639 v2

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T19:32:14.153900Z

measured 50 of 50 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:26:40.646360Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T15:26:42.549976Z

Reference resolution

49 of 49 outbound references displayed

verified exact0
verified fuzzy46
unresolved3
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a286a36e-cfde-4af3-96e6-193e8123dffc · outbound

This paper cites METEOR: An Au- tomatic Metric for MT Evaluation with Improved Correla- tion with Human Judgments.

MTA: Multimodal Task Alignment for BEV Perception and Captioning METEOR: An Au- tomatic Metric for MT Evaluation with Improved Correla- tion with Human Judgments

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.678020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a97ef46c-5d46-4cbe-8662-c239dd29ab29 · outbound

This paper cites Lang, Sourabh V ora, Venice Erin Liong, Qiang Xu, Anush Krishnan, Yu Pan, Gi- ancarlo Baldan, and Oscar Beijbom.

MTA: Multimodal Task Alignment for BEV Perception and Captioning Lang, Sourabh V ora, Venice Erin Liong, Qiang Xu, Anush Krishnan, Yu Pan, Gi- ancarlo Baldan, and Oscar Beijbom

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.668004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 26319c7d-d4da-4e16-bb57-390c2ef5d34a · outbound

This paper cites In- ternLM2 Technical Report.

MTA: Multimodal Task Alignment for BEV Perception and Captioning In- ternLM2 Technical Report

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.657779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 392df1de-3ed1-41e6-9cc0-64cb5b00bfe9 · outbound

This paper cites Rehg, and Chao Zheng.

MTA: Multimodal Task Alignment for BEV Perception and Captioning Rehg, and Chao Zheng

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.646923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 078278d7-8649-4397-981e-761ba0ffbd8f · outbound

This paper cites End-to-end Autonomous Driving: Challenges and Frontiers.

MTA: Multimodal Task Alignment for BEV Perception and Captioning End-to-end Autonomous Driving: Challenges and Frontiers

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.636171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2383dca6-332b-4ca5-b93c-5055a0f462aa · outbound

This paper cites End-to-End 3D Dense Captioning with V ote2Cap-DETR.

MTA: Multimodal Task Alignment for BEV Perception and Captioning End-to-End 3D Dense Captioning with V ote2Cap-DETR

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.626594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 08695401-f447-4a32-8da9-4c07c9044e04 · outbound

This paper cites V ote2Cap-DETR++: Decoupling Localization and Describ- ing for End-to-End 3D Dense Captioning.

MTA: Multimodal Task Alignment for BEV Perception and Captioning V ote2Cap-DETR++: Decoupling Localization and Describ- ing for End-to-End 3D Dense Captioning

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.615883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3f141258-fb25-487c-a759-907d35a498bd · outbound

This paper cites an unresolved cited work.

MTA: Multimodal Task Alignment for BEV Perception and Captioning Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-12T19:32:14.605993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 725fbf58-ff26-4b3f-a44c-e0000d374a51 · outbound

This paper cites InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks.

MTA: Multimodal Task Alignment for BEV Perception and Captioning InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.595277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation eeb2e83e-8c6f-48ed-a4fc-623f43e65fc7 · outbound

This paper cites ST-P3: End-to-end Vision-based Au- tonomous Driving via Spatial-Temporal Feature Learning.

MTA: Multimodal Task Alignment for BEV Perception and Captioning ST-P3: End-to-end Vision-based Au- tonomous Driving via Spatial-Temporal Feature Learning

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.585277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 639306cd-9d7b-41d7-bcab-0527f4bff043 · outbound

This paper cites Planning-oriented Autonomous Driving.

MTA: Multimodal Task Alignment for BEV Perception and Captioning Planning-oriented Autonomous Driving

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.573135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3d2df9a6-f293-4597-b19c-db9c863ad356 · outbound

This paper cites EMMA: End-to-End Multimodal Model for Autonomous Driving.

MTA: Multimodal Task Alignment for BEV Perception and Captioning EMMA: End-to-End Multimodal Model for Autonomous Driving

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.561424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3e7051d3-6095-4831-8cad-9a075df5a55a · outbound

This paper cites Le, Yunhsuan Sung, Zhen Li, and Tom Duerig.

MTA: Multimodal Task Alignment for BEV Perception and Captioning Le, Yunhsuan Sung, Zhen Li, and Tom Duerig

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.548734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6eae8335-299d-47df-8695-6948b558ddc4 · outbound

This paper cites Bench2Drive: Towards Multi-Ability Bench- marking of Closed-Loop End-To-End Autonomous Driving.

MTA: Multimodal Task Alignment for BEV Perception and Captioning Bench2Drive: Towards Multi-Ability Bench- marking of Closed-Loop End-To-End Autonomous Driving

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.536434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b5d55b94-5677-48ac-84af-79cc313a74a4 · outbound

This paper cites V AD: Vectorized Scene Representation for Efficient Autonomous Driving.

MTA: Multimodal Task Alignment for BEV Perception and Captioning V AD: Vectorized Scene Representation for Efficient Autonomous Driving

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.524840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4ef75481-1973-423b-b96c-e103f3384c43 · outbound

This paper cites TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes.

MTA: Multimodal Task Alignment for BEV Perception and Captioning TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.513422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation add425f1-8a70-43f9-b8e0-5f6a88b087af · outbound

This paper cites MaPLe: Multi-modal Prompt Learning.

MTA: Multimodal Task Alignment for BEV Perception and Captioning MaPLe: Multi-modal Prompt Learning

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.501930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c973eec2-addd-46ee-b60a-d7c0b968bebd · outbound

This paper cites Driving Everywhere with Large Language Model Policy Adaptation.

MTA: Multimodal Task Alignment for BEV Perception and Captioning Driving Everywhere with Large Language Model Policy Adaptation

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.490592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8ad6e984-59ac-44a6-b104-7692462b5724 · outbound

This paper cites BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models.

MTA: Multimodal Task Alignment for BEV Perception and Captioning BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T19:32:14.054228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a2b9821-72c2-4293-bcd9-944f4330e743 · outbound

This paper cites BEVFormer: Learning Bird’s-Eye-View Representation from Multi- Camera Images via Spatiotemporal Transformers.

MTA: Multimodal Task Alignment for BEV Perception and Captioning BEVFormer: Learning Bird’s-Eye-View Representation from Multi- Camera Images via Spatiotemporal Transformers

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.473009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e8b4156f-a2bb-4245-9c97-32dff58c00b6 · outbound

This paper cites AIDE: An Automatic Data Engine for Object Detection in Au- tonomous Driving.

MTA: Multimodal Task Alignment for BEV Perception and Captioning AIDE: An Automatic Data Engine for Object Detection in Au- tonomous Driving

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.464892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 112919d5-ea2f-41c4-b779-f12bf4ebf32a · outbound

This paper cites BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework.

MTA: Multimodal Task Alignment for BEV Perception and Captioning BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.455587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 05387a8e-eaff-451a-aee2-b99ef078be98 · outbound

This paper cites ROUGE: A Package for Automatic Evalu- ation of Summaries.

MTA: Multimodal Task Alignment for BEV Perception and Captioning ROUGE: A Package for Automatic Evalu- ation of Summaries

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.446019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8f1320ff-62c4-4e12-8bb3-913be02de2e5 · outbound

This paper cites BEVFusion: Multi- 9 Task Multi-Sensor Fusion with Unified Bird’s-Eye View Representation.

MTA: Multimodal Task Alignment for BEV Perception and Captioning BEVFusion: Multi- 9 Task Multi-Sensor Fusion with Unified Bird’s-Eye View Representation

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.435380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a593da1f-e0e1-455b-aa18-400bd765c6bd · outbound

This paper cites The Llama 3 Herd of Models.

MTA: Multimodal Task Alignment for BEV Perception and Captioning The Llama 3 Herd of Models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.424061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e3e59937-63d6-4ee4-aed8-189270d8515c · outbound

This paper cites Position: Prospective of Autonomous Driving - Multimodal LLMs, World Mod- els, Embodied Intelligence, AI Alignment, and Mamba.

MTA: Multimodal Task Alignment for BEV Perception and Captioning Position: Prospective of Autonomous Driving - Multimodal LLMs, World Mod- els, Embodied Intelligence, AI Alignment, and Mamba

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.414657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5dc38668-dbe9-43c5-a0e9-f221c782358c · outbound

This paper cites DRAMA: Joint Risk Localization and Cap- tioning in Driving.

MTA: Multimodal Task Alignment for BEV Perception and Captioning DRAMA: Joint Risk Localization and Cap- tioning in Driving

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.402369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7d5236cf-d935-436f-a806-143825c5f2d1 · outbound

This paper cites A Language Agent for Autonomous Driving.

MTA: Multimodal Task Alignment for BEV Perception and Captioning A Language Agent for Autonomous Driving

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.390258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 77691cd2-3185-49e6-8cd7-82aec81b005a · outbound

This paper cites LingoQA: Video Question Answering for Autonomous Driving.

MTA: Multimodal Task Alignment for BEV Perception and Captioning LingoQA: Video Question Answering for Autonomous Driving

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.380841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 10c87793-6202-458d-8091-d7946dc0a88b · outbound

This paper cites Qi, Runzhou Ge, Kratarth Goel, Zoey Yang, Scott Ettinger, Rami Al-Rfou, Dragomir Anguelov, and Yin Zhou.

MTA: Multimodal Task Alignment for BEV Perception and Captioning Qi, Runzhou Ge, Kratarth Goel, Zoey Yang, Scott Ettinger, Rami Al-Rfou, Dragomir Anguelov, and Yin Zhou

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.369688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 278b70f0-6816-47fb-ba74-170171150e36 · outbound

This paper cites Bleu: a Method for Automatic Evaluation of Machine Translation.

MTA: Multimodal Task Alignment for BEV Perception and Captioning Bleu: a Method for Automatic Evaluation of Machine Translation

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.359513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation edc1093e-a856-4046-b73b-c4f15788fce1 · outbound

This paper cites NuScenes-QA: A Multi-Modal Visual Ques- tion Answering Benchmark for Autonomous Driving Sce- nario.

MTA: Multimodal Task Alignment for BEV Perception and Captioning NuScenes-QA: A Multi-Modal Visual Ques- tion Answering Benchmark for Autonomous Driving Sce- nario

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.350818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3b372ac5-7d9f-4f94-83c3-c87a1c3e63e0 · outbound

This paper cites Learning Transferable Visual Models From Natural Language Supervision.

MTA: Multimodal Task Alignment for BEV Perception and Captioning Learning Transferable Visual Models From Natural Language Supervision

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-12T19:32:14.099810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7515c18-3b16-4d13-b943-91a56a458a50 · outbound

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

MTA: Multimodal Task Alignment for BEV Perception and Captioning DriveLM: Driving with Graph Visual Question Answering

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.332725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5bd17e93-fd3f-43a4-b6bb-1e630851895d · outbound

This paper cites Tokenize the World into Object-level Knowledge to Address Long-tail Events in Autonomous Driving.

MTA: Multimodal Task Alignment for BEV Perception and Captioning Tokenize the World into Object-level Knowledge to Address Long-tail Events in Autonomous Driving

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.323116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 11f0f184-521b-4f9e-b466-6313709c4412 · outbound

This paper cites DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models.

MTA: Multimodal Task Alignment for BEV Perception and Captioning DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.314317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8e0e775d-f927-4a0c-9d8d-f9804ebbcd74 · outbound

This paper cites Lawrence Zitnick, and Devi Parikh.

MTA: Multimodal Task Alignment for BEV Perception and Captioning Lawrence Zitnick, and Devi Parikh

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.306055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 84e84d35-fa8d-4d45-8867-05d0ccc8cdd7 · outbound

This paper cites Al- varez.

MTA: Multimodal Task Alignment for BEV Perception and Captioning Al- varez

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.297987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ea5991d9-253d-4792-80ab-2d8554365293 · outbound

This paper cites DETR3D: 3D Object De- tection from Multi-view Images via 3D-to-2D Queries.

MTA: Multimodal Task Alignment for BEV Perception and Captioning DETR3D: 3D Object De- tection from Multi-view Images via 3D-to-2D Queries

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.288727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8705a9cd-bc7f-47c3-a8d0-5ceeef908dab · outbound

This paper cites PARA-Drive: Parallelized Architecture for Real-time Autonomous Driving.

MTA: Multimodal Task Alignment for BEV Perception and Captioning PARA-Drive: Parallelized Architecture for Real-time Autonomous Driving

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.279173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 241a726d-53bd-4835-8136-612c80934ebe · outbound

This paper cites Florence-2: Advancing a Unified Representation for a Va- riety of Vision Tasks.

MTA: Multimodal Task Alignment for BEV Perception and Captioning Florence-2: Advancing a Unified Representation for a Va- riety of Vision Tasks

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.270033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3a0d6df6-9dba-4884-aed3-352d29e7d410 · outbound

This paper cites CoBEVT: Cooperative Bird’s Eye View Semantic Segmentation with Sparse Transformers.

MTA: Multimodal Task Alignment for BEV Perception and Captioning CoBEVT: Cooperative Bird’s Eye View Semantic Segmentation with Sparse Transformers

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.260408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4d057410-af34-4e9a-b3ee-fa5e618edfa7 · outbound

This paper cites Wong, Zhenguo Li, and Hengshuang Zhao.

MTA: Multimodal Task Alignment for BEV Perception and Captioning Wong, Zhenguo Li, and Hengshuang Zhao

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.248644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4a24f17e-59b8-4e4b-9e27-263125f921d0 · outbound

This paper cites BEVFormer v2: Adapt- ing Modern Image Backbones to Bird’s-Eye-View Recogni- tion via Perspective Supervision.

MTA: Multimodal Task Alignment for BEV Perception and Captioning BEVFormer v2: Adapt- ing Modern Image Backbones to Bird’s-Eye-View Recogni- tion via Perspective Supervision

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.236326Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5199b568-f85a-4dc7-a51b-a99d50c2cee9 · outbound

This paper cites BEVDiffuser: Plug-and-Play Diffusion Model for BEV Denoising with Ground-Truth Guidance.

MTA: Multimodal Task Alignment for BEV Perception and Captioning BEVDiffuser: Plug-and-Play Diffusion Model for BEV Denoising with Ground-Truth Guidance

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.223050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 60b98a47-2a22-48fd-8d21-67912726a4f1 · outbound

This paper cites Florence: A New Foundation Model for Computer Vision.

MTA: Multimodal Task Alignment for BEV Perception and Captioning Florence: A New Foundation Model for Computer Vision

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.213540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 18ed83e4-f60a-48b2-bcf3-87a291d48b7c · outbound

This paper cites X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Cap- tioning.

MTA: Multimodal Task Alignment for BEV Perception and Captioning X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Cap- tioning

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.201308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3a11d807-7e4b-4a57-9013-ed99e39a5933 · outbound

This paper cites LLaMA-Adapter: Efficient Fine-tuning of Lan- guage Models with Zero-init Attention.

MTA: Multimodal Task Alignment for BEV Perception and Captioning LLaMA-Adapter: Efficient Fine-tuning of Lan- guage Models with Zero-init Attention

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.191412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation eedb5c2f-ffc9-4c68-846e-8b7d2887aac0 · outbound

This paper cites Learning to Prompt for Vision-Language Models.

MTA: Multimodal Task Alignment for BEV Perception and Captioning Learning to Prompt for Vision-Language Models

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T19:32:14.180712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

Observation 15cb63b7-9c6a-4f8c-9bbf-8c1e62f2a4a6 · inbound

LTDA-Drive: LLMs-guided Generative Models based Long-tail Data Augmentation for Autonomous Driving cites this paper.

LTDA-Drive: LLMs-guided Generative Models based Long-tail Data Augmentation for Autonomous Driving MTA: Multimodal Task Alignment for BEV Perception and Captioning

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-08-07T15:26:42.627301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.