DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models | Paper Citation Record

Observation ccf5a602-8584-4e0b-baeb-56156e970724 · outbound

This paper cites Flamingo: a visual language model for few-shot learning.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Flamingo: a visual language model for few-shot learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2f5f7b5-a506-4685-b2a3-2377c7674897 · outbound

This paper cites Qwen3-VL Technical Report.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Qwen3-VL Technical Report

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-02T11:46:55.645434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation abd0245b-9c31-4e3f-a3f4-e997f35acf6e · outbound

This paper cites Qwen2.5-VL Technical Report.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Qwen2.5-VL Technical Report

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-02T11:46:55.648478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation bbbd61e1-c8f3-420c-a162-e50a31b2b5cb · outbound

This paper cites PaliGemma: A versatile 3B VLM for transfer.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models PaliGemma: A versatile 3B VLM for transfer

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-02T11:46:55.633298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 49ad2854-97ea-48a3-ad4a-d0b4ee09e0b1 · outbound

This paper cites an unresolved cited work.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 369a943b-0c55-4b83-845c-c7f3658c6899 · outbound

This paper cites π0: A vision-language-action flow model for general robot control.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models π0: A vision-language-action flow model for general robot control

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a47bdf3e-2509-4aa9-9c72-5f31048fb6c8 · outbound

This paper cites InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-02T11:46:55.638894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0495db46-511b-4d82-9032-17f7a70d1d70 · outbound

This paper cites Diffusion policy: Visuomotor policy learning via action diffusion.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Diffusion policy: Visuomotor policy learning via action diffusion

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f13f6095-bf0e-4f98-9dd9-28d7ac9ae1f4 · outbound

This paper cites Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-07-02T11:46:55.636251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 20b7a120-a796-479a-8510-223bb3597978 · outbound

This paper cites Molmo and pixmo: Open weights and open data for state-of-the-art vision-language models.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Molmo and pixmo: Open weights and open data for state-of-the-art vision-language models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71c96f1d-84ed-4942-bf21-aa3d4d9f4c95 · outbound

This paper cites Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dd58261-06c7-43f7-8ef2-c927534e9c04 · outbound

This paper cites TALL: Temporal activity localization via language query.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models TALL: Temporal activity localization via language query

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37f4d66c-d488-4476-98a5-0350c8a2f7ca · outbound

This paper cites Localizing moments in video with natural language.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Localizing moments in video with natural language

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 574c89ba-5672-4fff-9c3d-3b004d70f5f5 · outbound

This paper cites Denoising diffusion probabilistic models.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Denoising diffusion probabilistic models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51e06bdb-d2c9-447d-8612-64500553faeb · outbound

This paper cites Lora: Low-rank adaptation of large language models.Iclr, 1(2):3, 2022.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Lora: Low-rank adaptation of large language models.Iclr, 1(2):3, 2022

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2a3ab53-3dfc-45a8-ad00-215c2cf06940 · outbound

This paper cites VTimeLLM: Empower LLM to grasp video moments.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models VTimeLLM: Empower LLM to grasp video moments

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1ca992f-2d90-4deb-bce3-73f44f9ed9e4 · outbound

This paper cites Prismatic vlms: Investigating the design space of visually-conditioned language models.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Prismatic vlms: Investigating the design space of visually-conditioned language models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfee4243-3740-4c21-ba9e-0c2c1f25203c · outbound

This paper cites Referitgame: Referring to objects in photographs of natural scenes.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Referitgame: Referring to objects in photographs of natural scenes

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dae655b-af99-4981-8e5e-be67ccb24be7 · outbound

This paper cites Language-free training for zero-shot video grounding.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Language-free training for zero-shot video grounding

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a42c444d-2c8b-4c6f-b415-0e74a11f4f7b · outbound

This paper cites OpenVLA: An open-source vision-language-action model.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models OpenVLA: An open-source vision-language-action model

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dfa550c-87e6-4a06-b4f2-fa3e4e705ec5 · outbound

This paper cites Dense- captioning events in videos.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Dense- captioning events in videos

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0df7b436-0101-47c3-8394-4f12fb37bf14 · outbound

This paper cites BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22c7016f-6232-4ada-a241-944be645b0ef · outbound

This paper cites Mvbench: A comprehensive multi-modal video understanding benchmark.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Mvbench: A comprehensive multi-modal video understanding benchmark

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 791f67d9-2455-404c-a022-f47cc7db2edc · outbound

This paper cites Back to Basics: Let Denoising Generative Models Denoise.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Back to Basics: Let Denoising Generative Models Denoise

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-02T11:46:55.642747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8f659ae9-0f3c-4e94-ab1e-499bcadc089f · outbound

This paper cites Evaluating real-world robot manipulation policies in simulation.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Evaluating real-world robot manipulation policies in simulation

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f411fe3c-e914-4462-91ca-471357330ada · outbound

This paper cites UniVTG: Towards unified video-language temporal grounding.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models UniVTG: Towards unified video-language temporal grounding

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cbceac8-27eb-4801-827c-92fcd496913a · outbound

This paper cites an unresolved cited work.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17628147-70c9-47f9-a981-2470f4ee4642 · outbound

This paper cites Libero: Benchmarking knowledge transfer for lifelong robot learning.Advances in Neural Information Processing Systems, 36:44776–44791, 2023.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Libero: Benchmarking knowledge transfer for lifelong robot learning.Advances in Neural Information Processing Systems, 36:44776–44791, 2023

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e6e92c4-34f9-4f93-9cde-913d6c952b3f · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca1229c5-4588-4b09-bace-39d432ba5e56 · outbound

This paper cites Flow straight and fast: Learning to generate and transfer data with rectified flow.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Flow straight and fast: Learning to generate and transfer data with rectified flow

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32c98f78-c653-43c9-80e5-7a6b4cd2a1f3 · outbound

This paper cites Unitime: A language-empowered unified model for cross-domain time series forecasting.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Unitime: A language-empowered unified model for cross-domain time series forecasting

Reference 31

Resolution: malformed identifier; arxiv_id, observed 2026-07-02T11:46:55.651527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation daf17f2c-62f8-4cae-b998-d210a1bc9d71 · outbound

This paper cites an unresolved cited work.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 798a8ea7-e220-42e8-85a8-2d3428905f9f · outbound

This paper cites Decoupled weight decay regularization.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Decoupled weight decay regularization

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 144ab426-3db2-4f17-9c66-88a0b4c00fa4 · outbound

This paper cites Valley: Video assistant with large language model enhanced ability.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Valley: Video assistant with large language model enhanced ability

Reference 34

Resolution: verified exact; doi, observed 2026-06-28T03:11:30.318499Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation cd70a692-d87c-447b-bc15-900ed1a3a118 · outbound

This paper cites Video-ChatGPT: Towards detailed video understanding via large vision and language models.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Video-ChatGPT: Towards detailed video understanding via large vision and language models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f39d479a-2aec-48df-9392-2455b6a3d960 · outbound

This paper cites Yuille, and Kevin Murphy.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Yuille, and Kevin Murphy

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41069113-3eaf-46a5-b9d6-c279929d4e8e · outbound

This paper cites Trespassing the boundaries: Labeling temporal bounds for object interactions in egocentric video.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Trespassing the boundaries: Labeling temporal bounds for object interactions in egocentric video

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97aee435-53ad-4367-8f5a-8f8ab25b32e5 · outbound

This paper cites Snag: Scalable and accurate video grounding.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Snag: Scalable and accurate video grounding

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fde93205-503a-4f94-8d15-1eac75398095 · outbound

This paper cites Zero-shot natural language video localization.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Zero-shot natural language video localization

Reference 39

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1ddca02-e7af-4671-aa2f-b63e6d1b100d · outbound

This paper cites Henriques, Yang Liu, Andrew Zisserman, and Samuel Albanie.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Henriques, Yang Liu, Andrew Zisserman, and Samuel Albanie

Reference 40

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c03464e7-fb9a-4817-9621-e3248787f36b · outbound

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

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Open x- embodiment: Robotic learning datasets and rt-x models: Open x-embodiment collaboration 0

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ca90936-b3f9-47a2-a756-0b2f8201f8e7 · outbound

This paper cites Scalable diffusion models with transformers.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Scalable diffusion models with transformers

Reference 42

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b808d883-fc05-4375-960c-89a75d39fd09 · outbound

This paper cites Movie Gen: A Cast of Media Foundation Models.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Movie Gen: A Cast of Media Foundation Models

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-07-02T11:46:55.631004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 95c57808-42c6-4aab-b54d-fcae42e2414c · outbound

This paper cites Enrich and detect: Video temporal grounding with multimodal LLMs.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Enrich and detect: Video temporal grounding with multimodal LLMs

Reference 44

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97057a09-647f-4a5a-8e9b-d28f0394a72a · outbound

This paper cites Momentor: Advancing video large language model with fine-grained temporal reasoning.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Momentor: Advancing video large language model with fine-grained temporal reasoning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7215a9a-bee1-4df8-a38e-97cbf0ada2f2 · outbound

This paper cites Chatvtg: Video temporal grounding via chat with video dialogue large language models.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Chatvtg: Video temporal grounding via chat with video dialogue large language models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cc68753-7076-4d98-b28c-40f8ed9f5351 · outbound

This paper cites TimeChat: A time-sensitive multimodal large language model for long video understanding.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models TimeChat: A time-sensitive multimodal large language model for long video understanding

Reference 47

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1caf53bf-d45b-45cd-ad5a-d2ab1025957c · outbound

This paper cites High- resolution image synthesis with latent diffusion models.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models High- resolution image synthesis with latent diffusion models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 012bd99f-ca27-4811-a4da-e8f0aa6c523f · outbound

This paper cites Hollywood in homes: Crowdsourcing data collection for activity understanding.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Hollywood in homes: Crowdsourcing data collection for activity understanding

Reference 49

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2297b42-08f2-4f5c-9911-38ce6827710f · outbound

This paper cites Score-based generative modeling through stochastic differential equations.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Score-based generative modeling through stochastic differential equations

Reference 50

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b9516eb-9718-4fec-85e3-347a492617d4 · outbound

This paper cites Moment quantization for video temporal grounding.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Moment quantization for video temporal grounding

Reference 51

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61d34f0c-a5b5-47d7-9b1a-49af527c4358 · outbound

This paper cites Attention is all you need.Advances in neural information processing systems, 30, 2017.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Attention is all you need.Advances in neural information processing systems, 30, 2017

Reference 52

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c26f7c0-931a-4256-8799-d8d0f9e8eb9a · outbound

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

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Wan: Open and Advanced Large-Scale Video Generative Models

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-07-02T11:46:55.663465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 499609a7-c8ef-4e56-817a-0679e2ae38f6 · outbound

This paper cites COSMO: COntrastive Streamlined MultimOdal Model with Interleaved Pre-Training.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models COSMO: COntrastive Streamlined MultimOdal Model with Interleaved Pre-Training

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-07-02T11:46:55.666603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 2b4ef27c-3f60-4165-ae80-ced4a3e76709 · outbound

This paper cites InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Reference 55

Resolution: verified exact; local_arxiv, observed 2026-07-02T11:46:55.669598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 815b454e-b518-40fb-b2f0-9ca95622d5ac · outbound

This paper cites InternVid: A large-scale video-text dataset for multimodal understanding and generation.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models InternVid: A large-scale video-text dataset for multimodal understanding and generation

Reference 56

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 737b8a5d-8c30-4bc3-9818-ba8fe654a9b6 · outbound

This paper cites Vla-adapter: An effective paradigm for tiny-scale vision-language-action model.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Vla-adapter: An effective paradigm for tiny-scale vision-language-action model

Reference 57

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4438bce-39e3-4a81-88d8-8fcb2c7a5e47 · outbound

This paper cites HawkEye: Training Video-Text LLMs for Grounding Text in Videos.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models HawkEye: Training Video-Text LLMs for Grounding Text in Videos

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-07-02T11:46:55.672672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f614ba8c-3bb3-4bad-befb-d39b9cd4c338 · outbound

This paper cites Towards visual grounding: A survey.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Towards visual grounding: A survey.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025

Reference 59

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd1a0dff-cd6c-42ed-9153-a053061bc930 · outbound

This paper cites an unresolved cited work.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Unresolved cited work

Reference 60

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8993a40a-b4e5-44ee-b1d1-47d6c70e7627 · outbound

This paper cites Vlaser: Vision-language-action model with synergistic embodied reasoning.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Vlaser: Vision-language-action model with synergistic embodied reasoning

Reference 61

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e391880d-6be2-4892-b3f3-568f793cf3f4 · outbound

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

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models World Action Models are Zero-shot Policies

Reference 62

Resolution: verified exact; local_arxiv, observed 2026-07-02T11:46:55.654698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6837e88c-06f0-44dd-942d-02228bcc87f7 · outbound

This paper cites Modeling context in referring expressions.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Modeling context in referring expressions

Reference 63

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d08aa57-362b-4f3e-8a93-5c3cf1e774d8 · outbound

This paper cites Self-chained image-language model for video localization and question answering.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Self-chained image-language model for video localization and question answering

Reference 64

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7367b85-f001-45c6-9f7e-acf84312fb1f · outbound

This paper cites Fast-WAM: Do World Action Models Need Test-time Future Imagination?.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Fast-WAM: Do World Action Models Need Test-time Future Imagination?

Reference 65

Resolution: verified exact; local_arxiv, observed 2026-07-02T11:46:55.660321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e034433b-9690-4454-93e8-c8ec5b1434de · outbound

This paper cites Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi

Reference 66

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b277255-8762-4f73-a6bd-91c2fae93455 · outbound

This paper cites Hierarchical video-moment retrieval and step-captioning.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Hierarchical video-moment retrieval and step-captioning

Reference 67

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5408c1d3-ca35-48bc-b506-83cf769e3b7a · outbound

This paper cites Video-LLaMA: An instruction-tuned audio-visual language model for video understanding.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Video-LLaMA: An instruction-tuned audio-visual language model for video understanding

Reference 68

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e3979c6-1517-4f9f-9dfb-ed7d09fa703d · outbound

This paper cites VLM4VLA: Revis- iting vision-language-models in vision-language-action models.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models VLM4VLA: Revis- iting vision-language-models in vision-language-action models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 772d6add-ffbc-4ca8-8df8-ff7cedae1b29 · outbound

This paper cites arXiv preprint arXiv:2512.14698 , year=.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models arXiv preprint arXiv:2512.14698 , year=

Reference 70

Resolution: verified exact; arxiv_id, observed 2026-07-02T11:46:55.657654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 290e7c1c-aa05-40ec-9f58-290336248b9a · outbound

This paper cites (Br +B h)Rn(H) + (Br +B h)2 r log(2/δ) n # . (13) Furthermore, sincew(t)≥1, R(0)− R( ˆh)≥E ∥m(X)∥ 2 2 −App H −Cτ −2.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models (Br +B h)Rn(H) + (Br +B h)2 r log(2/δ) n # . (13) Furthermore, sincew(t)≥1, R(0)− R( ˆh)≥E ∥m(X)∥ 2 2 −App H −Cτ −2

Reference 71

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c77c1107-59b9-4782-8bd7-99799bcbe3a0 · outbound

This paper cites 16 For fixed (r, t), the map u7→ϕ r,t(u) =w(t)∥u−r∥ 2 2 is Lipschitz in u with constant at most 2τ −2(Bh +B r).

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models 16 For fixed (r, t), the map u7→ϕ r,t(u) =w(t)∥u−r∥ 2 2 is Lipschitz in u with constant at most 2τ −2(Bh +B r)

Reference 72

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cec65d27-60e5-46d8-af3b-1d290597ae96 · outbound

This paper cites Decomposing the right-hand side: L(ˆh)− L(m) = L(ˆh)− L(h ⋆ H) + L(h⋆ H)− L(m) = L(ˆh)− L(h ⋆ H) + AppH.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Decomposing the right-hand side: L(ˆh)− L(m) = L(ˆh)− L(h ⋆ H) + L(h⋆ H)− L(m) = L(ˆh)− L(h ⋆ H) + AppH

Reference 73

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 455d2768-f2aa-4e32-bd24-b910a975abfb · outbound

This paper cites 17 Conversely, for any full-target predictor H, define hH(X)≜H( ˜X)−g(z) , where ˜X= (y t −(1− t)g(z), t, z).

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models 17 Conversely, for any full-target predictor H, define hH(X)≜H( ˜X)−g(z) , where ˜X= (y t −(1− t)g(z), t, z)

Reference 74

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e83daf3e-1dd1-469e-9fd0-68cc1af1a474 · outbound

This paper cites an unresolved cited work.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Unresolved cited work

Reference 75

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2eb9235e-6bc1-4216-b3ff-b7c09a34c83a · outbound

This paper cites an unresolved cited work.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Unresolved cited work

Reference 76

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fc261e5-7b80-41a7-9437-cac0c5df0471 · outbound

This paper cites an unresolved cited work.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Unresolved cited work

Reference 77

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcbb69e3-ce2e-4d11-a366-db4e54a5d4ba · outbound

This paper cites an unresolved cited work.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Unresolved cited work

Reference 78

Resolution: unresolved; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9215499-1e1d-4692-8c83-66965cac3320 · outbound

This paper cites LinearLinearLinear noise𝑡z! Self-Attention+𝑦Linear Sampler 𝑦!mix Base Predictor MLPTokenizerOr z! z! 𝑦.

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models LinearLinearLinear noise𝑡z! Self-Attention+𝑦Linear Sampler 𝑦!mix Base Predictor MLPTokenizerOr z! z! 𝑦

Reference 79

Resolution: malformed identifier; no resolver link, observed 2026-06-28T03:03:23.071178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers