Paper Citation Record · LEDGER

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning

As of 4 August 2026, this Paper Citation Record lists 72 of 72 outbound references and 3 inbound Pith citation observations for arXiv:2512.03963.

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

pith.paper-citation-record.v1
2512.03963 v3

Coverage vector

measured 72 of 72 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-17T02:18:21.718091Z

measured 75 of 75 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-03T06:30:56.289259+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T04:17:27.916261Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

72 of 72 outbound references displayed

verified exact35
verified fuzzy36
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9e924d67-296f-4bc0-97c4-95c6e387773f · outbound

This paper cites GPT-4 Technical Report.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning GPT-4 Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-17T02:18:52.240459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ca102fe4-0294-4bc1-9fbe-3246bf0dcebe · outbound

This paper cites Localizing mo- ments in video with natural language.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Localizing mo- ments in video with natural language

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.929711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation c2da755f-03bf-48c4-8594-4bb41a80e636 · outbound

This paper cites Qwen2.5-VL Technical Report.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Qwen2.5-VL Technical Report

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-17T02:18:52.236564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 2d14289e-c51c-4387-99ec-71096cad233b · outbound

This paper cites UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-17T02:18:52.266369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 23aaa48a-bfdf-4790-98c1-42b278245487 · outbound

This paper cites Dense events grounding in video.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Dense events grounding in video

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.927612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation c6fec625-18a3-4d76-9307-8443d9984044 · outbound

This paper cites Activitynet: A large-scale video benchmark for human activity understanding.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Activitynet: A large-scale video benchmark for human activity understanding

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.925448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6a65651b-f8ad-4a84-80c0-e377032b98ea · outbound

This paper cites Flashvtg: Feature layering and adaptive score handling network for video temporal grounding.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Flashvtg: Feature layering and adaptive score handling network for video temporal grounding

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.923441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation cd5c16b1-0bb6-4f72-b4ca-8e53382e30c7 · outbound

This paper cites Scaling rl to long videos.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Scaling rl to long videos

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-17T02:18:52.378019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 42e182a2-3342-41fe-9686-0d1cf0474f6d · outbound

This paper cites VisRL: Intention-Driven Visual Perception via Reinforced Reasoning.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning VisRL: Intention-Driven Visual Perception via Reinforced Reasoning

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-17T02:18:52.374154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 1b69e8a0-90a9-4dce-8cd0-419b334bec29 · outbound

This paper cites Video-R1: Reinforcing Video Reasoning in MLLMs.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Video-R1: Reinforcing Video Reasoning in MLLMs

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-17T02:18:52.279116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ebccfd11-141e-4040-af8c-0d4fabdf6973 · outbound

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

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.921377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 68b7ba79-714e-4aeb-92c4-ee1a6901d77f · outbound

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

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Tall: Temporal activity localization via language query

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.919212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ecea151b-2de8-4a09-91a9-e993788542b7 · outbound

This paper cites TAR: Temporal Anchor-Constrained Reasoning for Video Temporal Grounding.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning TAR: Temporal Anchor-Constrained Reasoning for Video Temporal Grounding

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:17:07.011358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 520d7b46-2d7f-4254-a6a2-34761e1c5191 · outbound

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

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-17T02:18:52.257349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 169e689b-ea81-47b2-ae35-2c795d170f3c · outbound

This paper cites TRACE: Temporal Grounding Video LLM via Causal Event Modeling.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning TRACE: Temporal Grounding Video LLM via Causal Event Modeling

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-17T02:18:52.385855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation c545c391-4de8-4bf9-9af6-5814e52614dd · outbound

This paper cites Vtimellm: Empower llm to grasp video moments.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Vtimellm: Empower llm to grasp video moments

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.917145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a01b7b66-7d29-4ad0-94ec-e21dfb402f7b · outbound

This paper cites Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-17T02:18:52.289328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 9807d542-83f1-4aec-9b6c-a81ac8618563 · outbound

This paper cites Online Video Understanding: OVBench and VideoChat-Online.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Online Video Understanding: OVBench and VideoChat-Online

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-17T02:18:52.274928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 4623874d-a6f0-4582-b3d5-c36b164e0407 · outbound

This paper cites in the wild.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning in the wild

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.914937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f2974a46-ed9a-4530-a305-09ee1de41461 · outbound

This paper cites OpenAI o1 System Card.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning OpenAI o1 System Card

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-17T02:18:52.365201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a1bfd47c-1aea-4da4-a8d9-9ffb80f8ef83 · outbound

This paper cites Knowing where to focus: Event-aware transformer for video grounding.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Knowing where to focus: Event-aware transformer for video grounding

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.912742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation de5e88f1-43a6-4c72-9611-8fbe04d39583 · outbound

This paper cites Dense-captioning events in videos.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Dense-captioning events in videos

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.910580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6c2f1939-f828-48b5-941a-67ca5bde11a3 · outbound

This paper cites Detecting mo- ments and highlights in videos via natural language queries.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Detecting mo- ments and highlights in videos via natural language queries

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.907868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation c12dd039-c2f9-4ce8-818e-28bf6ffea39e · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning LLaVA-OneVision: Easy Visual Task Transfer

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-17T02:18:52.294965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation b52f970c-bf0a-4400-9c52-e9db42d95dfe · outbound

This paper cites Unmasked teacher: Towards training-efficient video foundation models.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Unmasked teacher: Towards training-efficient video foundation models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.905506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 01f84cc9-2158-465c-85cd-b87dd00ccf88 · outbound

This paper cites Mo- mentdiff: Generative video moment retrieval from random to real.Advances in neural information processing systems, 36:65948–65966.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Mo- mentdiff: Generative video moment retrieval from random to real.Advances in neural information processing systems, 36:65948–65966

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.902868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 272ecf85-534d-471f-9d58-5b4347c00ece · outbound

This paper cites VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-17T02:18:52.299074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 93ac2896-e900-4888-a00a-4a25f5a5458d · outbound

This paper cites Ground- inggpt: Language enhanced multi-modal grounding model.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Ground- inggpt: Language enhanced multi-modal grounding model

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.900629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation d7c17fae-3323-4fa8-bc27-438b4c46233a · outbound

This paper cites Video-llava: Learning united visual repre- sentation by alignment before projection.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Video-llava: Learning united visual repre- sentation by alignment before projection

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.841392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation e56712fc-fcc8-4a34-96fa-f3204fd3b467 · outbound

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

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Univtg: Towards unified video- language temporal grounding

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.898220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 681f3c37-9bc1-4d10-bcc4-050b33aa5877 · outbound

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

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.896063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation b8c9c9b0-1b9b-45fe-920c-371565cd023a · outbound

This paper cites Umt: Unified multi-modal transformers for joint video moment retrieval and highlight detection.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Umt: Unified multi-modal transformers for joint video moment retrieval and highlight detection

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.893610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 672cd8b6-56a2-4a32-a61b-78fd726cba21 · outbound

This paper cites r 2-tuning: Ef- ficient image-to-video transfer learning for video temporal grounding.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning r 2-tuning: Ef- ficient image-to-video transfer learning for video temporal grounding

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.890767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 28b801d3-bcaa-4514-b818-0c7cdf0e3eab · outbound

This paper cites TempCompass: Do Video LLMs Really Understand Videos?.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning TempCompass: Do Video LLMs Really Understand Videos?

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-17T02:46:17.144047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 442ec364-5fa3-4d06-918a-45a016735ab8 · outbound

This paper cites an unresolved cited work.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-05-17T02:18:52.888371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 4f370744-bb59-4f16-9eb1-72d9333d5167 · outbound

This paper cites Visual-RFT: Visual Reinforcement Fine-Tuning.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Visual-RFT: Visual Reinforcement Fine-Tuning

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-17T02:18:52.360675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a810bf84-4b8e-4662-a534-5e19cae1e3c7 · outbound

This paper cites MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-05-17T02:18:52.382073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ce32cea4-58d5-429f-acab-add86dd88f39 · outbound

This paper cites Correlation-guided query-dependency calibration in video representation learning for temporal grounding.CoRR.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Correlation-guided query-dependency calibration in video representation learning for temporal grounding.CoRR

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.885789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a2f9eeaa-84bd-46d6-ac96-24c143f27db4 · outbound

This paper cites Query-dependent video representa- tion for moment retrieval and highlight detection.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Query-dependent video representa- tion for moment retrieval and highlight detection

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.883621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 9dc16043-078a-4a3c-8d20-3d1239b663b5 · outbound

This paper cites SpaceR: Reinforcing MLLMs in Video Spatial Reasoning.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning SpaceR: Reinforcing MLLMs in Video Spatial Reasoning

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-05-17T02:18:52.244560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 1a5daa42-d2f4-4fb3-af9d-0cf2f6326335 · outbound

This paper cites Per- ception test: A diagnostic benchmark for multimodal video models.Advances in Neural Information Processing Sys- tems, 36:42748–42761.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Per- ception test: A diagnostic benchmark for multimodal video models.Advances in Neural Information Processing Sys- tems, 36:42748–42761

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.881302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 11d2dfa6-32f8-47de-a608-34136f45a500 · outbound

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

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Chatvtg: Video temporal grounding via chat with video dialogue large language models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.878949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 59f2e683-7596-40d4-8c8c-769b76484e69 · outbound

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

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Learning transferable visual models from natural language supervi- sion

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.876556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6dbe3818-759c-4abe-ae7f-eb186a401164 · outbound

This paper cites Timechat: A time-sensitive multimodal large lan- guage model for long video understanding.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Timechat: A time-sensitive multimodal large lan- guage model for long video understanding

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.873515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 4f603076-e551-4285-867f-d759b3d35f27 · outbound

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

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-05-17T02:18:52.248653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6d828343-faca-4796-998e-a3172586f1a0 · outbound

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

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-05-17T02:18:52.253010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation e4818a9e-30d2-4592-9db8-3dd509e5649c · outbound

This paper cites End-to-end dense video grounding via parallel regression.Computer Vi- sion and Image Understanding, 242:103980.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning End-to-end dense video grounding via parallel regression.Computer Vi- sion and Image Understanding, 242:103980

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.870909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 1459d225-e80c-4a46-bab7-4e39c11f7548 · outbound

This paper cites Moviechat: From dense token to sparse memory for long video understanding.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Moviechat: From dense token to sparse memory for long video understanding

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.868466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 7e7cee7c-7670-4ba0-9e21-e339cd5aec3f · outbound

This paper cites Tr- detr: Task-reciprocal transformer for joint moment retrieval and highlight detection.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Tr- detr: Task-reciprocal transformer for joint moment retrieval and highlight detection

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.865957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f233cbca-53fe-4135-bf8b-a2ad4156c04e · outbound

This paper cites Hierarchical semantic correspondence net- works for video paragraph grounding.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Hierarchical semantic correspondence net- works for video paragraph grounding

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.863440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 15dd6e88-c57e-4c4c-837a-008464009a0f · outbound

This paper cites Hierarchical semantic correspondence net- works for video paragraph grounding.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Hierarchical semantic correspondence net- works for video paragraph grounding

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.860479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation dc84d14d-1295-446c-b300-38fb62d65e0f · outbound

This paper cites Tspo: Temporal sampling policy optimization for long- form video language understanding.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Tspo: Temporal sampling policy optimization for long- form video language understanding

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-17T02:18:52.356084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 862cdbb2-b580-43cb-b6df-242a8ec5a795 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Gemini: A Family of Highly Capable Multimodal Models

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-05-17T02:18:52.302760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation c6333379-37db-4fd4-85b4-7502732d183e · outbound

This paper cites Videorft: Incentivizing video reasoning capability in mllms via reinforced fine-tuning.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Videorft: Incentivizing video reasoning capability in mllms via reinforced fine-tuning

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-17T02:18:52.351204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a8c5d2f2-9c0e-49b3-b0e0-b42e0379d4fd · outbound

This paper cites InternVideo: General Video Foundation Models via Generative and Discriminative Learning.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning InternVideo: General Video Foundation Models via Generative and Discriminative Learning

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-05-17T02:18:52.306944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f8404e5c-5d49-4305-b484-126752c65f39 · outbound

This paper cites Internvideo2: Scaling foundation models for mul- timodal video understanding.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Internvideo2: Scaling foundation models for mul- timodal video understanding

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.857516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation c2633b38-8492-4fae-b0b6-62c18d264932 · outbound

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

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning HawkEye: Training Video-Text LLMs for Grounding Text in Videos

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-17T02:18:52.343793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 5de38293-abb8-4a48-8d1d-41bbe9413f47 · outbound

This paper cites Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-17T02:18:52.339400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation fb327704-a237-408e-84ee-7a14cf52e717 · outbound

This paper cites Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding

Reference 60

Resolution: verified exact; arxiv_id, observed 2026-05-17T02:40:06.763282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 1a187403-cbb5-4c2f-8eba-367d2645778b · outbound

This paper cites Visionary-r1: Mitigating shortcuts in visual reasoning with reinforcement learning.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Visionary-r1: Mitigating shortcuts in visual reasoning with reinforcement learning

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-17T02:18:52.284171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6a123d00-0d84-4dba-92cd-0ef2c475cd52 · outbound

This paper cites Can i trust your answer? visually grounded video question answering.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Can i trust your answer? visually grounded video question answering

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.854622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 1b539996-056c-4907-9e4c-50a5e54ba3c3 · outbound

This paper cites Bridging the gap: A unified video comprehension framework for mo- ment retrieval and highlight detection.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Bridging the gap: A unified video comprehension framework for mo- ment retrieval and highlight detection

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.851888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a30d6193-0b77-4a33-8a28-fdcf02fa13f9 · outbound

This paper cites VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-05-17T02:18:52.335434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation dbb608f1-cb63-4ed3-ad90-f84c4bacb0c0 · outbound

This paper cites Videochat-r1.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Videochat-r1

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-05-17T02:18:52.314177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 067c528d-c020-458e-8a3a-3237b3e1d735 · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 66

Resolution: verified exact; local_arxiv, observed 2026-05-17T02:18:52.328163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation e0fb155f-e300-4ee5-a867-e80b8a875f35 · outbound

This paper cites TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning

Reference 67

Resolution: verified exact; arxiv_id, observed 2026-05-17T02:18:52.310729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 3b27a866-be10-47e8-90f6-c954341edf38 · outbound

This paper cites Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

Reference 68

Resolution: verified exact; local_arxiv, observed 2026-05-17T02:18:52.324847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation be23abb0-5110-4e32-841d-bccc4487b546 · outbound

This paper cites Sc-captioner: Improving image captioning with self- correction by reinforcement learning.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Sc-captioner: Improving image captioning with self- correction by reinforcement learning

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.849268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 7e940b54-6378-4f98-b9df-28dc33c57448 · outbound

This paper cites TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning

Reference 70

Resolution: verified exact; arxiv_id, observed 2026-05-17T02:18:52.321509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6ff04040-ff6f-49d2-9d95-6d3bd7fc1f47 · outbound

This paper cites Hacs: Human action clips and segments dataset for recognition and temporal localization.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Hacs: Human action clips and segments dataset for recognition and temporal localization

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.846707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation b5e099b8-c0de-49f0-bddb-704e8764274b · outbound

This paper cites Group Sequence Policy Optimization.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Group Sequence Policy Optimization

Reference 72

Resolution: verified exact; local_arxiv, observed 2026-05-17T02:18:52.317842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 72669cb1-ea7a-4f24-8e64-5a80eb90dc0f · outbound

This paper cites Rethinking the video sampling and reasoning strategies for temporal sentence grounding.

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning Rethinking the video sampling and reasoning strategies for temporal sentence grounding

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:18:52.843915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Pith citing papers

Observation 38fb59fc-0b9b-4067-9d2c-c447183f7ddc · inbound

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks cites this paper.

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:27.916261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce54db9b-5438-4540-9a1b-cbffd719bea6 · inbound

DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences cites this paper.

DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-12T11:31:14.532101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31e83b57-04d5-45c2-93b1-b4bffa41c296 · inbound

TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs cites this paper.

TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-01T18:04:16.823032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.