LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs | Paper Citation Record

Observation 87599cec-a8c3-49a6-98fb-d1bb2e9aacb7 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Direct preference optimization: Your language model is secretly a reward model

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:56.790748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c91fee19-a402-43d6-aa39-22017afc1f14 · outbound

This paper cites Generative multimodal models are in-context learners.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Generative multimodal models are in-context learners

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:56.569181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5c70d3fd-489c-4376-a198-173679d4ffed · outbound

This paper cites Vila: On pre-training for visual language models.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Vila: On pre-training for visual language models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:45.550694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4ee9b8e-b97c-4647-b1b4-ce1639322efc · outbound

This paper cites Improved baselines with visual instruction tuning.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Improved baselines with visual instruction tuning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:45.661244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a366eb47-61fc-4a47-ac23-8144fe241e3d · outbound

This paper cites Llava-next: Improved reasoning, ocr, and world knowledge, January 2024.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Llava-next: Improved reasoning, ocr, and world knowledge, January 2024

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:45.761050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e67d2d0e-a974-45a8-ac93-dc7007a9bd20 · outbound

This paper cites Llava-next: A strong zero-shot video understanding model, April 2024.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Llava-next: A strong zero-shot video understanding model, April 2024

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:45.887667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 967a0eea-1615-4424-ac6f-5c8e99da5241 · outbound

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

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs LLaVA-OneVision: Easy Visual Task Transfer

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:45.998856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e09aaaa5-b745-416b-afaa-963f8e4c80b2 · outbound

This paper cites LLaVA-Video: Video Instruction Tuning With Synthetic Data.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs LLaVA-Video: Video Instruction Tuning With Synthetic Data

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:46.132778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d141351-52b8-4878-ae0c-406649785dd2 · outbound

This paper cites Llama 3 model card.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Llama 3 model card

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:46.243169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43ba7005-2f35-48eb-9b53-0d20f3e5b38c · outbound

This paper cites Detecting and preventing hallucinations in large vision language models.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Detecting and preventing hallucinations in large vision language models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:56.294640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0aec69c4-55a2-4614-a893-da89764a2ef1 · outbound

This paper cites Tuning large multimodal models for videos using reinforcement learning from AI feedback.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Tuning large multimodal models for videos using reinforcement learning from AI feedback

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:56.112709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 133ef95f-1b8f-492a-a37f-8edfac11ae9d · outbound

This paper cites ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:46.520071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62eede0d-e51d-42aa-8b72-ca8e342585ba · outbound

This paper cites Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:46.600253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94a971de-4074-476a-9cf7-63b5e04448ba · outbound

This paper cites Temporal Preference Optimization for Long-Form Video Understanding.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Temporal Preference Optimization for Long-Form Video Understanding

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:46.708160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c508bcee-1390-4374-963a-a09fa2b00bcc · outbound

This paper cites Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:46.995120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d84090d-c768-4a67-be3f-dbbf84471ef6 · outbound

This paper cites From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:47.055899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11c3c272-c05d-49cc-abdd-ef5cafae400c · outbound

This paper cites Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:47.117231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f636b544-d400-46e2-9613-c3a0e5458869 · outbound

This paper cites Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:47.187005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ec5bba3-48a6-487e-b041-1bc3367e23d9 · outbound

This paper cites DPO-Shift: Shifting the Distribution of Direct Preference Optimization.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs DPO-Shift: Shifting the Distribution of Direct Preference Optimization

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-07T10:28:54.149778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 551e7d34-90c3-4fd9-adf5-b9717b571467 · outbound

This paper cites Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:47.390690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c671aef6-8fcd-43e7-b4ee-7f5795c410e1 · outbound

This paper cites Introducing chatgpt.CoRR, 2022.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Introducing chatgpt.CoRR, 2022

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:55.929693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation eab90330-9598-42d5-bee6-5e593e4ab5a7 · outbound

This paper cites GPT-4 technical report.CoRR, 2023.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs GPT-4 technical report.CoRR, 2023

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:47.602865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdc7ab15-ccc6-490e-9e1f-900c4fb4f293 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:47.725396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1994fffd-2d34-401e-90fa-5bd7a6787b76 · outbound

This paper cites Qwen2 Technical Report.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Qwen2 Technical Report

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:47.829591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3596279b-d390-4ac8-8476-d3fc2816c3c1 · outbound

This paper cites Deep reinforcement learning from human preferences.Advances in neural information processing systems, 30, 2017.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Deep reinforcement learning from human preferences.Advances in neural information processing systems, 30, 2017

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:47.913327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab522e8b-65f0-4613-8b55-db444a01e5c3 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Constitutional AI: Harmlessness from AI Feedback

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:48.035884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cd34a1f-f641-495b-8c86-e039e87f0a81 · outbound

This paper cites Preference ranking optimization for human alignment.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Preference ranking optimization for human alignment

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:48.096937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98d5ad29-7c6a-41bb-900b-d36ab5f2d551 · outbound

This paper cites LiPO: Listwise Preference Optimization through Learning-to-Rank.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs LiPO: Listwise Preference Optimization through Learning-to-Rank

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:48.212275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2706551a-be43-4870-ba5b-aeb482090f73 · outbound

This paper cites Orpo: Monolithic preference optimization without reference model.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Orpo: Monolithic preference optimization without reference model

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:48.339711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e9011be-a790-4f63-91ec-4a4a6320fcfe · outbound

This paper cites SimPO: Simple Preference Optimization with a Reference-Free Reward.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs SimPO: Simple Preference Optimization with a Reference-Free Reward

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:48.465974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7406bc35-b70f-497b-b0f2-4f08220f4fd1 · outbound

This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs KTO: Model Alignment as Prospect Theoretic Optimization

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:48.558901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17fbe66b-8f0a-4173-81f6-023008380142 · outbound

This paper cites β-dpo: Direct preference optimization with dynamic β.Advances in Neural Information Processing Systems, 37:129944–129966, 2024.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs β-dpo: Direct preference optimization with dynamic β.Advances in Neural Information Processing Systems, 37:129944–129966, 2024

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:55.714997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 41dcf136-d98c-40d1-9cea-83db0000177c · outbound

This paper cites Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:55.511918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 853e42d9-1765-442f-9db5-228dbbe3669d · outbound

This paper cites Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness.arXiv preprint arXiv:2405.17220, 2024.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness.arXiv preprint arXiv:2405.17220, 2024

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:48.905011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96db0a19-af0d-4def-b013-5187b34ca691 · outbound

This paper cites Silkie: Preference Distillation for Large Visual Language Models.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Silkie: Preference Distillation for Large Visual Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:49.027723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 689686d6-4939-47c3-a39c-cfdbe7056327 · outbound

This paper cites Calibrated Self-Rewarding Vision Language Models.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Calibrated Self-Rewarding Vision Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:49.151530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f21cf8d-a24b-47be-a337-9c536218f6ed · outbound

This paper cites Aligning Modalities in Vision Large Language Models via Preference Fine-tuning.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Aligning Modalities in Vision Large Language Models via Preference Fine-tuning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:49.316868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6a66a8c-c5fb-4e99-9b94-f1979f5e9ac7 · outbound

This paper cites Strengthening multimodal large language model with bootstrapped preference optimization.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Strengthening multimodal large language model with bootstrapped preference optimization

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:55.332426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c1555e19-d7ec-4741-bafd-f014c10d7c53 · outbound

This paper cites Self-Supervised Visual Preference Alignment.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Self-Supervised Visual Preference Alignment

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:49.538730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40649a4a-21ce-4624-8dde-4a990aab741a · outbound

This paper cites Enhancing Large Vision Language Models with Self-Training on Image Comprehension.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Enhancing Large Vision Language Models with Self-Training on Image Comprehension

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:49.630859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4faa711-20ac-454d-a55f-eed1ac93a9dc · outbound

This paper cites V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:49.730599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7219ed15-c1e1-48dd-91da-592f664f44aa · outbound

This paper cites LLaVA-Critic: Learning to Evaluate Multimodal Models.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs LLaVA-Critic: Learning to Evaluate Multimodal Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:49.885639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6333614-1407-4612-933e-b8d170676237 · outbound

This paper cites Gpt-4v(ision) system card.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Gpt-4v(ision) system card

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:50.011445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1fe44d6-e2ed-434f-a21f-4265d75d4059 · outbound

This paper cites MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:50.117579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3270e2b8-a8ea-4c7b-b7af-cb578d67f968 · outbound

This paper cites Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:50.207227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77c20d65-4420-448d-8ece-1103be391e81 · outbound

This paper cites Longvideobench: A benchmark for long-context interleaved video-language understanding, 2024.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Longvideobench: A benchmark for long-context interleaved video-language understanding, 2024

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:50.305434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d08fe25-05d8-44b6-baff-994531e31581 · outbound

This paper cites MLVU: Benchmarking Multi-task Long Video Understanding.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs MLVU: Benchmarking Multi-task Long Video Understanding

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:50.404469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26833bff-6594-4913-b455-b17868a7c612 · outbound

This paper cites Next-qa: Next phase of question- answering to explaining temporal actions.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Next-qa: Next phase of question- answering to explaining temporal actions

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:55.165696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 543f8e17-0ffc-4fd6-aac0-f39935557265 · outbound

This paper cites Tarsier: Recipes for Training and Evaluating Large Video Description Models.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Tarsier: Recipes for Training and Evaluating Large Video Description Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:50.622545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e688c280-5d0b-486c-b6e6-65394988a969 · outbound

This paper cites Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:50.714518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f80aa099-eb9c-451d-9aa0-396919a9d63b · outbound

This paper cites Video-LLaVA: Learning United Visual Representation by Alignment Before Projection.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:50.810656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96c989f9-ebcf-4710-9e98-2e1186146552 · outbound

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

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:50.920945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2782dec-d4a8-494b-bbe4-8deb106d887f · outbound

This paper cites ShareGPT4Video: Improving Video Understanding and Generation with Better Captions.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs ShareGPT4Video: Improving Video Understanding and Generation with Better Captions

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:51.015037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67ea4abd-87d7-4b0b-9e40-e8b935b22aa5 · outbound

This paper cites Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:51.104238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04fb546c-0951-41d1-bce2-934208d8a927 · outbound

This paper cites aws-prototyping/long-llava-qwen2-7b, 2024.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs aws-prototyping/long-llava-qwen2-7b, 2024

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:54.932150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 97b1818a-42de-4fdb-820d-985568e79bc4 · outbound

This paper cites Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:51.431837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d56b795a-64cc-4291-86fd-07789b11d2f0 · outbound

This paper cites Long Context Transfer from Language to Vision.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Long Context Transfer from Language to Vision

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:51.563326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbeb08f8-64c3-46e3-a966-d5eae9f61395 · outbound

This paper cites Temporal alignment networks for long-term video.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Temporal alignment networks for long-term video

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:54.760273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ded1134d-8f6e-40d4-bcd3-355b0f706f3f · outbound

This paper cites MVBench: A Comprehensive Multi-modal Video Understanding Benchmark.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs MVBench: A Comprehensive Multi-modal Video Understanding Benchmark

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:51.806239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90c069d5-78fa-4889-9b20-ecc8e2e66d6c · outbound

This paper cites MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:51.919841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 841de52e-6fdb-4cd1-932e-e5d78859507a · outbound

This paper cites PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:52.036063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5bc3b82-eb86-4917-8094-c69ed13df073 · outbound

This paper cites VideoChat: Chat-Centric Video Understanding.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs VideoChat: Chat-Centric Video Understanding

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:52.131174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 025af6e4-5523-48a3-bbb0-a31e17236f2c · outbound

This paper cites Vista-llama: Reducing hallucination in video language models via equal distance to visual tokens.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Vista-llama: Reducing hallucination in video language models via equal distance to visual tokens

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:54.600521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d4fe6a54-53d8-4197-bbb9-0a3aba7e0de1 · outbound

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

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Moviechat: From dense token to sparse memory for long video understanding

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:54.420895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6381f0d3-ecab-48cd-815c-29a40fcc0c55 · outbound

This paper cites Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:52.406829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5518530f-bb48-4847-adfb-cf52eff7b58f · outbound

This paper cites CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:52.514103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1649634-71a0-4263-bd39-1fb94d03ec3e · outbound

This paper cites ST-LLM: Large Language Models Are Effective Temporal Learners.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs ST-LLM: Large Language Models Are Effective Temporal Learners

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:52.598295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7630b6a7-429d-4150-9796-7b38c732fd6a · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:52.675004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27afb509-f49e-4f96-9c8d-6ab3dd4736e1 · outbound

This paper cites Qwen2.5-VL Technical Report.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Qwen2.5-VL Technical Report

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:52.769185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efd4f661-ed5e-4a93-8567-59ebe3793f39 · outbound

This paper cites Visual Instruction Tuning.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Visual Instruction Tuning

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:52.855846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e873ec0a-ab0b-4f29-a3b5-edc9fc45642c · outbound

This paper cites Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:52.987620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45796a56-d9a6-4f0d-ba93-5557fe424b6e · outbound

This paper cites Aligning Large Multimodal Models with Factually Augmented RLHF.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs Aligning Large Multimodal Models with Factually Augmented RLHF

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:53.072713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers