TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/VLM-RLAIF

VLM-RLAIF

Reported on 18 benchmarks across 3 tasks · 1 paper · 18 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Reasoning12 results

  • Generative Visual Question AnsweringonVideoInstruct
    Consistency· 2024-02-06
    3.32
    best: 3.81 (PPLLaVA-7B-dpo)
    SOTA
    Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI FeedbackarXiv:2402.03746
  • Generative Visual Question AnsweringonVideoInstruct
    Contextual Understanding· 2024-02-06
    4
    best: 4.21 (PPLLaVA-7B-dpo)
    SOTA
    Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI FeedbackarXiv:2402.03746
  • Generative Visual Question AnsweringonVideoInstruct
    Correctness of Information· 2024-02-06
    3.63
    best: 3.85 (PPLLaVA-7B-dpo)
    SOTA
    Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI FeedbackarXiv:2402.03746
  • Generative Visual Question AnsweringonVideoInstruct
    Detail Orientation· 2024-02-06
    3.25
    best: 3.56 (PPLLaVA-7B-dpo)
    SOTA
    Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI FeedbackarXiv:2402.03746
  • Generative Visual Question AnsweringonVideoInstruct
    Temporal Understanding· 2024-02-06
    3.23
    SOTA
    Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI FeedbackarXiv:2402.03746
  • Generative Visual Question AnsweringonVideoInstruct
    mean· 2024-02-06
    3.49
    best: 3.73 (PPLLaVA-7B-dpo)
    SOTA
    Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI FeedbackarXiv:2402.03746
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    Consistency· 2024-02-06
    3.32
    best: 3.81 (PPLLaVA-7B-dpo)
    SOTA
    Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI FeedbackarXiv:2402.03746
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    Contextual Understanding· 2024-02-06
    4
    best: 4.21 (PPLLaVA-7B-dpo)
    SOTA
    Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI FeedbackarXiv:2402.03746
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    Correctness of Information· 2024-02-06
    3.63
    best: 3.85 (PPLLaVA-7B-dpo)
    SOTA
    Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI FeedbackarXiv:2402.03746
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    Detail Orientation· 2024-02-06
    3.25
    best: 3.56 (PPLLaVA-7B-dpo)
    SOTA
    Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI FeedbackarXiv:2402.03746
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    Temporal Understanding· 2024-02-06
    3.23
    SOTA
    Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI FeedbackarXiv:2402.03746
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    mean· 2024-02-06
    3.49
    best: 3.73 (PPLLaVA-7B-dpo)
    SOTA
    Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI FeedbackarXiv:2402.03746

Natural Language Processing6 results

  • Visual Question Answering (VQA)onVideoInstruct
    Consistency· 2024-02-06
    3.32
    best: 3.81 (PPLLaVA-7B-dpo)
    SOTA
    Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI FeedbackarXiv:2402.03746
  • Visual Question Answering (VQA)onVideoInstruct
    Contextual Understanding· 2024-02-06
    4
    best: 4.21 (PPLLaVA-7B-dpo)
    SOTA
    Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI FeedbackarXiv:2402.03746
  • Visual Question Answering (VQA)onVideoInstruct
    Correctness of Information· 2024-02-06
    3.63
    best: 3.85 (PPLLaVA-7B-dpo)
    SOTA
    Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI FeedbackarXiv:2402.03746
  • Visual Question Answering (VQA)onVideoInstruct
    Detail Orientation· 2024-02-06
    3.25
    best: 3.56 (PPLLaVA-7B-dpo)
    SOTA
    Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI FeedbackarXiv:2402.03746
  • Visual Question Answering (VQA)onVideoInstruct
    Temporal Understanding· 2024-02-06
    3.23
    SOTA
    Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI FeedbackarXiv:2402.03746
  • Visual Question Answering (VQA)onVideoInstruct
    mean· 2024-02-06
    3.49
    best: 3.73 (PPLLaVA-7B-dpo)
    SOTA
    Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI FeedbackarXiv:2402.03746