Alternatives and similar repositories for Kangaroo

Users that are interested in Kangaroo are comparing it to the libraries listed below

• longvideobench / LongVideoBench
  [Neurips 24' D&B] Official Dataloader and Evaluation Scripts for LongVideoBench.
  ☆113Updated last year
• Cooperx521 / PyramidDrop
  (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
  ☆141Updated 10 months ago
• CASIA-IVA-Lab / VideoNIAH
  VideoNIAH: A Flexible Synthetic Method for Benchmarking Video MLLMs
  ☆54Updated 10 months ago
• 42Shawn / LLaVA-PruMerge
  LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
  ☆162Updated 4 months ago
• SliMM-X / CoMP-MM
  Official repository of "CoMP: Continual Multimodal Pre-training for Vision Foundation Models"
  ☆43Updated 10 months ago
• Open-Reasoner-Zero / Open-Vision-Reasoner
  [NeurIPS 2025] The official repository for our paper, "Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reason…
  ☆153Updated 4 months ago
• PKU-YuanGroup / Video-Bench
  A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models!
  ☆137Updated 2 years ago
• hshjerry / VideoEspresso
  [CVPR 2025 Oral] VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection
  ☆134Updated 6 months ago
• JierunChen / Ref-L4
  Evaluation code for Ref-L4, a new REC benchmark in the LMM era
  ☆55Updated last year
• MME-Benchmarks / MME-RealWorld
  ✨✨ [ICLR 2025] MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
  ☆152Updated 3 months ago
• HJYao00 / DenseConnector
  【NeurIPS 2024】Dense Connector for MLLMs
  ☆180Updated last year
• zai-org / LVBench
  [ICCV 2025] LVBench: An Extreme Long Video Understanding Benchmark
  ☆135Updated 6 months ago
• Visual-AI / PruneVid
  [ACL 2025] PruneVid: Visual Token Pruning for Efficient Video Large Language Models
  ☆66Updated 8 months ago
• baaivision / DenseFusion
  DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception
  ☆159Updated last year
• llyx97 / TempCompass
  [ACL 2024 Findings] "TempCompass: Do Video LLMs Really Understand Videos?", Yuanxin Liu, Shicheng Li, Yi Liu, Yuxiang Wang, Shuhuai Ren, …
  ☆127Updated 9 months ago
• TimeMarker-LLM / TimeMarker
  A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability
  ☆105Updated last year
• JoeLeelyf / OVO-Bench
  [CVPR 2025] OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?
  ☆118Updated 6 months ago
• rese1f / aurora
  [ICLR 2025] AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
  ☆138Updated 7 months ago
• MMStar-Benchmark / MMStar
  [NeurIPS 2024] This repo contains evaluation code for the paper "Are We on the Right Way for Evaluating Large Vision-Language Models"
  ☆203Updated last year
• DCDmllm / Momentor
  ☆80Updated last year
• whwu95 / FreeVA
  FreeVA: Offline MLLM as Training-Free Video Assistant
  ☆68Updated last year
• SCZwangxiao / video-ReTaKe
  Official implementation of paper ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding
  ☆38Updated 10 months ago
• QQ-MM / Video-CCAM
  A lightweight flexible Video-MLLM developed by TencentQQ Multimedia Research Team.
  ☆74Updated last year
• bronyayang / Law_of_Vision_Representation_in_MLLMs
  [COLM'25] Official implementation of the Law of Vision Representation in MLLMs
  ☆176Updated 3 months ago
• Ahnsun / merlin
  [ECCV2024] Official code implementation of Merlin: Empowering Multimodal LLMs with Foresight Minds
  ☆96Updated last year
• ywh187 / FitPrune
  ☆64Updated last week
• appletea233 / Temporal-R1
  Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency
  ☆60Updated 7 months ago
• foundation-multimodal-models / CAPTURE
  ☆81Updated last year
• ncTimTang / AKS
  [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding
  ☆169Updated last month
• RupertLuo / VoCoT
  VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models
  ☆77Updated last year