Pith. sign in

REVIEW 29 cited by

Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2408.15542 v1 pith:HZNBXM2F submitted 2024-08-28 cs.CV cs.AIcs.MM

Jiajun Liu , Yibing Wang , Hanghang Ma , Xiaoping Wu , Xiaoqi Ma , Xiaoming Wei , Jianbin Jiao , Enhua Wu
show 1 more author
Jie Hu
This is my paper
classification cs.CVcs.AIcs.MM
keywords videodatakangaroolongmodelsvideosinputbenchmarks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Rapid advancements have been made in extending Large Language Models (LLMs) to Large Multi-modal Models (LMMs). However, extending input modality of LLMs to video data remains a challenging endeavor, especially for long videos. Due to insufficient access to large-scale high-quality video data and the excessive compression of visual features, current methods exhibit limitations in effectively processing long videos. In this paper, we introduce Kangaroo, a powerful Video LMM aimed at addressing these challenges. Confronted with issue of inadequate training data, we develop a data curation system to build a large-scale dataset with high-quality annotations for vision-language pre-training and instruction tuning. In addition, we design a curriculum training pipeline with gradually increasing resolution and number of input frames to accommodate long videos. Evaluation results demonstrate that, with 8B parameters, Kangaroo achieves state-of-the-art performance across a variety of video understanding benchmarks while exhibiting competitive results on others. Particularly, on benchmarks specialized for long videos, Kangaroo excels some larger models with over 10B parameters and proprietary models.

Discussion (0). Sign in to comment.

Forward citations

Cited by 29 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. An Efficient Streaming Video Understanding Framework with Agentic Control

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    R3-Streaming uses cascaded control with age-aware memory forgetting and TB-GRPO reinforcement learning to reach SOTA scores of 57.92 on OVO-Bench and 76.36 on StreamingBench with 95-96% fewer visual tokens.

  2. OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    OASIS organizes streaming video into hierarchical events and retrieves memory on-demand via intent-driven refinement to improve long-horizon accuracy and compositional reasoning with bounded token costs.

  3. StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos

    cs.CV 2025-12 unverdicted novelty 7.0 of 10

    StreamGaze is a new benchmark and QA generation pipeline that measures how well MLLMs leverage gaze trajectories for temporal reasoning and proactive intention prediction in streaming egocentric videos.

  4. Video-R1: Reinforcing Video Reasoning in MLLMs

    cs.CV 2025-03 conditional novelty 7.0 of 10

    Video-R1 uses temporal-aware RL and mixed datasets to boost video reasoning in MLLMs, with a 7B model reaching 37.1% on VSI-Bench and surpassing GPT-4o.

  5. LVBench: An Extreme Long Video Understanding Benchmark

    cs.CV 2024-06 accept novelty 7.0 of 10

    LVBench is a new benchmark for extreme long video understanding that evaluates multimodal large language models on hour-scale videos using tasks designed to probe extended memory and comprehension.

  6. EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agent Specialization

    cs.AI 2026-07 conditional novelty 6.0 of 10

    EmoAgent-R1 combines dynamic agent routing with a token-reweighted GRPO variant (P-GRPO) to reach 77.85% mean on MER-UniBench, exceeding AffectGPT-R1 by 1.90 points.

  7. Latent Visual Cache for Video Reasoning

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A recurrent latent visual cache in the decoder, trained with contrastive key-frame alignment and a vision-grounded GRPO reward, improves video reasoning accuracy while shortening answers.

  8. Native Active Perception as Reasoning for Omni-Modal Understanding

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    OmniAgent formulates omni-modal video understanding as a POMDP with on-demand actions that distill cues into persistent text memory, showing positive test-time scaling and SOTA results on benchmarks like LVBench where...

  9. Native Active Perception as Reasoning for Omni-Modal Understanding

    cs.CV 2026-06 conditional novelty 6.0 of 10

    OmniAgent turns long-video understanding into a query-driven observe-think-act loop with a persistent text memory, outperforming larger passive models on LVBench.

  10. Reasoning as Intersection: Consensus-Frame Alignment for Visual Focus in Video-MLLMs

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    CF-GRPO creates a consensus frame prior from intrinsic video cues and aligns it with model frame-use scores via a reward signal to enable evidence-aware reasoning in Video-MLLMs without temporal annotations.

  11. StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    StreamOV proposes evidence-guided long-short term memory and a hidden-state-driven trigger for efficient online audio-visual reasoning in streaming videos, along with the SOVBench benchmark for multi-turn evaluation.

  12. An Efficient Streaming Video Understanding Framework with Agentic Control

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    R3-Streaming uses cascaded control, age-aware memory forgetting, and TB-GRPO reinforcement learning to reach SOTA scores on streaming video benchmarks while cutting visual token usage by 95-96%.

  13. Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    Response-G1 uses query-guided scene graphs, memory retrieval, and augmented prompting to improve when Video-LLMs decide to respond during streaming videos.

  14. One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    XComp reaches extreme video compression (one token per selective frame) via learnable progressive token compression and question-conditioned frame selection, lifting LVBench accuracy from 42.9 percent to 46.2 percent ...

  15. Small Vision-Language Models are Smart Compressors for Long Video Understanding

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    Tempo uses a 6B SVLM as a local temporal compressor with training-free adaptive token allocation to achieve SOTA long-video understanding at 0.5-16 tokens per frame, scoring 52.3 on 4101s LVBench under 8K budget.

  16. HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

    cs.CV 2026-01 unverdicted novelty 6.0 of 10

    HERMES organizes the KV cache into a hierarchical memory to enable real-time streaming video understanding in MLLMs, achieving 10x faster TTFT and up to 11.4% accuracy gains on streaming benchmarks with 68% fewer tokens.

  17. CAViAR: Critic-Augmented Video Agentic Reasoning

    cs.CV 2025-09 conditional novelty 6.0 of 10

    CAViAR, an agent-plus-critic system for long video reasoning, improves on direct video LLM inference across LVBench, Neptune, and ActivityNet-RTL.

  18. Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A multi-turn reinforcement learning framework where a 7B video LLM iteratively retrieves relevant video segments, guided by a gated bi-level reward, achieves state-of-the-art accuracy on VideoMME, MLVU, and EgoSchema ...

  19. LAVA: Language Driven Scalable and Versatile Traffic Video Analytics

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A natural-language video analytics system combining bandit-based sampling, open-vocabulary detection, and trajectory linking reports higher query accuracy than closed-world baselines on a new 18-predicate traffic benchmark.

  20. Flash-VStream: Efficient Real-Time Understanding for Long Video Streams

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Flash-VStream uses a two-memory design (clustered low-res summaries plus high-res key-frame details) to answer questions about long videos with state-of-the-art benchmark scores and sub-second latency.

  21. SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics

    cs.LG 2025-06 unverdicted novelty 6.0 of 10

    SmolVLA is a small efficient VLA model that achieves performance comparable to 10x larger models while training on one GPU and deploying on consumer hardware via community data and chunked asynchronous action prediction.

  22. SmolVLM: Redefining small and efficient multimodal models

    cs.AI 2025-04 unverdicted novelty 6.0 of 10

    SmolVLM-256M outperforms a 300-times larger model using under 1 GB GPU memory, while the 2.2B version matches state-of-the-art VLMs at half the memory cost.

  23. MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models

    cs.CV 2025-01 unverdicted novelty 6.0 of 10

    MotionBench is a new benchmark showing poor fine-grained motion understanding in VLMs and proposes TE Fusion to improve performance with higher frame rates.

  24. VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling

    cs.CV 2024-12 unverdicted novelty 6.0 of 10

    VideoChat-Flash applies hierarchical video token compression to achieve ~50x reduction in context length for long videos while maintaining near-original performance on long-context benchmarks.

  25. Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    Response-G1 uses query-guided scene graph generation, memory retrieval, and retrieval-augmented prompting to improve proactive response timing in streaming video understanding.

  26. Scaling Video Understanding via Compact Latent Multi-Agent Collaboration

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    MACF decouples agent perception budgets from overall video length using latent token collaboration to scale video understanding in MLLMs beyond current limits.

  27. Video-LevelGauge: Investigating Contextual Positional Bias in Large Video Language Models

    cs.CV 2025-08 conditional novelty 5.0 of 10

    Identical video questions get different accuracy when placed at the start, middle, or end of a long context, and the new benchmark maps this bias across 27 video-language models.

  28. InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning

    cs.CV 2026-06 unverdicted novelty 4.0 of 10

    InternVideo3 introduces Multimodal Contextual Reasoning and M^2LA attention to enable closed-loop evidence accumulation in long-video understanding and agentic tool use, reporting strong benchmark results.

  29. VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding

    cs.CV 2025-01 unverdicted novelty 4.0 of 10

    VideoLLaMA3 uses a vision-centric training paradigm and token-reduction design to reach competitive results on image and video benchmarks.

Pith tools