REVIEW 19 cited by
Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input
Not yet reviewed by Pith; the record is open.
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
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.
Forward citations
Cited by 19 Pith papers
-
EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agent Specialization
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.
-
Latent Visual Cache for Video Reasoning
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.
-
Native Active Perception as Reasoning for Omni-Modal Understanding
OmniAgent turns long-video understanding into a query-driven observe-think-act loop with a persistent text memory, outperforming larger passive models on LVBench.
-
CAViAR: Critic-Augmented Video Agentic Reasoning
CAViAR, an agent-plus-critic system for long video reasoning, improves on direct video LLM inference across LVBench, Neptune, and ActivityNet-RTL.
-
Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding
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 ...
-
LAVA: Language Driven Scalable and Versatile Traffic Video Analytics
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.
-
Flash-VStream: Efficient Real-Time Understanding for Long Video Streams
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.
-
GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning
GRPO-CARE improves answer accuracy and reasoning coherence over standard GRPO on a new video reasoning benchmark, with a 6.7 point gain on the hardest level and a 24.5 point higher consistency rate.
-
Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency
A GRPO-based post-training recipe for video LLMs using discrete QA rewards plus continuous temporal IoU rewards with variance-based data selection outperforms SFT and Video-R1.
-
ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding
A reinforcement-learned frame selection policy, trained with reward margins from a reference video-LLM, improves video QA accuracy of LLaVA-OV and InternVL3 across several benchmarks.
-
Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
Omni-R1 uses GRPO reinforcement learning to train a global reasoning model that selects keyframes and rewrites queries for a detail model, improving video and audio-visual segmentation and out-of-domain QA.
-
TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos
TUNA introduces a 1,000-video benchmark with dense temporal captions and 1,432 multiple-choice questions, and finds that current video LMMs are weakest at camera motion, action sequences, and multi-subject scenes.
-
Clapper: Compact Learning and Video Representation in VLMs
Clapper achieves 13x visual token compression in video VLMs with maintained or improved QA accuracy using a slow-fast representation and a TimePerceiver module.
-
ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning
ViaRL uses rule-based reinforcement learning to train a frame selector for video QA, improving Qwen2.5-VL on VideoMME, LVBench, and MLVU by several points.
-
Video-LevelGauge: Investigating Contextual Positional Bias in Large Video Language Models
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.
-
Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs
A CLIP-scored, Gumbel-Max frame sampler with per-frame multi-resolution allocation improves long-video question answering in Video-LLMs under a fixed token budget.
-
ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding
ReAgent-V is an agentic video understanding framework whose critic agent generates real-time rewards to refine answers and filter training data, yielding gains of up to 6.9%, 2.1%, and 9.8% across three applications.
-
FlexSelect: Flexible Token Selection for Efficient Long Video Understanding
FlexSelect selects a small fraction of query-relevant visual tokens using attention from an intermediate layer, improving long-video accuracy and inference speed across multiple VideoLLMs.
-
Reinforcing Video Reasoning with Focused Thinking
A GRPO variant with token-level KL weighting and partial-credit rewards improves video-QA on modified multi-answer benchmarks, but transfer to original single-answer benchmarks is not established.
Discussion (0). Sign in to comment.