AURA: Always-On Understanding and Real-Time Assistance via Video Streams
Paper • 2604.04184 • Published • 50
Video Understanding
-
-
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding
Paper • 2403.09626 • Published • 15 -
ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding
Paper • 2506.01300 • Published -
Mobile-VideoGPT: Fast and Accurate Video Understanding Language Model
Paper • 2503.21782 • Published -
VideoNSA: Native Sparse Attention Scales Video Understanding
Paper • 2510.02295 • Published • 10 -
VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding
Paper • 2603.22285 • Published • 49 -
AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding
Paper • 2603.28696 • Published • 6 -
Dense Video Understanding with Gated Residual Tokenization
Paper • 2509.14199 • Published • 3 -
PSA: Pyramid Sparse Attention for Efficient Video Understanding and Generation
Paper • 2512.04025 • Published • 4 -
EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use
Paper • 2602.15329 • Published • 1 -
Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory
Paper • 2602.18434 • Published -
Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge
Paper • 2501.13468 • Published -
Video Inference for Human Mesh Recovery with Vision Transformer
Paper • 2507.08981 • Published • 1 -
Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
Paper • 2501.12375 • Published • 23 -
V-Rex: Real-Time Streaming Video LLM Acceleration via Dynamic KV Cache Retrieval
Paper • 2512.12284 • Published -
HoliTom: Holistic Token Merging for Fast Video Large Language Models
Paper • 2505.21334 • Published • 21 -
Accurate and Fast Compressed Video Captioning
Paper • 2309.12867 • Published -
Unleashing Hour-Scale Video Training for Long Video-Language Understanding
Paper • 2506.05332 • Published • 3 -
Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning
Paper • 2601.21037 • Published • 15 -
Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language Models
Paper • 2603.02872 • Published • 1 -
Efficient Video Sampling: Pruning Temporally Redundant Tokens for Faster VLM Inference
Paper • 2510.14624 • Published • 2 -
Rethinking Chain-of-Thought Reasoning for Videos
Paper • 2512.09616 • Published • 19 -
Inference Compute-Optimal Video Vision Language Models
Paper • 2505.18855 • Published -
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
Paper • 2402.03161 • Published • 16 -
Select Less, Reason More: Prioritizing Evidence Purity for Video Reasoning
Paper • 2510.15440 • Published -
When Thinking Drifts: Evidential Grounding for Robust Video Reasoning
Paper • 2510.06077 • Published -
VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding
Paper • 2412.02186 • Published • 23 -
VIDEOP2R: Video Understanding from Perception to Reasoning
Paper • 2511.11113 • Published • 112 -
QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design
Paper • 2505.16175 • Published • 42 -
Towards Video Thinking Test: A Holistic Benchmark for Advanced Video Reasoning and Understanding
Paper • 2507.15028 • Published • 21 -
Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding
Paper • 2508.20478 • Published • 18 -
Breaking Down Video LLM Benchmarks: Knowledge, Spatial Perception, or True Temporal Understanding?
Paper • 2505.14321 • Published • 11 -
Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding
Paper • 2512.05774 • Published • 7 -
LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning
Paper • 2509.24786 • Published • 7 -
Online Video Understanding: A Comprehensive Benchmark and Memory-Augmented Method
Paper • 2501.00584 • Published -
DATE: Dynamic Absolute Time Enhancement for Long Video Understanding
Paper • 2509.09263 • Published -
Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos
Paper • 2408.14023 • Published -
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
Paper • 2604.05015 • Published • 234 -
VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
Paper • 2501.00599 • Published • 46 -
Vidi2: Large Multimodal Models for Video Understanding and Creation
Paper • 2511.19529 • Published • 2 -
Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement Learning
Paper • 2602.01649 • Published -
Token-Efficient Long Video Understanding for Multimodal LLMs
Paper • 2503.04130 • Published • 96 -
ShareGPT4Video: Improving Video Understanding and Generation with Better Captions
Paper • 2406.04325 • Published • 74 -
Apollo: An Exploration of Video Understanding in Large Multimodal Models
Paper • 2412.10360 • Published • 147 -
ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding
Paper • 2508.21496 • Published • 55 -
MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
Paper • 2406.14515 • Published • 33 -
Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks
Paper • 2501.08326 • Published • 34 -
Vidi: Large Multimodal Models for Video Understanding and Editing
Paper • 2504.15681 • Published • 14 -
SkillFormer: Unified Multi-View Video Understanding for Proficiency Estimation
Paper • 2505.08665 • Published • 5 -
Visual Context Window Extension: A New Perspective for Long Video Understanding
Paper • 2409.20018 • Published • 11 -
PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance
Paper • 2411.02327 • Published • 11 -
VideoAds for Fast-Paced Video Understanding: Where Opensource Foundation Models Beat GPT-4o & Gemini-1.5 Pro
Paper • 2504.09282 • Published -
VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting
Paper • 2603.14659 • Published • 6 -
MOSS-ChatV: Reinforcement Learning with Process Reasoning Reward for Video Temporal Reasoning
Paper • 2509.21113 • Published • 6 -
Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models
Paper • 2511.23478 • Published -
Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence
Paper • 2510.20579 • Published • 56 -
OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?
Paper • 2501.05510 • Published • 44 -
Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
Paper • 2512.00891 • Published • 16 -
A Simple Baseline for Streaming Video Understanding
Paper • 2604.02317 • Published • 72 -
Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
Paper • 2503.00540 • Published • 3 -
StreamChat: Chatting with Streaming Video
Paper • 2412.08646 • Published • 18 -
Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models
Paper • 2603.11896 • Published • 10 -
CurveStream: Boosting Streaming Video Understanding in MLLMs via Curvature-Aware Hierarchical Visual Memory Management
Paper • 2603.19571 • Published • 2 -
StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding
Paper • 2411.03628 • Published • 2 -
VideoScaffold: Elastic-Scale Visual Hierarchies for Streaming Video Understanding in MLLMs
Paper • 2512.22226 • Published -
Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs
Paper • 2510.17364 • Published -
Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding
Paper • 2504.13915 • Published -
VideoLLM-online: Online Video Large Language Model for Streaming Video
Paper • 2406.11816 • Published • 26 -
VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation
Paper • 2408.16730 • Published -
TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos
Paper • 2504.17343 • Published • 13 -
HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
Paper • 2601.14724 • Published • 75 -
Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video
Paper • 2510.14560 • Published