[ICLR 2026] FOCUS: Efficient Keyframe Selection for Long Video Understanding
☆76Apr 23, 2026Updated 3 months ago
Alternatives and similar repositories for FOCUS
Users that are interested in FOCUS are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding☆231Dec 19, 2025Updated 7 months ago
- The official repository for paper "FlexSelect: Flexible Token Selection for Efficient Long Video Understanding".☆31Sep 19, 2025Updated 10 months ago
- The official implementation of "Helen: Optimizing CTR Prediction Models with Frequency-wise Hessian Eigenvalue Regularization"☆16Mar 14, 2024Updated 2 years ago
- [ACL 2025 Findings] GenS: Generative Frame Sampler for Long Video Understanding☆22Aug 21, 2025Updated 11 months ago
- Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation☆20Jun 11, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- TStar is a unified temporal search framework for long-form video question answering☆97Mar 23, 2026Updated 4 months ago
- EVA: Efficient Reinforcement Learning for End-to-End Video Agent☆26May 6, 2026Updated 3 months ago
- ☆36Feb 18, 2026Updated 5 months ago
- [CVPR 2026 Highlight] WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning☆104Jul 29, 2026Updated 2 weeks ago
- [ICLR 2026] Official repo for "FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting"☆50Oct 9, 2025Updated 10 months ago
- [ICCV 2025] Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs☆61Feb 2, 2026Updated 6 months ago
- [AAAI 2025] Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos☆38May 27, 2025Updated last year
- [Main Conference @ EACL'26] [Workshop @ NeurIPS'24] 🎞️ LVNet.☆44Feb 10, 2026Updated 6 months ago
- [ICCV'25] HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics☆37Sep 10, 2025Updated 11 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Agentic Keyframe Search for Video Question Answering☆18Jun 30, 2026Updated last month
- WikiVideo: Article Generation from Multiple Videos☆15Nov 14, 2025Updated 9 months ago
- [CVPR 2026] VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking☆67Mar 23, 2026Updated 4 months ago
- Official Code for paper "Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding""☆18Jun 2, 2026Updated 2 months ago
- ☆19May 15, 2026Updated 3 months ago
- Fast, memory-efficient attention column reduction (e.g., sum, mean, max)☆50Feb 10, 2026Updated 6 months ago
- [CVPR 2026] Official repo for "VideoSSR: Video Self-Supervised Reinforcement Learning"☆48Nov 11, 2025Updated 9 months ago
- [CVPR 2025] Official PyTorch Implementation of GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmenta…☆70Jun 23, 2025Updated last year
- Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models☆19Jan 21, 2026Updated 6 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Tempo: Small Vision-Language Models are Smart Compressors for Long Video Understanding, ECCV 2026☆79Jul 26, 2026Updated 2 weeks ago
- Code for "Agentic Very Long Video Understanding" (EGAgent) [ACL 2026 Main]☆54Jul 1, 2026Updated last month
- [CVPR 2026] LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding☆52Jul 7, 2026Updated last month
- [CVPR2026 Highlight] FlexMem: Scaling the Long Video Understanding of MLLMs via Visual Memory Mechanism☆34Apr 10, 2026Updated 4 months ago
- Official repository for Parallax (Parameterized Local Linear Attention)☆68Jul 30, 2026Updated 2 weeks ago
- [CVPR 2026 Highlight] VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding☆126Apr 17, 2026Updated 3 months ago
- [NeurIPS 2025 Spotlight] Official PyTorch implementation of Vgent☆50Nov 30, 2025Updated 8 months ago
- [ACL 2023] The official implementation of "CAME: Confidence-guided Adaptive Memory Optimization"☆100Mar 22, 2025Updated last year
- [ACM MM 2025] ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models☆18Jul 15, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactions☆16Jun 28, 2026Updated last month
- [AAAI-25]Code for SEAL☆15Sep 25, 2025Updated 10 months ago
- [CVPR 2026] LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling☆260Jun 24, 2026Updated last month
- [ICCV 2025] Implementation of the paper "Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs"☆82Oct 25, 2025Updated 9 months ago
- [NeurIPS 2025] Official code for paper: Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs.☆106Sep 20, 2025Updated 10 months ago
- ☆28Mar 5, 2026Updated 5 months ago
- EgoToM is an egocentric theory-of-mind benchmark built on Ego4D videos, containing multi-choice questions that evaluate multimodal large …☆16Apr 1, 2025Updated last year