5,419,468 AI resources indexedWorking toward the world’s largest AI resource index.
Publications about AI methods and applications.
Research paper by Liang Chen and collaborators. Published 2024-03-11. Topics: Large Vision-Language Models, LLaVA-1.5, QwenVL-Chat, Video-LLaVA, attention computation.
Research paper by Hesong Wang and collaborators. Published 2026-05-28. Topics: video large language models, visual tokens, time-to-first-token, vision encoder, token compression.
Research paper by Xinlong Wang and collaborators. Published 2024-09-27. Topics: next-token prediction, multimodal models, transformer, discrete space, multimodal sequences.
Research paper by Kele Shao and collaborators. Published 2025-05-27. Topics: video LLMs, video tokens, FastV, inner-LLM pruning, outer-LLM pruning.
Research paper by Teng Hu and collaborators. Published 2025-05-07. Topics: multi-modal, video generation, identity consistency, image-text fusion, LLaVA.
Research paper by Zhenyi Liao and collaborators. Published 2025-04-01. Topics: multi-modal large language models, visual-spatial intelligence, R1-Zero-like training, Chain of Thought, GRPO.
Research paper by Shaolei Zhang and collaborators. Published 2025-01-07. Topics: real-time large multimodal models, LMMs, GPT-4o, vision tokens, text tokens.
Research paper by Leqi Shen and collaborators. arXiv record dated 2025-03-14. Research area: Computer vision.
Research paper by Feng Li and collaborators. Published 2024-07-10. Topics: Large Multimodal Models, LLMs, Multi-image, Multi-frame, Multi-view.
Research paper by Boyuan Sun and collaborators. arXiv record dated 2026-04-20. Research area: Computer vision.
Research paper by Bo Li and collaborators. Published 2024-08-06. Topics: multimodal models, LMMs, LLaVA-OneVision, single-image, multi-image.
Research paper by Boyuan Sun and collaborators. Published 2025-06-27. Topics: token compression strategy, Semantic Connected Components (SCC), spatio-temporal token compression strategy, video question answering, long video understanding.
Try a broader search or clear some filters.
Platform labels describe intended use. Read each resource's author credits, requirements and available access methods.