Awesome Similarity Search
πŸ“„Papers🧭TopicsπŸ”₯TrendingπŸ—ΊοΈMapπŸ†LeaderboardsπŸŽ“LearnπŸ€–Ask AI
β‹―More
πŸ‘₯AuthorsπŸ“šReading PacksπŸ› οΈToolsπŸ“Blogsβœ‰οΈNewsletterπŸ”–Saved
+ Add Paper

← authors Β· overview

Junnan Li

13 papers Β· 99 citations
Most-cited papers
  • ULIP-2: Towards Scalable Multimodal Pre-training For 3D Understanding
    2023 Β· 88 citations
  • Longvideobench: A Benchmark For Long-context Interleaved Video-language Understanding
    2024 Β· 10 citations
  • Generative Frame Sampler For Long Video Understanding
    2025 Β· 1 citations
  • GPA: Learning GUI Process Automation From Demonstrations
    2026
  • Mcp-universe: Benchmarking Large Language Models With Real-world Model Context Protocol Servers
    2025
  • Active Video Perception: Iterative Evidence Seeking For Agentic Long Video Understanding
    2025
  • Rgbt-ground Benchmark: Visual Grounding Beyond RGB In Complex Real-world Scenarios
    2025
Topics
Visual LanguageVideo Understanding3D VisionBrowser AgentsCode AgentsOrchestrationBenchmarksObject Detection

Stay Updated

E-Mail Digest

Submit a paper Β· Privacy Β· Terms

Β© 2026 Awesome Papers.