Dahua Lin
29 papers · 7 citations
Most-cited papers
- How Far Are We To GPT-4V? Closing The Gap To Commercial Multimodal Models With Open-source Suites2024 · 1136 citations
- CARAFE: Content-aware Reassembly Of Features2019 · 770 citations
- Are We On The Right Way For Evaluating Large Vision-language Models?2024 · 736 citations
- Region Proposal By Guided Anchoring2019 · 545 citations
- Internlm2 Technical Report2024 · 378 citations
- Internlm-xcomposer2: Mastering Free-form Text-image Composition And Comprehension In Vision-language Large Model2024 · 372 citations
- Pointllm: Empowering Large Language Models To Understand Point Clouds2023 · 339 citations
- How Far Are We To GPT-4V? Closing The Gap To Commercial Multimodal Models With Open-source Suites2024 · 339 citations
- Sharegpt4v: Improving Large Multi-modal Models With Better Captions2023 · 237 citations
- Omniobject3d: Large-vocabulary 3D Object Dataset For Realistic Perception, Reconstruction And Generation2023 · 176 citations
- Anysplat: Feed-forward 3D Gaussian Splatting From Unconstrained Views2025 · 7 citations
- Caprl: Stimulating Dense Image Caption Capabilities Via Reinforcement Learning2025
- From Pixels To Words -- Towards Native Vision-language Primitives At Scale2025
- The Prism Hypothesis: Harmonizing Semantic And Pixel Representations Via Unified Autoencoding2025
- Mcpverse: An Expansive, Real-world Benchmark For Agentic Tool Use2025
Topics