Multimodal Understanding | Jin Wanghttps://jinjinw.com/tag/multimodal-understanding/Multimodal UnderstandingWowchemy (https://wowchemy.com)en-usFri, 22 May 2026 00:00:00 +0000https://jinjinw.com/media/icon_hub90c490752e80582a66e6b83d4f30712_9669_512x512_fill_lanczos_center_3.pngMultimodal Understandinghttps://jinjinw.com/tag/multimodal-understanding/Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Drivinghttps://jinjinw.com/publication/fast-ddrive/Fri, 22 May 2026 00:00:00 +0000https://jinjinw.com/publication/fast-ddrive/Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLMhttps://jinjinw.com/publication/fast-dvlm/Wed, 08 Apr 2026 00:00:00 +0000https://jinjinw.com/publication/fast-dvlm/Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learninghttps://jinjinw.com/publication/cross-modal-identity-mapping/Mon, 02 Mar 2026 00:00:00 +0000https://jinjinw.com/publication/cross-modal-identity-mapping/INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Samplinghttps://jinjinw.com/publication/inter/Wed, 30 Jul 2025 00:00:00 +0000https://jinjinw.com/publication/inter/Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic Viewhttps://jinjinw.com/publication/game-theory/Wed, 01 May 2024 00:00:00 +0000https://jinjinw.com/publication/game-theory/