Latest

• Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought
• NVILA: Efficient Frontier Visual Language Models
• Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks
• Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders
• T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching
• LITA: Language Instructed Temporal-localization Assistant
• PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees
• Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition
• I^2SB: Image-to-Image Schrödinger Bridge
• Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning
• MinVIS: A minimal video instance segmentation framework without video-based training
• Test-time prompt tuning for zero-shot generalization in vision-language models