2025-04-14

Models

• [ ]

Papers

• [2504.08736] GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation

• [2504.08685] Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model

• [2504.07963] PixelFlow: Pixel-Space Generative Models with Flow

• [2504.07405] FlexIP: Dynamic Control of Preservation and Personality for Customized Image Generation

• [2504.06256] Transfer between Modalities with MetaQueries

• [2504.02612] Fine-Tuning Visual Autoregressive Models for Subject-Driven Generation

• [2504.10479] InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

• [2504.10471] MIEB: Massive Image Embedding Benchmark

• [2504.11346] Seedream 3.0 Technical Report

• [2504.10465] Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding

• [2504.10443] Multimodal Long Video Modeling Based on Temporal Dynamic Context

Code

• [ ]

Articles

• [ ]

Videos

• [ ]

Other

• [ ]

Tweets