ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning Paper • 2604.19254 • Published Apr 21 • 29
Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence? Paper • 2604.03016 • Published Apr 3 • 37
view article Article Welcome Gemma 4: Frontier multimodal intelligence on device +5 merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift • Apr 2 • 899
Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting Paper • 2603.25745 • Published Mar 26 • 16
Group3D: MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection Paper • 2603.21944 • Published Mar 23 • 26
Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model Paper • 2603.21986 • Published Mar 23 • 125
Hidden Dynamics of Massive Activations in Transformer Training Paper • 2508.03616 • Published Aug 5, 2025 • 19
OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation Paper • 2410.17799 • Published Oct 23, 2024 • 13