view article Article There is no such thing as a tokenizer-free lunch By catherinearnett • Sep 25 • 86
AMDGPU onnx Collection optimized image generation ONNX models for AMD Ryzen (TM) AI GPUs and Radeon Discrete GPUs • 18 items • Updated Jul 11 • 10
SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training Paper • 2505.11594 • Published May 16 • 75
Elucidating the Design Space of Diffusion-Based Generative Models Paper • 2206.00364 • Published Jun 1, 2022 • 18
PaliGemma 2 Release Collection Vision-Language Models available in multiple 3B, 10B and 28B variants. • 32 items • Updated Jul 10 • 150
Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks Paper • 2311.06242 • Published Nov 10, 2023 • 95
DOCCI: Descriptions of Connected and Contrasting Images Paper • 2404.19753 • Published Apr 30, 2024 • 13
Analyzing and Improving the Training Dynamics of Diffusion Models Paper • 2312.02696 • Published Dec 5, 2023 • 34
I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization Paper • 2311.10126 • Published Nov 16, 2023 • 10
Infinite Photorealistic Worlds using Procedural Generation Paper • 2306.09310 • Published Jun 15, 2023 • 15
FasterViT: Fast Vision Transformers with Hierarchical Attention Paper • 2306.06189 • Published Jun 9, 2023 • 31