-
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
Paper • 2402.04252 • Published • 25 -
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Paper • 2402.03749 • Published • 12 -
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Paper • 2402.04615 • Published • 39 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 20
Collections
Discover the best community collections!
Collections including paper arxiv:2412.09428
-
Flowing from Words to Pixels: A Framework for Cross-Modality Evolution
Paper • 2412.15213 • Published • 25 -
No More Adam: Learning Rate Scaling at Initialization is All You Need
Paper • 2412.11768 • Published • 40 -
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
Paper • 2412.13663 • Published • 103 -
Autoregressive Video Generation without Vector Quantization
Paper • 2412.14169 • Published • 13
-
GenEx: Generating an Explorable World
Paper • 2412.09624 • Published • 84 -
Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation
Paper • 2412.09428 • Published • 7 -
BrushEdit: All-In-One Image Inpainting and Editing
Paper • 2412.10316 • Published • 33 -
FashionComposer: Compositional Fashion Image Generation
Paper • 2412.14168 • Published • 16
-
SoundCTM: Uniting Score-based and Consistency Models for Text-to-Sound Generation
Paper • 2405.18503 • Published • 9 -
DITTO-2: Distilled Diffusion Inference-Time T-Optimization for Music Generation
Paper • 2405.20289 • Published • 10 -
LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes
Paper • 2406.02897 • Published • 13 -
Audio Mamba: Bidirectional State Space Model for Audio Representation Learning
Paper • 2406.03344 • Published • 18