-
Taming LLMs by Scaling Learning Rates with Gradient Grouping
Paper • 2506.01049 • Published • 38 -
Switch EMA: A Free Lunch for Better Flatness and Sharpness
Paper • 2402.09240 • Published • 5 -
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
Paper • 2410.06373 • Published • 36 -
OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning
Paper • 2209.04851 • Published • 3
Collections
Discover the best community collections!
Collections including paper arxiv:2410.06373
-
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
Paper • 2410.06373 • Published • 36 -
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
Paper • 2504.00999 • Published • 95 -
What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models
Paper • 2503.24235 • Published • 54 -
MoCha: Towards Movie-Grade Talking Character Synthesis
Paper • 2503.23307 • Published • 138
-
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
Paper • 2402.04252 • Published • 29 -
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Paper • 2402.03749 • Published • 14 -
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Paper • 2402.04615 • Published • 44 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 23
-
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
Paper • 2404.15653 • Published • 29 -
MoDE: CLIP Data Experts via Clustering
Paper • 2404.16030 • Published • 15 -
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
Paper • 2405.12130 • Published • 50 -
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Paper • 2405.12981 • Published • 33
-
Taming LLMs by Scaling Learning Rates with Gradient Grouping
Paper • 2506.01049 • Published • 38 -
Switch EMA: A Free Lunch for Better Flatness and Sharpness
Paper • 2402.09240 • Published • 5 -
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
Paper • 2410.06373 • Published • 36 -
OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning
Paper • 2209.04851 • Published • 3
-
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
Paper • 2410.06373 • Published • 36 -
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
Paper • 2504.00999 • Published • 95 -
What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models
Paper • 2503.24235 • Published • 54 -
MoCha: Towards Movie-Grade Talking Character Synthesis
Paper • 2503.23307 • Published • 138
-
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
Paper • 2404.15653 • Published • 29 -
MoDE: CLIP Data Experts via Clustering
Paper • 2404.16030 • Published • 15 -
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
Paper • 2405.12130 • Published • 50 -
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Paper • 2405.12981 • Published • 33
-
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
Paper • 2402.04252 • Published • 29 -
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Paper • 2402.03749 • Published • 14 -
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Paper • 2402.04615 • Published • 44 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 23