Siyuan Li

Lupin1998's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 2 days ago

XAttention: Block Sparse Attention with Antidiagonal Scoring

Paper • 2503.16428 • Published 27 days ago • 14

upvoted 2 papers 9 days ago

From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing

Paper • 2411.11916 • Published Nov 18, 2024 • 3

Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions

Paper • 2406.05688 • Published Jun 9, 2024 • 1

upvoted 8 papers 11 days ago

OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning

Paper • 2306.11249 • Published Jun 20, 2023 • 1

OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning

Paper • 2209.04851 • Published Sep 11, 2022 • 2

SemiReward: A General Reward Model for Semi-supervised Learning

Paper • 2310.03013 • Published Oct 4, 2023 • 2

AutoMix: Unveiling the Power of Mixup for Stronger Classifiers

Paper • 2103.13027 • Published Mar 24, 2021 • 1

A Survey on Mixup Augmentations and Beyond

Paper • 2409.05202 • Published Sep 8, 2024 • 1

Improved Visual-Spatial Reasoning via R1-Zero-Like Training

Paper • 2504.00883 • Published 15 days ago • 60

Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Paper • 2409.12191 • Published Sep 18, 2024 • 78

Multi-Token Attention

Paper • 2504.00927 • Published 15 days ago • 43

upvoted a paper 14 days ago

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization

Paper • 2504.00999 • Published 15 days ago • 78

upvoted 4 papers 6 months ago

Efficient Multi-order Gated Aggregation Network

Paper • 2211.03295 • Published Nov 7, 2022 • 3

Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN

Paper • 2205.13943 • Published May 27, 2022 • 1

Switch EMA: A Free Lunch for Better Flatness and Sharpness

Paper • 2402.09240 • Published Feb 14, 2024 • 3

Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning

Paper • 2410.06373 • Published Oct 8, 2024 • 34