Siyuan Li

Lupin1998's activity

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

upvoted 3 papers about 2 months ago

Efficient Multi-order Gated Aggregation Network

Paper • 2211.03295 • Published Nov 7, 2022 • 2

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 • 3

liked 8 models about 2 months ago

MogaNet/moganet_xtiny_224_in1k

Image Classification • Updated Mar 13, 2023 • 1

MogaNet/moganet_xtiny_256_in1k

Image Classification • Updated Mar 13, 2023 • 2

MogaNet/moganet_tiny_224_in1k

Image Classification • Updated Mar 13, 2023 • 1

MogaNet/moganet_tiny_256_in1k

Image Classification • Updated Mar 13, 2023 • 1

MogaNet/moganet_small_224_in1k

Image Classification • Updated Mar 13, 2023 • 1

MogaNet/moganet_base_224_in1k

Image Classification • Updated Mar 13, 2023 • 1

MogaNet/moganet_large_224_in1k

Image Classification • Updated Mar 13, 2023 • 1

MogaNet/moganet_xlarge_224_in1k

Image Classification • Updated Mar 13, 2023 • 1

authored 9 papers about 2 months ago

Cascade-DETR: Delving into High-Quality Universal Object Detection

Paper • 2307.11035 • Published Jul 20, 2023

Behavior Contrastive Learning for Unsupervised Skill Discovery

Paper • 2305.04477 • Published May 8, 2023

Rethinking Memory and Communication Cost for Efficient Large Language Model Training

Paper • 2310.06003 • Published Oct 9, 2023 • 2

SemiReward: A General Reward Model for Semi-supervised Learning

Paper • 2310.03013 • Published Oct 4, 2023 • 1

LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memory

Paper • 2404.11163 • Published Apr 17

Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts

Paper • 2405.19893 • Published May 30 • 29

Efficient Multi-order Gated Aggregation Network

Paper • 2211.03295 • Published Nov 7, 2022 • 2

Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences

Paper • 2406.08128 • Published Jun 12

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

Paper • 2406.05688 • Published Jun 9