Xiaohan Qin (SJTU) & (SII)

galaxy-1's activity

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

commented a paper 2 days ago

DepthGraft: Structural Regularization through Hierarchical Cross-Layer KV Reconstruction

Paper • 2611.03142 • Published 13 days ago • 16 •

4

upvoted a paper 2 days ago

On the Design of Hyper-Connections: Simplification, Stability, and Scalability

Paper • 2611.05984 • Published 11 days ago • 29

upvoted a paper 4 days ago

DepthGraft: Structural Regularization through Hierarchical Cross-Layer KV Reconstruction

Paper • 2611.03142 • Published 13 days ago • 16

submitted a paper to Daily Papers 4 days ago

DepthGraft: Structural Regularization through Hierarchical Cross-Layer KV Reconstruction

Paper • 2611.03142 • Published 13 days ago • 16

upvoted 2 papers about 1 month ago

DoSA: Dots Sparse Attention

Paper • 2610.13990 • Published Sep 26 • 68

Multi-Stream Attention Residuals

Paper • 2610.13630 • Published Oct 9 • 44

submitted a paper to Daily Papers about 1 month ago

Multi-Stream Attention Residuals

Paper • 2610.13630 • Published Oct 9 • 44

upvoted a paper 4 months ago

xHC: Expanded Hyper-Connections

Paper • 2607.14530 • Published Jul 16 • 53

upvoted a paper 6 months ago

NITP: Next Implicit Token Prediction for LLM Pre-training

Paper • 2605.24956 • Published May 24 • 33

upvoted a paper 8 months ago

Residual Stream Duality in Modern Transformer Architectures

Paper • 2603.16039 • Published Mar 17 • 4

authored a paper 8 months ago

FineRMoE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach

Paper • 2603.13364 • Published Mar 9 • 9

upvoted a paper 8 months ago

FineRMoE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach

Paper • 2603.13364 • Published Mar 9 • 9

upvoted 2 papers 10 months ago

Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space

Paper • 2512.24617 • Published Dec 31, 2025 • 67

mHC: Manifold-Constrained Hyper-Connections

Paper • 2512.24880 • Published Dec 31, 2025 • 336

upvoted a paper 11 months ago

Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss

Paper • 2512.23447 • Published Dec 29, 2025 • 67

authored a paper about 1 year ago

ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning

Paper • 2510.18250 • Published Oct 21, 2025 • 14

upvoted 4 papers about 1 year ago

ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning

Paper • 2510.18250 • Published Oct 21, 2025 • 14

Glyph: Scaling Context Windows via Visual-Text Compression

Paper • 2510.17800 • Published Oct 20, 2025 • 69

Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization

Paper • 2510.13554 • Published Oct 15, 2025 • 59

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

Paper • 2509.12201 • Published Sep 15, 2025 • 107