hankai

hankaixyz's activity

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

upvoted a paper 19 days ago

VersatileFFN: Achieving Parameter Efficiency in LLMs via Adaptive Wide-and-Deep Reuse

Paper • 2512.14531 • Published 19 days ago • 12

submitted a paper to Daily Papers 19 days ago

VersatileFFN: Achieving Parameter Efficiency in LLMs via Adaptive Wide-and-Deep Reuse

Paper • 2512.14531 • Published 19 days ago • 12

authored 3 papers about 1 month ago

Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting

Paper • 2404.18911 • Published Apr 29, 2024 • 30

Revealing the Power of Post-Training for Small Language Models via Knowledge Distillation

Paper • 2509.26497 • Published Sep 30, 2025

ROOT: Robust Orthogonalized Optimizer for Neural Network Training

Paper • 2511.20626 • Published Nov 25, 2025 • 43

upvoted a paper about 1 month ago

ROOT: Robust Orthogonalized Optimizer for Neural Network Training

Paper • 2511.20626 • Published Nov 25, 2025 • 43

commented a paper about 1 month ago

ROOT: Robust Orthogonalized Optimizer for Neural Network Training

Paper • 2511.20626 • Published Nov 25, 2025 • 43 •

5

liked a model about 2 months ago

Lpzhan/openPangu-embedded-gguf

1B • Updated Nov 6, 2025 • 34 • 2

New activity in facebook/MobileLLM-Pro 3 months ago

Seems lagging behind Pangu-1B

🔥 👀 5

3

#4 opened 3 months ago by

hankaixyz

upvoted a paper 4 months ago

Benchmarking Optimizers for Large Language Model Pretraining

Paper • 2509.01440 • Published Sep 1, 2025 • 24

liked a model 4 months ago

FreedomIntelligence/openPangu-Ultra-MoE-718B

734B • Updated Nov 4, 2025 • 6 • 2

liked 3 models 5 months ago

FreedomIntelligence/openPangu-Embedded-1B

Text Generation • 1B • Updated Aug 21, 2025 • 16 • 6

FreedomIntelligence/openPangu-Embedded-7B

Text Generation • 8B • Updated Aug 21, 2025 • 164 • 6

PIKA665/openPangu-Embedded-1B

1B • Updated Aug 4, 2025 • 7 • 1

liked a model 6 months ago

IntervitensInc/pangu-pro-moe-model

Text Generation • 72B • Updated Jul 9, 2025 • 71 • 45

upvoted 2 papers over 1 year ago

Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting

Paper • 2404.18911 • Published Apr 29, 2024 • 30

DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models

Paper • 2403.00818 • Published Feb 26, 2024 • 19

liked a model over 1 year ago

jamesHD2001/DenseMamba-1.3B

Updated Apr 11, 2024 • 8 • 1

authored 2 papers almost 2 years ago

Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets

Paper • 2010.14819 • Published Oct 28, 2020

GhostNet: More Features from Cheap Operations

Paper • 1911.11907 • Published Nov 27, 2019 • 1