Kitsun

KitsuVp's activity

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

updated a model about 1 hour ago

KitsuVp/NeoLLM

84.6M • Updated about 1 hour ago • 403 • 5

New activity in KitsuVp/NeoLLM about 21 hours ago

Update NeoLLM model and configuration sources

#1 opened about 21 hours ago by

KitsuVp

upvoted a collection 1 day ago

WTF GENIUS PAPERS

Collection

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 490 items • Updated about 4 hours ago • 106

upvoted 2 papers 1 day ago

Learning to Learn a Language

Paper • 2610.05879 • Published 26 days ago • 9

Copy-Paste Language Models

Paper • 2610.19247 • Published 18 days ago • 10

upvoted 15 papers about 1 month ago

AdamHD: Decoupled Huber Decay Regularization for Language Model Pre-Training

Paper • 2511.14721 • Published Nov 18, 2025 • 1

Correction of Decoupled Weight Decay

Paper • 2512.08217 • Published Apr 13 • 1

Stochastic Rounding for LLM Training: Theory and Practice

Paper • 2502.20566 • Published Feb 27, 2025 • 1

The AdEMAMix Optimizer: Better, Faster, Older

Paper • 2409.03137 • Published Sep 5, 2024 • 7

Next-Latent Prediction Transformers Learn Compact World Models

Paper • 2511.05963 • Published Nov 8, 2025 • 7

Output Embedding Centering for Stable LLM Pretraining

Paper • 2601.02031 • Published Apr 2 • 1

MiLe Loss: a New Entropy-Weighed Loss for Mitigating the Bias of Learning Difficulties in Large Language Models

Paper • 2310.19531 • Published Jan 15 • 1

LAuReL: Learned Augmented Residual Layer

Paper • 2411.07501 • Published Nov 12, 2024 • 1

Attention Residuals

Paper • 2603.15031 • Published Mar 16 • 203

SimpleGPT: Improving GPT via A Simple Normalization Strategy

Paper • 2602.01212 • Published Feb 1 • 4

GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling

Paper • 2506.22049 • Published Jun 27, 2025 • 3

The Curse of Depth in Large Language Models

Paper • 2502.05795 • Published Feb 9, 2025 • 41

SeeDNorm: Self-Rescaled Dynamic Normalization

Paper • 2510.22777 • Published Oct 26, 2025 • 1

Rethinking Attention Output Projection: Structured Hadamard Transforms for Efficient Transformers

Paper • 2603.08343 • Published Mar 9 • 2

You Need Better Attention Priors

Paper • 2601.15380 • Published Jan 21 • 2