Yu li

Yukkkop's activity

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

upvoted 2 collections 5 days ago

2026 February 🏮 - China Open Source Highlights

Collection

28 items • Updated about 8 hours ago • 9

2026 January⛄️ - China Open Source Highlights

Collection

38 items • Updated 14 days ago • 6

upvoted a paper 6 days ago

DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models

Paper • 2501.18590 • Published Jan 30, 2025 • 1

upvoted 3 papers 8 days ago

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression

Paper • 2510.13999 • Published Oct 15, 2025 • 12

LLaDA2.1: Speeding Up Text Diffusion via Token Editing

Paper • 2602.08676 • Published 8 days ago • 66

AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders

Paper • 2602.05027 • Published 13 days ago • 59

upvoted 12 papers 9 days ago

DINO-SAE: DINO Spherical Autoencoder for High-Fidelity Image Reconstruction and Generation

Paper • 2601.22904 • Published 18 days ago • 15

PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss

Paper • 2602.02493 • Published 15 days ago • 42

Beyond Output Critique: Self-Correction via Task Distillation

Paper • 2602.00871 • Published 17 days ago • 2

Self-Improving Pretraining: using post-trained models to pretrain better models

Paper • 2601.21343 • Published 20 days ago • 16

Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better

Paper • 2602.05393 • Published 13 days ago • 7

Chronicals: A High-Performance Framework for LLM Fine-Tuning with 3.51x Speedup over Unsloth

Paper • 2601.02609 • Published Jan 6 • 2

Reinforcement Learning from Meta-Evaluation: Aligning Language Models Without Ground-Truth Labels

Paper • 2601.21268 • Published 20 days ago • 4

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Paper • 2601.22975 • Published 18 days ago • 100

Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation

Paper • 2512.20908 • Published Dec 24, 2025 • 29

Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits

Paper • 2512.20578 • Published Dec 23, 2025 • 86

Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge

Paper • 2601.08808 • Published Jan 13 • 39

Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks

Paper • 2601.03448 • Published Jan 6 • 13

upvoted 2 collections 9 days 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. • 67 items • Updated about 8 hours ago • 7

TINY MODELS WITH BIG INTELLIGENCE

Collection

Tiny (<30B) models that tend to outperform their same-parameter counterparts. • 12 items • Updated about 3 hours ago • 2