Yu li

Yukkkop's activity

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

upvoted a paper 4 days ago

STEP3-VL-10B Technical Report

Paper • 2601.09668 • Published Jan 14 • 194

upvoted a paper 9 days ago

tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction

Paper • 2602.20160 • Published 12 days ago • 10

upvoted a paper 12 days ago

Llama-3.1-FoundationAI-SecurityLLM-Reasoning-8B Technical Report

Paper • 2601.21051 • Published Jan 28 • 14

upvoted a collection 14 days ago

Creative Writing Datasets

Collection

High-quality creative writing and storytelling data. • 35 items • Updated 12 days ago • 4

upvoted 2 papers 14 days ago

RynnBrain: Open Embodied Foundation Models

Paper • 2602.14979 • Published 22 days ago • 43

SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning

Paper • 2602.13515 • Published 22 days ago • 43

upvoted 2 collections 23 days ago

2026 February 🏮 - China Open Source Highlights

Collection

29 items • Updated 5 days ago • 10

2026 January⛄️ - China Open Source Highlights

Collection

38 items • Updated Feb 3 • 6

upvoted a paper 24 days ago

DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models

Paper • 2501.18590 • Published Jan 30, 2025 • 1

upvoted 2 papers 26 days ago

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

Paper • 2510.13999 • Published Oct 15, 2025 • 14

LLaDA2.1: Speeding Up Text Diffusion via Token Editing

Paper • 2602.08676 • Published 27 days ago • 68

upvoted 9 papers 27 days ago

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

Paper • 2602.05027 • Published Feb 4 • 60

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

Paper • 2601.22904 • Published Jan 30 • 15

PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss

Paper • 2602.02493 • Published Feb 2 • 44

Beyond Output Critique: Self-Correction via Task Distillation

Paper • 2602.00871 • Published Jan 31 • 2

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

Paper • 2601.21343 • Published Jan 29 • 17

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

Paper • 2602.05393 • Published about 1 month ago • 8

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 Jan 29 • 4

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

Paper • 2601.22975 • Published Jan 30 • 109