Wang Weiyi PRO

kaupane's activity

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

upvoted a paper 8 days ago

FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent Space

Paper • 2602.02092 • Published 9 days ago • 18

upvoted an article 9 days ago

view article

Article

The Heterogeneous Feature of RoPE-based Attention in Long-Context LLMs

• 

Nov 15, 2025

•

14

upvoted a paper 19 days ago

Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model

Paper • 2601.15892 • Published 20 days ago • 53

upvoted a paper 21 days ago

ReCode: Updating Code API Knowledge with Reinforcement Learning

Paper • 2506.20495 • Published Jun 25, 2025 • 10

upvoted 2 papers 22 days ago

ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development

Paper • 2601.11077 • Published 26 days ago • 64

AstroReason-Bench: Evaluating Unified Agentic Planning across Heterogeneous Space Planning Problems

Paper • 2601.11354 • Published 26 days ago • 4

upvoted a paper about 2 months ago

Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield

Paper • 2511.22677 • Published Nov 27, 2025 • 32

upvoted 2 papers 3 months ago

Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm

Paper • 2511.04570 • Published Nov 6, 2025 • 215

REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers

Paper • 2504.10483 • Published Apr 14, 2025 • 22

upvoted a collection 3 months ago

Cerebras REAP

Collection

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 26 items • Updated 14 days ago • 105

upvoted 2 papers 4 months ago

NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos

Paper • 2510.08568 • Published Oct 9, 2025 • 2

Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer

Paper • 2510.06590 • Published Oct 8, 2025 • 76

upvoted an article 7 months ago

view article

Article

5 Things You Need to Know About Moonshot AI and Kimi K2, the New #1 model on the Hub

• 

Jul 15, 2025

•

24

upvoted a collection 9 months ago

Deepseek Papers

Collection

Deepseek papers collection • 29 items • Updated 2 days ago • 320

upvoted 4 collections 10 months ago

high-quality Chinese training datasets

Collection

a suite of high-quality Chinese datasets, used for pretraining, fine-tuning or preference alignment. And the models trained on these datasets. • 13 items • Updated May 22, 2025 • 24

Unsloth 4-bit Dynamic Quants

Collection

Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit • 28 items • Updated 7 days ago • 94

Qwen3

Collection

Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants. • 79 items • Updated 7 days ago • 261

GLM-4-0414

Collection

GLM-4-0414 series model • 8 items • Updated Jun 30, 2025 • 134

upvoted 2 papers 10 months ago

Kimi-VL Technical Report

Paper • 2504.07491 • Published Apr 10, 2025 • 137

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published Apr 7, 2025 • 205