Zhichen Zeng

CharyZeng's activity

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

authored a paper 6 days ago

PTXBench: Benchmark and Adapt LLMs for GPU Kernel Optimization with Architecture-specific PTX

Paper • 2608.17379 • Published 8 days ago • 3

updated a model 21 days ago

CharyZeng/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16-4layer

36B • Updated 21 days ago • 20

published a model 21 days ago

CharyZeng/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16-4layer

36B • Updated 21 days ago • 20

updated a model 24 days ago

CharyZeng/Inkling-Small-4layer

18B • Updated 24 days ago • 127

published a model 24 days ago

CharyZeng/Inkling-Small-4layer

18B • Updated 24 days ago • 127

updated a model 29 days ago

CharyZeng/Inkling-4layer

Image-Text-to-Text • 38B • Updated 29 days ago • 32

published 2 models 29 days ago

CharyZeng/Inkling-4layer

Image-Text-to-Text • 38B • Updated 29 days ago • 32

CharyZeng/DeepSeek-V4-Pro-4layer

Text Generation • 54B • Updated Apr 25 • 24

authored a paper 2 months ago

HierSVA: A Data Synthesis Pipeline, Dataset, and Benchmark for LLM-Driven Hierarchical Hardware Formal Verification

Paper • 2606.13706 • Published Jun 9

updated a model 2 months ago

CharyZeng/Kimi-K2.5-2layer

21B • Updated Jun 16 • 28

updated a model 3 months ago

CharyZeng/Kimi-K2.5-4layer

56B • Updated Jun 2 • 4

published a model 3 months ago

CharyZeng/Kimi-K2.5-4layer

56B • Updated Jun 2 • 4

authored 2 papers 3 months ago

Local Linear Attention: An Optimal Interpolation of Linear and Softmax Attention For Test-Time Regression

Paper • 2510.01450 • Published Oct 1, 2025 • 2

Parallax: Parameterized Local Linear Attention for Language Modeling

Paper • 2605.29157 • Published May 27 • 11

upvoted a paper 3 months ago

Parallax: Parameterized Local Linear Attention for Language Modeling

Paper • 2605.29157 • Published May 27 • 11

updated 2 models 4 months ago

CharyZeng/DeepSeek-V4-Pro-4layer

Text Generation • 54B • Updated Apr 25 • 24

CharyZeng/DeepSeek-V4-Flash-4layer

Text Generation • 15B • Updated Apr 25 • 16

published 2 models 4 months ago

CharyZeng/DeepSeek-V4-Flash-4layer

Text Generation • 15B • Updated Apr 25 • 16

CharyZeng/Kimi-K2.5-2layer

21B • Updated Jun 16 • 28

updated a dataset 4 months ago

AccRL/accrl-training

Updated Jul 7 • 42