Yingfa Chen

chen-yingfa's activity

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

authored 4 papers 2 days ago

StateFlow: Sequence Pipeline Parallelism for Long-Context Modeling with Linear Recurrence

Paper • 2608.06838 • Published Aug 7

Latent Compaction with Test-Time Training

Paper • 2610.20582 • Published 3 days ago • 8

Frontier Language Models Struggle to Copy: Text Can Be Better Viewed in 2D

Paper • 2607.16072 • Published Jul 17 • 1

Rethinking the Role of Efficient Attention in Hybrid Architectures

Paper • 2606.15378 • Published Jun 13 • 21

upvoted a paper 2 days ago

Latent Compaction with Test-Time Training

Paper • 2610.20582 • Published 3 days ago • 8

submitted a paper to Daily Papers 2 days ago

Latent Compaction with Test-Time Training

Paper • 2610.20582 • Published 3 days ago • 8

authored 4 papers 4 months ago

MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling

Paper • 2602.11761 • Published Feb 12 • 8

Student-in-the-Loop Chain-of-Thought Distillation via Generation-Time Selection

Paper • 2604.02819 • Published Apr 3 • 1

DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices

Paper • 2605.10933 • Published May 11 • 3

Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It

Paper • 2606.11052 • Published Jun 9 • 17

upvoted a paper 4 months ago

Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It

Paper • 2606.11052 • Published Jun 9 • 17

liked a model 6 months ago

chen-yingfa/HypeNet-5B

5B • Updated Apr 28 • 15 • 1

updated a model 6 months ago

chen-yingfa/HypeNet-5B

5B • Updated Apr 28 • 15 • 1

updated a collection 6 months ago

HypeNet

Collection

The models for the paper: Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts • 2 items • Updated Apr 28

published a model 6 months ago

chen-yingfa/HypeNet-5B

5B • Updated Apr 28 • 15 • 1

updated a collection 6 months ago

HypeNet

Collection

The models for the paper: Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts • 2 items • Updated Apr 28

liked a model 6 months ago

chen-yingfa/HypeNet-2B

2B • Updated Apr 7 • 192 • 2

updated a model 6 months ago

chen-yingfa/HypeNet-2B

2B • Updated Apr 7 • 192 • 2

published a model 6 months ago

chen-yingfa/HypeNet-2B

2B • Updated Apr 7 • 192 • 2

upvoted an article 7 months ago

view article

Article

Welcome Gemma 4: Frontier multimodal intelligence on device

• 
• 
• +5

merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift

•

Apr 2

• 929