khtsly

khtsly's activity

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

commented a paper 17 days ago

Multi-Stream Attention Residuals

Paper • 2610.13630 • Published 29 days ago • 42 •

5

New activity in IFM/K2-Horizon-32B about 2 months ago

training cutoff

1

#3 opened about 2 months ago by

khtsly

New activity in XingChen-AGI/Xing4.0-29B-A4B about 2 months ago

training data knowledge cutoff

1

#10 opened about 2 months ago by

khtsly

New activity in SHSLab/Step-5-Preview-BF16 about 2 months ago

Request: DOI

10

#1 opened about 2 months ago by

win10

New activity in openbmb/Ultra-FineWeb about 2 months ago

newer snapshot (upto Q3 2026)

1

#25 opened about 2 months ago by

khtsly

New activity in openbmb/UltraData-Code about 2 months ago

typescript

🚀 2

2

#2 opened about 2 months ago by

khtsly

New activity in openbmb/UltraX-Preview about 2 months ago

snapshot date

2

#7 opened about 2 months ago by

khtsly

New activity in Agnes-AI/Agnes-3.0-Flash about 2 months ago

number of active parameters

👍 4

1

#1 opened about 2 months ago by

inikishev

how much tokens is this model trained? and knowledge cutoff date?

👀 1

#2 opened about 2 months ago by

khtsly

New activity in Qwen/Qwen3.8-Flash-Next 2 months ago

GatedDeltaNet-2 (GDN-2) ??

❤️ 5

1

#13 opened 2 months ago by

khtsly

New activity in ornith-ai/Ornith-1.5-35B-A3B 3 months ago

base model?

1

#19 opened 3 months ago by

khtsly

New activity in omarkamali/wikipedia-monthly 3 months ago

any updates?

1

#8 opened 3 months ago by

khtsly

commented 3 papers 3 months ago

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

Paper • 2608.16072 • Published Aug 17 • 30 •

6

Dion3: Full-Stack Orthogonal Updates

Paper • 2608.11612 • Published Aug 12 • 11 •

4

Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus

Paper • 2608.12149 • Published Aug 12 • 23 •

4

New activity in AxiomicLabs/GPT-X2.5-135M 3 months ago

dataset quality

2

#5 opened 3 months ago by

khtsly

commented 3 papers 3 months ago

Multi-Head Attention Residuals

Paper • 2607.27230 • Published Jul 22 • 12 •

3

xHC: Expanded Hyper-Connections

Paper • 2607.14530 • Published Jul 16 • 53 •

3

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published Jul 27 • 524 •

10

New activity in moonshotai/Kimi-K3 3 months ago

Kimi K3 Air? Flash???

👍 1

2

#74 opened 3 months ago by

Kosh69