Selen Su

selensu's activity

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

updated 4 models 1 day ago

NextTransformer/mHC-49B-Tokens

Text Generation • 1B • Updated 1 day ago

NextTransformer/HC-49B-Tokens

Text Generation • 1B • Updated 1 day ago

NextTransformer/SSSL-49B-Tokens

Text Generation • 1B • Updated 1 day ago

NextTransformer/Dense-Baseline-49B-Tokens

Text Generation • 1B • Updated 1 day ago

updated 3 collections 1 day ago

Others

Collection

1 item • Updated 1 day ago

Residual

Collection

2 items • Updated 1 day ago

Baseline

Collection

1 item • Updated 1 day ago

published 4 models 1 day ago

NextTransformer/mHC-49B-Tokens

Text Generation • 1B • Updated 1 day ago

NextTransformer/HC-49B-Tokens

Text Generation • 1B • Updated 1 day ago

NextTransformer/SSSL-49B-Tokens

Text Generation • 1B • Updated 1 day ago

NextTransformer/Dense-Baseline-49B-Tokens

Text Generation • 1B • Updated 1 day ago

upvoted a paper 9 days ago

Wave Forcing: Towards Speed-of-Light Streaming Video Generation

Paper • 2611.00859 • Published 12 days ago • 129

upvoted a paper 16 days ago

Work Agents: Systems, Capabilities, and Optimization

Paper • 2610.35845 • Published 17 days ago • 116

upvoted 3 papers 22 days ago

Embodied Task Agents Can Perform Fine Manipulation through Tactile In-Context Learning

Paper • 2610.27613 • Published 23 days ago • 24

Truncate or Not? A Scaling Study of Looped Transformers with Truncated Backpropagation

Paper • 2610.26030 • Published 23 days ago • 33

HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs

Paper • 2610.26770 • Published 24 days ago • 33

upvoted a paper 24 days ago

Execution Before Memory: Diagnosing Memory Failures in Video World Models

Paper • 2610.23542 • Published 27 days ago • 28

upvoted a paper 26 days ago

Can World and Action Modeling Benefit Each Other under Unified Causal Training?

Paper • 2610.21095 • Published 28 days ago • 29

submitted a paper to Daily Papers 27 days ago

Can World and Action Modeling Benefit Each Other under Unified Causal Training?

Paper • 2610.21095 • Published 28 days ago • 29