Rustam Uzdenov

SUPERustam's activity

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

liked a Space 4 days ago

Running on Zero

Agents

18

CADENA Stepwise CAD

📐

18

Turn a 3D mesh into a parametric CadQuery program

liked a model 4 days ago

kulibinai/cadena

Image-to-Text • Updated 4 days ago • 16

liked a dataset 4 days ago

kulibinai/cadena-bench

Viewer • Updated 4 days ago • 3.4k • 291 • 4

authored a paper 4 days ago

CADENA: Stepwise CAD Reverse Engineering

Paper • 2608.00799 • Published 8 days ago • 36

upvoted a paper 4 days ago

CADENA: Stepwise CAD Reverse Engineering

Paper • 2608.00799 • Published 8 days ago • 36

liked a Space about 2 months ago

Running

31

Weight-Space Geometry of Offline Reasoning Training

🧭

31

Interactive weight-space geometry of six reasoning losses

upvoted a paper about 2 months ago

A Geometric Account of Activation Steering through Angle-Norm Decomposition

Paper • 2606.06735 • Published Jun 4 • 27

upvoted 2 articles 4 months ago

view article

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

• 
• 
• +7

aminediroHF, qgallouedec, kashif, lewtun, edbeeching, albertvillanova, nouamanetazi, lvwerra, sergiopaniego

•

Mar 10

• 174

view article

Article

TRL v1.0: Post-Training Library Built to Move with the Field

• 
• 
• +2

qgallouedec, stevhliu, pcuenq, sergiopaniego

•

Mar 31

• 58

upvoted a collection 5 months ago

Qwen3.5

Collection

21 items • Updated Mar 9 • 1.75k

liked a model 6 months ago

kulibinai/cadevolve-rl1

2B • Updated Feb 19 • 125 • 6

liked a dataset 6 months ago

kulibinai/cadevolve

Viewer • Updated Feb 19 • 2M • 152 • 15

upvoted 2 papers 6 months ago

CADEvolve: Creating Realistic CAD via Program Evolution

Paper • 2602.16317 • Published Feb 18 • 30

AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders

Paper • 2602.05027 • Published Feb 4 • 63

upvoted an article 6 months ago

view article

Article

No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL

• 
• 
• +4

toslali-ibm, mirinflim, qgallouedec, esnible, rganti, mudhakar

•

Jun 3, 2025

• 101

liked a model 6 months ago

maksimko123/cadrille

2B • Updated Jun 2, 2025 • 2.04k • 9

upvoted 4 papers 9 months ago

GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms

Paper • 2511.17592 • Published Nov 17, 2025 • 122

Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story

Paper • 2511.15210 • Published Nov 19, 2025 • 91

Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation

Paper • 2511.14993 • Published Nov 19, 2025 • 235

LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics

Paper • 2511.08544 • Published Nov 11, 2025 • 12