Olga Tsymboi

oltsy's activity

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

authored 2 papers 9 days ago

T-Search: An Open Agentic Retriever and Playground for Hard Multi-Step Search

Paper • 2610.06782 • Published 26 days ago • 4

Closing Cost-Quality Gap in Document VLMs: Difficulty-Aware Data Curation and Quality-Adjusted Deployment Economics

Paper • 2609.01575 • Published Sep 1

authored a paper about 2 months ago

From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix

Paper • 2609.01572 • Published Sep 1 • 37

upvoted a paper about 2 months ago

From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix

Paper • 2609.01572 • Published Sep 1 • 37

liked a dataset 3 months ago

ai-forever/RUMBA

Viewer • Updated Jul 24 • 3.09k • 316 • 2

upvoted a collection 3 months ago

T-search

Collection

T-Search model and evaluation datasets. • 7 items • Updated Jul 29 • 23

liked a Space 3 months ago

Running

44

T-Search: an open agentic retriever

🔎

44

Open agentic retriever for hard multi-step search

liked 2 models 4 months ago

t-tech/T-Search-NVFP4

Text Generation • 21B • Updated Jul 16 • 116 • 16

t-tech/T-Search-FP8

Text Generation • 36B • Updated Jul 16 • 120 • 13

liked 2 datasets 4 months ago

t-tech/SynthComp

Viewer • Updated Jul 16 • 790 • 172 • 14

t-tech/TRuST

Viewer • Updated Jul 16 • 324 • 386 • 17

liked a model 4 months ago

t-tech/T-Search

Text Generation • 36B • Updated Jul 16 • 372 • 57

authored a paper 5 months ago

Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows

Paper • 2604.23855 • Published Apr 26 • 2

upvoted a paper 5 months ago

Trust-Region Behavior Blending for On-Policy Distillation

Paper • 2605.31159 • Published May 29 • 65

upvoted a paper 9 months ago

F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare

Paper • 2602.06717 • Published Feb 6 • 77

liked a model 10 months ago

t-tech/T-pro-it-2.1

Text Generation • 33B • Updated Dec 23, 2025 • 739 • • 38

submitted a paper to Daily Papers 11 months ago

T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground

Paper • 2512.10430 • Published Dec 11, 2025 • 121

authored a paper 11 months ago

T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground

Paper • 2512.10430 • Published Dec 11, 2025 • 121

upvoted a paper 11 months ago

T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground

Paper • 2512.10430 • Published Dec 11, 2025 • 121

updated a collection 11 months ago

T-pro-2.0

Collection

Hybrid reasoning model based on Qwen3 32B • 7 items • Updated Mar 2 • 30