Muhtasham Oblokulov

muhtasham's activity

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

upvoted an article about 14 hours ago

view article

Article

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

• 
• 
• +7

4 days ago

•

42

upvoted 2 articles 16 days ago

view article

Article

Custom Kernels for All from Codex and Claude

• 
• 
• +2

29 days ago

•

69

view article

Article

Codex 正在推动 AI 模型的开源与训练流程

• 
• 

Dec 11, 2025

•

11

upvoted a collection 17 days ago

Qwen3.5

Collection

21 items • Updated 4 days ago • 1.15k

upvoted a collection 25 days ago

LateOn-Code 💻

Collection

State-of-the-art late interaction code retrieval models • 6 items • Updated 10 days ago • 16

upvoted an article 25 days ago

view article

Article

LateOn-Code & ColGrep: LightOn unveils state-of-the-art code retrieval models and code search tooling

• 

29 days ago

•

50

upvoted 2 papers 27 days ago

Robust Speech Recognition via Large-Scale Weak Supervision

Paper • 2212.04356 • Published Dec 6, 2022 • 52

Single-minus gluon tree amplitudes are nonzero

Paper • 2602.12176 • Published 29 days ago • 8

upvoted an article 30 days ago

view article

Article

From Golden Gate Bridge to Broken JSON: Why Anthropic's SAE Steering Fails for Structured Output

• 

Feb 7

•

22

upvoted a collection about 1 month ago

Open Coding Agents

Collection

13 items • Updated 8 days ago • 51

upvoted 3 articles about 2 months ago

view article

Article

Universal Assisted Generation: Faster Decoding with Any Assistant Model

• 
• 
• +6

Oct 29, 2024

•

60

view article

Article

An Optimal Lossy Variant of Speculative Decoding

• 

Jun 12, 2024

•

4

view article

Article

Faster Text Generation with Self-Speculative Decoding

• 
• 
• +2

Nov 20, 2024

•

64

upvoted 3 collections about 2 months ago

Qwen3-TTS

Collection

7 items • Updated Jan 22 • 323

Quantized translategemma

Collection

Quickly tested with vLLM. Not fully compatible yet. • 7 items • Updated Jan 19 • 3

PII & De-Identification

Collection

Models for extracting PII entities and de-identifying clinical text, with support for HIPAA and GDPR compliance. • 278 items • Updated 3 days ago • 33

upvoted a collection 2 months ago

UncheatableEval

Collection

5 items • Updated Jan 14 • 2

upvoted an article 3 months ago

view article

Article

ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval

• 

Mar 18, 2025

•

16

upvoted 2 collections 3 months ago

SAM Audio

Collection

The SAM Audio model licenses allow for redistribution so long as the original license files are included • 9 items • Updated Dec 25, 2025 • 4

ViDoRe Benchmark V3

Collection

ViDoRe V3 is our latest benchmark, engineered to set a new industry gold standard for multi-modal, enterprise document retrieval evaluation. • 8 items • Updated Jan 14 • 20