Sugato Ray's picture

Sugato Ray PRO

sugatoray

·

https://linkedin.com/in/sugatoray

AI & ML interests

None yet

Recent Activity

commented on a paper 3 days ago

Git Context Controller: Manage the Context of LLM-based Agents like Git

upvoted a paper 3 days ago

Git Context Controller: Manage the Context of LLM-based Agents like Git

updated a collection 5 days ago

View all activity

Organizations

upvoted a paper 3 days ago

Git Context Controller: Manage the Context of LLM-based Agents like Git

Paper • 2508.00031 • Published Jul 30, 2025 • 1

upvoted a paper 5 days ago

AttentionRetriever: Attention Layers are Secretly Long Document Retrievers

Paper • 2602.12278 • Published 6 days ago • 1

upvoted an article 5 days ago

Article

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

6 days ago

•

44

upvoted a paper 11 days ago

Accelerating Scientific Research with Gemini: Case Studies and Common Techniques

Paper • 2602.03837 • Published 15 days ago • 5

upvoted an article 13 days ago

Article

Community Evals: Because we're done trusting black-box leaderboards over the community

+5

15 days ago

•

69

upvoted a collection 15 days ago

Qwen3-Coder-Next

4 items • Updated 15 days ago • 86

upvoted a paper 20 days ago

Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability

Paper • 2601.18778 • Published 23 days ago • 40

upvoted a collection 20 days ago

Kimi K2.5

Moonshot's most powerful model • 2 items • Updated 15 days ago • 51

upvoted a paper 22 days ago

Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Paper • 2601.11868 • Published Jan 17 • 32

upvoted a paper 24 days ago

Qwen3-TTS Technical Report

Paper • 2601.15621 • Published 28 days ago • 67

upvoted 2 collections 24 days ago

Qwen3-TTS

7 items • Updated 27 days ago • 295

VibeVoice

Frontier Text-to-Speech Models https://microsoft.github.io/VibeVoice/ • 9 items • Updated 28 days ago • 209

upvoted a paper 25 days ago

LLM-in-Sandbox Elicits General Agentic Intelligence

Paper • 2601.16206 • Published 27 days ago • 84

upvoted 2 articles 25 days ago

Article

VLM-OCR Recipes on GPU Infrastructure

Jan 15

•

14

Article

Open Responses: What you need to know

+2

Jan 15

•

106

upvoted a collection 25 days ago

GutenOCR

3 items • Updated 27 days ago • 6

upvoted a paper 25 days ago

GutenOCR: A Grounded Vision-Language Front-End for Documents

Paper • 2601.14490 • Published 29 days ago • 37

upvoted a paper 27 days ago

Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities

Paper • 2503.04721 • Published Mar 6, 2025 • 3

upvoted a collection 27 days ago

Nemotron Speech

Open, state-of-the-art, production‑ready enterprise speech models from the NVIDIA Speech research team for ASR, TTS, Speaker Diarization and S2S • 9 items • Updated 14 days ago • 38

upvoted a paper 28 days ago

AIBrix: Towards Scalable, Cost-Effective Large Language Model Inference Infrastructure

Paper • 2504.03648 • Published Feb 22, 2025 • 1