Senthil Kumar N PRO

Senthi1Kumar's activity

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

upvoted a paper about 10 hours ago

Qwen3-ASR Technical Report

Paper • 2601.21337 • Published Jan 29 • 46

upvoted a paper 1 day ago

Work Agents: Systems, Capabilities, and Optimization

Paper • 2610.35845 • Published 4 days ago • 119

upvoted an article 2 days ago

view article

Article

Hugging Face ❤️ TorchTPU: TPUs, Natively

• 
• 
• +3

tengomucho, Jingya, pagezyhf, jeffboudier, regisss

•

10 days ago

• 51

upvoted 2 papers 5 days ago

Agent World Model in the Wild: Computer-Use Agent Environment Synthesis

Paper • 2610.26828 • Published 11 days ago • 102

Heartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice Agents

Paper • 2610.26233 • Published 11 days ago • 35

upvoted 3 papers 8 days ago

RubatoCodec: Budgeted Adaptive Speech Tokenization with Streaming Decoding

Paper • 2610.29434 • Published 9 days ago • 15

Qwen-Audio-3.1-ASR Technical Report

Paper • 2610.28711 • Published 10 days ago • 37

Cache Engineering for Agents

Paper • 2610.28577 • Published 10 days ago • 161

upvoted a paper 9 days ago

CoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents

Paper • 2610.24960 • Published 12 days ago • 56

upvoted 2 papers 10 days ago

LEV: Thinking Fast and Deep with Looped Decision Models

Paper • 2610.20951 • Published 16 days ago • 106

Has GPT-6-Astra Achieved Embodied Intelligence?

Paper • 2610.22471 • Published 15 days ago • 328

upvoted a paper 13 days ago

EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud Delegation

Paper • 2610.17560 • Published 17 days ago • 31

upvoted a paper 17 days ago

SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments

Paper • 2610.12611 • Published 22 days ago • 102

upvoted a paper 20 days ago

TokenRouter: Efficient Serving System for Token-Level LLM Routing

Paper • 2610.12242 • Published 22 days ago • 145

upvoted an article about 1 month ago

view article

Article

**Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization**

• 

nvidia

•

Sep 23

• 72

upvoted 5 papers about 1 month ago

ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search

Paper • 2609.13356 • Published Sep 11 • 240

SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue

Paper • 2609.26780 • Published Sep 22 • 105

When2Think: Learning When and How Much to Reason

Paper • 2609.19671 • Published Sep 28 • 50

RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2609.20784 • Published Sep 17 • 57

Self-Evolving Search Index

Paper • 2609.19656 • Published Sep 17 • 57