Ramkumar

ramrattle

·

https://github.com/ramrattle

AI & ML interests

Telecom and virtualization

Recent Activity

liked a model about 18 hours ago

drowzeys/DeepSeek-V4.1-Flash-Abliterated-Cybersecurity-Unleashed

liked a model 8 days ago

Playtime-AI/Minimax_H3-Sydney_Sweeney

liked a model 9 days ago

meta-models/Muse-Glimmer-30B

View all activity

Organizations

upvoted a collection 13 days ago

MobileMoE

a family of on-device MoE language models with sub-billion active parameters (0.3-0.9B active and 1.3-5.3B total) that establish a new Pareto frontier • 11 items • Updated 14 days ago • 28

upvoted 2 papers 3 months ago

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

Paper • 2606.28733 • Published Jun 27 • 151

Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents

Paper • 2511.07397 • Published Jul 1 • 13

upvoted a collection 3 months ago

OTel-Reranker

3 items • Updated Mar 2 • 3

upvoted a paper 3 months ago

Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories

Paper • 2606.11176 • Published Jun 9 • 133

upvoted a collection 6 months ago

Qwen3.5

Qwen3.5 is Qwen's new model family including Qwen3.5 Small: 0.8B, 2B, 4B, 9B and Qwen3.5 Medium: 35B-A3B, 27B, 122B-A10B and 397B-A17B. • 25 items • Updated 19 days ago • 167

upvoted a collection 8 months ago

Qwen3-TTS

7 items • Updated Jan 22 • 389

upvoted an article about 2 years ago

Article

Energy Scores for AI Models

sasha

•

May 9, 2024

• 38