nithin

nithin12342

nithin12342
nithin-gurusamy-68a76a324

AI & ML interests

Aspiring Software Developer | 🌐 Full-Stack Explorer | 🤖 AI Engineer-in-Progress Passionate about building scalable apps, automating workflows, and craft

Recent Activity

upvoted a paper about 4 hours ago

Training Open Models for Agentic Phone Use

updated a collection 1 day ago

Ai papper for efficient ai model

upvoted a paper 1 day ago

SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG

View all activity

nithin

AI & ML interests

Recent Activity

Organizations

nithin12342 's collections 7

Training Open Models for Agentic Phone Use

Code as Agent Harness

REFRAG: Rethinking RAG based Decoding

OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation

Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model

Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders

NAACL: Noise-AwAre Verbal Confidence Calibration for LLMs in RAG Systems

NeuROK: Generative 4D Neural Object Kinematics

The Physical AI Inference Gap in Batch-1 LLM Decode

NOVAglow646/Monet-SFT-125K

Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning

Qwen3.5-Omni Technical Report

REFRAG: Rethinking RAG based Decoding

OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Training Open Models for Agentic Phone Use

NeuROK: Generative 4D Neural Object Kinematics

The Physical AI Inference Gap in Batch-1 LLM Decode

Code as Agent Harness

NOVAglow646/Monet-SFT-125K

REFRAG: Rethinking RAG based Decoding

Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning

Qwen3.5-Omni Technical Report

REFRAG: Rethinking RAG based Decoding

OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation

Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model

Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders

NAACL: Noise-AwAre Verbal Confidence Calibration for LLMs in RAG Systems