surajitdb's profile picture. Teacher and Researcher in AI and ML . Machine learning application in time series data, Geoinformatics, Climatology, Probabilistic forecasting, Hydrology.

Surajit Deb Barma

@surajitdb

Teacher and Researcher in AI and ML . Machine learning application in time series data, Geoinformatics, Climatology, Probabilistic forecasting, Hydrology.

Surajit Deb Barma reposted

Stanford just pulled off something wild 🤯 They made models smarter without touching a single weight. The paper’s called Agentic Context Engineering (ACE), and it flips the whole fine-tuning playbook. Instead of retraining, the model rewrites itself. It runs a feedback loop…

Yesterday_work_'s tweet image. Stanford just pulled off something wild 🤯

They made models smarter without touching a single weight.

The paper’s called Agentic Context Engineering (ACE), and it flips the whole fine-tuning playbook.

Instead of retraining, the model rewrites itself.

It runs a feedback loop…

Surajit Deb Barma reposted

Google is releasing a 5-Day AI Agents course on Kaggle. Their last course had over 420,000 learners. This one covers: > Agents and their architectures > Tools & MCP integration > Context Engineering > Evaluating the quality of agents > Prototype to Production

Hesamation's tweet image. Google is releasing a 5-Day AI Agents course on Kaggle. Their last course had over 420,000 learners.

This one covers:

> Agents and their architectures
> Tools & MCP integration
> Context Engineering
> Evaluating the quality of agents
> Prototype to Production

Surajit Deb Barma reposted

Microsoft just killed the GPU mafia! 🤯 They've open-sourced bitnet.cpp, a blazing-fast 1-bit LLM inference framework optimized for CPUs. This is a major step forward for running large models locally, without expensive GPUs or cloud costs. Demo app + repo + paper in 🧵 ↓


Surajit Deb Barma reposted

🚀 Introducing 𝐀𝐠𝐞𝐧𝐭 𝐒3, the most advanced computer-use agent, now 𝐚𝐩𝐩𝐫𝐨𝐚𝐜𝐡𝐢𝐧𝐠 𝐡𝐮𝐦𝐚𝐧-𝐥𝐞𝐯𝐞𝐥 𝐩𝐞𝐫𝐟𝐨𝐫𝐦𝐚𝐧𝐜𝐞🧠💻 Just one year ago, Agent S scored ~20% on OSWorld: SOTA then, but far from human 72%. Today, Agent S3 reaches 6̳9̳.̳9̳%̳ (⬆10% over…


Surajit Deb Barma reposted

GeoAI Made Easy: Learn the Python Package Step-by-Step (Beginner Friendly) In this beginner-friendly tutorial, you'll learn how to use the powerful GeoAI Python package to detect buildings and other objects from satellite imagery — step by step. Whether you're new to GeoAI or…

giswqs's tweet image. GeoAI Made Easy: Learn the Python Package Step-by-Step (Beginner Friendly)

In this beginner-friendly tutorial, you'll learn how to use the powerful GeoAI Python package to detect buildings and other objects from satellite imagery — step by step. Whether you're new to GeoAI or…

Surajit Deb Barma reposted

People often ask how did the Unitree robots get so good all of a sudden. It wasn't all of a sudden, and it's because they ship their hardware and open source their SDKs. Arguably these robots are nearly useless out of the box, but you have full dev control of them. Because of…


Surajit Deb Barma reposted

Looking for a systematic hydrometeorological dataset for Indian catchments? Join us for CAMELS-IND workshop at #IAHS2025 at @iitroorkee. Details: iahs2025.com/SECAMELS Register: forms.gle/9yhiDVFPfWrZLn… @pankaj_iisc @nikk_mn @IAHS_AISH @ShailzaSha41025

AshutoshHydro's tweet image. Looking for a systematic hydrometeorological dataset for Indian catchments?  

Join us for CAMELS-IND workshop at #IAHS2025 at @iitroorkee.   

Details: iahs2025.com/SECAMELS
Register: forms.gle/9yhiDVFPfWrZLn…

@pankaj_iisc
@nikk_mn 
@IAHS_AISH 
@ShailzaSha41025

Surajit Deb Barma reposted

Farewell ARIMA, it’s been a good run. Meet the newcomer on the scene: AR-KAN. #timeseries #forecasting arxiv.org/pdf/2509.02967

predict_addict's tweet image. Farewell ARIMA, it’s been a good run. Meet the newcomer on the scene: AR-KAN.

#timeseries #forecasting 

arxiv.org/pdf/2509.02967

Surajit Deb Barma reposted

Excited to launch "Novix"🚀, our PhD-level AI-Scientist designed for autonomous scientific discovery. Novix revolutionizes research workflows through comprehensive capabilities spanning: deep research, innovative ideation, intelligent coding, advanced data analysis, automated…


Surajit Deb Barma reposted

Anthropic continues to crush it with these guides. This is a good example of what context engineering involves.

omarsar0's tweet image. Anthropic continues to crush it with these guides. 

This is a good example of what context engineering involves.

Surajit Deb Barma reposted

NN-SVG: Create neural network architecture drawings parametrically! Export them to SVG files and use them in your work!


Surajit Deb Barma reposted

At MIT, I learned about RNNs in my NLP class with Prof. Michael Collins. He built a model from my keystrokes to predict who I was. To me, it felt like a magic box. Years later, when I had to teach RNNs, I forced myself to go inside the box. ⬇️ Download: byhand.ai/rnn


Surajit Deb Barma reposted

Let's Learn MCP with Python - Tutorial Series Here's your comprehensive guide to understanding and building Model Context Protocol (MCP) Servers for Python developers through interactive learning experiences. Repo readme: msft.it/6014sR9Pk

VisualStudio's tweet image. Let's Learn MCP with Python - Tutorial Series
Here's your comprehensive guide to understanding and building Model Context Protocol (MCP) Servers for Python developers through interactive learning experiences.
Repo readme: msft.it/6014sR9Pk

Surajit Deb Barma reposted

Couldn't resist. Here's a pure PyTorch from-scratch re-implementation of Gemma 3 270M in a Jupyter Notebook (uses about 1.49 GB RAM): github.com/rasbt/LLMs-fro…

rasbt's tweet image. Couldn't resist. 
Here's a pure PyTorch from-scratch re-implementation of Gemma 3 270M in a Jupyter Notebook (uses about 1.49 GB RAM): github.com/rasbt/LLMs-fro…

Gemma 3 270M! Great to see another awesome, small open-weight LLM for local tinkering. Here's a side-by-side comparison with Qwen3. Biggest surprise that it only has 4 attention heads!

rasbt's tweet image. Gemma 3 270M! Great to see another awesome, small open-weight LLM for local tinkering.
Here's a side-by-side comparison with Qwen3. Biggest surprise that it only has 4 attention heads!


Surajit Deb Barma reposted

Meta just released DINOv3, a generalist, state-of-the-art computer vision model trained with SSL that produces superior high-resolution visual features. Blog post: ai.meta.com/blog/dinov3-se… GitHub: github.com/facebookresear…


Loading...

Something went wrong.


Something went wrong.