Vignesh Padmanabhan (@vigg_1991) 's Twitter Profile
Vignesh Padmanabhan

@vigg_1991

Lead Data Scientist @Codvo2 | Working on internal AI projects and for client @SparkCognition | Masters @FollowStevens | Unleashing the power of LLMs | TS | CV

ID: 120717378

calendar_today07-03-2010 09:40:42

2,2K Tweet

448 Followers

2,2K Following

Unsloth AI (@unslothai) 's Twitter Profile Photo

A Complete Guide to Fine-tuning LLMs in 20 mins! Learn to: • Choose the correct model & training method (LoRA, FFT, GRPO) • Build Datasets & Chat templates • Train with Unsloth notebooks • Run & deploy your LLM in llama.cpp, Ollama & Open WebUI Docs: docs.unsloth.ai

Google Research (@googleresearch) 's Twitter Profile Photo

Let your wearable data "speak" for itself! Introducing SensorLM, a family of sensor-language foundation models trained on ~60 million hours of data, enabling robust wearable data understanding with natural language. → goo.gle/4lSLwQi

Ritchie Vink (@ritchievink) 's Twitter Profile Photo

Polars 1.32 is out and it lands a lot! Let's go through a few: 1/4 Selectors are now implemented in Rust and we can finally select arbitrary nested types:

Polars 1.32 is out and it lands a lot!

Let's go through a few:

1/4
Selectors are now implemented in Rust and we can finally select arbitrary nested types:
Google Research (@googleresearch) 's Twitter Profile Photo

Introducing Nested Learning: A new ML paradigm for continual learning that views models as nested optimization problems to enhance long context processing. Our proof-of-concept model, Hope, shows improved performance in language modeling. Learn more: goo.gle/47LJrzI

Introducing Nested Learning: A new ML paradigm for continual learning that views models as nested optimization problems to enhance long context processing. Our proof-of-concept model, Hope, shows improved performance in language modeling. Learn more: goo.gle/47LJrzI
Weaviate • vector database (@weaviate_io) 's Twitter Profile Photo

Vector search: fast, accurate, or affordable. Pick... all three? ✨ Most engineering teams are trapped in an expensive cycle: as their AI applications scale, they're forced to choose between performance and budget. More data means bigger infrastructure bills, slower searches,

Vector search: fast, accurate, or affordable.

Pick... all three? ✨

Most engineering teams are trapped in an expensive cycle: as their AI applications scale, they're forced to choose between performance and budget. More data means bigger infrastructure bills, slower searches,
Cameron R. Wolfe, Ph.D. (@cwolferesearch) 's Twitter Profile Photo

The original PPO-based RLHF pipeline had 4 model copies: 1. Policy 2. Reference 3. Critic 4. Reward Model Recent GRPO-based RLVR pipelines have eliminated all of these models except for the policy. - The critic is no longer needed because values are estimated from group

The original PPO-based RLHF pipeline had 4 model copies:

1. Policy
2. Reference
3. Critic
4. Reward Model

Recent GRPO-based RLVR pipelines have eliminated all of these models except for the policy.

- The critic is no longer needed because values are estimated from group
Sebastian Raschka (@rasbt) 's Twitter Profile Photo

I (finally) put together a new LLM Architecture Gallery that collects the architecture figures all in one place! sebastianraschka.com/llm-architectu…

I (finally) put together a new LLM Architecture Gallery that collects the architecture figures all in one place!
sebastianraschka.com/llm-architectu…
Shann³ (@shannholmberg) 's Twitter Profile Photo

how autoresearch works, simplified it's a pattern that lets AI agents run experiments and improve anything you can measure three files is all you need, everyone should be running it. ↓ > program. md is where you tell the agent what to do. your goal, the rules it has to

how autoresearch works, simplified

it's a pattern that lets AI agents run experiments and improve anything you can measure

three files is all you need, everyone should be running it. ↓

> program. md is where you tell the agent what to do. your goal, the rules it has to
Andrej Karpathy (@karpathy) 's Twitter Profile Photo

LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating

Sydney Runkle (@sydneyrunkle) 's Twitter Profile Photo

we just shipped support for subagents with `deepagents deploy`! add an agents/ dir to your project with an AGENTS.md per specialized subagent. subagents are great for task delegation with isolated/optimized context docs.langchain.com/oss/python/dee…

we just shipped support for subagents with `deepagents deploy`!

add an agents/ dir to your project with an AGENTS.md per specialized subagent.

subagents are great for task delegation with isolated/optimized context

docs.langchain.com/oss/python/dee…