Sharad Vikram
@sharadvikram
Researcher @ Google Deepmind. I work on JAX + Pallas (http://github.com/google/jax) and Gemini. In the past I worked on Oryx and TFP. I like learning.
Built with JAX!
Introducing Gemini 1.0, our most capable and general AI model yet. Built natively to be multimodal, it’s the first step in our Gemini-era of models. Gemini is optimized in three sizes - Ultra, Pro, and Nano Gemini Ultra’s performance exceeds current state-of-the-art results on…
🚨Breaking: @GoogleDeepMind’s latest Gemini-2.5-Pro is now ranked #1 across all LMArena leaderboards 🏆 Highlights: - #1 in all text arenas (Coding, Style Control, Creative Writing, etc) - #1 on the Vision leaderboard with a ~70 pts lead! - #1 on WebDev Arena, surpassing Claude…
We’re releasing an updated Gemini 2.5 Pro (I/O edition) to make it even better at coding. 🚀 You can build richer web apps, games, simulations and more - all with one prompt. In @GeminiApp, here's how it transformed images of nature into code to represent unique patterns 🌱
What a finish! Gemini 2.5 Pro just completed Pokémon Blue!  Special thanks to @TheCodeOfJoel for creating and running the livestream, and to everyone who cheered Gem on along the way.
GPP became the CHAMP!!!!! twitch.tv/gemini_plays_p…
Battling E4 now!
Recently had the pleasure of lecturing back at Princeton in a grad seminar. I took the opportunity to cover how scaling laws have evolved since their inception, leaning heavily on great external content from my colleagues @borgeaud_s @jalayrac @jacobaustin132 . Content in thread
⚡ The latest Gemini 2.5 Flash has arrived on the leaderboard! Ranked jointly at #2 and matching top models such as GPT 4.5 Preview & Grok-3! Highlights: 🏆 tied #1 in Hard Prompts, Coding, and Longer Query 💠 Top 4 across all categories 💵 5-10x cheaper than Gemini-2.5-Pro…
Gemini 2.5 Flash just dropped. ⚡ As a hybrid reasoning model, you can control how much it ‘thinks’ depending on your 💰 - making it ideal for tasks like building chat apps, extracting data and more. Try an early version in @Google AI Studio → ai.dev
(2/2) I also visualized the speed of Gemini’s progress through the game - it hasn’t even been two weeks since the stream started!
📣 Deep Research is now powered by Gemini 2.5 Pro, our most intelligent AI model. ✨ This upgraded Deep Research is now even better at: 🔍 Finding & synthesizing information 📊 Providing more insightful reports 🧠 Analytical reasoning Gemini Advanced users can access the new…
Check out twitch.tv/gemini_plays_p…, Gemini 2.5 Pro is on the verge of finishing execution of a long-term plan: 1. Visited Rock Tunnel after getting 3rd badge; 2. Attempted Rock Tunnel without HM05 Flash; 3. Filled up dex to acquire HM05 Flash; 4. Caught Pikachu to teach Flash!
Big update to our MathArena USAMO evaluation: Gemini 2.5 Pro, which was released *the same day* as our benchmark, is the first model to achieve non-trivial amount of points (24.4%). The speed of progress is really mind-blowing.
Gemini 2.5 Pro is taking off 🚀🚀🚀 The team is sprinting, TPUs are running hot, and we want to get our most intelligent model into more people’s hands asap. Which is why we decided to roll out Gemini 2.5 Pro (experimental) to all Gemini users, beginning today. Try it at no…
📣 Today, we’re introducing Gemini 2.5, our most intelligent AI model. An experimental version of Gemini 2.5 Pro is available now in the Gemini app for Gemini Advanced users: gemini.google.com/app Let’s get into this update ⬇️🧵
BREAKING: Gemini 2.5 Pro is now #1 on the Arena leaderboard - the largest score jump ever (+40 pts vs Grok-3/GPT-4.5)! 🏆 Tested under codename "nebula"🌌, Gemini 2.5 Pro ranked #1🥇 across ALL categories and UNIQUELY #1 in Math, Creative Writing, Instruction Following, Longer…
Think you know Gemini? 🤔 Think again. Meet Gemini 2.5: our most intelligent model 💡 The first release is Pro Experimental, which is state-of-the-art across many benchmarks - meaning it can handle complex problems and give more accurate responses. Try it now →…
1/ Gemini 2.5 is here, and it’s our most intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on…
Native image generation with Gemini 2.0 Flash is now available to all developers via an experimental release in the Gemini API and Google AI Studio!! The chat based image editing and creation is so much fun to play with 🧵
A nice and concise R1 inference jax:tpu port by @rdyro128523. Good for both reading and running. Watch the repo for more.
Deepseek R1 inference in pure JAX! Currently on TPU, with GPU and distilled models in-progress. Features MLA-style attention, expert/tensor parallelism & int8 quantization. Contributions welcome!
Deepseek R1 inference in pure JAX! Currently on TPU, with GPU and distilled models in-progress. Features MLA-style attention, expert/tensor parallelism & int8 quantization. Contributions welcome!
Making LLMs run efficiently can feel scary, but scaling isn’t magic, it’s math! We wanted to demystify the “systems view” of LLMs and wrote a little textbook called “How To Scale Your Model” which we’re releasing today. 1/n
Words can’t describe how legendary @AlecRad is. We live in a world he built
Just when you thought it was over... we’re introducing Gemini 2.0 Flash Thinking, a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and more 🧵
Interactive and interleaved image generation is one of the areas where Gemini 2 Flash shines! A thread for some cool examples: