pavan @_mpavan

research scientist @mistralai • audio + vision prev post-training tool-use + agents @google gemini @uofillinois @iitmadras alum Joined March 2023

Tweets

15
Followers

31
Following

234
Likes

73

pavan @_mpavan

2 months ago

Check out our Voxtral paper now on arxiv: arxiv.org/abs/2507.13264 Details on on pre-training, fine-tuning and alignment, with ablations covering how to chose the optimal model architecture and pre-training format!

Mistral AI @MistralAI

2 months ago

38 201 1K 70K 325

Download Image

0 2 11 2K 3

Download Image

Mistral AI @MistralAI

3 months ago

Introducing Mistral Small 3.2, a small update to Mistral Small 3.1 to improve: - Instruction following: Small 3.2 is better at following precise instructions - Repetition errors: Small 3.2 produces less infinite generations or repetitive answers - Function calling: Small…

55 233 2K 237K 297

Download Image

lmarena.ai @arena

5 months ago

📰 News in Arena: Mistral Medium 3 makes a strong debut with the community! Highlights: 💠 #11 overall in chat: a +90 point leap from Mistral Large 💠Top-tier in technical domains (#5 in Math, #7 in Hard Prompts & Coding) 💠#9 in WebDev Arena Congrats to @MistralAI on the…

Mistral AI @MistralAI

5 months ago

105 384 3K 521K 569

Download Image

6 47 306 41K 37

Download Image

pavan @_mpavan

7 months ago

Checkout the latest multimodal Mistral Small 3.1. Performs quite well compared to competition while being smaller, faster and Apache 2.0.

Mistral AI @MistralAI

7 months ago

Checkout the latest multimodal Mistral Small 3.1. Performs quite well compared to competition while being smaller, faster and Apache 2.0.

270 1K 8K 857K 1K

Download Image

0 0 2 104 0

Amjad Masad @amasad

2 years ago

Bard can read your Replit or Github projects in less than a second and make suggestions 🤯

103 195 2K 455K 407

Download Image

Faris Masad @masadfrost

2 years ago

Bard will undoubtedly eat ChatGPT's lunch. The product is a lot nicer to use already and their teams are iterating super fast! According to some people at OpenAI, the org is in the worst of both worlds, too ossified to move like a start-up, and too small for big co moves.