Daniel D'souza
@mrdanieldsouza
Followers
780
Following
5K
Media
68
Statuses
2K
Research Engineer @Cohere_Labs💙 | @UMichECE Alum 〽️ | 🇮🇳✖️🇺🇸 💫"The Universe Works in Mysterious Ways"💫
Ann Arbor, MI
Joined November 2016
“Best Paper Award” @ ACL 2024.🪄What an incredible culmination of perseverance to connect and represent languages around the 🗺️! 🪄. 🤗 Huge thanks to the @aclmeeting committee for recognizing the massive effort behind Project Aya @CohereForAI 💙 #ACL2024
I'm incredibly proud that Aya received #ACL2024 Best Paper Award 🥹. Huge congratulations to the Aya team and @CohereForAI community who make this possible by for extending frontiers of LLMs to multilingual, building Aya Model and Aya Dataset 🌿🌏
3
7
48
RT @rohanpaul_ai: Unimodal explainability tricks people into thinking a multimodal system uses every input. This paper builds three strict….
0
6
0
RT @oumayma_es_: Announcement: Papers in the park in Casablanca - Morocco is coming in the upcoming weeks .Stay tuned 👀 .@Cohere_Labs @sara….
0
4
0
RT @_akhaliq: When Life Gives You Samples. The Benefits of Scaling up Inference Compute for Multilingual LLMs
0
28
0
RT @Cohere_Labs: “When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs”. Led by: @ammar__khairi ….
0
3
0
RT @Cohere_Labs: Can we improve the performance of LLMs during inference without the need for extensive sampling OR special reward models?….
0
9
0
🚨New Recipe just dropped! 🚨 . "LLMonade 🍋" ➡️ squeeze max performance from your multilingual LLMs at inference time !👀🔥. 🧑🍳@ammar__khairi shows you how to .1⃣ Harvest your Lemons 🍋🍋🍋🍋🍋.2⃣ Pick the Best One 🍋.
🚀 Want better LLM performance without extra training or special reward models?.Happy to share my work with @Cohere_labs : "When Life Gives You Samples: Benefits of Scaling Inference Compute for Multilingual LLMs".👀How we squeeze more from less at inference 🍋, details in 🧵
0
6
21
RT @ammar__khairi: 💪🏼Huge thanks to my incredible mentors: Julia Kreutzer @mrdanieldsouza, @YeS855811, @sarahookr for guiding me and suppor….
0
5
0
RT @ammar__khairi: We introduce two new selection techniques: CHOPs🥢 and X-MBR ⚖️, designed to amplify multilingual performance gains. Test….
0
1
0
RT @weiyinko_ml: We're looking for a new member for the multilingual team with a focus on data engineering! Please apply at the link below:.
0
7
0
Learn more here! ⤵️.
🚨 Wait, adding simple markers 📌during training unlocks outsized gains at inference time?! 🤔 🚨. Thrilled to share our latest work at @Cohere_Labs: “Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers“ that explores this phenomenon!. Details in 🧵 ⤵️
0
0
1
🥇Certified FRESH! 🍅: "Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers". Thanks for the spotlight @TheTuringPost ! 🤝 💯.
The freshest research papers of the week. Our top 7:. ▪️ Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers.▪️ Steering LLM Thinking with Budget Guidance.▪️ Truncated Proximal Policy Optimization.▪️ Reinforcement Learning with Verifiable Rewards.▪️
2
0
9
Yooo 👀 and there’s pizza!?! 🍕.
Papers ✅. Park ⏳. Tomorrow at Trinity Bellwoods come learn about @Cohere_Labs new paper improving models performance on rare cases
0
3
9
RT @Cohere_Labs: We’re proud to have released 9 open models — all built to support research, experimentation, and real-world impact. 🌎. The….
0
12
0
🤝Arbitration is the future 🤝 . “Why rely on a single teacher 🧑🏻🏫 when you can synthetically generate a much higher quality dataset by relying on specialized teacher models? 🧑🏻🏫👩🏫👨🏿🏫”. Check out this fantastic summary of our recently accepted ACL 2025 work ✨.
How can AI capture the nuances of different languages?💬🗨️. By using a team of specialized teacher models via Multilingual Arbitration we've achieved up to 19.5% improvement in win rates across languages. Find us at ACL to discuss how we can further break down language barriers.
0
6
22
RT @Cohere_Labs: 🤹 How do we move away from complicated and brittle prompt engineering at inference for under-represented tasks?🤔. 🧠 Our la….
0
11
0
RT @ahmetustun89: Can we train models for better inference-time control instead of over-complex prompt engineering❓. Turns out the key is i….
0
8
0
RT @sarahookr: Thanks @_akhaliq for the spotlight on our work. I really believe strongly in this wider direction — of taking the pressure o….
0
10
0
Thanks for the feature @_akhaliq ! 😄🤝.
Cohere presents Treasure Hunt. Real-time Targeting of the Long Tail using Training-Time Markers
0
1
14
💪🏼Huge thanks to my incredible mentors and collaborators: @ahmetustun89, Julia Kreutzer, @sarahookr, @adrien_morisot for guiding me and supporting this work ✨. Check out the arxiv release here! 📜 :
0
1
8
TLDR: 🧠We propose a generalizable and systematic framework to optimize training protocols using a detailed taxonomy 📝. 🎛️This provides (optional) levers 🎮 at inference time to improve controllability and boost performance on underrepresented use cases 💯📈
1
0
7