Jimmy Lin

I profess CS-ly at @UWaterloo. Previously, I monkeyed code for @Twitter, slides for @Cloudera, and scienced for @yupp_ai.

[Nour Jedidi @nour_jedidi]

The official version of our paper “Don’t ‘Overthink’ Pointwise Reranking: Is Reasoning Truly Necessary?” is out! 🎉

📄 https://t.co/wPioDrMACN

See the 🧵 below for details! 👇

[Sahel Sharifymoghaddam @Sahel_Sharify]

Love BrowseComp-Plus? Meet 𝐂𝐌𝐀𝐒𝐒! 🚀
https://t.co/AJY898CbwZ

🔥Your next challenge for agentic search: 423 question–answer pairs spanning BrowseComp-Plus, DeepSearchQA, Total Recall QA, and HotpotQA—all projected onto ClimbMix, a realistic corpus of over 550M documents.

[Jimmy Lin @lintool]

Our backbone: https://t.co/8h0oKVq8Pr
Our reranker: https://t.co/XtkLzw4Rnp

[Jimmy Lin @lintool]

tl;dr - the team @Sahel_Sharify @Lingwei_Gu @nour_jedidi speedran nanochat by @karpathy using ClimbMix by @shizhediao et al. and then SFT'ed on relevance data from @beirmug @crystina_z to arrive at a competitive pointwise reranker: https://t.co/QQgZ2rk4my

[Jimmy Lin @lintool]

It's about as good as SFT'ing Qwen, Gemma, etc. and just a bit worse than listwise GPT-6.1 Sol... all with just a handful of GPUs.

[Jimmy Lin @lintool]

Fully open = transparent, sovereign = you're in control - You can do it too, let us show you how! Rigorous understanding FTW!

[Jimmy Lin @lintool]

What are we up to? 🏡 Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Search w/ @Sahel_Sharify @Lingwei_Gu @nour_jedidi https://t.co/QQgZ2rjwx0

[Jimmy Lin @lintool]

Milestone 1️⃣ - we built a competitive pointwise decoder-only reranker completely from scratch - pre-training from ClimbMix + supervised fine-tuning on RLHN relevance data... with just a few GPUs... and it wasn't even that hard!

[Jimmy Lin @lintool]

You mean, building things that are actually useful... and that people care about? Nice but how unacademic! 👍 Congratulations! I look forward to learning more! ❤️

[Hamed Zamani @HamedZamani]

We are releasing the most significant technology transfer effort by the CIIR in the last decade. Please share with your network.

In this thread you will learn what Nage enables you to do.

🧵👇

[Dongfu Jiang @DongfuJiang]

PhD defended today! 🎓

Huge thanks to my supervisor @WenhuChen for all the guidance and support throughout this journey, and to all my committee members for their time, thoughtful questions, and feedback.

Next stop: joining Meta FAIR as a Research Scientist. Excited for what’s ahead!

[Nour Jedidi @nour_jedidi]

Excited to share that our paper was accepted to EMNLP Findings 🎉

We ask a simple question: Does reasoning improve pointwise rerankers?

The answer? It can actually hurt... even for Rank1, a reranker trained to reason-then-answer 😱

📄 https://t.co/ZyL7fYghDL

[Nour Jedidi @nour_jedidi]

To make an LLM a strong dense retriever, you often need training…

But what if you only have a few-examples 🥩🥦 and no training budget?

Just add RICE 🍚, a simple way to turn your LLM into an effective dense retriever that requires zero training 👨‍🍳

📄 https://t.co/A1dQGj4ShG

[Jimmy Lin @lintool]

Yo, I heard you like leaderboards. So I created another one: with ACM Fellows and Turing Award winners. Another target for citation and h-index benchmaxxing. 💪 https://t.co/wC4vjYIlPc

[Jimmy Lin @lintool]

@michaelfreedman And from 2014: https://t.co/P4jmUF6ZKI

[Jimmy Lin @lintool]

I'm in a good mood because "grep is all you need" and "BM25 is all you need" both recently drew from (separate) Bernoullis and came back positive. Now I can claim that both have been +1ed by LLMs (wait, I meant peers). #nerdref

[Jimmy Lin @lintool]

@michaelfreedman Ahead of you on that one... https://t.co/sNTYyepZzH (but yes, need to update...)

[Jimmy Lin @lintool]

Summer passed in a blur... 🏖️🦩🍹 and I forgot to congratulate @HosnaOH for finishing her Master's! Her work with @amirhkarimi_ "A Unified Perturbation Framework for Analyzing Leaderboard Stability and Manipulation" https://t.co/lWser4x4lG just got a +1 from NeurIPS, so yay! 🎉

[Jimmy Lin @lintool]

@chaochunh Thanks for chiming in!

[Jimmy Lin @lintool]

Achievement unlocked! 🔓 Does this come with stat bonuses or help with saving throws? https://t.co/UdBFnOyAIA

[Jimmy Lin @lintool]

@_weiping Thanks! Decades of post-training, so questionable sample efficiency...

[Jimmy Lin @lintool]

@zhuofengli96475 Thanks! I think the secret is just more rollouts...