←
Jimmy Lin4,557 posts
Jimmy Lin avatar

Jimmy Lin

@lintool

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

◷ Joined February 2010▧ 438 Photos and videos
Nour Jedidi avatar
⟳ Jimmy Lin retweeted
Nour Jedidi@nour_jedidi·Nov 5

The official version of our paper “Don’t ‘Overthink’ Pointwise Reranking: Is Reasoning Truly Necessary?” is out! 🎉 📄 aclanthology.org/2026.findin… See the 🧵 below for details! 👇

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 😱 📄 nourj98.github.io/papers/don…

Post attachment
Sahel Sharifymoghaddam avatar
⟳ Jimmy Lin retweeted
Sahel Sharifymoghaddam@Sahel_Sharify·Oct 28

Love BrowseComp-Plus? Meet 𝐂𝐌𝐀𝐒𝐒! 🚀 cmass.tech 🔥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.

Post attachment
Jimmy Lin avatar
Jimmy Lin@lintool·Oct 19

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 avatar
Jimmy Lin@lintool·Oct 19

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: arxiv.org/abs/2610.11922

Jimmy Lin avatar
Jimmy Lin@lintool·Oct 9

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

Jimmy Lin avatar
Jimmy Lin@lintool·Oct 9

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 avatar
Jimmy Lin@lintool·Oct 8

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

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 avatar
⟳ Jimmy Lin retweeted
Dongfu Jiang@DongfuJiang·Oct 5

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!

Post attachment
Nour Jedidi avatar
⟳ Jimmy Lin retweeted
Nour Jedidi@nour_jedidi·Oct 1

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 😱 📄 nourj98.github.io/papers/don…

Post attachment

🚨Do passage rerankers really need explicit reasoning?🤔—Maybe Not! Our findings: ⚖️Standard rerankers outperform those w/ step-by-step reasoning! 🚫Disable reasoning from reasoning reranker actually improves reranking accuracy!🤯 👇But, why? 📰arxiv.org/abs/2505.16886 (1/6)

Post attachment
Nour Jedidi avatar
⟳ Jimmy Lin retweeted
Nour Jedidi@nour_jedidi·Sep 30

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 👨‍🍳 📄 arxiv.org/abs/2609.38099

Jimmy Lin avatar
Jimmy Lin@lintool·Sep 25

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 avatar
Jimmy Lin@lintool·Sep 25

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" arxiv.org/abs/2605.15761 just got a +1 from NeurIPS, so yay! 🎉

Post attachment