AI Dynamics

Global AI News Aggregator

About

@hugo_larochelle

  • OpenLeaf Clarifications: Discovery Tool, Not Citation Button

    By

    @hugo_larochelle

    –

    wanted to make a few clarifications on openleaf as there’s lot of love from people (thanks❤️!) but also some misunderstanding: 1. "this encourages blind citation" — openleaf links every suggested paper for a reason. you're supposed to read it before citing (the paper link is right there). it's a discovery tool, and most def not a "cite for me" button. also, its ranking is purely content-based — no citation count, no popularity metrics — specifically to avoid unfair concentration of citations to a select few papers/institutions. 2. "if you do your lit search after writing a paragraph, you're doing it wrong" — agree! but the demo showed a simplified flow. the real use case: you've read 20 papers, but there are 1000s published monthly. you will miss relevant ones. openleaf helps you find them. already working on improvements to make it even better: – reading your existing .bib so it's aware of what you already cite – analyzing full paper text, not just abstracts – better reasoning track progress, suggest features, or pick up an issue! github.com/Demfier/openleaf/… Gaurav Sahu (@dem_fier) ever been here? open overleaf → write a paragraph → "hmm…this needs a citation" → open 15 different tabs → skim 8 abstracts → find the 1 actually relevant paper → format bibtex → paste it back on overleaf if so, i built a plugin just for you. meet openleaf: → reads your paper paragraph by paragraph → searches major academic databases → filters out irrelevant papers using ai → one click to add BibTeX to your .bib you'll also find the 🤝 friendly and 🔥 fire reviewers there. i don't think i need to tell you what they do 🙂 free. open source. no account. no data collection. works with ollama, openrouter, openai api and more. github.com/demfier/openleaf dear algorithm, please show this to my fellow researchers in need 🙏 #overleaf #latex #opensource #academictwitter — https://nitter.net/dem_fier/status/2033002945973752297#m

    → View original post on X — @hugo_larochelle, 2026-03-16 15:07 UTC

  • OpenLeaf: AI-powered citation plugin for Overleaf researchers

    By

    @hugo_larochelle

    –

    ever been here? open overleaf → write a paragraph → "hmm…this needs a citation" → open 15 different tabs → skim 8 abstracts → find the 1 actually relevant paper → format bibtex → paste it back on overleaf if so, i built a plugin just for you. meet openleaf: → reads your paper paragraph by paragraph → searches major academic databases → filters out irrelevant papers using ai → one click to add BibTeX to your .bib you'll also find the 🤝 friendly and 🔥 fire reviewers there. i don't think i need to tell you what they do 🙂 free. open source. no account. no data collection. works with ollama, openrouter, openai api and more. github.com/demfier/openleaf dear algorithm, please show this to my fellow researchers in need 🙏 #overleaf #latex #opensource #academictwitter

    → View original post on X — @hugo_larochelle, 2026-03-15 02:10 UTC

  • LLM2Vec-Gen: Frozen LLMs Generate Better Embeddings Through Reasoning
    LLM2Vec-Gen: Frozen LLMs Generate Better Embeddings Through Reasoning

    By

    @hugo_larochelle

    –

    LLM2Vec-Gen represents a major paradigm shift for embeddings/retrieval. Why encode the query when the LLM already knows what to look for and can directly produce an embedding for it? Best part: it’s self-supervised, and it does all of this while the LLM remains completely frozen. Think about it: "solve x² + 3x − 4 = 0" has zero reasoning in it. But the LLM's response does. By encoding the response, the embedding captures the reasoning — and the better the LLM reasons, the better the embedding. This is why our results scale with model size. As LLMs get smarter, our embeddings automatically get better. LLM2Vec-Gen is also the first demonstration of the promise of @ylecun's JEPA for text embeddings. The alignment loss is JEPA — predict in representation space, not token space. The reconstruction loss goes beyond — it keeps embeddings decodable. This paradigm shift opens new frontiers: 🔬 Can we build a full JEPA for language where the teacher and student are the same LLM? ⚡ Can LLMs reason in compressed space without ever generating text? 🤖 Can agents reason in compression tokens and carry that directly into retrieval? 💬 Can agents talk to each other in compression tokens instead of text — dense, fast, and still human-readable? LLM2Vec-Gen is a first step toward all four. Vaibhav Adlakha (@vaibhav_adlakha) Your LLM already knows the answer. Why is your embedding model still encoding the question? 🚨Introducing LLM2Vec-Gen: your frozen LLM generates the answer's embedding in a single forward pass — without ever generating the answer. Not only that, the frozen LLM can decode the embedding back into text. 🏆 SOTA self-supervised embeddings 🛡️ Free transfer of instruction-following, safety, and reasoning — https://nitter.net/vaibhav_adlakha/status/2032065008603951187#m

    → View original post on X — @hugo_larochelle, 2026-03-12 12:37 UTC

  • Classical hyperparameter tuning outperforms AI coding agent

    By

    @hugo_larochelle

    –

    I wrote something about the recent hype about automatic AI research. tdlr: at least this time, a classical hyperparameter tuning beat the fancy AI coding agent Ravid Shwartz Ziv (@ziv_ravid) x.com/i/article/203175290702… — https://nitter.net/ziv_ravid/status/2031790304123326532#m

    → View original post on X — @hugo_larochelle, 2026-03-11 21:57 UTC

  • Montreal Deep Tech Scene Booming with Major AI Company Hires

    By

    @hugo_larochelle

    –

    Montreal deep tech scene is getting hot!! Many recent hires of Cohere, Mistral, Periodic Labs, Poolside are all based in Montreal. And now, AMI will have an office here 🔥 It's a no-brainer, though. @Mila_Quebec has the highest concentration of deep learning expertise with interdisciplinary connections. Thanks to recent US regulation changes on immigration, no more brain drain! Let's build more in Canada! Yann LeCun (@ylecun) Unveiling our new startup Advanced Machine Intelligence (AMI Labs). We just completed our seed round: $1.03B / 890M€, one the largest seeds ever, probably the largest for a European company. We're hiring! [the background image is the Veil Nebula – a picture I took from my backyard, most appropriate for an unveiling] More details here: techcrunch.com/2026/03/09/ya… — https://nitter.net/ylecun/status/2031268686984527936#m

    → View original post on X — @hugo_larochelle, 2026-03-10 20:55 UTC

  • LLMs Can Generate Superior Embeddings Without Model Changes

    By

    @hugo_larochelle

    –

    Controversial take: you don't need any of this. LLMs have gone through a lot of training already, so there ought to be a better method to turn them into extremely good embedding models. This is what my group has been working on. LLM2Vec is one such idea. We have some exciting developments recently where LLMs themselves can generate superior embeddings with zero changes to the LLM. Stay tuned! dr. jack morris (@jxmnop) x.com/i/article/203102900413… — https://nitter.net/jxmnop/status/2031051636068782402#m

    → View original post on X — @hugo_larochelle, 2026-03-10 03:59 UTC

  • Machine Translation for Vision Challenge at CVPR 2026 MAPS Workshop
    Machine Translation for Vision Challenge at CVPR 2026 MAPS Workshop

    By

    @hugo_larochelle

    –

    Come participate in the Machine Translation for Vision Challenge! The winners will be announced at our MAPS workshop (sites.google.com/corp/view/m…) at CVPR 2026! MAPS – CVPR 2026 Workshop (@maps_cvpr) Introducing the Machine Translation for Vision (MTV) Challenge at #CVPR2026! Can your model localize (culturally adapt) images — not just translate text, but reimagine visuals for different cultures? 🌍 — https://nitter.net/maps_cvpr/status/2031031324211843212#m

    → View original post on X — @hugo_larochelle, 2026-03-09 15:50 UTC

  • Autoresearch Papers and Karpathy’s Autonomous AI Research Framework
    Autoresearch Papers and Karpathy’s Autonomous AI Research Framework

    By

    @hugo_larochelle

    –

    Great to see autoresearch blowing up becoz of the legendary Karpathy sensei. This year will ofc be an exciting year for automated AI research. For all of you guys excited to jump onto it, hopefully our papers will be some helpful references: – automated feedback loop for research agents to optimize LLM pre-training and post-training stacks: nitter.net/ChengleiSi/status/2014… – generating novel research ideas with LLMs, along with a comparison against human experts: nitter.net/ChengleiSi/status/1833… – evaluating the effectiveness of LLM-generated ideas through experiment execution: nitter.net/ChengleiSi/status/1939… – finetuning LLMs to directly predict the effectiveness of research ideas: nitter.net/jiaxinwen22/status/192… Andrej Karpathy (@karpathy) I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like to play over the weekend. It's basically nanochat LLM training core stripped down to a single-GPU, one file version of ~630 lines of code, then: – the human iterates on the prompt (.md) – the AI agent iterates on the training code (.py) The goal is to engineer your agents to make the fastest research progress indefinitely and without any of your own involvement. In the image, every dot is a complete LLM training run that lasts exactly 5 minutes. The agent works in an autonomous loop on a git feature branch and accumulates git commits to the training script as it finds better settings (of lower validation loss by the end) of the neural network architecture, the optimizer, all the hyperparameters, etc. You can imagine comparing the research progress of different prompts, different agents, etc. github.com/karpathy/autorese… Part code, part sci-fi, and a pinch of psychosis 🙂 — https://nitter.net/karpathy/status/2030371219518931079#m

    → View original post on X — @hugo_larochelle, 2026-03-09 06:18 UTC

  • Women in AI: Three Pioneers Building Equitable Technology
    Women in AI: Three Pioneers Building Equitable Technology

    By

    @hugo_larochelle

    –

    Who builds AI shapes what it becomes. Ahead of International Women's Day on March 8, we're sharing the stories of three @ai4goodlab alumni — Aaina Garg, Busayo Ososanwo, and Abby Buller — who are proving that technical excellence and a commitment to building a more equitable world go hand in hand. From de-biasing hiring algorithms to managing multiple applied AI projects and advancing AI research at one of Canada’s leading applied research institutions, these women didn't wait until they felt "ready." They started anyway. mila.quebec/en/news/three-ai…

    → View original post on X — @hugo_larochelle, 2026-03-06 15:30 UTC

  • LLM Agent Time Horizons: New Analysis on Model Capabilities

    By

    @hugo_larochelle

    –

    Ever since @METR_Evals
    ' fascinating work on LLM agent time horizons, I've wanted to see other attempts to draw conclusions from the same data. In a separate approach by Fengyuan and Jay, we too infer an exponential, but with shorter horizons for recent models (~2h vs METR's ~5h)

    → View original post on X — @hugo_larochelle,