Andrew Williams

PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation Alexandre Piché, Ehsan Kamalloo, Rafael Pardinas, Xiaoyin Chen, Dzmitry Bahdanau. Action editor: Sebastian Tschiatschek. openreview.net/forum?id=A35ak… #pipelinerl #accelerato

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/openle… dear algorithm, please show this to my fellow researchers in need 🙏 #overleaf #latex #opensource #academictwitter

I gave a talk on LLM zero-sum learning dynamics last week at MSR Montreal. I went over a few things that were not in the paper but that I'm particularly excited about; one of those is the connection between generalization and zero-sum learning. youtu.be/UyK3DgWY7yw

I have found Mila to be a great place to do a PhD. Feel free to reach out if you have any questions!

Great opportunity for those new to ML research!

LLMs have complex joint beliefs about all sorts of quantities. And my postdoc @jamesrequeima visualized them! In this thread we show LLM predictive distributions conditioned on data and free-form text. LLMs pick up on all kinds of subtle and unusual structure: 🧵

This is fun because LLMs can condition on free-form side information, and make predictions about anything. This turns qualitative knowledge into quantitative predictions. Here we condition Llama 3 on two datapoints, plus text. Changing the text changes the meaning of the data.

🚀 We have released our paper on ReTreever! 🌳🔍 ReTreever organizes and represents documents in a binary tree across various granular levels, balancing cost & utility while enhancing retrieval transparency. 📜 Read it here: arxiv.org/pdf/2502.07971 #AI @ServiceNowRSRCH 🧵👇

Happy to announce AlignVLM📏: a novel approach to bridging vision and language latent spaces for multimodal understanding in VLMs! 🌍📄🖼️ 🔗 Read the paper: arxiv.org/abs/2502.01341 🧵👇 Thread

this is paper is kinda wild. turns out that if you simply ask an LLM to straight out predict a timeseries like this: ``` (t1, v1) (t2, v2) (t3, v3) (t4, v4) (t5, v5) ``` making sure to prepend the prompt like this: ``` Here is some context about the task. Make sure to factor in any background knowledge, satisfy any constraints, and respect any scenarios. ((context)) ``` it will just… do it? beating SOTA timeseries forcasting?! llama 3.1 405b directly prompted is more precise at forecasting real-world series than: - stats-based timeseries models (ARIMA, ETS) - foundation models specifically trained for time series (eg. chronos) - multimodal forecasting models (eg, time-LLM) peak 'bitter lesson' behavior lol

📢 New paper “Language model scaling laws and zero-sum learning” @scifordl #NeurIPS2024 ℹ️openreview.net/forum?id=yBq2g… TL;DR: scaling improves LMs by mitigating zero-sum learning, a mechanism that could be targeted directly and independent of scale. W205 @ 4:30pm (1/12)🧵

Starting the workshop on Time Series in the Age of Large Models (TSALM) at #NeurIPS2024 with @tomaspfister's invited talk on Multimodal Time Series Modeling!

🚀 Excited to present our work on VCR: Visual Caption Restoration – the 1st and unique VLM benchmark testing if VLMs can focus on tiny but crucial details! 📍 Join us at #NeurIPS24 on Sunday, Dec 15, West Ballroom B 🛠️ Dive into the details: github.com/tianyu-z/VCR

🚀A game-changer for open-access multimodal AI! BigDocs is paving the way for transparent, accountable, and innovative document reasoning and code generation. Check it out! 💡👏

🎉 Excited to introduce BigDocs! An open, transparent multimodal dataset designed for: 📄 Documents 🌐 Web content 🖥️ GUI understanding 👨‍💻 Code generation from images We’re also launching BigDocs-Bench, featuring 10 tasks to test models on: ➡️ Document, Web, GUI Visual reasoning ➡️ Converting images into JSON, Markdown, LaTeX, SVG, and more! 📜 Paper: arxiv.org/pdf/2412.04626 huggingface.co/papers/2412.04… 🌍 Website bigdocs.github.io

Learned optimizers can’t generalize to large unseen tasks…. Until now! Excited to present μLO: Compute-Efficient Meta-Generalization of Learned Optimizers! Don’t miss my talk about it next Sunday at the OPT2024 Neurips Workshop :) 🧵arxiv.org/abs/2406.00153 1/N

Spent the weekend hacking together Exa embeddings over 4500 NeurIPS 2024 papers - neurips.exa.ai Let's you: - do otherwise impossible searches ("transformer architectures inspired by neuroscience") - explore a 2D t-SNE plot - chat with Claude about multiple papers

🌟🌟🌟 We just released BigDocs: An Open Multimodal Dataset — our latest work on scaling document understanding across diverse data types! 📄 👉 Dive into the details: servicenow.com/blogs/2024/big… 🧠 or come see us at the #NeurIPS2024 RBFM workshop! #AI @ServiceNowRSRCH #bigdocs

🧵 Excited to be at #NeurIPS2024 next week. Let's grab a coffee and chat if you're around! Also drop by at our workshop on Time Series in the Age of Large Models on Sunday 🗓️ We have an exciting schedule: 🎓 6 invited talks 🖼️ 60+ posters 🎤 11 contributed talks ✨ and more!