Chris Pal's Avatar

Chris Pal

@chrisjpal.bsky.social

Professor, Mila, Polytechnique Montreal, DIRO, UdeM Distinguished Scientist, ServiceNow Research https://sites.google.com/view/christopher-pal

30 Followers  |  24 Following  |  3 Posts  |  Joined: 24.11.2024  |  1.6823

Latest posts by chrisjpal.bsky.social on Bluesky

Post image

2025 BERT is NeoBERT! We have fully pre-trained a next-generation encoder for 2.1T tokens with the latest advances in data, training, and architecture. This is a heroic effort from my PhD student, Lola Le Breton, in collaboration with Quentin Fournier and Mariam El Mezouar (1/n)

28.02.2025 16:30 — 👍 39    🔁 11    💬 1    📌 4
Post image

🎉 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:
➡️ Document, Web, GUI Visual reasoning
➡️ Converting images into JSON, Markdown, LaTeX, SVG, and more!

10.12.2024 18:34 — 👍 16    🔁 8    💬 1    📌 2

I think it is the AC's job to detect when a reviewer's criticisms have been addressed, but the reviewer has checked out, and then throw out that reviewer's score. I think this should be made an official policy of ICLR. Reviewers who do this are being far worse that just rude.

05.12.2024 02:00 — 👍 4    🔁 0    💬 1    📌 0

This could easily be a photo of exactly what you describe.

26.11.2024 15:00 — 👍 2    🔁 0    💬 0    📌 0
Post image

LLMs have a lot of potential for science, but scientists can be particularly sensitive to factuality, nuances, and hallucinations. The new ScholarQABench benchmark in this paper looks pretty useful for the community to monitor progress on LLMs for science. arxiv.org/html/2411.14199

25.11.2024 01:20 — 👍 1    🔁 1    💬 0    📌 0

@chrisjpal is following 20 prominent accounts