No coffee/tea outside the official coffee/time times. I was spoiled by #COLM2026.
Is there tea/coffee at #EMNLP2026 right now? Or should I caffeinate before heading over? very important and urgent questions
October 25, 2026 at 11:37 AM
No coffee/tea outside the official coffee/time times. I was spoiled by #COLM2026.
Accepted at #COLM2026: Switching Linear Attention, from Scott Linderman's lab at Stanford, keeps linear attention's fixed-size state but lets each output switch among components, narrowing the gap to softmax attention. Marlowe was among its GPU resources. arxiv.org/abs/2609.39034
October 22, 2026 at 4:57 PM
Accepted at #COLM2026: Switching Linear Attention, from Scott Linderman's lab at Stanford, keeps linear attention's fixed-size state but lets each output switch among components, narrowing the gap to softmax attention. Marlowe was among its GPU resources. arxiv.org/abs/2609.39034
A great week with the language modeling community at @colmweb.org. Thanks to everyone who connected with our team. See you next year! #COLM2026
October 12, 2026 at 8:51 PM
A great week with the language modeling community at @colmweb.org. Thanks to everyone who connected with our team. See you next year! #COLM2026
If you were missing some more direct advice about “what to do” at #COLM2026, this paper might be a place to look!
New #AIES paper w/ @benzevgreen.bsky.social & @tisjune.bsky.social - "Deconstructing AI Hype: A Playbook for Resistance"! Read here: shreyachowdhary.net/files/decons...
We argue that AI hype is a problem not because it misdescribes AI, but because it facilitates AI entrenchment.
We argue that AI hype is a problem not because it misdescribes AI, but because it facilitates AI entrenchment.
October 9, 2026 at 4:40 PM
If you were missing some more direct advice about “what to do” at #COLM2026, this paper might be a place to look!
if you're at #colm2026, why not come listen to some fun #tokenization talks?
Continental 1, all day long
tokenization-workshop.github.io/schedule/
Continental 1, all day long
tokenization-workshop.github.io/schedule/
Second Tokenization Workshop @ COLM 2026 | Schedule
tokenization-workshop.github.io
October 9, 2026 at 4:12 PM
if you're at #colm2026, why not come listen to some fun #tokenization talks?
Continental 1, all day long
tokenization-workshop.github.io/schedule/
Continental 1, all day long
tokenization-workshop.github.io/schedule/
If you are at #COLM2026, be sure to check out our workshop on responsibly enabling data for foundation models -- starting at 8:45 AM in Union Square 17&18 / Fourth Floor.
Featuring posters and contributed talks, as well as amazing plenary speakers 😲😲😲
Featuring posters and contributed talks, as well as amazing plenary speakers 😲😲😲
October 9, 2026 at 3:30 PM
If you are at #COLM2026, be sure to check out our workshop on responsibly enabling data for foundation models -- starting at 8:45 AM in Union Square 17&18 / Fourth Floor.
Featuring posters and contributed talks, as well as amazing plenary speakers 😲😲😲
Featuring posters and contributed talks, as well as amazing plenary speakers 😲😲😲
TAG mentioned! at #colm2026 (by @adinawilliams.bsky.social maybe?)
in context of this really cool paper on compound tokenization arxiv.org/abs/2610.055...
in context of this really cool paper on compound tokenization arxiv.org/abs/2610.055...
October 8, 2026 at 5:21 PM
TAG mentioned! at #colm2026 (by @adinawilliams.bsky.social maybe?)
in context of this really cool paper on compound tokenization arxiv.org/abs/2610.055...
in context of this really cool paper on compound tokenization arxiv.org/abs/2610.055...
That's a wrap on #COLM2026! Thank you to everyone who stopped by our booth, joined our evening gathering, & talked open research with us.
Catch up on the papers, interviews, & highlights from the week. 👇
allenai.org/blog/colm-20...
Catch up on the papers, interviews, & highlights from the week. 👇
allenai.org/blog/colm-20...
Ai2 at COLM 2026: Open research, from models to agents for science | Ai2
Ai2 joined COLM 2026 to share advances in open language models, training infrastructure, and AI for science, including Olmo Hybrid, Asta, and Bolmo, while connecting with the broader research communit...
allenai.org
October 10, 2026 at 12:31 AM
That's a wrap on #COLM2026! Thank you to everyone who stopped by our booth, joined our evening gathering, & talked open research with us.
Catch up on the papers, interviews, & highlights from the week. 👇
allenai.org/blog/colm-20...
Catch up on the papers, interviews, & highlights from the week. 👇
allenai.org/blog/colm-20...
"[LLMs] are no more gods than are markets or bureaucracies"
@himself.bsky.social at #COLM2026
Precisely the parallelisms that our 'Why We Fear AI' takes as its starting points, too
@himself.bsky.social at #COLM2026
Precisely the parallelisms that our 'Why We Fear AI' takes as its starting points, too
October 8, 2026 at 5:12 PM
"[LLMs] are no more gods than are markets or bureaucracies"
@himself.bsky.social at #COLM2026
Precisely the parallelisms that our 'Why We Fear AI' takes as its starting points, too
@himself.bsky.social at #COLM2026
Precisely the parallelisms that our 'Why We Fear AI' takes as its starting points, too
favorite paper of #colm2026 (so far): CoBPE arxiv.org/pdf/2610.055...
combine modifiers with their heads on the fly to create compositional tokens. shorter sequence length, better downstream results
combine modifiers with their heads on the fly to create compositional tokens. shorter sequence length, better downstream results
arxiv.org
October 8, 2026 at 5:19 PM
favorite paper of #colm2026 (so far): CoBPE arxiv.org/pdf/2610.055...
combine modifiers with their heads on the fly to create compositional tokens. shorter sequence length, better downstream results
combine modifiers with their heads on the fly to create compositional tokens. shorter sequence length, better downstream results
Russ Salakhutdinov and I were both at our first #COLM2026, so I asked him what he made of it. It reminded him of NeurIPS ten years ago, when you could get through all the posters! And he had good advice for early-career researchers.
youtu.be/YrmhHUqfVlY?...
#WiAIR ##wiairpodcast
youtu.be/YrmhHUqfVlY?...
#WiAIR ##wiairpodcast
Is COLM the New NeurIPS? Russ Salakhutdinov on Agents, Evals and Long-Horizon Tasks
YouTube video by Women in AI Research WiAIR
youtu.be
October 8, 2026 at 8:04 PM
Russ Salakhutdinov and I were both at our first #COLM2026, so I asked him what he made of it. It reminded him of NeurIPS ten years ago, when you could get through all the posters! And he had good advice for early-career researchers.
youtu.be/YrmhHUqfVlY?...
#WiAIR ##wiairpodcast
youtu.be/YrmhHUqfVlY?...
#WiAIR ##wiairpodcast
RT @i_beltagy: Heading back from #colm2026 with a question I heard over and over from researchers and academics: are you still building Olmo models?
I know it has been an up-and-down year for @allen_ai, but I’m surprised this is even a question.
I know it has been an up-and-down year for @allen_ai, but I’m surprised this is even a question.
October 9, 2026 at 5:14 AM
RT @i_beltagy: Heading back from #colm2026 with a question I heard over and over from researchers and academics: are you still building Olmo models?
I know it has been an up-and-down year for @allen_ai, but I’m surprised this is even a question.
I know it has been an up-and-down year for @allen_ai, but I’m surprised this is even a question.
This afternoon at #COLM2026 (Poster 18): Multi-agent systems are great for complex tasks, but successful completion requires that agents "play nicely" with each other. When one agent hoards all the compute or API credits, this leaves the entire task at risk.
October 7, 2026 at 10:34 PM
This afternoon at #COLM2026 (Poster 18): Multi-agent systems are great for complex tasks, but successful completion requires that agents "play nicely" with each other. When one agent hoards all the compute or API credits, this leaves the entire task at risk.
Today at 12:00pm, don't miss our live demonstration on EmbeddingGemma 2 at the @COLM_conf Google booth (#107). Connect with Sahil Dua and explore an open multimodal model that unifies text, images, audio, and video representations. #COLM2026 @GoogleDeepMind
October 8, 2026 at 6:50 PM
Today at 12:00pm, don't miss our live demonstration on EmbeddingGemma 2 at the @COLM_conf Google booth (#107). Connect with Sahil Dua and explore an open multimodal model that unifies text, images, audio, and video representations. #COLM2026 @GoogleDeepMind
Interested in privacy-preserving synthetic data?
Catch Alex Bie at the @COLM_conf Google booth (#107) today, at 2:00 PM PT for an encore presentation of ContinuousBench, evaluating knowledge transfer and data contamination in DP synthesis.@GoogleDeepMind
Join the conversation at #COLM2026!
Catch Alex Bie at the @COLM_conf Google booth (#107) today, at 2:00 PM PT for an encore presentation of ContinuousBench, evaluating knowledge transfer and data contamination in DP synthesis.@GoogleDeepMind
Join the conversation at #COLM2026!
Join Alex Bie at the @COLM_conf Google booth #107 today at 5:00 PM for a walkthrough of ContinuousBench, a standardized benchmark designed to measure knowledge transfer in differentially private (DP) synthesis.
October 8, 2026 at 7:35 PM
Interested in privacy-preserving synthetic data?
Catch Alex Bie at the @COLM_conf Google booth (#107) today, at 2:00 PM PT for an encore presentation of ContinuousBench, evaluating knowledge transfer and data contamination in DP synthesis.@GoogleDeepMind
Join the conversation at #COLM2026!
Catch Alex Bie at the @COLM_conf Google booth (#107) today, at 2:00 PM PT for an encore presentation of ContinuousBench, evaluating knowledge transfer and data contamination in DP synthesis.@GoogleDeepMind
Join the conversation at #COLM2026!
Missed yesterday's demo on adaptive agent environments?
Stop by the #COLM2026 Google booth #107 today at 11:00 AM PT to catch Zifeng Wang presenting EnvHarness — a flexible framework enabling co-evolution between LLM agents and their training environments.
Stop by the #COLM2026 Google booth #107 today at 11:00 AM PT to catch Zifeng Wang presenting EnvHarness — a flexible framework enabling co-evolution between LLM agents and their training environments.
LLM agents learn by interacting with environments, but static setups limit their growth.
October 8, 2026 at 4:35 PM
Missed yesterday's demo on adaptive agent environments?
Stop by the #COLM2026 Google booth #107 today at 11:00 AM PT to catch Zifeng Wang presenting EnvHarness — a flexible framework enabling co-evolution between LLM agents and their training environments.
Stop by the #COLM2026 Google booth #107 today at 11:00 AM PT to catch Zifeng Wang presenting EnvHarness — a flexible framework enabling co-evolution between LLM agents and their training environments.
AI-powered smart glasses that guide delivery drivers from van to the customer's doorstep, hands-free. Hear from Amazon applied scientist Yelin Kim on the computer vision and edge AI behind it at @colmweb.org. #COLM2026.
October 7, 2026 at 11:16 PM
AI-powered smart glasses that guide delivery drivers from van to the customer's doorstep, hands-free. Hear from Amazon applied scientist Yelin Kim on the computer vision and edge AI behind it at @colmweb.org. #COLM2026.
🎤 Can you out-rhyme the AI agent? Stop by the Amazon booth at @colmweb.org for a live AI rap battle demo, plus talks on multi-agent systems and responsible AI for science: https://amzn.to/4jsMYKM #COLM2026
October 8, 2026 at 4:24 PM
🎤 Can you out-rhyme the AI agent? Stop by the Amazon booth at @colmweb.org for a live AI rap battle demo, plus talks on multi-agent systems and responsible AI for science: https://amzn.to/4jsMYKM #COLM2026
What’s happening at #COLM2026? 👀🎤
Ai2 Comms Lead @kylelwiggers.bsky.social catches up with Senior Director of NLP @nlpnoah.bsky.social to talk agentic models, the next iteration of Olmo, & more!
At COLM? Come say hi at booth 302! 👋
Ai2 Comms Lead @kylelwiggers.bsky.social catches up with Senior Director of NLP @nlpnoah.bsky.social to talk agentic models, the next iteration of Olmo, & more!
At COLM? Come say hi at booth 302! 👋
October 7, 2026 at 7:25 PM
What’s happening at #COLM2026? 👀🎤
Ai2 Comms Lead @kylelwiggers.bsky.social catches up with Senior Director of NLP @nlpnoah.bsky.social to talk agentic models, the next iteration of Olmo, & more!
At COLM? Come say hi at booth 302! 👋
Ai2 Comms Lead @kylelwiggers.bsky.social catches up with Senior Director of NLP @nlpnoah.bsky.social to talk agentic models, the next iteration of Olmo, & more!
At COLM? Come say hi at booth 302! 👋
Our work at #COLM2026 asks whether we can measure how well models collaborate cheaply and quickly *before* we configure our multi-agent teams. Drawing techniques from behavioral economics, we show that you can measure the cooperative profile of models—and models do differ!
Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows
Multi-agent systems built from teams of large language models (LLMs) are increasingly deployed for collaborative scientific reasoning and problem-solving. These systems require agents to coordinate un...
arxiv.org
October 7, 2026 at 10:34 PM
Our work at #COLM2026 asks whether we can measure how well models collaborate cheaply and quickly *before* we configure our multi-agent teams. Drawing techniques from behavioral economics, we show that you can measure the cooperative profile of models—and models do differ!
October 6, 2026 at 7:09 PM