✨ #NeurIPS2025 paper: Scalable Feature Learning on Huge Knowledge Graphs for Downstream Machine Learning
Combining contrastive learning and message passing markedly improves features created from embedding graphs, scalable to huge graphs.
It taught us a lot on graph feature learning 👇
1/10
Combining contrastive learning and message passing markedly improves features created from embedding graphs, scalable to huge graphs.
It taught us a lot on graph feature learning 👇
1/10
November 28, 2025 at 3:46 PM
✨ #NeurIPS2025 paper: Scalable Feature Learning on Huge Knowledge Graphs for Downstream Machine Learning
Combining contrastive learning and message passing markedly improves features created from embedding graphs, scalable to huge graphs.
It taught us a lot on graph feature learning 👇
1/10
Combining contrastive learning and message passing markedly improves features created from embedding graphs, scalable to huge graphs.
It taught us a lot on graph feature learning 👇
1/10
We jointly amortize Bayesian inference and active data acquisition within a single architecture.
Excited to share our #NeurIPS2025 ✨Spotlight✨ paper “ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition”!
www.huangdaolang.com/aline/
Excited to share our #NeurIPS2025 ✨Spotlight✨ paper “ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition”!
www.huangdaolang.com/aline/
December 3, 2025 at 5:32 AM
We jointly amortize Bayesian inference and active data acquisition within a single architecture.
Excited to share our #NeurIPS2025 ✨Spotlight✨ paper “ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition”!
www.huangdaolang.com/aline/
Excited to share our #NeurIPS2025 ✨Spotlight✨ paper “ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition”!
www.huangdaolang.com/aline/
Excited to share a new preprint, accepted as a spotlight at #NeurIPS2025!
Humans are imperfect decision-makers, and autonomous systems should understand how we deviate from idealized rationality
Our paper aims to address this! 👀🧠✨
arxiv.org/abs/2510.25951
a 🧵⤵️
Humans are imperfect decision-makers, and autonomous systems should understand how we deviate from idealized rationality
Our paper aims to address this! 👀🧠✨
arxiv.org/abs/2510.25951
a 🧵⤵️
Estimating cognitive biases with attention-aware inverse planning
People's goal-directed behaviors are influenced by their cognitive biases, and autonomous systems that interact with people should be aware of this. For example, people's attention to objects in their...
arxiv.org
November 13, 2025 at 1:20 PM
Excited to share a new preprint, accepted as a spotlight at #NeurIPS2025!
Humans are imperfect decision-makers, and autonomous systems should understand how we deviate from idealized rationality
Our paper aims to address this! 👀🧠✨
arxiv.org/abs/2510.25951
a 🧵⤵️
Humans are imperfect decision-makers, and autonomous systems should understand how we deviate from idealized rationality
Our paper aims to address this! 👀🧠✨
arxiv.org/abs/2510.25951
a 🧵⤵️
Excited to present these results at #NeurIPS2025!
✨My new paper on core principles of reinforcement learning was accepted as a Spotlight presentation at @neuripsconf.bsky.social !✨
✨My new paper on core principles of reinforcement learning was accepted as a Spotlight presentation at @neuripsconf.bsky.social !✨
November 27, 2025 at 11:27 AM
Excited to present these results at #NeurIPS2025!
✨My new paper on core principles of reinforcement learning was accepted as a Spotlight presentation at @neuripsconf.bsky.social !✨
✨My new paper on core principles of reinforcement learning was accepted as a Spotlight presentation at @neuripsconf.bsky.social !✨
Syntax that spuriously correlates with safe domains can jailbreak LLMs - e.g. below with GPT4o mini
Our paper (co w/ Vinith Suriyakumar) on syntax-domain spurious correlations will appear at #NeurIPS2025 as a ✨spotlight!
+ @marzyehghassemi.bsky.social, @byron.bsky.social, Levent Sagun
Our paper (co w/ Vinith Suriyakumar) on syntax-domain spurious correlations will appear at #NeurIPS2025 as a ✨spotlight!
+ @marzyehghassemi.bsky.social, @byron.bsky.social, Levent Sagun
October 24, 2025 at 4:23 PM
Syntax that spuriously correlates with safe domains can jailbreak LLMs - e.g. below with GPT4o mini
Our paper (co w/ Vinith Suriyakumar) on syntax-domain spurious correlations will appear at #NeurIPS2025 as a ✨spotlight!
+ @marzyehghassemi.bsky.social, @byron.bsky.social, Levent Sagun
Our paper (co w/ Vinith Suriyakumar) on syntax-domain spurious correlations will appear at #NeurIPS2025 as a ✨spotlight!
+ @marzyehghassemi.bsky.social, @byron.bsky.social, Levent Sagun
Excited to share my essay with @carrot0817.bsky.social, Kaia Gao on the representational substrate of world-reasoning in both humans and machines has been accepted to the SpaVLE Workshop at #NeurIPS2025✨
a thread (1/n)
a thread (1/n)
November 2, 2025 at 11:50 PM
Excited to share my essay with @carrot0817.bsky.social, Kaia Gao on the representational substrate of world-reasoning in both humans and machines has been accepted to the SpaVLE Workshop at #NeurIPS2025✨
a thread (1/n)
a thread (1/n)
At #Neurips2025 this week with @cohereforai.bsky.social 🤩
This is what brought me into research: the ✨Network Effect ✨
Let's build the next breakthrough together!
#LabLegends
This is what brought me into research: the ✨Network Effect ✨
Let's build the next breakthrough together!
#LabLegends
December 2, 2025 at 3:29 PM
At #Neurips2025 this week with @cohereforai.bsky.social 🤩
This is what brought me into research: the ✨Network Effect ✨
Let's build the next breakthrough together!
#LabLegends
This is what brought me into research: the ✨Network Effect ✨
Let's build the next breakthrough together!
#LabLegends
Professional achievement: UNLOCKED! 🏆✨ I'm honored to share that I am serving as an Assistant Chair for #NeurIPS2025's brand new Position Paper Track!
June 4, 2025 at 2:32 AM
Professional achievement: UNLOCKED! 🏆✨ I'm honored to share that I am serving as an Assistant Chair for #NeurIPS2025's brand new Position Paper Track!
🎉 Exciting news from ELLIS Unit Milan: our Unit has 22 papers accepted at #NeurIPS2025!
Huge congratulations to all authors and collaborators for this outstanding achievement 👏✨
Stay tuned as we’ll share more details on these papers when the conference approaches!
Huge congratulations to all authors and collaborators for this outstanding achievement 👏✨
Stay tuned as we’ll share more details on these papers when the conference approaches!
September 29, 2025 at 9:38 AM
🎉 Exciting news from ELLIS Unit Milan: our Unit has 22 papers accepted at #NeurIPS2025!
Huge congratulations to all authors and collaborators for this outstanding achievement 👏✨
Stay tuned as we’ll share more details on these papers when the conference approaches!
Huge congratulations to all authors and collaborators for this outstanding achievement 👏✨
Stay tuned as we’ll share more details on these papers when the conference approaches!
Just 1 day left until #NeurIPS2025 kicks off! The Cohere and Cohere Labs teams are ready to dive into a packed week of research, conversations, and community at the San Diego Convention Center✨
Come visit our booth — we’d love to chat and send you home with some swag!
Come visit our booth — we’d love to chat and send you home with some swag!
December 1, 2025 at 11:00 AM
Just 1 day left until #NeurIPS2025 kicks off! The Cohere and Cohere Labs teams are ready to dive into a packed week of research, conversations, and community at the San Diego Convention Center✨
Come visit our booth — we’d love to chat and send you home with some swag!
Come visit our booth — we’d love to chat and send you home with some swag!
#NeurIPS2025. Mixing different datasets to train your LLM?
✨ We can help you find the perfect blend!
📈 Few small-model experiments → scaling law fit → your optimal mixture.
🎯 Easy + efficient.
Chat with us 💬 Poster #3414. Thu, Dec 4, 11am arxiv.org/abs/2507.09404
✨ We can help you find the perfect blend!
📈 Few small-model experiments → scaling law fit → your optimal mixture.
🎯 Easy + efficient.
Chat with us 💬 Poster #3414. Thu, Dec 4, 11am arxiv.org/abs/2507.09404
Scaling Laws for Optimal Data Mixtures
Large foundation models are typically trained on data from multiple domains, with the data mixture--the proportion of each domain used--playing a critical role in model performance. The standard appro...
arxiv.org
December 2, 2025 at 6:47 PM
#NeurIPS2025. Mixing different datasets to train your LLM?
✨ We can help you find the perfect blend!
📈 Few small-model experiments → scaling law fit → your optimal mixture.
🎯 Easy + efficient.
Chat with us 💬 Poster #3414. Thu, Dec 4, 11am arxiv.org/abs/2507.09404
✨ We can help you find the perfect blend!
📈 Few small-model experiments → scaling law fit → your optimal mixture.
🎯 Easy + efficient.
Chat with us 💬 Poster #3414. Thu, Dec 4, 11am arxiv.org/abs/2507.09404
🚀 NeurIPS 2025 is flipping the script on AI with innovative architectures like transformers and smart training techniques! 🧠✨ What’s your take on the future of AI? #AIRevolution #NeurIPS2025 #MachineLearning LINK
January 18, 2026 at 4:18 AM
🚀 NeurIPS 2025 is flipping the script on AI with innovative architectures like transformers and smart training techniques! 🧠✨ What’s your take on the future of AI? #AIRevolution #NeurIPS2025 #MachineLearning LINK