Prof. René Vidal’s group at the University of Pennsylvania’s GRASP Laboratory explored this problem in their recent publication titled “SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations”...
Read more:
www.grasp.upenn.edu/news/simple-...

#GRASP #GRASPLab #NeurIPS25

🧵Excited to present our latest work at #Neurips25! Together with @avm.bsky.social, we discover 𝐜𝐡𝐚𝐧𝐧𝐞𝐥𝐬 𝐭𝐨 𝐢𝐧𝐟𝐢𝐧𝐢𝐭𝐲: regions in neural networks loss landscapes where parameters diverge to infinity (in regression settings!)

We find that MLPs in these channels can take derivatives and compute GLUs 🤯

👋 I’m at @neuripsconf.bsky.social in San Diego 🌴Hit me up if you’d like to talk imprecise probabilities, learning theory, good old statistics, or simply anything Bayesian 🤓 #NeurIPS2025 #NeurIPS #NeurIPS25

Approximate Domain Unlearning: Enabling Safer and More Controllable Vision-Language Models The proposed approximate unlearning technique differentiates between domains while preserving the generalization capability  Approximate unlearning removes irrelevant information from vision-langua…

BREAKING TODAY! Approximate Domain Unlearning: Enabling Safer and More Controllable Vision-Language Models -- radicaldatascience.wordpress.com/2025/12/02/a...

#AI #VLM #vision @neuripsconf.bsky.social #NeurIPS #neurips25

Looking forward to #NeurIPS25 this week 🏝️! I'll be presenting at Poster Session 3 (11-2 on Thursday). Feel free to reach out!

It's common today to learn predictive user representations for multiple downstream tasks. But these representations can generate unfair predictions. So, in our recent #NeurIPS25 paper, we propose bounding the unfairness across all models for any task with fine-grained control.

🎉 Accepted papers at NeurIPS 2025 🎉
The team is proud to announce that several paper were accepted at #NeurIPS25. Looking forward to meet in Paris (25th-26th Nov), Copenhagen or San Diego (1st-7th Dec)!
Let's present our papers ⬇️

Our paper “The Flood Complex – Large-Scale Persistent Homology on Millions of Points” is accepted at #NeurIPS25 🎉

📄 Preprint: arxiv.org/pdf/2509.22432
💻 Code: open + ready to use

The goal is to bridge Causal Inference with Explainable AI, providing estimand-agnostic strategies to facilitate the use of these techniques for non-experts.

See you at #NeurIPS25!

Now accepted to #neurips25 datasets & benchmarks!
See you in San Diego! 🥳

GitHub - lab-cosmo/flashmd: A universal ML model to predict molecular dynamics trajectories with long time steps A universal ML model to predict molecular dynamics trajectories with long time steps - lab-cosmo/flashmd

Bragging time - ⚡ FlashMD⚡ was accepted as a spotlight paper at #NeurIPS25. if you still haven't checked it out, it's already on the #arxiv arxiv.org/abs/2505.19350, the code is at flashmd.org and the 🧑‍🍳📖 is here atomistic-cookbook.org/examples/fla.... Congrats to Filippo, Sanggyu and Augustinus!

Accepted to #NeurIPS25! 🥳 Big congrats to Stephen !! glad to be part of it @flatironinstitute.org