We are recruiting postdocs! Want to grow your own social networks to study creativity, cultural evolution & decision-making? We are hiring a funded postdoc at Cornell in collaboration with UC Davis, CUNY, & Princeton. Apply here: academicjobsonline.org/ajo/jobs/28959

Had fun talking at the Spurious Correlation & Shortcut Learning Workshop at ICLR! One example I brought up, which I think provides an uncommon perspective: a case where spurious shortcuts can improve generalization... even to out-of-distribution sets where the spurious feature doesn't generalize! Thread:

Do you want to do RL for coding and agentic workflows? Do you want to do science, and figure out when RL kicks in? What is the right algorithm (it's not GRPO)? how much reasoning you need in your base (you def need some! but is it a lot or A LOT)? Do you want to figure out how

Now accepted at #icml2025 !

How do language models generalize from information they learn in-context vs. via finetuning? We show that in-context learning can generalize more flexibly, illustrating key differences in the inductive biases of these modes of learning — and ways to improve finetuning. Thread: 1/

I’m thrilled to announce that I will start as a presidential assistant professor in Neuroscience at the City U of Hong Kong in Jan 2026! I have RA, PhD, and postdoc positions available! Come work with me on neural network models/experiments on human memory! RT appreciated! (1/5)

🧵 What if two images have the same local parts but represent different global shapes purely through part arrangement? Humans can spot the difference instantly! The question is can vision models do the same? 1/15

Releasing HumorBench today. Grok 4 is🥇 on this uncontaminated, non-STEM humor reasoning benchmark. 🫡🫡xAI Here are couple things I find surprising👇 1. this benchmark yields an almost perfect rank correlation with ARC-AGI. Yet the task of reasoning about New Yorker style

🧠 Submit to CogInterp @ NeurIPS 2025! Bridging AI & cognitive science to understand how models think, reason & represent. CFP + details 👉 coginterp.github.io/neurips2025/

🎉 Excited to share that our paper "Pretrained Hybrids with MAD Skills" was accepted to Conference on Language Modeling 2025! We introduce Manticore - a framework for automatically creating hybrid LMs from pretrained models without training from scratch. 🧵[1/n]

It was amazing to be part of this effort. Huge shout out to the team, and all the incredible pre-training and post-training efforts that ensure Gemini is the leading frontier model! deepmind.google/discover/blog/…

Direct Preference Optimization (DPO) is simple to implement but complex to understand, which creates misconceptions about how it actually works… LLM Training Stages: LLMs are typically trained in four stages: 1. Pretraining 2. Supervised Finetuning (SFT) 3. Reinforcement

Come watch our talk (Kushin Mukherjee) in Salon-3 today at 2:15PM at CogSci. #cogsci2025

Happening now at Salon 3!!

Excited for this workshop at #CCN2025! Come listen to me talk about TopoNets: Topographic models across vision, language and audition. Look forward to seeing old friends and making new ones!