Explainable Machine Learning

🚨 New paper! arxiv.org/abs/2603.06610 Are you sure your post-trained LLM isn’t forgetting something? Adapting LLMs is known to cause forgetting. We usually measure it via general knowledge benchmarks. But if MMLU doesn’t drop…. are you really fine?

BayesVLM provides reliable uncertainty for pretrained vision-language models without retraining or inference-time sampling. It improves zero-shot calibration, reduces overconfident errors under domain shift, and enables more sample-efficient active learning with negligible overhead.

BayesVLM places a Laplace posterior over the final projection layers and analytically propagates uncertainty to cosine similarities. This avoids Monte Carlo sampling while enabling efficient uncertainty-aware inference and active learning.

🥳Happy to share that we have three papers accepted to #ICLR2026. Congrats to our authors and see you in Rio🌴🇧🇷. Check the thread for highlights👇

Check out our new work on getting more out of your Vision Transformers without fine-tuning by leveraging intermediate representations when probing! We find that attentive probing is most robust for fusing across layers while showing exactly which layers matter for what task 👇

4/ Invited talk: The Asymmetry of Adaptation: Reverse-Engineering Multimodal In-Context Learning Yiran Huang & @zeynepakata 📍[🇺🇸 NeurIPS CCFM Workshop]: Sunday, December 7th 2025, 8:15 AM - 9:00 AM, San Diego Convention Center, Upper Level Room 25ABC

3/ Concept-Guided Interpretability via Neural Chunking @shuchen_wu , Stephan Alaniz , @ShyamgopalKart1, Peter Dayan, Eric Schulz, @zeynepakata 📍[🇺🇸NeurIPS]: Fri, Dec 5, 2025 • 11:00 AM – 2:00 PM PST, Exhibit Hall C,D,E #2113

Our EML members have arrived in beautiful San Diego for #NeurIPS2025! 🌴 We’re excited to share our latest research — three poster presentations and one workshop presentation. Check out the thread below 👇 and come say hi to our authors!