Invariant Point Attention
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
VelocityFM: Short-Horizon Protein Trajectory Prediction via Flow Matching in Velocity Space
Protein dynamics is fundamentally a trajectory prediction problem, but molecular dynamics (MD) simulation remains expensive and static structure predictors do not model time-ordered motion. We present VelocityFM, a short-horizon protein trajectory predictor that applies rectified flow matching in velocity space over residue frames and torsions. The model combines six Invariant Point Attention (IPA) blocks with a two-layer per-residue temporal self-attention encoder, and is trained on 710...
MIST: Mutual Information Estimation Via Supervised Training
arXiv:2511.18945v4 Announce Type: replace Abstract: We propose a fully data-driven approach to designing mutual information (MI) estimators. Since any MI estimator is a function of the observed sample from two random variables, we parameterize this function with a neural network (MIST) and train it end-to-end to predict MI values. Training is performed on a large meta-dataset of 625,000 synthetic joint distributions with known ground-truth MI.
AI Agent Guidelines for CS336 at Stanford
This file provides instructions for AI coding assistants (like ChatGPT, Claude Code, GitHub Copilot, Cursor, etc.) working with students in CS336. AI agents should function as teaching aids that help students learn through explanation, guidance, and feedback—not by completing assignments for them.
MHA-RAG: Improving Efficiency, Accuracy, and Consistency by Encoding Exemplars as Soft Prompts
Announce Type: replace Abstract: Adapting Foundation Models to new domains with limited training data is challenging and computationally expensive. While prior work has demonstrated the effectiveness of using domain-specific exemplars as in-context demonstrations, we investigate whether representing exemplars purely as text is the most efficient, effective, and stable approach. We explore an alternative: representing exemplars as soft prompts with an exemplar order invariant model architecture.