16 papers
When Geometry Aligns: Dihedral Hidden-State Transformations in UNet, ViT, and DiT Architectures
Mojtaba Faramarzi, Alex Lamb, Irina Rish
Diffusion architectures now encompass convolutional UNets as well as transformer-based designs such as Diffusion Transformers (DiTs), inspired by Vision Transformers (ViTs), yet th…
Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent
Hiroki Naganuma, Shagun Gupta, Youssef Briki +4
To maximize hardware utilization, modern machine learning systems typically employ large constant or manually tuned batch size schedules, relying on heuristics that are brittle and…
MuLoCo: Muon is a practical inner optimizer for DiLoCo
Benjamin Thérien, Xiaolong Huang, Aaron Defazio +2
DiLoCo is a powerful framework for training large language models (LLMs), enabling larger optimal batch sizes and increased accelerator utilization under networking constraints. Ho…
LLM Pretraining Shapes a Generalizable Manifold: Insights into Cross-Modal Transfer to Time Series
Alexis Roger, Prateek Humane, Zhenghan Tai +4
Can language-pretrained transformers become effective time-series forecasters, and why? In this paper, we show that cross-modal transfer arises because language pretraining precond…
Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks?
Rishika Bhagwatkar, Kevin Kasa, Abhay Puri +5
AI agents are vulnerable to indirect prompt injection attacks, where malicious instructions embedded in external content or tool outputs cause unintended or harmful behavior. Inspi…
LO: Compute-Efficient Meta-Generalization of Learned Optimizers
Benjamin Thérien, Charles-Ãtienne Joseph, Boris Knyazev +3
Learned optimizers (LOs) have the potential to significantly reduce the wall-clock training time of neural networks. However, they can struggle to optimize unseen tasks (meta-gener…