Search papers, labs, and topics across Lattice.
14 papers from MIT CSAIL on Training Efficiency & Optimization
Forget complex fixed-point machinery: this work offers a dramatically simpler and more efficient route from external regret to $桅$-regret minimization.
Exact robust regression at scale is now possible: a new algorithm solves the NP-hard Least Trimmed Squares problem orders of magnitude faster than existing methods.
EquiformerV3 achieves state-of-the-art performance in atomistic modeling by combining architectural improvements with optimized software, enabling accurate energy-conserving simulations.
Forget simulating backward dynamics: solve stochastic optimal control problems by just watching the system relax forward.
Stabilizing test-time training with an elastic prior lets you reconstruct 4D scenes from long video sequences without catastrophic forgetting, even with smaller memory chunks.
Finally, a rigorous mathematical framework lets you treat deep learning architectures as composable algebraic objects, opening the door to formal verification and automated design.
Training superword tokenizers just got 600x faster, unlocking practical use of subword tokenization across pre-tokenization boundaries.
Demystifying LLMs for the masses might be as simple as turning their mechanics into a game.
Neural networks can accurately predict polymer free energies, even when traditional methods like Bennett Acceptance Ratio fail due to poor phase-space overlap.
By dynamically adjusting contrastive learning temperatures based on data density, MM-TS achieves state-of-the-art results on multimodal long-tail datasets.
Lattice QCD calculations just got a whole lot faster: normalizing flows slash variance by up to 60x in key observables.
E(3)-equivariant networks just got a whole lot faster: a new algorithm cuts the complexity of Clebsch-Gordan Tensor Products from $O(L^6)$ to $O(L^4\log^2 L)$ without sacrificing completeness.
Ditch the geometry-to-property map: this work uses the external potential as the primary input for machine learning models, unlocking a scalable and equivariant approach to predicting electronic structure.
Self-supervised learning beats supervised learning for ECG interpretation when labeled data is scarce, unlocking more robust and generalizable AI-driven cardiac diagnostics.
