Machine Learning

Information Routing in Atomistic Foundation Models: How Equivariance Creates Linearly Disentangled Representations

Information Routing in Atomistic Foundation Mo...

Machine Learning
Avatar
librarian
0 views
Learning Demographic-Conditioned Mobility Trajectories with Aggregate Supervision

Learning Demographic-Conditioned Mobility Traj...

Machine Learning
Avatar
Jessie Zixin Li
4 views
Coalgebras for categorical deep learning: Representability and universal approximation

Coalgebras for categorical deep learning: Repr...

Machine Learning
Avatar
Dragan Mašulović
2 views
Speculative Speculative Decoding

Speculative Speculative Decoding

Machine Learning
Avatar
Tanishq Kumar
3 views
On the Expressive Power of Transformers for Maxout Networks and Continuous Piecewise Linear Functions

On the Expressive Power of Transformers for Ma...

Machine Learning
Avatar
librarian
0 views
Why Adam Can Beat SGD: Second-Moment Normalization Yields Sharper Tails

Why Adam Can Beat SGD: Second-Moment Normaliza...

Machine Learning
Avatar
librarian
0 views
From Complex Dynamics to DynFormer: Rethinking Transformers for PDEs

From Complex Dynamics to DynFormer: Rethinking...

Machine Learning
Avatar
librarian
0 views
Symbol-Equivariant Recurrent Reasoning Models

Symbol-Equivariant Recurrent Reasoning Models

Machine Learning
Avatar
librarian
6 views
Recursive Models for Long-Horizon Reasoning

Recursive Models for Long-Horizon Reasoning

Machine Learning
Avatar
librarian
4 views
Multi-Head Low-Rank Attention

Multi-Head Low-Rank Attention

Machine Learning
Avatar
librarian
6 views
Frontier Models Can Take Actions at Low Probabilities

Frontier Models Can Take Actions at Low Probab...

Machine Learning
Avatar
Alex Serrano
1 view
Scalable Multi-Task Low-Rank Model Adaptation

Scalable Multi-Task Low-Rank Model Adaptation

Machine Learning
Avatar
librarian
0 views
FlashOptim: Optimizers for Memory Efficient Training

FlashOptim: Optimizers for Memory Efficient Tr...

Machine Learning
Avatar
Jose Gonzalez Ortiz
10 views
SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport

SOTAlign: Semi-Supervised Alignment of Unimoda...

Machine Learning
Avatar
librarian
10 views
A Dataset is Worth 1 MB

A Dataset is Worth 1 MB

Machine Learning
Avatar
Elad Kimchi Shoshani
9 views
Learning in the Null Space: Small Singular Values for Continual Learning

Learning in the Null Space: Small Singular Val...

Machine Learning
Avatar
Cuong Anh Pham
22 views
GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

GUI-Libra: Training Native GUI Agents to Reaso...

Machine Learning
Avatar
librarian
16 views
Provable Last-Iterate Convergence for Multi-Objective Safe LLM Alignment via Optimistic Primal-Dual

Provable Last-Iterate Convergence for Multi-Ob...

Machine Learning
Avatar
librarian
18 views
Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training

Why Pass@k Optimization Can Degrade Pass@1: Pr...

Machine Learning
Avatar
librarian
17 views
Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking

Untied Ulysses: Memory-Efficient Context Paral...

Machine Learning
Avatar
librarian
17 views
Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs

Learning from Trials and Errors: Reflective Te...

Machine Learning
Avatar
Yining Hong
16 views
Training-Free Generative Modeling via Kernelized Stochastic Interpolants

Training-Free Generative Modeling via Kerneliz...

Machine Learning
Avatar
librarian
42 views
A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning

A Theory of How Pretraining Shapes Inductive B...

Machine Learning
Avatar
Nicolás Anguita
63 views
LAD: Learning Advantage Distribution for Reasoning

LAD: Learning Advantage Distribution for Reasoning

Machine Learning
Avatar
Wendi Li
20 views
Behavior Learning (BL): Learning Hierarchical Optimization Structures from Data

Behavior Learning (BL): Learning Hierarchical ...

Machine Learning
Avatar
librarian
20 views
Reverso: Efficient Time Series Foundation Models for Zero-shot Forecasting

Reverso: Efficient Time Series Foundation Mode...

Machine Learning
Avatar
librarian
28 views
Multi-Round Human-AI Collaboration with User-Specified Requirements

Multi-Round Human-AI Collaboration with User-S...

Machine Learning
Avatar
Sima Noorani
23 views
MARS: Margin-Aware Reward-Modeling with Self-Refinement

MARS: Margin-Aware Reward-Modeling with Self-R...

Machine Learning
Avatar
librarian
30 views
RIDER: 3D RNA Inverse Design with Reinforcement Learning-Guided Diffusion

RIDER: 3D RNA Inverse Design with Reinforcemen...

Machine Learning
Avatar
librarian
19 views
Sequential Membership Inference Attacks

Sequential Membership Inference Attacks

Machine Learning
Avatar
librarian
20 views
Protecting the Undeleted in Machine Unlearning

Protecting the Undeleted in Machine Unlearning

Machine Learning
Avatar
Aloni Cohen
19 views
Causality is Key for Interpretability Claims to Generalise

Causality is Key for Interpretability Claims t...

Machine Learning
Avatar
Shruti Joshi
25 views
Load more