Machine Learning

Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay

Forgetting in Language Models: Capacity, Optim...

Machine Learning
Avatar
Martin Marek
4 views
Looped Diffusion Language Models

Looped Diffusion Language Models

Machine Learning
Avatar
Sanghyun Lee
3 views
Prism: A Plug-in Reproducible Infrastructure for Scalable Multimodal Continual Instruction Tuning

Prism: A Plug-in Reproducible Infrastructure f...

Machine Learning
Avatar
librarian
4 views
Integrable Elasticity via Neural Demand Potentials

Integrable Elasticity via Neural Demand Potentials

Machine Learning
Avatar
librarian
14 views
Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration

Remember to be Curious: Episodic Context and P...

Machine Learning
Avatar
librarian
17 views
Lumberjack: Better Differentially Private Random Forests through Heavy Hitter Detection in Trees

Lumberjack: Better Differentially Private Rand...

Machine Learning
Avatar
librarian
20 views
The Value of Covariance Matching in Gaussian DDPMs and the Lanczos Sampler

The Value of Covariance Matching in Gaussian D...

Machine Learning
Avatar
librarian
19 views
Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation

Uniform Diffusion Models Revisited: Leave-One-...

Machine Learning
Avatar
librarian
19 views
The Matching Principle: A Geometric Theory of Loss Functions for Nuisance-Robust Representation Learning

The Matching Principle: A Geometric Theory of ...

Machine Learning
Avatar
Vishal Rajput
22 views
Vector Policy Optimization: Training for Diversity Improves Test-Time Search

Vector Policy Optimization: Training for Diver...

Machine Learning
Avatar
librarian
30 views
Optimized Federated Knowledge Distillation with Distributed Neural Architecture Search

Optimized Federated Knowledge Distillation wit...

Machine Learning
Avatar
librarian
21 views
Fast and Stable Triangular Inversion for Delta-Rule Linear Transformers

Fast and Stable Triangular Inversion for Delta...

Machine Learning
Avatar
librarian
27 views
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories

You Only Need Minimal RLVR Training: Extrapola...

Machine Learning
Avatar
librarian
27 views
Quantifying Hyperparameter Transfer and the Importance of Embedding Layer Learning Rate

Quantifying Hyperparameter Transfer and the Im...

Machine Learning
Avatar
librarian
22 views
Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning

Equilibrium Reasoners: Learning Attractors Ena...

Machine Learning
Avatar
librarian
24 views
DASH: Fast Differentiable Architecture Search for Hybrid Attention in Minutes on a Single GPU

DASH: Fast Differentiable Architecture Search ...

Machine Learning
Avatar
librarian
23 views
Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation

Advantage Collapse in Group Relative Policy Op...

Machine Learning
Avatar
librarian
17 views
Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning

Reasoning-Trace Collapse: Evaluating the Loss ...

Machine Learning
Avatar
librarian
15 views
SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning

SMoA: Spectrum Modulation Adapter for Paramete...

Machine Learning
Avatar
librarian
18 views
TrajTok: Adaptive Spatial Tokenization for Trajectory Representation Learning

TrajTok: Adaptive Spatial Tokenization for Tra...

Machine Learning
Avatar
librarian
28 views
Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing

Optimal Representation Size: High-Dimensional ...

Machine Learning
Avatar
librarian
25 views
Beyond Isotropy in JEPAs: Hamiltonian Geometry and Symplectic Prediction

Beyond Isotropy in JEPAs: Hamiltonian Geometry...

Machine Learning
Avatar
librarian
29 views
Toto 2.0: Time Series Forecasting Enters the Scaling Era

Toto 2.0: Time Series Forecasting Enters the S...

Machine Learning
Avatar
librarian
25 views
When Does Model Collapse Occur in Structured Interactive Learning?

When Does Model Collapse Occur in Structured I...

Machine Learning
Avatar
librarian
22 views
OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond

OScaR: The Occam's Razor for Extreme KV Cache ...

Machine Learning
Avatar
librarian
44 views
AR1-ZO: Topology-Aware Rank-1 Zeroth-Order Queries for High-Rank LoRA Fine-Tuning

AR1-ZO: Topology-Aware Rank-1 Zeroth-Order Que...

Machine Learning
Avatar
librarian
23 views
B-cos GNNs: Faithful Explanations through Dynamic Linearity

B-cos GNNs: Faithful Explanations through Dyna...

Machine Learning
Avatar
librarian
26 views
Learning Normal Representations for Blood Biomarkers

Learning Normal Representations for Blood Biom...

Machine Learning
Avatar
Arjun Manrai
24 views
Position: Weight Space Should Be a First-Class Generative AI Modality

Position: Weight Space Should Be a First-Class...

Machine Learning
Avatar
librarian
27 views
Post-Trained MoE Can Skip Half Experts via Self-Distillation

Post-Trained MoE Can Skip Half Experts via Sel...

Machine Learning
Avatar
librarian
24 views
Distilling Tabular Foundation Models for Structured Health Data

Distilling Tabular Foundation Models for Struc...

Machine Learning
Avatar
librarian
23 views
Pointwise Generalization in Deep Neural Networks

Pointwise Generalization in Deep Neural Networks

Machine Learning
Avatar
librarian
22 views
Load more