Home | Tags | #p-jegelka

#p-jegelka

BHL+26

Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability

ICML 2026

#p-jegelka

GZW+26

SSL4RL: Revisiting Self-Supervised Learning as Intrinsic Reward for Visual-Language Reasoning

ICML 2026

#p-jegelka

BHL+26a

Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability

WSS @ICML 2026

#p-jegelka

BJN+26

Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models

Preprint (May. 2026)

#p-jegelka

WWY+26

When More Is Less: Understanding Chain-of-Thought Length in LLMs

ICLR 2026

#p-jegelka

PLG+25

GL Equivariant Metanetworks for Learning on Low Rank Weight Spaces

LOG 2025

#p-jegelka

YAM+25

Learning Linear Attention in Polynomial Time

NeurIPS 2025

#p-jegelka

CST+25

Fairness Aware Reward Optimization

Preprint (Nov. 2025)

#p-jegelka

HKK+25

Lost in Serialization: Invariance and Generalization of LLM Graph Reasoners

Preprint (Nov. 2025)

#p-jegelka

KTJ+25

Symmetries in Weight Space Learning: To Retain or Remove?

HiLD @ICML 2025

#p-jegelka

STJ+25

Learning With Exact Invariances in Polynomial Time

ICML 2025

#p-jegelka

DWL+25

Finsler Multi-Dimensional Scaling: Manifold Learning for Asymmetric Dimensionality Reduction and Embedding

CVPR 2025

#p-cremers #p-jegelka

BLJ+25

A Projection-Based Framework for Gradient-Free and Parallel Learning

Preprint (Jun. 2025)

#p-jegelka #p-sra

SJ25

Learning Equivariant Models by Discovering Symmetries With Learnable Augmentations

Preprint (Jun. 2025)

#p-jegelka

GLW+25

G1: Teaching LLMs to Reason on Graphs With Reinforcement Learning

Preprint (May. 2025)

#p-jegelka

FWL+25

What Is Wrong With Perplexity for Long-Context Language Modeling?

ICLR 2025

#p-jegelka

RJL25

Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs

ICLR 2025

#p-jegelka

TJ25

Generalization Bounds for Canonicalization: A Comparative Study With Group Averaging

ICLR 2025

#p-jegelka

ZWC+25

Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness

ICLR 2025

#p-jegelka

HJ25

Higher-Order Graphon Neural Networks: Approximation and Cut Distance

ICLR 2025

#p-jegelka

MWL+24

A Canonicalization Perspective on Invariant and Equivariant Learning

NeurIPS 2024

#p-jegelka

WHG+24

Understanding the Role of Equivariance in Self-Supervised Learning

NeurIPS 2024

#p-jegelka

WWW+24

A Theoretical Understanding of Self-Correction Through In-Context Alignment

NeurIPS 2024

#p-jegelka

YKL+24

Are Graph Neural Networks Optimal Approximation Algorithms?

NeurIPS 2024

#p-jegelka

BLS+24

Topologically Faithful Multi-Class Segmentation in Medical Images

MICCAI 2024

#p-bauer-u #p-jegelka #p-rueckert

GLR+24

Simplicity Bias via Global Convergence of Sharpness Minimization

Preprint (Oct. 2024)

#p-jegelka

GSR+24a

On the Role of Depth and Looping for In-Context Learning With Task Diversity

Preprint (Oct. 2024)

#p-jegelka

PLG+24

Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models

Preprint (Oct. 2024)

#p-jegelka

2018-12-10 - Last modified: 2018-12-10