Imagen de Portada

Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gao, Boyan, Zhao, Bo, Gowda, Shreyank N, Xing, Xingrun, Yang, Yibo, Hospedales, Timothy, Clifton, David A.
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

FE-Adapter: Adapting Image-based Emotion Classifiers to Videos
por: Gowda, Shreyank N, et al.
Publicado: (2024)

Optimization-Inspired Few-Shot Adaptation for Large Language Models
por: Gao, Boyan, et al.
Publicado: (2025)

CC-SAM: SAM with Cross-feature Attention and Context for Ultrasound Image Segmentation
por: Gowda, Shreyank N, et al.
Publicado: (2024)

Masks and Manuscripts: Advancing Medical Pre-training with End-to-End Masking and Narrative Structuring
por: Gowda, Shreyank N, et al.
Publicado: (2024)

An Empirical Study of Multi-Generation Sampling for Jailbreak Detection in Large Language Models
por: Luo, Hanrui, et al.
Publicado: (2026)

Geometric Characterisation and Structured Trajectory Surrogates for Clinical Dataset Condensation
por: Nganjimi, Pafue Christy, et al.
Publicado: (2026)

Improving Clinical Dataset Condensation with Mode Connectivity-based Trajectory Surrogates
por: Nganjimi, Pafue Christy, et al.
Publicado: (2025)

SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking
por: Xing, Xingrun, et al.
Publicado: (2024)

Is Temporal Prompting All We Need For Limited Labeled Action Recognition?
por: Gowda, Shreyank N, et al.
Publicado: (2025)

Trust Region On-Policy Distillation
por: Xing, Xingrun, et al.
Publicado: (2026)

Adaptive Data Dropout: Towards Self-Regulated Learning in Deep Neural Networks
por: Gahir, Amar, et al.
Publicado: (2026)

Prompt Injection Detection is Regime-Dependent: A Deployment-Aware Evaluation with Interpretable Structural Signals
por: Akinrele, Akindoyin, et al.
Publicado: (2026)

EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models
por: Xing, Xingrun, et al.
Publicado: (2025)

CAPT: Class-Aware Prompt Tuning for Federated Long-Tailed Learning with Vision-Language Model
por: Hou, Shihao, et al.
Publicado: (2025)

Democratising Clinical AI through Dataset Condensation for Classical Clinical Models
por: Thakur, Anshul, et al.
Publicado: (2026)

FedHB: Hierarchical Bayesian Federated Learning
por: Kim, Minyoung, et al.
Publicado: (2023)

Prototype-Enhanced Confidence Modeling for Cross-Modal Medical Image-Report Retrieval
por: Gowda, Shreyank N, et al.
Publicado: (2025)

Better Later Than Sooner: Neuro-Symbolic Knowledge Graph Construction via Ontology-grounded Post-extraction Correction
por: Loconte, Lorenzo, et al.
Publicado: (2026)

A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning
por: Kim, Minyoung, et al.
Publicado: (2024)

Watt For What: Rethinking Deep Learning's Energy-Performance Relationship
por: Gowda, Shreyank N, et al.
Publicado: (2023)

Dataset Condensation for Time Series Classification via Dual Domain Matching
por: Liu, Zhanyu, et al.
Publicado: (2024)

On the Limitations of General Purpose Domain Generalisation Methods
por: Gouk, Henry, et al.
Publicado: (2022)

ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning
por: Chavhan, Ruchika, et al.
Publicado: (2024)

Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisation
por: Kim, Taehoon, et al.
Publicado: (2025)

Dataset Condensation with Latent Quantile Matching
por: Wei, Wei, et al.
Publicado: (2024)

VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning
por: Zong, Yongshuo, et al.
Publicado: (2024)

Telling Stories for Common Sense Zero-Shot Action Recognition
por: Gowda, Shreyank N, et al.
Publicado: (2023)

Sharpen Your Flow: Sharpness-Aware Sampling for Flow Matching
por: Gupta, Aditi, et al.
Publicado: (2026)

FATE: A Prompt-Tuning-Based Semi-Supervised Learning Framework for Extremely Limited Labeled Data
por: Liu, Hezhao, et al.
Publicado: (2025)

Extending Pretrained 10-Second ECG Foundation Models to Longer Horizons
por: Tang, Wei, et al.
Publicado: (2026)

Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization
por: Liu, Sihao, et al.
Publicado: (2024)

Boltzmann Generators for Condensed Matter via Riemannian Flow Matching
por: Hoffmann, Emil, et al.
Publicado: (2026)

Veritas-RPM: Provenance-Guided Multi-Agent False Positive Suppression for Remote Patient Monitoring
por: Misro, Aswini, et al.
Publicado: (2026)

Sensing Cardiac Health Across Scenarios and Devices: A Multi-Modal Foundation Model Pretrained on Heterogeneous Data from 1.7 Million Individuals
por: Gu, Xiao, et al.
Publicado: (2025)

Reimagining Reality: A Comprehensive Survey of Video Inpainting Techniques
por: Gowda, Shreyank N, et al.
Publicado: (2024)

Fool Your (Vision and) Language Model With Embarrassingly Simple Permutations
por: Zong, Yongshuo, et al.
Publicado: (2023)

Model Merging is Secretly Certifiable: Non-Vacuous Generalisation Bounds for Low-Shot Learning
por: Kim, Taehoon, et al.
Publicado: (2025)

Navigating Noise: A Study of How Noise Influences Generalisation and Calibration of Neural Networks
por: Ferianc, Martin, et al.
Publicado: (2023)

Bi-Directional Multi-Scale Graph Dataset Condensation via Information Bottleneck
por: Fu, Xingcheng, et al.
Publicado: (2024)

Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning
por: Springer, Jacob Mitchell, et al.
Publicado: (2024)