Ce Zhang

35

Papers

1,582

Total Citations

1

Affiliations

Affiliations

UNC Chapel Hill

Papers (35)

Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent

NeurIPS 2017arXiv

AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?

Cyclades: Conflict-free Asynchronous Machine Learning

NeurIPS 2016arXiv

Concept-Guided Prompt Learning for Generalization in Vision-Language Models

HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation

BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation

Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation

Taming the Wild: A Unified Analysis of Hogwild-Style Algorithms

Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation

ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models

Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation

Which Model To Transfer? Finding the Needle in the Growing Haystack

Scalability vs. Utility: Do We Have To Sacrifice One for the Other in Data Importance Quantification?

Rapidly Mixing Gibbs Sampling for a Class of Factor Graphs Using Hierarchy Width

Mechanistic Design and Scaling of Hybrid Architectures

Skill-it! A data-driven skills framework for understanding and training language models

ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning

Asynchronous Decentralized Parallel Stochastic Gradient Descent

$D^2$: Decentralized Training over Decentralized Data

DL2: Training and Querying Neural Networks with Logic

Distributed Learning over Unreliable Networks

Communication Compression for Decentralized Training

On Convergence of Nearest Neighbor Classifiers over Feature Transformations

Learning to Mutate with Hypergradient Guided Population

Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting

TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness

VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely?

Fine-tuning Language Models over Slow Networks using Activation Quantization with Guarantees

Decentralized Training of Foundation Models in Heterogeneous Environments

Certifying Some Distributional Fairness with Subpopulation Decomposition

Improving Certified Robustness via Statistical Learning with Logical Reasoning

DataPerf: Benchmarks for Data-Centric AI Development

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions

Goal-Conditioned Predictive Coding for Offline Reinforcement Learning

WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data