Graph Adversarial Diffusion Convolution
Comments Accepted by ICML 2024
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Causal Effect Identification in LiNGAM Models with Latent Confounders
Comments Accepted at International Conference on Machine Learning (ICML) 2024
What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding
Comments ICML 2024
Conditional Language Learning with Context
Comments To appear at the 41st International Conference on Machine Learning (ICML 2024)
Certifiably Byzantine-Robust Federated Conformal Prediction
Comments Accepted to ICML 2024
Understanding Stochastic Natural Gradient Variational Inference
Comments ICML 2024
Multi-Agent Reinforcement Learning Meets Leaf Sequencing in Radiotherapy
Comments Accepted by ICML 2024
Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation
Comments ICML 2024
Sparser, Better, Deeper, Stronger: Improving Sparse Training with Exact Orthogonal Initialization
Comments ICML 2024
MLIP: Efficient Multi-Perspective Language-Image Pretraining with Exhaustive Data Utilization
Comments ICML 2024
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer
Comments Accepted by ICML 2024, code and models are available at https://github.com/JiaDingCN/GeminiFusion
Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination
Comments Accepted at ICML 2024. 9 pages for main content, 34 pages in total
Unveiling the Cycloid Trajectory of EM Iterations in Mixed Linear Regression
Comments This paper was accepted by the 41st International Conference on Machine Learning (ICML 2024). The code for numerical experiments is available at https://github.com/dassein/cycloid_em_mlr
FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler
Comments This paper has been accepted by ICML'24
The Role of Learning Algorithms in Collective Action
Comments Accepted at the International Conference in Machine Learning (ICML), 2024
Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning
Comments ICML 2024 version
Wasserstein Wormhole: Scalable Optimal Transport Distance with Transformers
Comments Published at the Forty-first International Conference on Machine Learning (ICML2024)
Disguised Copyright Infringement of Latent Diffusion Models
Comments Accepted to ICML 2024
Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression
Comments Accepted to ICML'24
Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation
Comments Accepted in the Proceedings of the 41st International Conference on Machine Learning (ICML2024)
Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing
Journal ref International Conference on Machine Learning (ICML), 2024
Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Control
Comments ICML 2024
QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks
Comments ICML 2024
Challenges in Training PINNs: A Loss Landscape Perspective
Comments ICML 2024 Oral; 33 pages (including appendices), 10 figures, 3 tables
Compositional Generative Modeling: A Single Model is Not All You Need
Comments ICML 2024 (Position Track)
APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference
Comments Accepted to ICML 2024 Oral; code available at https://github.com/ROIM1998/APT
Observable Propagation: Uncovering Feature Vectors in Transformers
Comments 42 pages, 6 tables, 3 figures. ICML 2024
Controlled Decoding from Language Models
Comments ICML 2024
Adversarial Attacks on Combinatorial Multi-Armed Bandits
Comments 28 pages, Accepted to ICML 2024
Towards a Better Theoretical Understanding of Independent Subnetwork Training
Comments Accepted to International Conference on Machine Learning (ICML), 2024
