Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data Streams
Comments To appear at the Forty-first International Conference on Machine Learning (ICML 2024)
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL
Comments ICML 2024; 55 Pages
DFA-RAG: Conversational Semantic Router for Large Language Model with Definite Finite Automaton
Comments Accepted to ICML 2024
Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models
Comments Accepted by ICML 2024
Graph-enhanced Large Language Models in Asynchronous Plan Reasoning
Comments Accepted at ICML-2024
Cross-view Masked Diffusion Transformers for Person Image Synthesis
Comments ICML 2024
Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape
Comments ICML 2024 Oral
On Prompt-Driven Safeguarding for Large Language Models
Comments ICML 2024
DITTO: Diffusion Inference-Time T-Optimization for Music Generation
Comments Oral at ICML 2024
Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
Comments Accepted at ICML 2024
E$^{2}$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation
Comments ICML 2024. Project Page: https://yifanfanfanfan.github.io/e2gan/
Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes
Comments ICML 2024
LLark: A Multimodal Instruction-Following Language Model for Music
Comments ICML camera-ready version
Learning to Scale Logits for Temperature-Conditional GFlowNets
Comments ICML 2024, 23 pages, 21 figures
Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
Comments ICML 2024
Predictive Coding beyond Correlations
Comments 44 Pages, 24 Figures. Changed title and abstract, following the ICML accepted version
ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Data
Comments Accepted by the Forty-first International Conference on Machine Learning (ICML2024)
Kernel Debiased Plug-in Estimation: Simultaneous, Automated Debiasing without Influence Functions for Many Target Parameters
Comments To appear at the Forty-first International Conference on Machine Learning (ICML 2024)
Interpreting and Improving Diffusion Models from an Optimization Perspective
Comments 24 pages, 9 figures, 4 tables. To appear in ICML 2024
Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks
Comments Accepted to ICML 2024; Code available at https://github.com/epfml/REQ
Feature Importance Disparities for Data Bias Investigations
Comments ICML 2024 version. 9 pages, 5 figures, 3 tables. Appendix: 18 pages, 9 figures, 4 tables
Diffusion Model-Augmented Behavioral Cloning
Comments ICML 2024
Graph Generation with Diffusion Mixture
Comments ICML 2024
Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Models
Comments ICML 2024
DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation
Comments Accepted at ICML 2024. 22 pages, 5 figures
Activation-Descent Regularization for Input Optimization of ReLU Networks
Comments ICML'24 Proceedings
DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection
Comments Accepted by ICML 2024. Code is available at: https://wnjxyk.github.io/DeCoOp
Turnstile $\ell_p$ leverage score sampling with applications
Comments ICML 2024
Optimal bounds for $\ell_p$ sensitivity sampling via $\ell_2$ augmentation
Comments ICML 2024
Creative Text-to-Audio Generation via Synthesizer Programming
Comments Accepted to ICML 2024
