Lookbehind-SAM: k steps back, 1 step forward
Comments ICML 2024
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Generating Synthetic Population
Comments 6 pages, 3 figures, Oral presentation at NewInML workshop of the 39th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022
Multi-Source Conformal Inference Under Distribution Shift
Comments Accepted to ICML 2024, 39 pages, 13 figures
TimeX++: Learning Time-Series Explanations with Information Bottleneck
Comments Accepted by International Conference on Machine Learning (ICML 2024)
Gradient Boosted Filters For Signal Processing
Comments 9 pages, 12 figures. Submitted to ICML 2024 and subsequently rejected for insufficient evaluation
Sliced-Wasserstein Estimation with Spherical Harmonics as Control Variates
Comments Accepted to ICML 2024
Revisiting the Role of Language Priors in Vision-Language Models
Comments Published at ICML 2024. Website: https://linzhiqiu.github.io/papers/visual_gpt_score/
Jacobian Regularizer-based Neural Granger Causality
Comments 20 pages, 7 figures, ICML 2024
Generalizing Knowledge Graph Embedding with Universal Orthogonal Parameterization
Comments Accepted by ICML 2024
Compositional Text-to-Image Generation with Dense Blob Representations
Comments ICML 2024
Autonomous Sparse Mean-CVaR Portfolio Optimization
Comments ICML 2024
PARDEN, Can You Repeat That? Defending against Jailbreaks via Repetition
Comments Accepted at ICML 20224
Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular Domains
Comments ICML 2024, 18 pages (including supplementary materials)
KV-Runahead: Scalable Causal LLM Inference by Parallel Key-Value Cache Generation
Comments preprint for ICML 2024
PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning
Comments ICML 2024
convSeq: Fast and Scalable Method for Detecting Patterns in Spike Data
Comments This paper has been accepted to ICML 2024
Graph Distillation with Eigenbasis Matching
Comments Accepted by ICML 2024
Faster Gradient-Free Algorithms for Nonsmooth Nonconvex Stochastic Optimization
Comments ICML 2023
Policy Gradient in Robust MDPs with Global Convergence Guarantee
Journal ref International Conference on Machine Learning, 2023
Environment Design for Inverse Reinforcement Learning
Comments to appear at ICML 2024
Localizing Task Information for Improved Model Merging and Compression
Comments Accepted ICML 2024; The first two authors contributed equally to this work; Project website: https://tall-masks.github.io
Fast Timing-Conditioned Latent Audio Diffusion
Comments Accepted to ICML 2024. Code: https://github.com/Stability-AI/stable-audio-tools. Metrics: https://github.com/Stability-AI/stable-audio-metrics. Demo: https://stability-ai.github.io/stable-audio-demo
OXYGENERATOR: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learning
Comments Accepted to ICML 2024
Differentiable Model Scaling using Differentiable Topk
Comments Accepted by ICML 2024
Stealthy Imitation: Reward-guided Environment-free Policy Stealing
Comments Accepted at ICML 2024. Project page: https://zhixiongzh.github.io/stealthy-imitation
Linear Explanations for Individual Neurons
Comments Published in ICML 2024
MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysis
Comments This paper is accepted by ICML 2024
Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image Restoration
Comments ICML 2024
A Dense Reward View on Aligning Text-to-Image Diffusion with Preference
Comments 41st International Conference on Machine Learning (ICML 2024)
Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic
Comments Accepted by ICML 2024
