MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
Comments ICML 2024 (Oral); Project Website: https://open-vision-language.github.io/MagicLens/
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models
Comments ICML 2024
NExT-GPT: Any-to-Any Multimodal LLM
Comments ICML 2024 (Oral)
Latent Optimal Paths by Gumbel Propagation for Variational Bayesian Dynamic Programming
Comments Accepted by ICML 2024
Straight-Through meets Sparse Recovery: the Support Exploration Algorithm
Journal ref ICML 2024, the 41st International Conference on Machine Learning, Jul 2024, Vienna, Austria
GeoMFormer: A General Architecture for Geometric Molecular Representation Learning
Comments 25 pages, 13 tables, l figure; ICML 2024 camera ready version
Confidence Aware Inverse Constrained Reinforcement Learning
Comments Paper to appear in ICML 2024
Differentiable Distributionally Robust Optimization Layers
Comments In Forty-first International Conference on Machine Learning (2024)
Watermark Stealing in Large Language Models
Comments ICML 2024
Towards Theoretical Understandings of Self-Consuming Generative Models
Comments Accepted at ICML 2024
Adaptively Perturbed Mirror Descent for Learning in Games
Comments Accepted at ICML 2024
Landscaping Linear Mode Connectivity
Comments ICML 2024 HiLD workshop paper
Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
Comments 25 pages, ICML 2024 Accepted
Position: Benchmarking is Limited in Reinforcement Learning Research
Comments 19 pages, 13 figures, The Forty-first International Conference on Machine Learning (ICML 2024)
Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method
Comments Accepted at 41st International Conference on Machine Learning (ICML 2024)
An All-MLP Sequence Modeling Architecture That Excels at Copying
Comments Accepted by ICML 2024 Next Generation of Sequence Modeling Architectures Workshop
EVCL: Elastic Variational Continual Learning with Weight Consolidation
Comments Accepted at ICML 2024 Workshop on Structured Probabilistic Inference & Generative Modeling
Language Alignment via Nash-learning and Adaptive feedback
Comments Accepted at ICML 2024 Workshop on Models of Human Feedback for AI Alignment, Vienna, Austria
video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models
Comments Accepted at ICML 2024. arXiv admin note: substantial text overlap with arXiv:2310.05863
Testing the Feasibility of Linear Programs with Bandit Feedback
Comments Spotlight presentation at ICML 2024
DataFreeShield: Defending Adversarial Attacks without Training Data
Comments ICML 2024
Towards Bayesian Data Selection
Comments 5th Workshop on Data-Centric Machine Learning Research (DMLR) at ICML 2024
FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning
Comments ICML 2024
Adaptive Online Experimental Design for Causal Discovery
Comments To appear in Proceedings of ICML 24
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
Comments 22 pages; ICML 2024 Oral: https://icml.cc/virtual/2024/oral/35482
Automated Statistical Model Discovery with Language Models
Comments ICML 2024
Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills
Comments Proceedings of the 41st International Conference on Machine Learning, Vienna, Austria. PMLR 235, 2024
On Least Square Estimation in Softmax Gating Mixture of Experts
Comments Accepted to ICML 2024, 29 pages, 2 figures, 2 tables
A Dynamical Model of Neural Scaling Laws
Comments ICML Camera Ready. Included online SGD section with additional simulations and its connection to large sample limit of our gradient flow theory. Fixed typo in Appendix eq 112
Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?
Comments Accepted to ICML 2024, 47 pages, 2 figures, 2 tables
