A Theoretical Formulation of Many-body Message Passing Neural Networks
Comments Accepted as a paper at ICML GRaM Workshop, 2024
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Fine-Tuning Medical Language Models for Enhanced Long-Contextual Understanding and Domain Expertise
Comments 5 pages, 1 figure. Accepted by the Workshop on Long-Context Foundation Models (LCFM) at ICML 2024
Scaling Exponents Across Parameterizations and Optimizers
Comments 63 pages, International Conference on Machine Learning 2024
Amortizing Pragmatic Program Synthesis with Rankings
Comments icml 2024. This work supersedes and serves as a new version of arXiv:2309.03225
Accelerating Simulation of Two-Phase Flows with Neural PDE Surrogates
Comments Accepted at ICML 2024 AI for Science workshop
Image Clustering with External Guidance
Journal ref ICML 2024 (Oral)
Designing Decision Support Systems Using Counterfactual Prediction Sets
Comments Best paper award in the ICML 2023 AI&HCI Workshop, spotlight paper at ICML 2024
FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization
Comments Accepted to ICML 2023
Contingency-constrained economic dispatch with safe reinforcement learning
Journal ref 21st IEEE International Conference on Machine Learning and Applications (ICMLA), 2022, pp. 597-602
Isometric Representation Learning for Disentangled Latent Space of Diffusion Models
Journal ref Forty-first International Conference on Machine Learning (ICML 2024)
MaPPing Your Model: Assessing the Impact of Adversarial Attacks on LLM-based Programming Assistants
Comments 6 pages, 5 figures, Proceedings of the ICML 2024 Workshop on Trustworthy Multimodal Foundation Models and AI Agents
Graph Neural Networks and Spatial Information Learning for Post-Processing Ensemble Weather Forecasts
Comments Accepted paper at ICML 2024 - Machine Learning for Earth System Modeling Workshop (https://leap-stc.github.io/ml4esm-workshop/)
Toward Availability Attacks in 3D Point Clouds
Comments ICML 2024, 21 pages
Data-Efficient Molecular Generation with Hierarchical Textual Inversion
Comments ICML 2024
UltraFeedback: Boosting Language Models with Scaled AI Feedback
Comments ICML 2024 camera ready
Cross-lingual QA: A Key to Unlocking In-context Cross-lingual Performance
Comments Accepted to ICML 2024 Workshop on In-Context Learning
ODIM: Outlier Detection via Likelihood of Under-Fitted Generative Models
Comments 31 pages in total. Published at ICML 2024
Evaluating Model Bias Requires Characterizing its Mistakes
Comments 17 pages, 6 figures, ICML 2024
3D Geometric Shape Assembly via Efficient Point Cloud Matching
Comments Accepted to ICML 2024
Merging Improves Self-Critique Against Jailbreak Attacks
Comments Published at ICML 2024 Workshop on Foundation Models in the Wild
Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning
Comments ICML 2024, 19 pages
All-in-one simulation-based inference
Comments To be published in the proceedings of the 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria. PMLR 235, 2024
Fundamental Benefit of Alternating Updates in Minimax Optimization
Comments Accepted to ICML 2024 (Spotlight). 76 pages, 2 figures. Additional experiments (quadratic game, GAN) and proofs
A Closer Look at the Limitations of Instruction Tuning
Comments Accepted to ICML 2024
Learned Best-Effort LLM Serving
Comments Es-FoMo @ ICML 2024
Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods
Comments ICML 2024
Combining Neural Networks and Symbolic Regression for Analytical Lyapunov Function Discovery
Comments Workshop paper, accepted by Workshop on Foundations of Reinforcement Learning and Control at the 41st International Conference on Machine Learning, Vienna, Austria
Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations
Comments Accepted for publication at the 41st International Conference on Machine Learning (ICML) 2024, Vienna, Austria; Project Page: https://jhagnberger.github.io/vectorized-conditional-neural-field/
Partially Stochastic Infinitely Deep Bayesian Neural Networks
Comments 17 pages including supplementary material. Accepted at ICML 2024
Equivariant vs. Invariant Layers: A Comparison of Backbone and Pooling for Point Cloud Classification
Comments Published in the GRaM workshop at ICML 2024
