DistiLLM: Towards Streamlined Distillation for Large Language Models
Comments ICML 2024; Code is available at https://github.com/jongwooko/distillm
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Learning and Forgetting Unsafe Examples in Large Language Models
Comments accepted by ICML 24
Expressivity of Graph Neural Networks Through the Lens of Adversarial Robustness
Comments Published in ${2}^{nd}$ AdvML Frontiers workshop at ${40}^{th}$ International Conference on Machine Learning (ICML)
Bayesian Regret Minimization in Offline Bandits
Journal ref International Conference on Machine Learning, 2024
Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits
Comments To appear in the proceedings of ICML 2023
Matching domain experts by training from scratch on domain knowledge
Comments ICML 2024 (Large Language Models and Cognition)
Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Network
Comments 37 pages, 41 figures, to be published as an ICML 2024 paper
On Discrete Prompt Optimization for Diffusion Models
Comments ICML 2024. Code available at https://github.com/ruocwang/dpo-diffusion
Journal ref Proceedings of the 41st International Conference on Machine Learning (ICML 2024)
Privacy-Preserving Instructions for Aligning Large Language Models
Comments ICML 2024. Code available at https://github.com/google-research/google-research/tree/master/dp_instructions
Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models
Comments International Conference on Machine Learning, 2024
On the Generalization and Approximation Capacities of Neural Controlled Differential Equations
Comments ICLR 2024. First presented at the F4CLD Workshop at ICML 2023
Self-Cognition in Large Language Models: An Exploratory Study
Comments Accepted at ICML 2024 Large Language Models and Cognition Workshop
Coordination Failure in Cooperative Offline MARL
Comments Accepted at the Workshop on Aligning Reinforcement Learning Experimentalists and Theorists (ARLET) at the International Conference on Machine Learning, 2024
Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals
Comments Accepted to ICML 2024
Learning the boundary-to-domain mapping using Lifting Product Fourier Neural Operators for partial differential equations
Comments Accepted by ICML 2024 AI for Science Workshop
Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts
Comments The Forty-first International Conference on Machine Learning, 2024
Recovering the Pre-Fine-Tuning Weights of Generative Models
Comments ICML 2024. Project page: https://vision.huji.ac.il/spectral_detuning/
Generalization Error of Graph Neural Networks in the Mean-field Regime
Comments Accepted in ICML 2024
CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay
Comments ICML'24 camera-ready version
In-Context Reinforcement Learning for Variable Action Spaces
Comments ICML 2024
Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency
Comments Accepted by International Conference on Machine Learning (ICML) 2024
Total Variation Distance Meets Probabilistic Inference
Comments 25 pages. This work has been accepted for presentation at the International Conference on Machine Learning (ICML) 2024
Training-Free Acceleration of ViTs with Delayed Spatial Merging
Comments ICML 2024 ES-FoMo Workshop
Detecting and Identifying Selection Structure in Sequential Data
Comments ICML 2024
One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts
Comments ICML 2024. code available at https://github.com/ruocwang/mixture-of-prompts
Journal ref Proceedings of the 41st International Conference on Machine Learning (ICML), Vienna, Austria, 2024
Multimodal Prototyping for cancer survival prediction
Comments ICML 2024
SRViT: Vision Transformers for Estimating Radar Reflectivity from Satellite Observations at Scale
Comments Published as a workshop paper at "Machine Learning for Earth System Modeling", ICML 2024; added acknowledgements and github link
Uncertainty-Aware Reward-Free Exploration with General Function Approximation
Comments 32 pages, 5 figures, 4 tables, accepted by ICML 2024
Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes
Comments Presented at the 41st International Conference on Machine Learning (ICML) 2024. *Seedat & Huynh contributed equally
Frequency Modulation for Task-Oriented Communications and Multiple Access
Comments This paper has been accepted to the IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN) 2024
