LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
Comments Accepted to NeurIPS 2023 (Datasets and Benchmarks Track) as an oral presentation. Data, code, and models available at https://leandojo.org/
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Topological Parallax: A Geometric Specification for Deep Perception Models
Comments 18 pages, 6 figures. Preprint submitted to NeurIPS 2023
SALSA VERDE: a machine learning attack on Learning With Errors with sparse small secrets
Comments 18 pages, accepted to NeurIPS 2023
Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima
Comments 39 pages. v3 NeurIPS 2023 camera ready version
Semantic HELM: A Human-Readable Memory for Reinforcement Learning
Comments To appear at NeurIPS 2023, 10 pages (+ references and appendix), Code: https://github.com/ml-jku/helm
Katakomba: Tools and Benchmarks for Data-Driven NetHack
Comments Neural Information Processing Systems (NeurIPS 2023) Track on Datasets and Benchmarks. Source code at https://github.com/corl-team/katakomba
High-Fidelity Audio Compression with Improved RVQGAN
Comments Accepted at NeurIPS 2023 (spotlight)
Learning via Wasserstein-Based High Probability Generalisation Bounds
Comments Accepted to NeurIPS 2023
TIES-Merging: Resolving Interference When Merging Models
Comments Published at NeurIPS 2023, 23 Pages, 13 Figures, 14 Tables
Reliable Off-Policy Learning for Dosage Combinations
Comments Accepted at NeurIPS 2023
Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning
Comments NeurIPS 2023. Code is available at https://github.com/thuml/ContextWM
Explainable Brain Age Prediction using coVariance Neural Networks
Comments Camera ready version for NeurIPS 2023. arXiv admin note: substantial text overlap with arXiv:2305.01807
Jigsaw: Learning to Assemble Multiple Fractured Objects
Comments 18 pages, 9 figures, NeurIPS 2023
Flow Matching for Scalable Simulation-Based Inference
Comments NeurIPS 2023. Code available at https://github.com/dingo-gw/flow-matching-posterior-estimation
Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning
Comments NeurIPS 2023 poster
Visual Programming for Text-to-Image Generation and Evaluation
Comments NeurIPS 2023; Project website: https://vp-t2i.github.io
Entropy-dissipation Informed Neural Network for McKean-Vlasov Type PDEs
Comments Accepted to NeurIPS 2023
Synthetic Experience Replay
Comments Published at NeurIPS, 2023
Direct Preference-based Policy Optimization without Reward Modeling
Comments NeurIPS 2023
Implicit Convolutional Kernels for Steerable CNNs
Comments Accepted to 37th Conference on Neural Information Processing Systems (NeurIPS 2023)
Implicit variance regularization in non-contrastive SSL
Comments Accepted at NeurIPS 2023
CORL: Research-oriented Deep Offline Reinforcement Learning Library
Comments Conference on Neural Information Processing Systems (NeurIPS 2023) Track on Datasets and Benchmarks. Source code at https://github.com/corl-team/CORL
Causal Effect Identification in Uncertain Causal Networks
Comments 27 pages, 9 figures, NeurIPS 2023 conference, causal identification, causal discovery, probabilistic models
Combating Representation Learning Disparity with Geometric Harmonization
Comments Accepted to NeurIPS 2023 (spotlight)
CEIL: Generalized Contextual Imitation Learning
Comments NeurIPS 2023
Gaussian Membership Inference Privacy
Comments NeurIPS 2023 camera-ready. The first two authors contributed equally
No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions
Comments Update the camera-ready version for NeurIPS 2023
Improved Best-of-Both-Worlds Guarantees for Multi-Armed Bandits: FTRL with General Regularizers and Multiple Optimal Arms
Comments Update the camera-ready version for NeurIPS 2023
Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning
Comments 37th Conference on Neural Information Processing Systems (NeurIPS 2023)
Neuro-Inspired Fragmentation and Recall to Overcome Catastrophic Forgetting in Curiosity
Comments NeurIPS 2023 Workshop - Intrinsically Motivated Open-ended Learning
