Neural Sculpting: Uncovering hierarchically modular task structure in neural networks through pruning and network analysis
Journal ref 37th Conference on Neural Information Processing Systems (NeurIPS 2023)
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Implicit Transfer Operator Learning: Multiple Time-Resolution Surrogates for Molecular Dynamics
Comments 23 pages, 12 figures, 4 tables, NeurIPS 2023
Sharpness-Aware Minimization Leads to Low-Rank Features
Comments The camera-ready version (NeurIPS 2023)
Characterizing Out-of-Distribution Error via Optimal Transport
Comments NeurIPS 2023
LayoutGPT: Compositional Visual Planning and Generation with Large Language Models
Comments NeurIPS 2023
Training Energy-Based Normalizing Flow with Score-Matching Objectives
Comments Published at NeurIPS 2023. Code: https://github.com/chen-hao-chao/ebflow
Discriminative calibration: Check Bayesian computation from simulations and flexible classifier
Comments Published at Neural Information Processing Systems (NeurIPS 2023)
Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization
Comments Published at NeurIPS 2023. Camera-ready version
Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descent
Comments NeurIPS 2023; 60 pages, 8 figures
Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent
Comments 49 pages, NeurIPS 2023
Statistical Knowledge Assessment for Large Language Models
Comments Accepted by NeurIPS 2023
An Inverse Scaling Law for CLIP Training
Comments NeurIPS 2023 camera-ready
Towards Automated Circuit Discovery for Mechanistic Interpretability
Comments NeurIPS 2023 Spotlight
Understanding and Improving Feature Learning for Out-of-Distribution Generalization
Comments Yongqiang Chen, Wei Huang, and Kaiwen Zhou contributed equally; NeurIPS 2023, 55 pages, 64 figures
OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping
Comments Accepted by NeurIPS 2023 Track on Datasets and Benchmarks | OpenLane-V2 Dataset: https://github.com/OpenDriveLab/OpenLane-V2
Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text
Comments NeurIPS D&B 2023. Project homepage: https://github.com/allenai/mmc4
Reliable learning in challenging environments
Journal ref NeurIPS 2023
Black-box Backdoor Defense via Zero-shot Image Purification
Comments Accepted by NeurIPS 2023
Transformer-based Planning for Symbolic Regression
Comments NeurIPS 2023. Project code at: https://github.com/deep-symbolic-mathematics/TPSR
A General Theory of Correct, Incorrect, and Extrinsic Equivariance
Comments Published at NeurIPS 2023
Learning to Influence Human Behavior with Offline Reinforcement Learning
Comments Published at NeurIPS 2023; 13 pages, 10 figures
Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models
Comments Accepted at NeurIPS 2023
Star-Shaped Denoising Diffusion Probabilistic Models
Comments Accepted at NeurIPS 2023
Effective Robustness against Natural Distribution Shifts for Models with Different Training Data
Comments NeurIPS 2023
DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models
Comments Accepted by NeurIPS 2023
Oracle Complexity of Single-Loop Switching Subgradient Methods for Non-Smooth Weakly Convex Functional Constrained Optimization
Comments This work is published in the proceedings of NeurIPS 2023
Characterization and Learning of Causal Graphs with Small Conditioning Sets
Comments Published in NeurIPS'23. 41 pages
CGOF++: Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields
Comments Accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). This article is an extension of the NeurIPS'22 paper arXiv:2206.08361
Interactive Visual Reasoning under Uncertainty
Comments Accepted at NeurIPS 2023 (Datasets and Benchmarks)
Evaluating and Inducing Personality in Pre-trained Language Models
Comments Accepted at NeurIPS 2023 (Spotlight)
