NeurIPS 2023 Conference Submissions

Improvements on Uncertainty Quantification for Node Classification via Distance Based Regularization
Russell Alan Hart, Linlin Yu, Yifei Lou, Feng Chen
- Published: 21 Sept 2023, Last Modified: 02 Nov 2023
- NeurIPS 2023 poster
- Readers: Everyone
Relax, it doesn’t matter how you get there: A new self-supervised approach for multi-timescale behavior analysis
Mehdi Azabou, Michael Jacob Mendelson, Nauman Ahad, Maks Sorokin, Shantanu Thakoor, Carolina Urzay, Eva L Dyer
- Published: 21 Sept 2023, Last Modified: 02 Nov 2023
- NeurIPS 2023 spotlight
- Readers: Everyone
Spatial-frequency channels, shape bias, and adversarial robustness
Ajay Subramanian, Elena Sizikova, Najib J. Majaj, Denis G. Pelli
- Published: 21 Sept 2023, Last Modified: 05 Nov 2023
- NeurIPS 2023 oral
- Readers: Everyone
Normalization Layers Are All That Sharpness-Aware Minimization Needs
Maximilian Mueller, Tiffany Joyce Vlaar, David Rolnick, Matthias Hein
- Published: 21 Sept 2023, Last Modified: 02 Nov 2023
- NeurIPS 2023 poster
- Readers: Everyone
UP-DP: Unsupervised Prompt Learning for Data Pre-Selection with Vision-Language Models
Xin Li, Sima Behpour, Thang Doan, Wenbin He, Liang Gou, Liu Ren
- Published: 21 Sept 2023, Last Modified: 02 Nov 2023
- NeurIPS 2023 poster
- Readers: Everyone
$\varepsilon$-fractional core stability in Hedonic Games.
Simone Fioravanti, Michele Flammini, Bojana Kodric, Giovanna Varricchio
- Published: 21 Sept 2023, Last Modified: 14 Jan 2024
- NeurIPS 2023 poster
- Readers: Everyone
Beyond Invariance: Test-Time Label-Shift Adaptation for Addressing "Spurious" Correlations
Qingyao Sun, Kevin Patrick Murphy, Sayna Ebrahimi, Alexander D'Amour
- Published: 21 Sept 2023, Last Modified: 02 Nov 2023
- NeurIPS 2023 poster
- Readers: Everyone
Language Model Alignment with Elastic Reset
Michael Noukhovitch, Samuel Lavoie, Florian Strub, Aaron Courville
- Published: 21 Sept 2023, Last Modified: 02 Nov 2023
- NeurIPS 2023 poster
- Readers: Everyone
Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence
Grace Luo, Lisa Dunlap, Dong Huk Park, Aleksander Holynski, Trevor Darrell
- Published: 21 Sept 2023, Last Modified: 02 Nov 2023
- NeurIPS 2023 poster
- Readers: Everyone
Understanding Deep Gradient Leakage via Inversion Influence Functions
Haobo Zhang, Junyuan Hong, Yuyang Deng, Mehrdad Mahdavi, Jiayu Zhou
- Published: 21 Sept 2023, Last Modified: 04 Jan 2024
- NeurIPS 2023 poster
- Readers: Everyone
Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment
Royi Rassin, Eran Hirsch, Daniel Glickman, Shauli Ravfogel, Yoav Goldberg, Gal Chechik
- Published: 21 Sept 2023, Last Modified: 19 Jan 2024
- NeurIPS 2023 oral
- Readers: Everyone
The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation
Saurabh Saxena, Charles Herrmann, Junhwa Hur, Abhishek Kar, Mohammad Norouzi, Deqing Sun, David J. Fleet
- Published: 21 Sept 2023, Last Modified: 02 Nov 2023
- NeurIPS 2023 oral
- Readers: Everyone
Joint Prompt Optimization of Stacked LLMs using Variational Inference
Alessandro Sordoni, Xingdi Yuan, Marc-Alexandre Côté, Matheus Pereira, Adam Trischler, Ziang Xiao, Arian Hosseini, Friederike Niedtner, Nicolas Le Roux
- Published: 21 Sept 2023, Last Modified: 02 Nov 2023
- NeurIPS 2023 poster
- Readers: Everyone
Fast Scalable and Accurate Discovery of DAGs Using the Best Order Score Search and Grow Shrink Trees
Bryan Andrews, Joseph Ramsey, Ruben Sanchez Romero, Jazmin Camchong, Erich Kummerfeld
- Published: 21 Sept 2023, Last Modified: 02 Nov 2023
- NeurIPS 2023 poster
- Readers: Everyone
PROTES: Probabilistic Optimization with Tensor Sampling
Anastasia Batsheva, Andrei Chertkov, Gleb Ryzhakov, Ivan Oseledets
- Published: 21 Sept 2023, Last Modified: 15 Jan 2024
- NeurIPS 2023 poster
- Readers: Everyone
A unified framework for information-theoretic generalization bounds
Yifeng Chu, Maxim Raginsky
- Published: 21 Sept 2023, Last Modified: 02 Nov 2023
- NeurIPS 2023 poster
- Readers: Everyone
The Simplicity Bias in Multi-Task RNNs: Shared Attractors, Reuse of Dynamics, and Geometric Representation
Elia Turner, Omri Barak
- Published: 21 Sept 2023, Last Modified: 07 Jan 2024
- NeurIPS 2023 poster
- Readers: Everyone
Variational Gaussian processes for linear inverse problems
Thibault Christophe RANDRIANARISOA, Botond Szabo
- Published: 21 Sept 2023, Last Modified: 02 Nov 2023
- NeurIPS 2023 poster
- Readers: Everyone
Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning
Cristina Menghini, Andrew Delworth, Stephen Bach
- Published: 21 Sept 2023, Last Modified: 21 Dec 2023
- NeurIPS 2023 poster
- Readers: Everyone
(Out-of-context) Meta-learning in Language Models
Dmitrii Krasheninnikov, Egor Krasheninnikov, Bruno Kacper Mlodozeniec, David Krueger
- 11 May 2023 (modified: 12 Dec 2023)
- Submitted to NeurIPS 2023
- Readers: Everyone
Adaptive SGD with Polyak stepsize and Line-search: Robust Convergence and Variance Reduction
Xiaowen Jiang, Sebastian U Stich
- Published: 21 Sept 2023, Last Modified: 02 Nov 2023
- NeurIPS 2023 poster
- Readers: Everyone
First Order Stochastic Optimization with Oblivious Noise
Ilias Diakonikolas, Sushrut Karmalkar, Jongho Park, Christos Tzamos
- Published: 21 Sept 2023, Last Modified: 02 Nov 2023
- NeurIPS 2023 poster
- Readers: Everyone
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, Chelsea Finn
- Published: 21 Sept 2023, Last Modified: 02 Nov 2023
- NeurIPS 2023 oral
- Readers: Everyone
Affinity-Aware Graph Networks
Ameya Velingker, Ali Kemal Sinop, Ira Ktena, Petar Veličković, Sreenivas Gollapudi
- Published: 21 Sept 2023, Last Modified: 07 Nov 2023
- NeurIPS 2023 poster
- Readers: Everyone
Adaptive recurrent vision performs zero-shot computation scaling to unseen difficulty levels
Vijay Veerabadran, Srinivas Ravishankar, Yuan Tang, Ritik Raina, Virginia R. de Sa
- Published: 21 Sept 2023, Last Modified: 02 Nov 2023
- NeurIPS 2023 poster
- Readers: Everyone