NeurIPS

STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases

Shirley Wu, Shiyu Zhao, Michihiro Yasunaga, Kexin Huang, Kaidi Cao, Qian Huang, Vassilis N. Ioannidis, Karthik Subbian, James Zou, Jure Leskovec

Comments NeurIPS 2024 Track on Datasets and Benchmarks. 26 Pages, 6 Figures. Website: https://stark.stanford.edu/

Stepwise Alignment for Constrained Language Model Policy Optimization

Akifumi Wachi, Thien Q. Tran, Rei Sato, Takumi Tanabe, Youhei Akimoto

Comments Accepted at NeurIPS 2024. Code and models are available at https://github.com/line/sacpo

Why Transformers Need Adam: A Hessian Perspective

Yushun Zhang, Congliang Chen, Tian Ding, Ziniu Li, Ruoyu Sun, Zhi-Quan Luo

Comments Advances in Neural Information Processing Systems, 2024

Fundamental Convergence Analysis of Sharpness-Aware Minimization

Pham Duy Khanh, Hoang-Chau Luong, Boris S. Mordukhovich, Dat Ba Tran

Comments 34 pages

Journal ref Advances in Neural Information Processing Systems 2024

Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts

Hang Guo, Tao Dai, Yuanchao Bai, Bin Chen, Xudong Ren, Zexuan Zhu, Shu-Tao Xia

Comments Accepted by NeurIPS 2024

ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizons

Jiawen Zhang, Xumeng Wen, Zhenwei Zhang, Shun Zheng, Jia Li, Jiang Bian

Comments NeurIPS 2024 Datasets and Benchmarks Track

Augmentation-aware Self-supervised Learning with Conditioned Projector

Marcin Przewięźlikowski, Mateusz Pyla, Bartosz Zieliński, Bartłomiej Twardowski, Jacek Tabor, Marek Śmieja

Comments A short version of this paper appeared at the NeurIPS 2023 Workshop: Self-Supervised Learning - Theory and Practice (https://sslneurips23.github.io). The full paper was published (OA) in Knowledge-Based Systems (https://www.sciencedirect.com/science/article/pii/S0950705124012061)

Journal ref Knowledge-Based Systems, 2024, 112572, ISSN 0950-7051

Robustmix: Improving Robustness by Regularizing the Frequency Bias of Deep Nets

Jonas Ngnawe, Marianne Abemgnigni Njifon, Jonathan Heek, Yann Dauphin

Comments 8 pages, 4 figures, 3 tables. Workshop on Distribution Shifts, 36th Conference on Neural Information Processing Systems (NeurIPS 2022). https://openreview.net/forum?id=Na64z0YpOx

Is Distance Matrix Enough for Geometric Deep Learning?

Zian Li, Xiyuan Wang, Yinan Huang, Muhan Zhang

Comments NeurIPS 2023. This new version includes corrections of some minor typos and potentially unclear notations

Convergence of Manifold Filter-Combine Networks

David R. Johnson, Joyce Chew, Siddharth Viswanath, Edward De Brouwer, Deanna Needell, Smita Krishnaswamy, Michael Perlmutter

Comments Accepted to NeurIPS Workshop on Symmetry and Geometry in Neural Representations (Extended Abstract Track)

MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts

Rachel S. Y. Teo, Tan M. Nguyen

Comments 10 pages in the main text. Published at NeurIPS 2024. The code is available at https://github.com/rachtsy/MomentumSMoE

SignAttention: On the Interpretability of Transformer Models for Sign Language Translation

Pedro Alejandro Dal Bianco, Oscar Agustín Stanchi, Facundo Manuel Quiroga, Franco Ronchetti, Enzo Ferrante

Comments Accepted at IAI Workshop @ NeurIPS 2024

ANT: Adaptive Noise Schedule for Time Series Diffusion Models

Seunghan Lee, Kibok Lee, Taeyoung Park

Comments NeurIPS 2024

How Do Training Methods Influence the Utilization of Vision Models?

Paul Gavrikov, Shashank Agnihotri, Margret Keuper, Janis Keuper

Comments Accepted at the Interpretable AI: Past, Present and Future Workshop at NeurIPS 2024

FashionR2R: Texture-preserving Rendered-to-Real Image Translation with Diffusion Models

Rui Hu, Qian He, Gaofeng He, Jiedong Zhuang, Huang Chen, Huafeng Liu, Huamin Wang

Comments Accepted by NeurIPS 2024

Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction

Manuel Brenner, Christoph Jürgen Hemmer, Zahra Monfared, Daniel Durstewitz

Comments 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging

Zhenghao Pan, Haijin Zeng, Jiezhang Cao, Yongyong Chen, Kai Zhang, Yong Xu

Comments NeurIPS 2024

Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysis

Honglin Li, Yunlong Zhang, Pingyi Chen, Zhongyi Shui, Chenglu Zhu, Lin Yang

Comments NeurIPS-2024. arXiv admin note: text overlap with arXiv:2311.12885

Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set

Wenyuan Zhang, Yu-Shen Liu, Zhizhong Han

Comments Accepted by NeurIPS 2024. Project page: https://wen-yuan-zhang.github.io/GS-Pull/

Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust Optimization

Amir Hossein Saberi, Amir Najafi, Ala Emrani, Amin Behjati, Yasaman Zolfimoselo, Mahdi Shadrooy, Abolfazl Motahari, Babak H. Khalaj

Comments Published at Proceedings of Neural Information Processing Systems (NeurIPS) 2024

Learning Metadata-Agnostic Representations for Text-to-SQL In-Context Example Selection

Chuhong Mai, Ro-ee Tal, Thahir Mohamed

Comments Accepted to NeurIPS 2024 Table Representation Learning workshop

Debiasing Large Vision-Language Models by Ablating Protected Attribute Representations

Neale Ratzlaff, Matthew Lyle Olson, Musashi Hinck, Shao-Yen Tseng, Vasudev Lal, Phillip Howard

Comments NeurIPS workshop on SafeGenAI, 10 pages, 2 figures

A Formal Framework for Assessing and Mitigating Emergent Security Risks in Generative AI Models: Bridging Theory and Dynamic Risk Mitigation

Aviral Srivastava, Sourav Panda

Comments This paper was accepted in NeurIPS 2024 workshop on Red Teaming GenAI: What can we learn with Adversaries?

Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification

Haolin Liu, Artin Tajdini, Andrew Wagenmaker, Chen-Yu Wei

Comments NeurIPS 2024

Learning diffusion at lightspeed

Antonio Terpin, Nicolas Lanzetti, Martin Gadea, Florian Dörfler

Comments Accepted for presentation at, and publication in the proceedings of, the 38th Conference on Neural Information Processing Systems (NeurIPS 2024, oral)

TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs

Julia Gastinger, Shenyang Huang, Mikhail Galkin, Erfan Loghmani, Ali Parviz, Farimah Poursafaei, Jacob Danovitch, Emanuele Rossi, Ioannis Koutis, Heiner Stuckenschmidt, Reihaneh Rabbany, Guillaume Rabusseau

Comments 29 pages, 8 figures, 11 tables, accepted at NeurIPS 2024 Track on Datasets and Benchmarks

CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos

Trong-Thuan Nguyen, Pha Nguyen, Xin Li, Jackson Cothren, Alper Yilmaz, Khoa Luu

Comments Accepted to NeurIPS 2024

PertEval: Unveiling Real Knowledge Capacity of LLMs with Knowledge-Invariant Perturbations

Jiatong Li, Renjun Hu, Kunzhe Huang, Yan Zhuang, Qi Liu, Mengxiao Zhu, Xing Shi, Wei Lin

Comments Accepted by NeurIPS '24 D&B Spotlight; 28 pages, 15 figures, 14 tables

Boosting Graph Pooling with Persistent Homology

Chaolong Ying, Xinjian Zhao, Tianshu Yu

Comments Published at NeurIPS 2024

Journal ref Advances in Neural Information Processing Systems, 38 (2024)

Polyhedral Complex Derivation from Piecewise Trilinear Networks

Jin-Hwa Kim

Comments Accepted at NeurIPS 2024. Updated with the camera-ready version