NeurIPS

Diffusion Twigs with Loop Guidance for Conditional Graph Generation

Giangiacomo Mercatali, Yogesh Verma, Andre Freitas, Vikas Garg

Comments NeurIPS 2024. Code is available at https://github.com/Aalto-QuML/Diffusion_twigs

Context-Aware Testing: A New Paradigm for Model Testing with Large Language Models

Paulius Rauba, Nabeel Seedat, Max Ruiz Luyten, Mihaela van der Schaar

Comments Presented at the 38th Conference on Neural Information Processing Systems (NeurIPS 2024). *Rauba & Seedat contributed equally

Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting

Zongjiang Shang, Ling Chen, Binqing wu, Dongliang Cui

Comments Accepted by NeurIPS, 21 pages, and 8 figures

TrAct: Making First-layer Pre-Activations Trainable

Felix Petersen, Christian Borgelt, Stefano Ermon

Comments Published at NeurIPS 2024

Scalable Kernel Inverse Optimization

Youyuan Long, Tolga Ok, Pedro Zattoni Scroccaro, Peyman Mohajerin Esfahani

Comments NeurIPS 2024

Transformers to Predict the Applicability of Symbolic Integration Routines

Rashid Barket, Uzma Shafiq, Matthew England, Juergen Gerhard

Comments 10 pages, 5 figures, to be published in NeurIPS 2024 MATH-AI Workshop

Quantum Deep Equilibrium Models

Philipp Schleich, Marta Skreta, Lasse B. Kristensen, Rodrigo A. Vargas-Hernández, Alán Aspuru-Guzik

Comments To be published in NeurIPS 2024

Robust Sparse Regression with Non-Isotropic Designs

Chih-Hung Liu, Gleb Novikov

Comments NeurIPS 2024; Authors have equal contribution

Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training

Atli Kosson, Bettina Messmer, Martin Jaggi

Comments Accepted to NeurIPS 2024

Text-DiFuse: An Interactive Multi-Modal Image Fusion Framework based on Text-modulated Diffusion Model

Hao Zhang, Lei Cao, Jiayi Ma

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

AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery

Hangyu Zhou, Chia-Hsiang Kao, Cheng Perng Phoo, Utkarsh Mall, Bharath Hariharan, Kavita Bala

Comments Accepted at NeurIPS 2024 Datasets and Benchmarks Track. Code and data available at https://allclear.cs.cornell.edu/

Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?

Zhanke Zhou, Rong Tao, Jianing Zhu, Yiwen Luo, Zengmao Wang, Bo Han

Comments Accepted by NeurIPS 2024

Reasons and Solutions for the Decline in Model Performance after Editing

Xiusheng Huang, Jiaxiang Liu, Yequan Wang, Kang Liu

Comments 14 pages, 8 figures

Journal ref NeurIPS 2024

Graph Neural Networks Uncover Geometric Neural Representations in Reinforcement-Based Motor Learning

Federico Nardi, Jinpei Han, Shlomi Haar, A. Aldo Faisal

Comments 19 pages, 7 figures, accepted at the NeurIPS 2024 workshop on Symmetry and Geometry in Neural Representations (NeurReps 2024)

Neural Model Checking

Mirco Giacobbe, Daniel Kroening, Abhinandan Pal, Michael Tautschnig

Comments To appear in NeurIPS 2024

EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching

Xinwang Chen, Ning Liu, Yichen Zhu, Feifei Feng, Jian Tang

Comments Xinwang Chen and Ning Liu are with equal contributions. This paper has been accepted by NeurIPS 2024

Video Token Merging for Long-form Video Understanding

Seon-Ho Lee, Jue Wang, Zhikang Zhang, David Fan, Xinyu Li

Comments 21 pages, NeurIPS 2024

Journal ref NeurIPS 2024

Using Scenario-Writing for Identifying and Mitigating Impacts of Generative AI

Kimon Kieslich, Nicholas Diakopoulos, Natali Helberger

Comments Publication at NeurIPS'24 workshop Evaluating Evaluations: Examining Best Practices for Measuring Broader Impacts of Generative AI (EvalEval)

Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP

Chen Huang, Skyler Seto, Samira Abnar, David Grangier, Navdeep Jaitly, Josh Susskind

Comments NeurIPS 2024

Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach

Mathilde Caron, Alireza Fathi, Cordelia Schmid, Ahmet Iscen

Comments NeurIPS 2024

Provable Benefit of Cutout and CutMix for Feature Learning

Junsoo Oh, Chulhee Yun

Comments NeurIPS 2024 camera-ready version, 81 pages

Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning

Minghui Chen, Meirui Jiang, Xin Zhang, Qi Dou, Zehua Wang, Xiaoxiao Li

Comments Accepted at NeurIPS 2024

GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring

Dongwoo Lee, Joonkyu Park, Kyoung Mu Lee

Comments Accepted at NeurIPS 2024 Datasets & Benchmarks Track

Recovering Complete Actions for Cross-dataset Skeleton Action Recognition

Hanchao Liu, Yujiang Li, Tai-Jiang Mu, Shi-Min Hu

Comments accepted by NeurIPS 2024

Sample-Efficient Agnostic Boosting

Udaya Ghai, Karan Singh

Comments NeurIPS 2024 camera ready version

Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI

Hadassah Harland, Richard Dazeley, Peter Vamplew, Hashini Senaratne, Bahareh Nakisa, Francisco Cruz

Comments Accepted for the Pluralistic Alignment workshop at NeurIPS 2024

Global Convergence in Training Large-Scale Transformers

Cheng Gao, Yuan Cao, Zihao Li, Yihan He, Mengdi Wang, Han Liu, Jason Matthew Klusowski, Jianqing Fan

Comments to be published in 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

Stabilizing Linear Passive-Aggressive Online Learning with Weighted Reservoir Sampling

Skyler Wu, Fred Lu, Edward Raff, James Holt

Comments To appear in the 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

Disentangling Interpretable Factors with Supervised Independent Subspace Principal Component Analysis

Jiayu Su, David A. Knowles, Raul Rabadan

Comments 10 pages and 6 figures in the main text; To be published in the Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

Simulating User Agents for Embodied Conversational-AI

Daniel Philipov, Vardhan Dongre, Gokhan Tur, Dilek Hakkani-Tür

Comments 8 pages, 5 figures, 4 tables

Journal ref NeurIPS 2024 Workshop on Open-World Agents