TILOS at NeurIPS 2024
TILOS members, postdoctoral scholars, and graduate students presented more than two dozen research results at the Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), December 10-15, 2024 in Vancouver, British Columbia, Canada.
- The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof
Derek Lim, Theo Putterman, Robin Walters, Haggai Maron, Stefanie Jegelka - Constrained Diffusion Models via Dual Training
Shervin Khalafi, Dongsheng Ding, Alejandro Ribeiro - SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models
An-Chieh Cheng, Hongxu Yin, Yang Fu, Qiushan Guo, Ruihan Yang, Jan Kautz, Xiaolong Wang, Sifei Liu - Log-concave Sampling from a Convex Body with a Barrier: a Robust and Unified Dikin Walk
Yuzhou Gu, Nikki Lijing Kuang, Yian Ma, Zhao Song, Lichen Zhang - A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data
Adrian Remonda, Nicklas Hansen, Ayoub Raji, Nicola Musiu, Marko Bertogna, Eduardo Veas, Xiaolong Wang - Clustering with Non-adaptive Subset Queries
Hadley Black, Euiwoong Lee, Arya Mazumdar, Barna Saha - Are Graph Neural Networks Optimal Approximation Algorithms?
Morris Yau, Nikolaos Karalias, Eric Lu, Jessica Xu, Stefanie Jegelka - In-Context Symmetries: Self-Supervised Learning through Contextual World Models
Sharut Gupta, Chenyu Wang, Yifei Wang, Tommi Jaakkola, Stefanie Jegelka - Average gradient outer product as a mechanism for deep neural collapse
Daniel Beaglehole, Peter Súkeník, Marco Mondelli, Misha Belkin - A Canonicalization Perspective on Invariant and Equivariant Learning
George Ma, Yifei Wang, Derek Lim, Stefanie Jegelka, Yisen Wang - SEEV: Synthesis with Efficient Exact Verification for ReLU Neural Barrier Functions
Hongchao Zhang, Zhizhen Qin, Sicun Gao, Andrew Clark - On the Computational Landscape of Replicable Learning
Alkis Kalavasis, Amin Karbasi, Grigoris Velegkas, Felix Zhou - Transfer Learning for Latent Variable Network Models
Akhil Jalan, Arya Mazumdar, Soumendu Sundar Mukherjee, Purnamrita Sarkar - Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
Anay Mehrotra, Manolis Zampetakis, Paul Kassianik, Blaine Nelson, Hyrum Anderson, Yaron Singer, Amin Karbasi - Universal Rates for Active Learning
Steve Hanneke, Amin Karbasi, Shay Moran, Grigoris Velegkas - MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model
Minghua Liu, Chong Zeng, Xinyue Wei, Ruoxi Shi, Linghao Chen, Chao Xu, Mengqi Zhang, Zhaoning Wang, Xiaoshuai Zhang, Isabella Liu, Hongzhi Wu, Hao Su - On the Role of Attention Masks and LayerNorm in Transformers
Xinyi Wu, Amir Ajorlou, Yifei Wang, Stefanie Jegelka, Ali Jadbabaie - Length Optimization in Conformal Prediction
Shayan Kiyani, George J. Pappas, Hamed Hassani - Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference
Xunpeng Huang, Difan Zou, Hanze Dong, Zhang, Yian Ma, Tong Zhang - TSDS: Data Selection for Task-Specific Model Finetuning
Zifan Liu, Amin Karbasi, Theodoros Rekatsinas - JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko, Francesco Croce, Vikash Sehwag, Edgar Dobriban, Nicolas Flammarion, George J. Pappas, Florian Tramer, Hamed Hassani, Eric Wong - A Theoretical Understanding of Self-Correction through In-context Alignment
Yifei Wang, Yuyang Wu, Zeming Wei, Stefanie Jegelka, Yisen Wang - Understanding the Role of Equivariance in Self-supervised Learning
Yifei Wang, Kaiwen Hu, Sharut Gupta, Ziyu Ye, Yisen Wang, Stefanie Jegelka - First-Order Methods for Linearly Constrained Bilevel Optimization
Guy Kornowski, Swati Padmanabhan, Kai Wang, Zhe Zhang, Suvrit Sra - Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models
Alkis Kalavasis, Amin Karbasi, Argyris Oikonomou, Katerina Sotiraki, Grigoris Velegkas, Manolis Zampetakis