NeurIPS

Large Language Model Unlearning via Embedding-Corrupted Prompts

Chris Yuhao Liu, Yaxuan Wang, Jeffrey Flanigan, Yang Liu

Comments NeurIPS 2024 Poster

LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages

Andrew M. Bean, Simi Hellsten, Harry Mayne, Jabez Magomere, Ethan A. Chi, Ryan Chi, Scott A. Hale, Hannah Rose Kirk

Comments Oral presentation at NeurIPS 2024 Datasets and Benchmarks Track. 10 pages, 5 figures, 22 pages supplemental materials

Binarized Diffusion Model for Image Super-Resolution

Zheng Chen, Haotong Qin, Yong Guo, Xiongfei Su, Xin Yuan, Linghe Kong, Yulun Zhang

Comments Accepted to NeurIPS 2024. Code is available at https://github.com/zhengchen1999/BI-DiffSR

Progressive Entropic Optimal Transport Solvers

Parnian Kassraie, Aram-Alexandre Pooladian, Michal Klein, James Thornton, Jonathan Niles-Weed, Marco Cuturi

Comments In proceedings of the 38th conference on Advances in Neural Information Processing Systems (NeurIPs), 23 pages, 14 figures

BERTs are Generative In-Context Learners

David Samuel

Comments 26 pages, NeurIPS 2024

ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization

Luca Eyring, Shyamgopal Karthik, Karsten Roth, Alexey Dosovitskiy, Zeynep Akata

Comments NeurIPS 2024

LoFiT: Localized Fine-tuning on LLM Representations

Fangcong Yin, Xi Ye, Greg Durrett

Comments NeurIPS 2024 Camera Ready

What makes unlearning hard and what to do about it

Kairan Zhao, Meghdad Kurmanji, George-Octavian Bărbulescu, Eleni Triantafillou, Peter Triantafillou

Comments Accepted at NeurIPS 2024

Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation

Wooseong Cho, Taehyun Hwang, Joongkyu Lee, Min-hwan Oh

Comments Accepted in NeurIPS 2024

Bayesian Online Natural Gradient (BONG)

Matt Jones, Peter Chang, Kevin Murphy

Comments Final NeurIPS version, updated in response to reviews. 43 pages, 13 figures

Journal ref NeurIPS 2024

Preference Learning Algorithms Do Not Learn Preference Rankings

Angelica Chen, Sadhika Malladi, Lily H. Zhang, Xinyi Chen, Qiuyi Zhang, Rajesh Ranganath, Kyunghyun Cho

Comments NeurIPS 2024 camera-ready

An engine not a camera: Measuring performative power of online search

Celestine Mendler-Dünner, Gabriele Carovano, Moritz Hardt

Comments to appear at NeurIPS 2024

Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass

Ethan Shen, Alan Fan, Sarah M. Pratt, Jae Sung Park, Matthew Wallingford, Sham M. Kakade, Ari Holtzman, Ranjay Krishna, Ali Farhadi, Aditya Kusupati

Comments 23 pages, 16 figures, accepted at NeurIPS 2024

TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation

Chenyang Le, Yao Qian, Dongmei Wang, Long Zhou, Shujie Liu, Xiaofei Wang, Midia Yousefi, Yanmin Qian, Jinyu Li, Sheng Zhao, Michael Zeng

Comments Neural Information Processing Systems, poster

Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models

ShengYun Peng, Pin-Yu Chen, Matthew Hull, Duen Horng Chau

Comments NeurIPS'24

Efficient multi-prompt evaluation of LLMs

Felipe Maia Polo, Ronald Xu, Lucas Weber, Mírian Silva, Onkar Bhardwaj, Leshem Choshen, Allysson Flavio Melo de Oliveira, Yuekai Sun, Mikhail Yurochkin

Comments NeurIPS 2024

iVideoGPT: Interactive VideoGPTs are Scalable World Models

Jialong Wu, Shaofeng Yin, Ningya Feng, Xu He, Dong Li, Jianye Hao, Mingsheng Long

Comments NeurIPS 2024. Code is available at project website: https://thuml.github.io/iVideoGPT

Parameter-free Clipped Gradient Descent Meets Polyak

Yuki Takezawa, Han Bao, Ryoma Sato, Kenta Niwa, Makoto Yamada

Comments NeurIPS 2024

Linking In-context Learning in Transformers to Human Episodic Memory

Li Ji-An, Corey Y. Zhou, Marcus K. Benna, Marcelo G. Mattar

Comments NeurIPS 2024

Fisher Flow Matching for Generative Modeling over Discrete Data

Oscar Davis, Samuel Kessler, Mircea Petrache, İsmail İlkan Ceylan, Michael Bronstein, Avishek Joey Bose

Comments NeurIPS 2024

Representation Noising: A Defence Mechanism Against Harmful Finetuning

Domenic Rosati, Jan Wehner, Kai Williams, Łukasz Bartoszcze, David Atanasov, Robie Gonzales, Subhabrata Majumdar, Carsten Maple, Hassan Sajjad, Frank Rudzicz

Comments Published in NeurIPs 2024

Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning

Otmane Sakhi, Imad Aouali, Pierre Alquier, Nicolas Chopin

Comments NeuRIPS '24 Spotlight

Deterministic Policies for Constrained Reinforcement Learning in Polynomial Time

Jeremy McMahan

Comments Appearing at Neurips 2024

Sample-Efficient Constrained Reinforcement Learning with General Parameterization

Washim Uddin Mondal, Vaneet Aggarwal

Journal ref NeurIPS 2024

PhyRecon: Physically Plausible Neural Scene Reconstruction

Junfeng Ni, Yixin Chen, Bohan Jing, Nan Jiang, Bin Wang, Bo Dai, Puhao Li, Yixin Zhu, Song-Chun Zhu, Siyuan Huang

Comments NeurIPS'24. Project page: https://phyrecon.github.io/

PuLID: Pure and Lightning ID Customization via Contrastive Alignment

Zinan Guo, Yanze Wu, Zhuowei Chen, Lang Chen, Peng Zhang, Qian He

Comments NeurIPS 2024. Codes and models are available at https://github.com/ToTheBeginning/PuLID

MoVA: Adapting Mixture of Vision Experts to Multimodal Context

Zhuofan Zong, Bingqi Ma, Dazhong Shen, Guanglu Song, Hao Shao, Dongzhi Jiang, Hongsheng Li, Yu Liu

Comments NeurIPS 2024

VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time

Sicheng Xu, Guojun Chen, Yu-Xiao Guo, Jiaolong Yang, Chong Li, Zhenyu Zang, Yizhong Zhang, Xin Tong, Baining Guo

Comments NeurIPS 2024 (Oral) Camera ready. Project webpage: https://www.microsoft.com/en-us/research/project/vasa-1/

Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2)

Michael Saxon, Fatima Jahara, Mahsa Khoshnoodi, Yujie Lu, Aditya Sharma, William Yang Wang

Comments NeurIPS 2024 Spotlight

GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling

Bowen Zhang, Yiji Cheng, Jiaolong Yang, Chunyu Wang, Feng Zhao, Yansong Tang, Dong Chen, Baining Guo

Comments NIPS 2024 camera-ready version; Project page: https://gaussiancube.github.io/