NeurIPS

Evolution of SAE Features Across Layers in LLMs

Daniel Balcells, Benjamin Lerner, Michael Oesterle, Ediz Ucar, Stefan Heimersheim

Comments Presented at the Attributing Model Behavior at Scale (ATTRIB) workshop at NeurIPS 2024

Sm: enhanced localization in Multiple Instance Learning for medical imaging classification

Francisco M. Castro-Macías, Pablo Morales-Álvarez, Yunan Wu, Rafael Molina, Aggelos K. Katsaggelos

Comments 24 pages, 14 figures, 2024 Conference on Neural Information Processing Systems (NeurIPS 2024)

Characterizing stable regions in the residual stream of LLMs

Jett Janiak, Jacek Karwowski, Chatrik Singh Mangat, Giorgi Giglemiani, Nora Petrova, Stefan Heimersheim

Comments Presented at the Scientific Methods for Understanding Deep Learning (SciForDL) workshop at NeurIPS 2024

Evaluating Synthetic Activations composed of SAE Latents in GPT-2

Giorgi Giglemiani, Nora Petrova, Chatrik Singh Mangat, Jett Janiak, Stefan Heimersheim

Comments Presented at the Attributing Model Behavior at Scale (ATTRIB) workshop at NeurIPS 2024

You can remove GPT2's LayerNorm by fine-tuning

Stefan Heimersheim

Comments Presented at the Attributing Model Behavior at Scale (ATTRIB) and Interpretable AI: Past, Present, and Future workshops at NeurIPS 2024

Multi-modal Situated Reasoning in 3D Scenes

Xiongkun Linghu, Jiangyong Huang, Xuesong Niu, Xiaojian Ma, Baoxiong Jia, Siyuan Huang

Comments Accepted by NeurIPS 2024 Datasets and Benchmarks Track. Project page: https://msr3d.github.io/

IQA-EVAL: Automatic Evaluation of Human-Model Interactive Question Answering

Ruosen Li, Ruochen Li, Barry Wang, Xinya Du

Comments Accepted by NeurIPS 2024

Modulating Language Model Experiences through Frictions

Katherine M. Collins, Valerie Chen, Ilia Sucholutsky, Hannah Rose Kirk, Malak Sadek, Holli Sargeant, Ameet Talwalkar, Adrian Weller, Umang Bhatt

Comments NeurIPS Workshop on Behavioral ML; non-archival

UQE: A Query Engine for Unstructured Databases

Hanjun Dai, Bethany Yixin Wang, Xingchen Wan, Bo Dai, Sherry Yang, Azade Nova, Pengcheng Yin, Phitchaya Mangpo Phothilimthana, Charles Sutton, Dale Schuurmans

Journal ref NeurIPS 2024

Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs

Sukmin Yun, Haokun Lin, Rusiru Thushara, Mohammad Qazim Bhat, Yongxin Wang, Zutao Jiang, Mingkai Deng, Jinhong Wang, Tianhua Tao, Junbo Li, Haonan Li, Preslav Nakov, Timothy Baldwin, Zhengzhong Liu, Eric P. Xing, Xiaodan Liang, Zhiqiang Shen

Comments NeurIPS 2024 Datasets and Benchmarks Camera-ready Version. Website at https://mbzuai-llm.github.io/webpage2code/

Efficient Large Multi-modal Models via Visual Context Compression

Jieneng Chen, Luoxin Ye, Ju He, Zhao-Yang Wang, Daniel Khashabi, Alan Yuille

Comments NeurIPS 2024 Camera Ready; Code is available at https://github.com/Beckschen/LLaVolta

Investigating Annotator Bias in Large Language Models for Hate Speech Detection

Amit Das, Zheng Zhang, Najib Hasan, Souvika Sarkar, Fatemeh Jamshidi, Tathagata Bhattacharya, Mostafa Rahgouy, Nilanjana Raychawdhary, Dongji Feng, Vinija Jain, Aman Chadha, Mary Sandage, Lauramarie Pope, Gerry Dozier, Cheryl Seals

Comments Accepted at NeurIPS Safe Generative AI Workshop, 2024

MV2Cyl: Reconstructing 3D Extrusion Cylinders from Multi-View Images

Eunji Hong, Minh Hieu Nguyen, Mikaela Angelina Uy, Minhyuk Sung

Comments NeurIPS 2024. Project page: http://mv2cyl.github.io

Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning

Jaehyun Nam, Kyuyoung Kim, Seunghyuk Oh, Jihoon Tack, Jaehyung Kim, Jinwoo Shin

Comments NeurIPS 2024

BertaQA: How Much Do Language Models Know About Local Culture?

Julen Etxaniz, Gorka Azkune, Aitor Soroa, Oier Lopez de Lacalle, Mikel Artetxe

Comments NEURIPS Datasets & Benchmarks 2024

Lookback Prophet Inequalities

Ziyad Benomar, Dorian Baudry, Vianney Perchet

Comments Accepted as a conference paper at NeurIPS 2024

MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models

Zichun Yu, Spandan Das, Chenyan Xiong

Comments Accepted to NeurIPS 2024

Learning-Augmented Priority Queues

Ziyad Benomar, Christian Coester

Comments Accepted as a conference paper at NeurIPS 2024

ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search

Dan Zhang, Sining Zhoubian, Ziniu Hu, Yisong Yue, Yuxiao Dong, Jie Tang

Comments Accepted to NeurIPS 2024

Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching

Xinyin Ma, Gongfan Fang, Michael Bi Mi, Xinchao Wang

Comments Accepted at NeurIPS 2024

Leveraging partial stragglers within gradient coding

Aditya Ramamoorthy, Ruoyu Meng, Vrinda S. Girimaji

Comments 12 pages, 7 figures

Journal ref NeurIPS 2024 (Main Conference)

Verifiably Robust Conformal Prediction

Linus Jeary, Tom Kuipers, Mehran Hosseini, Nicola Paoletti

Comments Accepted at NeurIPS 2024

A Theoretical Understanding of Self-Correction through In-context Alignment

Yifei Wang, Yuyang Wu, Zeming Wei, Stefanie Jegelka, Yisen Wang

Comments Accepted at NeurIPS 2024

Exploring Context Window of Large Language Models via Decomposed Positional Vectors

Zican Dong, Junyi Li, Xin Men, Wayne Xin Zhao, Bingbing Wang, Zhen Tian, Weipeng Chen, Ji-Rong Wen

Comments Accepted by Neurips 2024 as a spotlight

Integrating GNN and Neural ODEs for Estimating Non-Reciprocal Two-Body Interactions in Mixed-Species Collective Motion

Masahito Uwamichi, Simon K. Schnyder, Tetsuya J. Kobayashi, Satoshi Sawai

Comments Accepted at NeurIPS 2024. Some contents are omitted due to arXiv's storage limit. Please refer to the full paper at OpenReview (NeurIPS 2024) or https://github.com/MasahitoUWAMICHI/collectiveMotionNN

SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion

Lu Han, Xu-Yang Chen, Han-Jia Ye, De-Chuan Zhan

Comments Accepted by NeurIPS 2024

When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback

Leon Lang, Davis Foote, Stuart Russell, Anca Dragan, Erik Jenner, Scott Emmons

Comments Advances in Neural Information Processing Systems 37 (NeurIPS 2024)

SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models

Dan Zhang, Ziniu Hu, Sining Zhoubian, Zhengxiao Du, Kaiyu Yang, Zihan Wang, Yisong Yue, Yuxiao Dong, Jie Tang

Comments Accepted to NeurIPS D&B Track 2024

Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression

Deqing Fu, Tian-Qi Chen, Robin Jia, Vatsal Sharan

Comments Accepted to NeurIPS 2024

Addressing Bias in Online Selection with Limited Budget of Comparisons

Ziyad Benomar, Evgenii Chzhen, Nicolas Schreuder, Vianney Perchet

Comments Accepted as a conference paper at NeurIPS 2024