Jailbreak Defense in a Narrow Domain: Limitations of Existing Methods and a New Transcript-Classifier Approach

Authors: Wang, Tony T., Hughes, John, Sleight, Henry, Schaeffer, Rylan, Agrawal, Rajashree, Barez, Fazl, Sharma, Mrinank, Mu, Jesse, Shavit, Nir, Perez, Ethan

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Cryptography and Security

Access URL: http://arxiv.org/abs/2412.02159

AGENTiGraph: An Interactive Knowledge Graph Platform for LLM-based Chatbots Utilizing Private Data

Authors: Zhao, Xinjie, Blum, Moritz, Yang, Rui, Yang, Boming, Carpintero, Luis Márquez, Pina-Navarro, Mónica, Wang, Tony, Li, Xin, Li, Huitao, Fu, Yanran, Wang, Rongrong, Zhang, Juntao, Li, Irene

Subject Terms: Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2410.11531

Understanding #vent Channels on Discord

Authors: Oladeji, Kayode, Wang, Tony, Yang, Diyi, Bruckman, Amy

Subject Terms: Computer Science - Social and Information Networks, Computer Science - Human-Computer Interaction

Access URL: http://arxiv.org/abs/2409.19166

Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation

Authors: Halawi, Danny, Wei, Alexander, Wallace, Eric, Wang, Tony T., Haghtalab, Nika, Steinhardt, Jacob

Subject Terms: Computer Science - Cryptography and Security, Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2406.20053

Can Go AIs be adversarially robust?

Authors: Tseng, Tom, McLean, Euan, Pelrine, Kellin, Wang, Tony T., Gleave, Adam

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2406.12843

3D Holistic OR Anonymization

Authors: Wang, Tony Danjun

Subject Terms: Computer Science - Computer Vision and Pattern Recognition, J.0

Access URL: http://arxiv.org/abs/2405.05261

Forbidden Facts: An Investigation of Competing Objectives in Llama-2

Authors: Wang, Tony T., Wang, Miles, Hariharan, Kaivalya, Shavit, Nir

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Cryptography and Security

Access URL: http://arxiv.org/abs/2312.08793

A PTAS for $\ell_0$-Low Rank Approximation: Solving Dense CSPs over Reals

Authors: Cohen-Addad, Vincent, Fan, Chenglin, Ghoshal, Suprovat, Lee, Euiwoong, de Mesmay, Arnaud, Newman, Alantha, Wang, Tony Chang

Subject Terms: Computer Science - Data Structures and Algorithms

Access URL: http://arxiv.org/abs/2311.00892

A Tetherless Microdriller for Maneuverability and On-Board Cargo Delivery Inside Viscoelastic Media

Authors: Wang, Tony, Yang, Daasol, Chen, Jiehao, Chow, Jocelyn, Hu, Yuhang, Hoang, Kimberly, Ansari, Azadeh

Source: 2022 International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS) Manipulation, Automation and Robotics at Small Scales (MARSS), 2022 International Conference on. :1-6 Jul, 2022

Relation: 2022 International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS)

Field Testing of a Stochastic Planner for ASV Navigation Using Satellite Images

Authors: Huang, Philip, Wang, Tony, Shkurti, Florian, Barfoot, Timothy D.

Subject Terms: Computer Science - Robotics

Access URL: http://arxiv.org/abs/2309.14657

CrossTalk: Intelligent Substrates for Language-Oriented Interaction in Video-Based Communication and Collaboration

Authors: Xia, Haijun, Wang, Tony, Gunturu, Aditya, Jiang, Peiling, Duan, William, Yao, Xiaoshuo

Subject Terms: Computer Science - Human-Computer Interaction, Computer Science - Artificial Intelligence, Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2308.03311

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

Authors: Casper, Stephen, Davies, Xander, Shi, Claudia, Gilbert, Thomas Krendl, Scheurer, Jérémy, Rando, Javier, Freedman, Rachel, Korbak, Tomasz, Lindner, David, Freire, Pedro, Wang, Tony, Marks, Samuel, Segerie, Charbel-Raphaël, Carroll, Micah, Peng, Andi, Christoffersen, Phillip, Damani, Mehul, Slocum, Stewart, Anwar, Usman, Siththaranjan, Anand, Nadeau, Max, Michaud, Eric J., Pfau, Jacob, Krasheninnikov, Dmitrii, Chen, Xin, Langosco, Lauro, Hase, Peter, Bıyık, Erdem, Dragan, Anca, Krueger, David, Sadigh, Dorsa, Hadfield-Menell, Dylan

Subject Terms: Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2307.15217

DisguisOR: Holistic Face Anonymization for the Operating Room

Authors: Bastian, Lennart, Wang, Tony Danjun, Czempiel, Tobias, Busam, Benjamin, Navab, Nassir

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2307.14241

Cliff-Learning

Authors: Wang, Tony T., Zablotchi, Igor, Shavit, Nir, Rosenfeld, Jonathan S.

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2302.07348

SDP Methods for Sensitivity-Constrained Privacy Funnel and Information Bottleneck Problems

Authors: Bu, Yuheng, Wang, Tony, Wornell, Gregory W.

Source: 2021 IEEE International Symposium on Information Theory (ISIT) Information Theory (ISIT), 2021 IEEE International Symposium on. :49-54 Jul, 2021

Relation: 2021 IEEE International Symposium on Information Theory (ISIT)

Characterizations for 25G/100G High Speed Fiber Optical Communication Applications with Hermetic eWLB (Embedded Wafer Level Ball Grid Array) Technology

Authors: Hsieh, Ming-Che, Bong, Yin-Yen, Huang, Li-Xia, Fang, Ching-Meng, Yong, Tack-Chee, Bai, Bryan, Wang, Tony, Yuan, Zhi-Lu, Li, Yun-Xia

Source: 2021 IEEE 71st Electronic Components and Technology Conference (ECTC) ECTC Electronic Components and Technology Conference (ECTC), 2021 IEEE 71st. :1701-1706 Jun, 2021

Relation: 2021 IEEE 71st Electronic Components and Technology Conference (ECTC)

Adversarial Policies Beat Superhuman Go AIs

Authors: Wang, Tony T., Gleave, Adam, Tseng, Tom, Pelrine, Kellin, Belrose, Nora, Miller, Joseph, Dennis, Michael D., Duan, Yawen, Pogrebniak, Viktor, Levine, Sergey, Russell, Stuart

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Cryptography and Security, Statistics - Machine Learning, I.2.6

Access URL: http://arxiv.org/abs/2211.00241

Ocular manifestations secondary to cocaine abuse

Authors: Rickels, Kaersti L. ^a, Ghaleb, Ramsey ^a, Elhusseiny, Abdelrahman M. ^a, Chauhan, Muhammad Z. ^a, Toma, Joseph ^{a, b}, Wang, Tony ^a, Cheng, Daniel ^a, Ali, Asim ^c, Sallam, Ahmed B. ^{a, b, ⁎}

Source: In Survey of Ophthalmology February 2025

Magnetically-Actuated Micro-Scale Bristle-Bots

Authors: Kim, DeaGyu, Hao, Zhijian, Wang, Tony H., Ansari, Azadeh

Source: 2020 International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS) Manipulation, Automation and Robotics at Small Scales (MARSS), 2020 International Conference on. :1-6 Jul, 2020

Relation: 2020 International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS)

Remiod: Reference-based Controlled Multiple Imputation of Longitudinal Binary and Ordinal Outcomes with non-ignorable missingness

Authors: Wang, Tony, Liu, Ying

Subject Terms: Statistics - Methodology, Statistics - Applications, Statistics - Computation

Access URL: http://arxiv.org/abs/2203.02771