Robert Mullins

88 papers A* 8A 2B 4C 1Misc 1Journal 51Unranked 21

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Beyond GEMM-Centric NPUs: Enabling Efficient Diffusion LLM Sampling. CoRR Binglei Lou, Haoran Wu, Yao Lai, Jiayi Nie, Can Xiao, Xuan Guo, Rika Antonova, Robert Mullins, Aaron Zhao
2026	J	`jnl`	CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents. CoRR Hanna Foerster, Robert Mullins, Tom Blanchard, Nicolas Papernot, Kristina Nikolic, Florian Tramèr, Ilia Shumailov, Cheng Zhang, Yiren Zhao
2026	J	`jnl`	Controllable and explainable personality sliders for LLMs at inference time. CoRR Florian Hoppe, David Khachaturov, Robert Mullins, Mark Huasong Meng
2026	J	`jnl`	Deep Kernel Fusion for Transformers. CoRR Zixi Zhang, Zhiwen Mo, Yiren Zhao, Robert Mullins
2026	J	`jnl`	KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware. CoRR Jiayi Nie, Haoran Wu, Yao Lai, Zeyu Cao, Cheng Zhang, Binglei Lou, Erwei Wang, Jianyi Cheng, Timothy M. Jones, Robert Mullins, Rika Antonova, Yiren Zhao
2025	J	`jnl`	"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models. CoRR Isha Gupta, David Khachaturov, Robert Mullins
2025	J	`jnl`	ASPO: Constraint-Aware Bayesian Optimization for FPGA-based Soft Processors. CoRR Haoran Wu, Ce Guo, Wayne Luk, Robert Mullins
2025	J	`jnl`	Adversarial Suffix Filtering: a Defense Pipeline for LLMs. CoRR David Khachaturov, Robert Mullins
2025	A*	`conf`	Architectural Neural Backdoors from First Principles. SP Harry Langford, Ilia Shumailov, Yiren Zhao, Robert Mullins, Nicolas Papernot
2025	B	`conf`	Aspo: Constraint-Aware Bayesian Optimization for Fpga-Based Soft Processors. FPL Haoran Wu, Ce Guo, Wayne Luk, Robert Mullins
2025	J	`jnl`	Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference. CoRR Haoran Wu, Can Xiao, Jiayi Nie, Xuan Guo, Binglei Lou, Jeffrey T. H. Wong, Zhiwen Mo, Cheng Zhang, Przemyslaw Forys, Wayne Luk, Hongxiang Fan, Jianyi Cheng, Timothy M. Jones, Rika Antonova, Robert Mullins, Aaron Zhao
2025	J	`jnl`	Feedback Forensics: A Toolkit to Measure AI Personality. CoRR Arduin Findeis, Timo Kaufmann, Eyke Hüllermeier, Robert Mullins
2025	J	`jnl`	Governments Should Mandate Tiered Anonymity on Social-Media Platforms to Counter Deepfakes and LLM-Driven Mass Misinformation. CoRR David Khachaturov, Roxanne Schnyder, Robert Mullins
2025	A*	`conf`	Inverse Constitutional AI: Compressing Preferences into Principles. ICLR Arduin Findeis, Timo Kaufmann, Eyke Hüllermeier, Samuel Albanie, Robert Mullins
2025	Misc	`conf`	LLM4DV: Using Large Language Models for Hardware Test Stimuli Generation. FCCM Zixi Zhang, Balint Szekely, Pedro Gimenes, Greg Chadwick, Hugo McNally, Jianyi Cheng, Robert Mullins, Yiren Zhao
2025	—	`conf`	Locking Machine Learning Models into Hardware. SaTML Eleanor Clifford, Adhithya Saravanan, Harry Langford, Cheng Zhang, Yiren Zhao, Robert Mullins, Ilia Shumailov, Jamie Hayes
2025	J	`jnl`	Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated. CoRR Hanna Foerster, Ilia Shumailov, Yiren Zhao, Harsh Chaudhari, Jamie Hayes, Robert Mullins, Yarin Gal
2025	J	`jnl`	Watermarking Needs Input Repetition Masking. CoRR David Khachaturov, Robert Mullins, Ilia Shumailov, Sumanth Dathathri
2024	J	`jnl`	Architectural Neural Backdoors from First Principles. CoRR Harry Langford, Ilia Shumailov, Yiren Zhao, Robert Mullins, Nicolas Papernot
2024	A*	`conf`	Beyond Slow Signs in High-fidelity Model Extraction. NeurIPS Hanna Foerster, Robert Mullins, Ilia Shumailov, Jamie Hayes
2024	J	`jnl`	Beyond Slow Signs in High-fidelity Model Extraction. CoRR Hanna Foerster, Robert Mullins, Ilia Shumailov, Jamie Hayes
2024	J	`jnl`	Complexity Matters: Effective Dimensionality as a Measure for Adversarial Robustness. CoRR David Khachaturov, Robert Mullins
2024	—	`conf`	ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks. SaTML Eleanor Clifford, Ilia Shumailov, Yiren Zhao, Ross J. Anderson, Robert Mullins
2024	J	`jnl`	Inverse Constitutional AI: Compressing Preferences into Principles. CoRR Arduin Findeis, Timo Kaufmann, Eyke Hüllermeier, Samuel Albanie, Robert Mullins
2024	J	`jnl`	Locking Machine Learning Models into Hardware. CoRR Eleanor Clifford, Adhithya Saravanan, Harry Langford, Cheng Zhang, Yiren Zhao, Robert Mullins, Ilia Shumailov, Jamie Hayes
2023	A*	`conf`	Architectural Backdoors in Neural Networks. CVPR Mikel Bober-Irizar, Ilia Shumailov, Yiren Zhao, Robert Mullins, Nicolas Papernot
2023	—	`conf`	Dynamic Stashing Quantization for Efficient Transformer Training. EMNLP (Findings) Guo Yang, Daniel Lo, Robert Mullins, Yiren Zhao
2023	J	`jnl`	Dynamic Stashing Quantization for Efficient Transformer Training. CoRR Guo Yang, Daniel Lo, Robert Mullins, Yiren Zhao
2023	J	`jnl`	Human-Producible Adversarial Examples. CoRR David Khachaturov, Yue Gao, Ilia Shumailov, Robert Mullins, Ross J. Anderson, Kassem Fawaz
2023	J	`jnl`	LLM4DV: Using Large Language Models for Hardware Test Stimuli Generation. CoRR Zixi Zhang, Greg Chadwick, Hugo McNally, Yiren Zhao, Robert Mullins
2023	—	`conf`	Revisiting Automated Prompting: Are We Actually Doing Better? ACL (2) Yulin Zhou, Yiren Zhao, Ilia Shumailov, Robert Mullins, Yarin Gal
2023	J	`jnl`	Revisiting Automated Prompting: Are We Actually Doing Better? CoRR Yulin Zhou, Yiren Zhao, Ilia Shumailov, Robert Mullins, Yarin Gal
2023	C	`conf`	Revisiting Structured Dropout. ACML Yiren Zhao, Oluwatomisin Dada, Robert Mullins, Xitong Gao
2022	J	`jnl`	Architectural Backdoors in Neural Networks. CoRR Mikel Bober-Irizar, Ilia Shumailov, Yiren Zhao, Robert Mullins, Nicolas Papernot
2022	J	`jnl`	Augmentation Backdoors. CoRR Joseph Rance, Yiren Zhao, Ilia Shumailov, Robert Mullins
2022	A*	`conf`	DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning. ICML Robert Hönig, Yiren Zhao, Robert Mullins
2022	J	`jnl`	Efficient Adversarial Training With Data Pruning. CoRR Maximilian Kaufmann, Yiren Zhao, Ilia Shumailov, Robert Mullins, Nicolas Papernot
2022	J	`jnl`	ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks. CoRR Eleanor Clifford, Ilia Shumailov, Yiren Zhao, Ross J. Anderson, Robert Mullins
2022	J	`jnl`	Model Architecture Adaption for Bayesian Neural Networks. CoRR Duo Wang, Yiren Zhao, Ilia Shumailov, Robert Mullins
2022	J	`jnl`	Muntjac - Open Source Multicore RV64 Linux-capable SoC. CoRR Xuan Guo, Daniel Bates, Robert Mullins, Alex Bradbury
2022	A*	`conf`	Rapid Model Architecture Adaption for Meta-Learning. NeurIPS Yiren Zhao, Xitong Gao, Ilia Shumailov, Nicolò Fusi, Robert Mullins
2022	J	`jnl`	Revisiting Embeddings for Graph Neural Networks. CoRR Skye Purchase, Aaron Zhao, Robert Mullins
2022	B	`conf`	Trace-and-brace (TAB): bespoke software countermeasures against soft errors. LCTES Yousun Ko, Alex Bradbury, Bernd Burgstaller, Robert Mullins
2021	J	`jnl`	DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning. CoRR Robert Hönig, Yiren Zhao, Robert Mullins
2021	J	`jnl`	Lane Compression: A Lightweight Lossless Compression Method for Machine Learning on Embedded Systems. ACM Trans. Embed. Comput. Syst. Yousun Ko, Alexandra W. Chadwick, Daniel Bates, Robert Mullins
2021	J	`jnl`	Rapid Model Architecture Adaption for Meta-Learning. CoRR Yiren Zhao, Xitong Gao, Ilia Shumailov, Nicolò Fusi, Robert Mullins
2021	A	`conf`	Sponge Examples: Energy-Latency Attacks on Neural Networks. EuroS&P Ilia Shumailov, Yiren Zhao, Daniel Bates, Nicolas Papernot, Robert Mullins, Ross Anderson
2020	J	`jnl`	Accelerate Cycle-Level Full-System Simulation of Multi-Core RISC-V Systems with Binary Translation. CoRR Xuan Guo, Robert Mullins
2020	—	`conf`	Blackbox Attacks on Reinforcement Learning Agents Using Approximated Temporal Information. DSN Workshops Yiren Zhao, Ilia Shumailov, Han Cui, Xitong Gao, Robert Mullins, Ross J. Anderson
2020	J	`jnl`	Learned Low Precision Graph Neural Networks. CoRR Yiren Zhao, Duo Wang, Daniel Bates, Robert Mullins, Mateja Jamnik, Pietro Liò
2020	J	`jnl`	Nudge Attacks on Point-Cloud DNNs. CoRR Yiren Zhao, Ilia Shumailov, Robert Mullins, Ross J. Anderson
2020	J	`jnl`	Probabilistic Dual Network Architecture Search on Graphs. CoRR Yiren Zhao, Duo Wang, Xitong Gao, Robert Mullins, Pietro Liò, Mateja Jamnik
2020	J	`jnl`	Sponge Examples: Energy-Latency Attacks on Neural Networks. CoRR Ilia Shumailov, Yiren Zhao, Daniel Bates, Nicolas Papernot, Robert Mullins, Ross J. Anderson
2020	—	`conf`	Towards Certifiable Adversarial Sample Detection. AISec@CCS Ilia Shumailov, Yiren Zhao, Robert Mullins, Ross J. Anderson
2020	J	`jnl`	Towards Certifiable Adversarial Sample Detection. CoRR Ilia Shumailov, Yiren Zhao, Robert Mullins, Ross J. Anderson
2019	—	`conf`	Automatic Generation of Multi-Precision Multi-Arithmetic CNN Accelerators for FPGAs. FPT Yiren Zhao, Xitong Gao, Xuan Guo, Junyi Liu, Erwei Wang, Robert Mullins, Peter Y. K. Cheung, George A. Constantinides, Cheng-Zhong Xu
2019	J	`jnl`	Automatic Generation of Multi-precision Multi-arithmetic CNN Accelerators for FPGAs. CoRR Yiren Zhao, Xitong Gao, Xuan Guo, Junyi Liu, Erwei Wang, Robert Mullins, Peter Y. K. Cheung, George A. Constantinides, Cheng-Zhong Xu
2019	J	`jnl`	Blackbox Attacks on Reinforcement Learning Agents Using Approximated Temporal Information. CoRR Yiren Zhao, Ilia Shumailov, Han Cui, Xitong Gao, Robert Mullins, Ross J. Anderson
2019	B	`conf`	Characterizing Sources of Ineffectual Computations in Deep Learning Networks. ISPASS Milos Nikolic, Mostafa Mahmoud, Andreas Moshovos, Yiren Zhao, Robert Mullins
2019	—	`conf`	Dynamic Channel Pruning: Feature Boosting and Suppression. ICLR (Poster) Xitong Gao, Yiren Zhao, Lukasz Dudziak, Robert Mullins, Cheng-Zhong Xu
2019	—	`conf`	Efficient Winograd or Cook-Toom Convolution Kernel Implementation on Widely Used Mobile CPUs. EMC2@HPCA/CVPR/ISCA Partha Maji, Andrew Mundy, Ganesh Dasika, Jesse G. Beu, Matthew Mattina, Robert Mullins
2019	J	`jnl`	Efficient Winograd or Cook-Toom Convolution Kernel Implementation on Widely Used Mobile CPUs. CoRR Partha Maji, Andrew Mundy, Ganesh Dasika, Jesse G. Beu, Matthew Mattina, Robert Mullins
2019	J	`jnl`	Efficient and Effective Quantization for Sparse DNNs. CoRR Yiren Zhao, Xitong Gao, Daniel Bates, Robert Mullins, Cheng-Zhong Xu
2019	J	`jnl`	Fast TLB Simulation for RISC-V Systems. CoRR Xuan Guo, Robert Mullins
2019	A*	`conf`	Focused Quantization for Sparse CNNs. NeurIPS Yiren Zhao, Xitong Gao, Daniel Bates, Robert Mullins, Cheng-Zhong Xu
2019	J	`jnl`	Sitatapatra: Blocking the Transfer of Adversarial Samples. CoRR Ilia Shumailov, Xitong Gao, Yiren Zhao, Robert Mullins, Ross Anderson, Cheng-Zhong Xu
2019	—	`conf`	To Compress Or Not To Compress: Understanding The Interactions Between Adversarial Attacks And Neural Network Compression. SysML Yiren Zhao, Ilia Shumailov, Robert Mullins, Ross Anderson
2018	J	`jnl`	Dynamic Channel Pruning: Feature Boosting and Suppression. CoRR Xitong Gao, Yiren Zhao, Lukasz Dudziak, Robert Mullins, Cheng-Zhong Xu
2018	—	`conf`	Mayo: A Framework for Auto-generating Hardware Friendly Deep Neural Networks. EMDL@MobiSys Yiren Zhao, Xitong Gao, Robert Mullins, Chengzhong Xu
2018	J	`jnl`	On the Reduction of Computational Complexity of Deep Convolutional Neural Networks. Entropy Partha Maji, Robert Mullins
2018	J	`jnl`	The Taboo Trap: Behavioural Detection of Adversarial Samples. CoRR Ilia Shumailov, Yiren Zhao, Robert Mullins, Ross Anderson
2018	J	`jnl`	To compress or not to compress: Understanding the Interactions between Adversarial Attacks and Neural Network Compression. CoRR Yiren Zhao, Ilia Shumailov, Robert Mullins, Ross Anderson
2017	—	`conf`	1D-FALCON: Accelerating Deep Convolutional Neural Network Inference by Co-optimization of Models and Underlying Arithmetic Implementation. ICANN (2) Partha Maji, Robert Mullins
2017	—	`conf`	ADaPT: optimizing CNN inference on IoT and mobile devices using approximately separable 1-D kernels. IML Partha Maji, Daniel Bates, Alexandra W. Chadwick, Robert Mullins
2016	J	`jnl`	Configurable memory systems for embedded many-core processors. CoRR Daniel Bates, Alexandra W. Chadwick, Robert Mullins
2016	B	`conf`	Performance implications of transient loop-carried data dependences in automatically parallelized loops. CC Niall Murphy, Timothy M. Jones, Robert Mullins, Simone Campanoni
2015	J	`jnl`	Exploiting Tightly-Coupled Cores. J. Signal Process. Syst. Daniel Bates, Alex Bradbury, Andreas Koltes, Robert Mullins
2013	—	`conf`	Exploiting tightly-coupled cores. ICSAMOS Daniel Bates, Alex Bradbury, Andreas Koltes, Robert Mullins
2008	—	`conf`	A Network of Time-Division Multiplexed Wiring for FPGAs. NOCS Rosemary M. Francis, Simon W. Moore, Robert Mullins
2007	—	`conf`	A Power and Energy Exploration of Network-on-Chip Architectures. NOCS Arnab Banerjee, Robert Mullins, Simon W. Moore
2007	—	`conf`	Demystifying Data-Driven and Pausible Clocking Schemes. ASYNC Robert Mullins, Simon W. Moore
2006	—	`conf`	Minimising Dynamic Power Consumption in On-Chip Networks. SoC Robert Mullins
2006	—	`conf`	The design and implementation of a low-latency on-chip network. ASP-DAC Robert Mullins, Andrew West, Simon W. Moore
2004	A*	`conf`	Low-Latency Virtual-Channel Routers for On-Chip Networks. ISCA Robert Mullins, Andrew West, Simon W. Moore
2003	J	`jnl`	Balanced self-checking asynchronous logic for smart card applications. Microprocess. Microsystems Simon W. Moore, Ross J. Anderson, Robert Mullins, George S. Taylor, Jacques J. A. Fournier
2003	A	`conf`	Security Evaluation of Asynchronous Circuits. CHES Jacques J. A. Fournier, Simon W. Moore, Huiyun Li, Robert Mullins, George S. Taylor
2002	—	`conf`	Improving Smart Card Security Using Self-Timed Circuits. ASYNC Simon W. Moore, Robert Mullins, Paul A. Cunningham, Ross J. Anderson, George S. Taylor
2002	—	`conf`	Point to Point GALS Interconnect. ASYNC George S. Taylor, Simon W. Moore, Robert Mullins, Peter Robinson