PPaperPicks

Philip Torr

University of Oxford, Department of Engineering Science, Oxford, UK

97 papers at tracked venues · 73 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0009-0006-0259-5732 ↗Google Scholar ↗Homepage ↗

Venues

NeurIPS ×23ECCV ×14ICLR ×14ICML ×11CVPR ×10ACL ×7EMNLP ×7AAAI ×4ICCV ×4BMVC ×1MICCAI ×1WACV ×1

Frequent coauthors

Adel Bibi
×25
Jindong Gu
×21
Fabio Pizzati
×8
Bernard Ghanem
×8
Ashkan Khakzar
×6
Aleksandar Petrov
×6
Francesco Pinto
×6
Volker Tresp
×5
Jakob Nicolaus Foerster
×5
Puneet K. Dokania
×5
Fazl Barez
×5
Zhenfei Yin
×4

Papers

  1. An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models (Abstract Reprint)
    AAAI 2026 ·
    Yangchen Pan
    ,
    Junfeng Wen
    ,
    Chenjun Xiao
    , Philip Torr
  2. Behavioral Consistency Validation for LLM Agents: An Analysis of Trading-Style Switching through Stock-Market Simulation
    ACL 2026 ·
    Zeping Li
    ,
    Guancheng Wan
    ,
    Keyang Chen
    ,
    Yu Chen
    ,
    Yiwen Zhao
    , Philip Torr,
    Guangnan Ye
    ,
    Zhenfei Yin
    ,
    Hongfeng Chai
  3. Can Editing LLMs Inject Harm?
    AAAI 2026 ·
    Canyu Chen
    ,
    Baixiang Huang
    ,
    Zekun Li
    ,
    Zhaorun Chen
    ,
    Shiyang Lai
    ,
    Xiongxiao Xu
    ,
    Jia-Chen Gu
    ,
    Jindong Gu
    ,
    Huaxiu Yao
    ,
    Chaowei Xiao
    ,
    Xifeng Yan
    ,
    William Yang Wang
    , Philip Torr,
    Dawn Song
    ,
    Kai Shu
  4. Deep Research Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks
    AAAI 2026 ·
    Haiyuan Wan
    ,
    Chen Yang
    ,
    Junchi Yu
    ,
    Meiqi Tu
    ,
    Jiaxuan Lu
    ,
    Di Yu
    ,
    Jianbao Cao
    ,
    Ben Gao
    ,
    Jiaqing Xie
    ,
    Aoran Wang
    ,
    Wenlong Zhang
    , Philip Torr,
    Dongzhan Zhou
  5. Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning
    ACL 2026 ·
    Zelin Tan
    ,
    Hejia Geng
    ,
    Xiaohang Yu
    ,
    Mulei Zhang
    ,
    Guancheng Wan
    ,
    Yifan Zhou
    ,
    Qiang He
    ,
    Xiangyuan Xue
    ,
    Heng Zhou
    ,
    Yutao Fan
    ,
    Zhong-Zhi Li
    ,
    Zaibin Zhang
    ,
    Guibin Zhang
    ,
    Chen Zhang
    ,
    Zhenfei Yin
    , Philip Torr,
    Lei Bai
  6. AlignGuard: Scalable Safety Alignment for Text-to-Image Generation
    ICCV 2025 ·
    Runtao Liu
    ,
    Chen I Chieh
    ,
    Jindong Gu
    ,
    Jipeng Zhang
    ,
    Renjie Pi
    ,
    Qifeng Chen
    , Philip Torr,
    Ashkan Khakzar
    ,
    Fabio Pizzati
  7. Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models
    ACL 2025 ·
    Kuofeng Gao
    ,
    Shutao Xia
    ,
    Ke Xu
    , Philip Torr,
    Jindong Gu
  8. Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models
    ICLR 2025 ·
    Wenxuan Zhang
    , Philip Torr,
    Mohamed Elhoseiny
    ,
    Adel Bibi
  9. CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents
    ACL 2025 ·
    Tianqi Xu
    ,
    Linyao Chen
    ,
    Dai-Jie Wu
    ,
    Yanjun Chen
    ,
    Zecheng Zhang
    ,
    Xiang Yao
    ,
    Zhiqiang Xie
    ,
    Yongchao Chen
    ,
    Shilong Liu
    ,
    Bochen Qian
    ,
    Anjie Yang
    ,
    Zhaoxuan Jin
    ,
    Jianbo Deng
    , Philip Torr,
    Bernard Ghanem
    ,
    Guohao Li
  10. Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?
    NeurIPS 2025 ·
    Junchi Yu
    ,
    Yujie Liu
    ,
    Jindong Gu
    , Philip H. S. Torr,
    Dongzhan Zhou
  11. Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning?
    WACV 2025 ·
    Shuo Chen
    ,
    Zhen Han
    ,
    Bailan He
    ,
    Jianzhe Liu
    ,
    Mark Buckley
    ,
    Yao Qin
    , Philip Torr,
    Volker Tresp
    ,
    Jindong Gu
  12. Can an Individual Manipulate the Collective Decisions of Multi-Agents?
    EMNLP 2025 ·
    Fengyuan Liu
    ,
    Rui Zhao
    ,
    Shuo Chen
    ,
    Guohao Li
    , Philip Torr,
    Lei Han
    ,
    Jindong Gu
  13. Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Ambiguous Prompts and Unanswerable Questions
    EMNLP 2025 ·
    Hazel Kim
    ,
    Tom A. Lamb
    ,
    Adel Bibi
    , Philip Torr,
    Yarin Gal
  14. Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
    NeurIPS 2025 ·
    Shuang Wu
    ,
    Youtian Lin
    ,
    Feihu Zhang
    ,
    Yifei Zeng
    ,
    Yikang Yang
    ,
    Yajie Bao
    ,
    Jiachen Qian
    ,
    Siyu Zhu
    ,
    Xun Cao
    , Philip H. S. Torr,
    Yao Yao
  15. Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models
    ICLR 2025 ·
    Francisco Eiras
    ,
    Aleksandar Petrov
    , Philip Torr,
    M. Pawan Kumar
    ,
    Adel Bibi
  16. FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models
    CVPR 2025 ·
    Haokun Chen
    ,
    Hang Li
    ,
    Yao Zhang
    ,
    Jinhe Bi
    ,
    Gengyuan Zhang
    ,
    Yueqi Zhang
    , Philip Torr,
    Jindong Gu
    ,
    Denis Krompass
    ,
    Volker Tresp
  17. Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation
    ICML 2025 ·
    Junlin Han
    ,
    Jianyuan Wang
    ,
    Andrea Vedaldi
    , Philip Torr,
    Filippos Kokkinos
  18. Focus On This, Not That! Steering LLMs with Adaptive Feature Specification
    ICML 2025 ·
    Tom A. Lamb
    ,
    Adam Davies
    ,
    Alasdair Paren
    , Philip Torr,
    Francesco Pinto
  19. Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models
    NeurIPS 2025 ·
    Hao Cheng
    ,
    Erjia Xiao
    ,
    Jing Shao
    ,
    Yichi Wang
    ,
    Le Yang
    ,
    Chao Shen
    , Philip H. S. Torr,
    Jindong Gu
    ,
    Renjing Xu
  20. LLM Jailbreak Detection for (Almost) Free!
    EMNLP 2025 ·
    Guorui Chen
    ,
    Yifan Xia
    ,
    Xiaojun Jia
    ,
    Zhijiang Li
    , Philip Torr,
    Jindong Gu
  21. Large Language Models Miss the Multi-agent Mark
    NeurIPS 2025 ·
    Emanuele La Malfa
    ,
    Gabriele La Malfa
    ,
    Samuele Marro
    ,
    Jie M. Zhang
    ,
    Elizabeth Black
    ,
    Michael Luck
    , Philip H. S. Torr,
    Michael J. Wooldridge
  22. Localizing Events in Videos with Multimodal Queries
    CVPR 2025 ·
    Gengyuan Zhang
    ,
    Mang Ling Ada Fok
    ,
    Jialu Ma
    ,
    Yan Xia
    ,
    Daniel Cremers
    , Philip Torr,
    Volker Tresp
    ,
    Jindong Gu
  23. MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents
    NeurIPS 2025 ·
    Lukas Aichberger
    ,
    Alasdair Paren
    ,
    Guohao Li
    , Philip H. S. Torr,
    Yarin Gal
    ,
    Adel Bibi
  24. Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System
    ACL 2025 ·
    Haoyang Su
    ,
    Renqi Chen
    ,
    Shixiang Tang
    ,
    Zhenfei Yin
    ,
    Xinzhe Zheng
    ,
    Jinzhe Li
    ,
    Biqing Qi
    ,
    Qi Wu
    ,
    Hui Li
    ,
    Wanli Ouyang
    , Philip Torr,
    Bowen Zhou
    ,
    Nanqing Dong
  25. MatchDiffusion: Training-Free Generation of Match-Cuts
    ICCV 2025 ·
    Alejandro Pardo
    ,
    Fabio Pizzati
    ,
    Tong Zhang
    ,
    Alexander Pondaven
    , Philip Torr,
    Juan C. Pérez
    ,
    Bernard Ghanem
  26. Measuring what Matters: Construct Validity in Large Language Model Benchmarks
    NeurIPS 2025 ·
    Andrew M. Bean
    ,
    Ryan Othniel Kearns
    ,
    Angelika Romanou
    ,
    Franziska Sofia Hafner
    ,
    Harry Mayne
    ,
    Jan Batzner
    ,
    Negar Foroutan Eghlidi
    ,
    Chris Schmitz
    ,
    Karolina Korgul
    ,
    Hunar Batra
    ,
    Oishi Deb
    ,
    Emma Beharry
    ,
    Cornelius Emde
    ,
    Thomas Foster
    ,
    Anna Gausen
    ,
    María Grandury
    ,
    Sophia Simeng Han
    ,
    Valentin Hofmann
    ,
    Lujain Ibrahim
    ,
    Hazel Kim
    ,
    Hannah Rose Kirk
    ,
    Fangru Lin
    ,
    Gabrielle K. Liu
    ,
    Lennart Luettgau
    ,
    Jabez Magomere
    ,
    Jonathan Rystrøm
    ,
    Anna Sotnikova
    ,
    Yushi Yang
    ,
    Yilun Zhao
    ,
    Adel Bibi
    ,
    Antoine Bosselut
    ,
    Ronald Clark
    ,
    Arman Cohan
    ,
    Jakob N. Foerster
    ,
    Yarin Gal
    ,
    Scott A. Hale
    ,
    Inioluwa Deborah Raji
    ,
    Christopher Summerfield
    , Philip H. S. Torr,
    Cozmin Ududec
    ,
    Luc Rocher
    ,
    Adam Mahdi
  27. Minimalist Concept Erasure in Generative Models
    ICML 2025 ·
    Yang Zhang
    ,
    Er Jin
    ,
    Yanfei Dong
    ,
    Yixuan Wu
    , Philip Torr,
    Ashkan Khakzar
    ,
    Johannes Stegmaier
    ,
    Kenji Kawaguchi
  28. Mixture of Experts Made Intrinsically Interpretable
    ICML 2025 ·
    Xingyi Yang
    ,
    Constantin Venhoff
    ,
    Ashkan Khakzar
    ,
    Christian Schröder de Witt
    ,
    Puneet K. Dokania
    ,
    Adel Bibi
    , Philip Torr
  29. Multimodal Pragmatic Jailbreak on Text-to-image Models
    ACL 2025 ·
    Tong Liu
    ,
    Zhixin Lai
    ,
    Jiawen Wang
    ,
    Gengyuan Zhang
    ,
    Shuo Chen
    , Philip Torr,
    Vera Demberg
    ,
    Volker Tresp
    ,
    Jindong Gu
  30. Olympus: A Universal Task Router for Computer Vision Tasks
    CVPR 2025 ·
    Yuanze Lin
    ,
    Yunsheng Li
    ,
    Dongdong Chen
    ,
    Weijian Xu
    ,
    Ronald Clark
    , Philip Torr
  31. On the Coexistence and Ensembling of Watermarks
    NeurIPS 2025 ·
    Aleksandar Petrov
    ,
    Shruti Agarwal
    , Philip H. S. Torr,
    Adel Bibi
    ,
    John P. Collomosse
  32. Open-World Objectness Modeling Unifies Novel Object Detection
    CVPR 2025 ·
    Shan Zhang
    ,
    Yao Ni
    ,
    Jinhao Du
    ,
    Yuan Xue
    , Philip Torr,
    Piotr Koniusz
    ,
    Anton van den Hengel
  33. PVUW 2025 Challenge Report: Advances in Pixel-level Understanding of Complex Videos in the Wild
    CVPR 2025 ·
    Henghui Ding
    ,
    Chang Liu
    ,
    Nikhila Ravi
    ,
    Shuting He
    ,
    Yunchao Wei
    ,
    Song Bai
    , Philip Torr
  34. Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers
    NeurIPS 2025 ·
    Wei Pang
    ,
    Kevin Qinghong Lin
    ,
    Xiangru Jian
    ,
    Xi He
    , Philip H. S. Torr
  35. PoisonBench: Assessing Language Model Vulnerability to Poisoned Preference Data
    ICML 2025 ·
    Tingchen Fu
    ,
    Mrinank Sharma
    , Philip Torr,
    Shay B. Cohen
    ,
    David Krueger
    ,
    Fazl Barez
  36. Reimagining Safety Alignment with An Image
    EMNLP 2025 ·
    Yifan Xia
    ,
    Guorui Chen
    ,
    Wenqian Yu
    ,
    Zhijiang Li
    , Philip Torr,
    Jindong Gu
  37. Shh, don't say that! Domain Certification in LLMs
    ICLR 2025 ·
    Cornelius Emde
    ,
    Alasdair Paren
    ,
    Preetham Arvind
    ,
    Maxime Guillaume Kayser
    ,
    Tom Rainforth
    ,
    Thomas Lukasiewicz
    , Philip Torr,
    Adel Bibi
  38. Stable Virtual Camera: Generative View Synthesis with Diffusion Models
    ICCV 2025 ·
    Jensen Zhou
    ,
    Hang Gao
    ,
    Vikram Voleti
    ,
    Aaryaman Vasishta
    ,
    Chun-Han Yao
    ,
    Mark Boss
    , Philip Torr,
    Christian Rupprecht
    ,
    Varun Jampani
  39. Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval
    NeurIPS 2025 ·
    Constantin Venhoff
    ,
    Ashkan Khakzar
    ,
    Sonia Joseph
    , Philip H. S. Torr,
    Neel Nanda
  40. Towards Certification of Uncertainty Calibration under Adversarial Attacks
    ICLR 2025 ·
    Cornelius Emde
    ,
    Francesco Pinto
    ,
    Thomas Lukasiewicz
    , Philip Torr,
    Adel Bibi
  41. Towards Interpreting Visual Information Processing in Vision-Language Models
    ICLR 2025 ·
    Clement Neo
    ,
    Luke Ong
    , Philip Torr,
    Mor Geva
    ,
    David Krueger
    ,
    Fazl Barez
  42. Towards Reliable Identification of Diffusion-based Image Manipulations
    NeurIPS 2025 ·
    Alex Costanzino
    ,
    Woody Bayliss
    ,
    Juil Sock
    ,
    Marc Górriz Blanch
    ,
    Danijela Horak
    ,
    Ivan Laptev
    , Philip H. S. Torr,
    Fabio Pizzati
  43. VIKI‑R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning
    NeurIPS 2025 ·
    Li Kang
    ,
    Xiufeng Song
    ,
    Heng Zhou
    ,
    Yiran Qin
    ,
    Jie Yang
    ,
    Xiaohong Liu
    , Philip H. S. Torr,
    Lei Bai
    ,
    Zhenfei Yin
  44. VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory
    ICCV 2025 ·
    Runjia Li
    , Philip Torr,
    Andrea Vedaldi
    ,
    Tomas Jakab
  45. Video Motion Transfer with Diffusion Transformers
    CVPR 2025 ·
    Alexander Pondaven
    ,
    Aliaksandr Siarohin
    ,
    Sergey Tulyakov
    , Philip Torr,
    Fabio Pizzati
  46. Vision-Language Models Do Not Understand Negation
    CVPR 2025 ·
    Kumail Alhamoud
    ,
    Shaden Alshammari
    ,
    Yonglong Tian
    ,
    Guohao Li
    , Philip H. S. Torr,
    Yoon Kim
    ,
    Marzyeh Ghassemi
  47. An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models
    ICLR 2024 ·
    Haochen Luo
    ,
    Jindong Gu
    ,
    Fengyuan Liu
    , Philip Torr
  48. As Firm As Their Foundations: Creating Transferable Adversarial Examples Across Downstream Tasks with CLIP
    BMVC 2024 ·
    Anjun Hu
    ,
    Jindong Gu
    ,
    Francesco Pinto
    ,
    Konstantinos Kamnitsas
    , Philip Torr
  49. CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios
    ECCV 2024 ·
    Qilang Ye
    ,
    Zitong Yu
    ,
    Rui Shao
    ,
    Xinyu Xie
    , Philip Torr,
    Xiaochun Cao
  50. CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor
    CVPR 2024 ·
    Shuyang Sun
    ,
    Runjia Li
    , Philip Torr,
    Xiuye Gu
    ,
    Siyang Li
  51. Can Large Language Model Agents Simulate Human Trust Behavior?
    NeurIPS 2024 ·
    Chengxing Xie
    ,
    Canyu Chen
    ,
    Feiran Jia
    ,
    Ziyu Ye
    ,
    Shiyang Lai
    ,
    Kai Shu
    ,
    Jindong Gu
    ,
    Adel Bibi
    ,
    Ziniu Hu
    ,
    David Jurgens
    ,
    James Evans
    , Philip Torr,
    Bernard Ghanem
    ,
    Guohao Li
  52. Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation
    ICLR 2024 ·
    Wenxuan Zhang
    ,
    Youssef Mohamed
    ,
    Bernard Ghanem
    , Philip Torr,
    Adel Bibi
    ,
    Mohamed Elhoseiny
  53. DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM
    ECCV 2024 ·
    Yixuan Wu
    ,
    Yizhou Wang
    ,
    Shixiang Tang
    ,
    Wenhao Wu
    ,
    Tong He
    ,
    Wanli Ouyang
    , Philip Torr,
    Jian Wu
  54. Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer
    NeurIPS 2024 ·
    Shuang Wu
    ,
    Youtian Lin
    ,
    Yifei Zeng
    ,
    Feihu Zhang
    ,
    Jingxi Xu
    , Philip Torr,
    Xun Cao
    ,
    Yao Yao
  55. Efficient Error Certification for Physics-Informed Neural Networks
    ICML 2024 ·
    Francisco Eiras
    ,
    Adel Bibi
    ,
    Rudy Bunel
    ,
    Krishnamurthy Dj Dvijotham
    , Philip Torr,
    M. Pawan Kumar
  56. Efficient Lifelong Model Evaluation in an Era of Rapid Progress
    NeurIPS 2024 ·
    Ameya Prabhu
    ,
    Vishaal Udandarao
    , Philip Torr,
    Matthias Bethge
    ,
    Adel Bibi
    ,
    Samuel Albanie
  57. Extracting Training Data From Document-Based VQA Models
    ICML 2024 ·
    Francesco Pinto
    ,
    Nathalie Rauschmayr
    ,
    Florian Tramèr
    , Philip Torr,
    Federico Tombari
  58. FedMedICL: Towards Holistic Evaluation of Distribution Shifts in Federated Medical Imaging
    MICCAI 2024 ·
    Kumail Alhamoud
    ,
    Yasir Ghunaim
    ,
    Motasem Alfarra
    ,
    Thomas Hartvigsen
    , Philip Torr,
    Bernard Ghanem
    ,
    Adel Bibi
    ,
    Marzyeh Ghassemi
  59. GaussCtrl: Multi-view Consistent Text-Driven 3D Gaussian Splatting Editing
    ECCV 2024 ·
    Jing Wu
    ,
    Jia-Wang Bian
    ,
    Xinghui Li
    ,
    Guangrun Wang
    ,
    Ian D. Reid
    , Philip Torr,
    Victor Adrian Prisacariu
  60. HelloFresh: LLM Evalutions on Streams of Real-World Human Editorial Actions across X Community Notes and Wikipedia edits
    ACL 2024 ·
    Tim Franzmeyer
    ,
    Aleksandar Shtedritski
    ,
    Samuel Albanie
    , Philip Torr,
    João F. Henriques
    ,
    Jakob N. Foerster
  61. Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models
    NeurIPS 2024 ·
    Arshia Hemmat
    ,
    Adam Davies
    ,
    Tom A. Lamb
    ,
    Jianhao Yuan
    , Philip Torr,
    Ashkan Khakzar
    ,
    Francesco Pinto
  62. Illusory Attacks: Information-theoretic detectability matters in adversarial attacks
    ICLR 2024 ·
    Tim Franzmeyer
    ,
    Stephen Marcus McAleer
    ,
    João F. Henriques
    ,
    Jakob Nicolaus Foerster
    , Philip Torr,
    Adel Bibi
    ,
    Christian Schröder de Witt
  63. Improving Adversarial Transferability via Model Alignment
    ECCV 2024 ·
    Avery Ma
    ,
    Amir-massoud Farahmand
    ,
    Yangchen Pan
    , Philip Torr,
    Jindong Gu
  64. Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
    ICLR 2024 ·
    Kuofeng Gao
    ,
    Yang Bai
    ,
    Jindong Gu
    ,
    Shu-Tao Xia
    , Philip Torr,
    Zhifeng Li
    ,
    Wei Liu
  65. Influencer Backdoor Attack on Semantic Segmentation
    ICLR 2024 ·
    Haoheng Lan
    ,
    Jindong Gu
    , Philip Torr,
    Hengshuang Zhao
  66. Interpreting Learned Feedback Patterns in Large Language Models
    NeurIPS 2024 ·
    Luke Marks
    ,
    Amir Abdullah
    ,
    Clement Neo
    ,
    Rauno Arike
    ,
    David Krueger
    , Philip Torr,
    Fazl Barez
  67. Label Delay in Online Continual Learning
    NeurIPS 2024 ·
    Botos Csaba
    ,
    Wenxuan Zhang
    ,
    Matthias Müller
    ,
    Ser Nam Lim
    , Philip Torr,
    Adel Bibi
  68. Latent Guard: A Safety Framework for Text-to-Image Generation
    ECCV 2024 ·
    Runtao Liu
    ,
    Ashkan Khakzar
    ,
    Jindong Gu
    ,
    Qifeng Chen
    , Philip Torr,
    Fabio Pizzati
  69. Model Merging and Safety Alignment: One Bad Model Spoils the Bunch
    EMNLP 2024 ·
    Hasan Hammoud
    ,
    Umberto Michieli
    ,
    Fabio Pizzati
    , Philip Torr,
    Adel Bibi
    ,
    Bernard Ghanem
    ,
    Mete Ozay
  70. NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning
    AAAI 2024 ·
    Linsheng Chen
    ,
    Guangrun Wang
    ,
    Liuchun Yuan
    ,
    Keze Wang
    ,
    Ken Deng
    , Philip H. S. Torr
  71. No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
    NeurIPS 2024 ·
    Vishaal Udandarao
    ,
    Ameya Prabhu
    ,
    Adhiraj Ghosh
    ,
    Yash Sharma
    , Philip Torr,
    Adel Bibi
    ,
    Samuel Albanie
    ,
    Matthias Bethge
  72. No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages
    EMNLP 2024 ·
    Youssef Mohamed
    ,
    Runjia Li
    ,
    Ibrahim Said Ahmad
    ,
    Kilichbek Haydarov
    , Philip Torr,
    Kenneth Church
    ,
    Mohamed Elhoseiny
  73. Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators
    ICML 2024 ·
    Jianhao Yuan
    ,
    Francesco Pinto
    ,
    Adam Davies
    , Philip Torr
  74. On Pretraining Data Diversity for Self-Supervised Learning
    ECCV 2024 ·
    Hasan Abed Al Kader Hammoud
    ,
    Tuhin Das
    ,
    Fabio Pizzati
    , Philip H. S. Torr,
    Adel Bibi
    ,
    Bernard Ghanem
  75. PVUW 2024 Challenge on Complex Video Understanding: Methods and Results
    ECCV 2024 ·
    Henghui Ding
    ,
    Chang Liu
    ,
    Yunchao Wei
    ,
    Nikhila Ravi
    ,
    Shuting He
    ,
    Song Bai
    , Philip Torr,
    Deshui Miao
    ,
    Xin Li
    ,
    Zhenyu He
    ,
    Yaowei Wang
    ,
    Ming-Hsuan Yang
    ,
    Zhensong Xu
    ,
    Jiangtao Yao
    ,
    Chengjing Wu
    ,
    Ting Liu
    ,
    Luoqi Liu
    ,
    Xinyu Liu
    ,
    Jing Zhang
    ,
    Kexin Zhang
    ,
    Yuting Yang
    ,
    Licheng Jiao
    ,
    Shuyuan Yang
    ,
    Mingqi Gao
    ,
    Jingnan Luo
    ,
    Jinyu Yang
    ,
    Jungong Han
    ,
    Feng Zheng
    ,
    Bin Cao
    ,
    Yisi Zhang
    ,
    Xuanxu Lin
    ,
    Xingjian He
    ,
    Bo Zhao
    ,
    Jing Liu
    ,
    Feiyu Pan
    ,
    Hao Fang
    ,
    Xiankai Lu
  76. Placing Objects in Context via Inpainting for Out-of-Distribution Segmentation
    ECCV 2024 ·
    Pau de Jorge
    ,
    Riccardo Volpi
    ,
    Puneet K. Dokania
    , Philip H. S. Torr,
    Grégory Rogez
  77. Porf: Pose residual field for accurate Neural surface Reconstruction
    ICLR 2024 ·
    Jia-Wang Bian
    ,
    Wenjing Bian
    ,
    Victor Adrian Prisacariu
    , Philip Torr
  78. Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AI
    ICML 2024 ·
    Francisco Eiras
    ,
    Aleksandar Petrov
    ,
    Bertie Vidgen
    ,
    Christian Schröder de Witt
    ,
    Fabio Pizzati
    ,
    Katherine Elkins
    ,
    Supratik Mukhopadhyay
    ,
    Adel Bibi
    ,
    Botos Csaba
    ,
    Fabro Steibel
    ,
    Fazl Barez
    ,
    Genevieve Smith
    ,
    Gianluca Guadagni
    ,
    Jon Chun
    ,
    Jordi Cabot
    ,
    Joseph Marvin Imperial
    ,
    Juan A. Nolazco-Flores
    ,
    Lori Landay
    ,
    Matthew Thomas Jackson
    ,
    Paul Röttger
    , Philip H. S. Torr,
    Trevor Darrell
    ,
    Yong Suk Lee
    ,
    Jakob N. Foerster
  79. Prompting a Pretrained Transformer Can Be a Universal Approximator
    ICML 2024 ·
    Aleksandar Petrov
    , Philip Torr,
    Adel Bibi
  80. RanDumb: Random Representations Outperform Online Continually Learned Representations
    NeurIPS 2024 ·
    Ameya Prabhu
    ,
    Shiven Sinha
    ,
    Ponnurangam Kumaraguru
    , Philip Torr,
    Ozan Sener
    ,
    Puneet K. Dokania
  81. Real-Fake: Effective Training Data Synthesis Through Distribution Matching
    ICLR 2024 ·
    Jianhao Yuan
    ,
    Jie Zhang
    ,
    Shuyang Sun
    , Philip Torr,
    Bo Zhao
  82. RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
    CVPR 2024 ·
    Yufan Chen
    ,
    Jiaming Zhang
    ,
    Kunyu Peng
    ,
    Junwei Zheng
    ,
    Ruiping Liu
    , Philip Torr,
    Rainer Stiefelhagen
  83. Scene-Conditional 3D Object Stylization and Composition
    ECCV 2024 ·
    Jinghao Zhou
    ,
    Tomas Jakab
    , Philip Torr,
    Christian Rupprecht
  84. Secret Collusion among AI Agents: Multi-Agent Deception via Steganography
    NeurIPS 2024 ·
    Sumeet Ramesh Motwani
    ,
    Mikhail Baranchuk
    ,
    Martin Strohmeier
    ,
    Vijay Bolina
    , Philip Torr,
    Lewis Hammond
    ,
    Christian Schröder de Witt
  85. Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation
    ECCV 2024 ·
    Francisco Eiras
    ,
    Kemal Oksuz
    ,
    Adel Bibi
    , Philip H. S. Torr,
    Puneet K. Dokania
  86. Select to Perfect: Imitating desired behavior from large multi-agent data
    ICLR 2024 ·
    Tim Franzmeyer
    ,
    Edith Elkind
    , Philip Torr,
    Jakob Nicolaus Foerster
    ,
    João F. Henriques
  87. Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation
    CVPR 2024 ·
    Hang Li
    ,
    Chengzhi Shen
    , Philip Torr,
    Volker Tresp
    ,
    Jindong Gu
  88. Set-based Neural Network Encoding Without Weight Tying
    NeurIPS 2024 ·
    Bruno Andreis
    ,
    Bedionita Soro
    , Philip H. S. Torr,
    Sung Ju Hwang
  89. Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation
    ICML 2024 ·
    Yibo Yang
    ,
    Xiaojie Li
    ,
    Motasem Alfarra
    ,
    Hasan Abed Al Kader Hammoud
    ,
    Adel Bibi
    , Philip Torr,
    Bernard Ghanem
  90. Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models
    EMNLP 2024 ·
    Michael Lan
    , Philip Torr,
    Fazl Barez
  91. Universal In-Context Approximation By Prompting Fully Recurrent Models
    NeurIPS 2024 ·
    Aleksandar Petrov
    ,
    Tom A. Lamb
    ,
    Alasdair Paren
    , Philip Torr,
    Adel Bibi
  92. VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models
    ECCV 2024 ·
    Junlin Han
    ,
    Filippos Kokkinos
    , Philip Torr
  93. What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
    NeurIPS 2024 ·
    Samyak Jain
    ,
    Ekdeep Singh Lubana
    ,
    Kemal Oksuz
    ,
    Tom Joy
    , Philip Torr,
    Amartya Sanyal
    ,
    Puneet K. Dokania
  94. When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations
    ICLR 2024 ·
    Aleksandar Petrov
    , Philip Torr,
    Adel Bibi
  95. Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution
    ECCV 2024 ·
    Fengyuan Liu
    ,
    Haochen Luo
    ,
    Yiming Li
    , Philip Torr,
    Jindong Gu
  96. WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models
    ECCV 2024 ·
    Zijian He
    ,
    Peixin Chen
    ,
    Guangrun Wang
    ,
    Guanbin Li
    , Philip H. S. Torr,
    Liang Lin
  97. uCAP: An Unsupervised Prompting Method for Vision-Language Models
    ECCV 2024 ·
    A. Tuan Nguyen
    ,
    Kai Sheng Tai
    ,
    Bor-Chun Chen
    ,
    Satya Narayan Shukla
    ,
    Hanchao Yu
    , Philip Torr,
    Tai-Peng Tian
    ,
    Ser-Nam Lim