Philip Torr

Can Editing LLMs Inject Harm? AAAI 2026 Deep Research Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks AAAI 2026 An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models (Abstract Reprint) AAAI 2026 Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning ACL 2026 Mixture of Experts Made Intrinsically Interpretable ICML 2025 Focus On This, Not That! Steering LLMs with Adaptive Feature Specification ICML 2025 Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation ICML 2025 PoisonBench: Assessing Language Model Vulnerability to Poisoned Preference Data ICML 2025 Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models ICLR 2025 Shh, don't say that! Domain Certification in LLMs ICLR 2025 Towards Certification of Uncertainty Calibration under Adversarial Attacks ICLR 2025 Towards Interpreting Visual Information Processing in Vision-Language Models ICLR 2025 Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models ICLR 2025 VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory ICCV 2025 Stable Virtual Camera: Generative View Synthesis with Diffusion Models ICCV 2025 AlignGuard: Scalable Safety Alignment for Text-to-Image Generation ICCV 2025 MatchDiffusion: Training-free Generation of Match-Cuts ICCV 2025 LLM Jailbreak Detection for (Almost) Free! EMNLP 2025 Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Ambiguous Prompts and Unanswerable Questions EMNLP 2025 Can an Individual Manipulate the Collective Decisions of Multi-Agents? EMNLP 2025 Reimagining Safety Alignment with An Image EMNLP 2025 Open-World Objectness Modeling Unifies Novel Object Detection CVPR 2025 FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models CVPR 2025 Video Motion Transfer with Diffusion Transformers CVPR 2025 Olympus: A Universal Task Router for Computer Vision Tasks CVPR 2025 Localizing Events in Videos with Multimodal Queries CVPR 2025 CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents ACL 2025 Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System ACL 2025 Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models ACL 2025 Multimodal Pragmatic Jailbreak on Text-to-image Models ACL 2025 Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning? WACV 2025 Minimalist Concept Erasure in Generative Models ICML 2025 Prompting a Pretrained Transformer Can Be a Universal Approximator ICML 2024 Interpreting Learned Feedback Patterns in Large Language Models NIPS 2024 Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models NIPS 2024 Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer NIPS 2024 HelloFresh: LLM Evalutions on Streams of Real-World Human Editorial Actions across X Community Notes and Wikipedia edits ACL 2024 Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation CVPR 2024 CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor CVPR 2024 RoDLA: Benchmarking the Robustness of Document Layout Analysis Models CVPR 2024 VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models ECCV 2024 CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios ECCV 2024 GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing ECCV 2024 WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models ECCV 2024 Latent Guard: a Safety Framework for Text-to-image Generation ECCV 2024 DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM ECCV 2024 Placing Objects in Context via Inpainting for Out-of-distribution Segmentation ECCV 2024 On Pretraining Data Diversity for Self-Supervised Learning ECCV 2024 Improving Adversarial Transferability via Model Alignment ECCV 2024 Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution ECCV 2024 Scene-Conditional 3D Object Stylization and Composition ECCV 2024 uCAP: An Unsupervised Prompting Method for Vision-Language Models ECCV 2024 Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models EMNLP 2024 No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages EMNLP 2024 Model Merging and Safety Alignment: One Bad Model Spoils the Bunch EMNLP 2024 Illusory Attacks: Information-theoretic detectability matters in adversarial attacks ICLR 2024 Select to Perfect: Imitating desired behavior from large multi-agent data ICLR 2024 An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models ICLR 2024 Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation ICLR 2024 When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations ICLR 2024 PORF: POSE RESIDUAL FIELD FOR ACCURATE NEURAL SURFACE RECONSTRUCTION ICLR 2024 Real-Fake: Effective Training Data Synthesis Through Distribution Matching ICLR 2024 Influencer Backdoor Attack on Semantic Segmentation ICLR 2024 Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images ICLR 2024 Efficient Error Certification for Physics-Informed Neural Networks ICML 2024 Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AI ICML 2024 Extracting Training Data From Document-Based VQA Models ICML 2024 Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation ICML 2024 Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators ICML 2024 FedMedICL: Towards Holistic Evaluation of Distribution Shifts in Federated Medical Imaging MICCAI 2024 How robust is unsupervised representation learning to distribution shift? ICLR 2023 Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning ICLR 2023 IS SYNTHETIC DATA FROM GENERATIVE MODELS READY FOR IMAGE RECOGNITION? ICLR 2023 Language Model Tokenizers Introduce Unfairness Between Languages NIPS 2023 Certifying Ensembles: A General Certification Theory with S-Lipschitzness ICML 2023 Graph Inductive Biases in Transformers without Message Passing ICML 2023 ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation NIPS 2023 Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union NIPS 2023 Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models NIPS 2023 OxfordTVG-HIC: Can Machine Make Humorous Captions from Images? ICCV 2023 KL Guided Domain Adaptation ICLR 2022 Gradient Matching for Domain Generalization ICLR 2022 Amortized Rejection Sampling in Universal Probabilistic Programming AISTATS 2022 Learning Multimodal VAEs through Mutual Supervision ICLR 2022 Make Some Noise: Reliable and Efficient Single-Step Adversarial Training NIPS 2022 Using Mixup as a Regularizer Can Surprisingly Improve Accuracy & Out-of-Distribution Robustness NIPS 2022 Adversarial Masking for Self-Supervised Learning ICML 2022 Communicating via Markov Decision Processes ICML 2022 Structure-Preserving 3D Garment Modeling with Neural Sewing Machines NIPS 2022 FedSR: A Simple and Effective Domain Generalization Method for Federated Learning NIPS 2022 Learn what matters: cross-domain imitation learning with task-relevant embeddings NIPS 2022 Capturing Label Characteristics in VAEs ICLR 2021 You Never Cluster Alone NIPS 2021 A Continuous Mapping For Augmentation Design NIPS 2021 FACMAC: Factored Multi-Agent Centralised Policy Gradients NIPS 2021 Overcoming the Convex Barrier for Simplex Inputs NIPS 2021 Looking Beyond Single Images for Contrastive Semantic Segmentation Learning NIPS 2021 Do Different Tracking Tasks Require Different Appearance Models? NIPS 2021 Progressive Skeletonization: Trimming more fat from a network at initialization ICLR 2021 Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models ICLR 2021 Understanding the effects of data parallelism and sparsity on neural network training ICLR 2021 Scaling the Convex Barrier with Active Sets ICLR 2021 How Benign is Benign Overfitting ? ICLR 2021 Using Hindsight to Anchor Past Knowledge in Continual Learning AAAI 2021 Mirror Descent View for Neural Network Quantization AISTATS 2021 Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation NIPS 2020 Domain-invariant Stereo Matching Networks ECCV 2020 Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection ECCV 2020 Box2Seg: Attention Weighted Loss and Discriminative Feature Learning for Weakly Supervised Segmentation ECCV 2020 Lagrangian Decomposition for Neural Network Verification UAI 2020 Calibrating Deep Neural Networks using Focal Loss NIPS 2020 Continual Learning in Low-rank Orthogonal Subspaces NIPS 2020 STEER : Simple Temporal Regularization For Neural ODE NIPS 2020 Devon: Deformable Volume Network for Learning Optical Flow WACV 2020 Multi-Agent Common Knowledge Reinforcement Learning NIPS 2019 Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models NIPS 2019 Controllable Text-to-Image Generation NIPS 2019 Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model NIPS 2019 SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITY ICLR 2019 Meta-learning with differentiable closed-form solvers ICLR 2019 With Friends Like These, Who Needs Adversaries? NIPS 2018 A Unified View of Piecewise Linear Neural Network Verification NIPS 2018 Deep Fully-Connected Part-Based Models for Human Pose Estimation ACML 2018 Learning Disentangled Representations with Semi-Supervised Deep Generative Models NIPS 2017 Adaptive Neural Compilation NIPS 2016 Learning feed-forward one-shot learners NIPS 2016 An embarrassingly simple approach to zero-shot learning ICML 2015 BING: Binarized Normed Gradients for Objectness Estimation at 300fps CVPR 2014 Higher Order Priors for Joint Intrinsic Image, Objects, and Attributes Estimation NIPS 2013 Learning Anchor Planes for Classification NIPS 2011 Improved Moves for Truncated Convex Models NIPS 2008 An Analysis of Convex Relaxations for MAP Estimation NIPS 2007