Philip Torr

41

Papers

1,051

Total Citations

Papers (41)

Learning feed-forward one-shot learners

NeurIPS 2016arXiv

Learning Disentangled Representations with Semi-Supervised Deep Generative Models

NeurIPS 2017arXiv

Stable Virtual Camera: Generative View Synthesis with Diffusion Models

Adaptive Neural Compilation

NeurIPS 2016arXiv

Real-Fake: Effective Training Data Synthesis Through Distribution Matching

VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory

PoisonBench: Assessing Language Model Vulnerability to Poisoned Preference Data

Towards Reliable Identification of Diffusion-based Image Manipulations

6402 NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning

MatchDiffusion: Training-free Generation of Match-Cuts

OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?

Domain-invariant Stereo Matching Networks

Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection

Box2Seg: Attention Weighted Loss and Discriminative Feature Learning for Weakly Supervised Segmentation

SafetyDPO: Scalable Safety Alignment for Text-to-Image Generation

A Continuous Mapping For Augmentation Design

You Never Cluster Alone

Make Some Noise: Reliable and Efficient Single-Step Adversarial Training

Using Mixup as a Regularizer Can Surprisingly Improve Accuracy & Out-of-Distribution Robustness

Structure-Preserving 3D Garment Modeling with Neural Sewing Machines

Learn what matters: cross-domain imitation learning with task-relevant embeddings

FedSR: A Simple and Effective Domain Generalization Method for Federated Learning

Language Model Tokenizers Introduce Unfairness Between Languages

Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models

Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union

ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation

An embarrassingly simple approach to zero-shot learning

With Friends Like These, Who Needs Adversaries?

A Unified View of Piecewise Linear Neural Network Verification

Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models

Controllable Text-to-Image Generation

Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model

Multi-Agent Common Knowledge Reinforcement Learning

Continual Learning in Low-rank Orthogonal Subspaces

STEER : Simple Temporal Regularization For Neural ODE

Calibrating Deep Neural Networks using Focal Loss

Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation

Do Different Tracking Tasks Require Different Appearance Models?

NeurIPS 2021arXiv

Looking Beyond Single Images for Contrastive Semantic Segmentation Learning

Overcoming the Convex Barrier for Simplex Inputs

FACMAC: Factored Multi-Agent Centralised Policy Gradients