Picture for Philip Torr

Philip Torr

Interpreting Reward Models in RLHF-Tuned Language Models Using Sparse Autoencoders

Add code
Oct 12, 2023
Viaarxiv icon

PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction

Oct 12, 2023
Figure 1 for PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction
Figure 2 for PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction
Figure 3 for PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction
Figure 4 for PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction
Viaarxiv icon

AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments

Oct 10, 2023
Figure 1 for AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments
Figure 2 for AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments
Figure 3 for AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments
Figure 4 for AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments
Viaarxiv icon

Exploring Non-additive Randomness on ViT against Query-Based Black-Box Attacks

Sep 12, 2023
Viaarxiv icon

Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants

Add code
Aug 03, 2023
Figure 1 for Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants
Figure 2 for Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants
Figure 3 for Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants
Figure 4 for Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants
Viaarxiv icon

A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models

Add code
Jul 24, 2023
Viaarxiv icon

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

Jul 21, 2023
Figure 1 for OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?
Figure 2 for OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?
Figure 3 for OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?
Figure 4 for OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?
Viaarxiv icon

ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation

Add code
Jun 29, 2023
Figure 1 for ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation
Figure 2 for ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation
Figure 3 for ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation
Figure 4 for ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation
Viaarxiv icon

Reliable Evaluation of Adversarial Transferability

Add code
Jun 14, 2023
Figure 1 for Reliable Evaluation of Adversarial Transferability
Figure 2 for Reliable Evaluation of Adversarial Transferability
Figure 3 for Reliable Evaluation of Adversarial Transferability
Figure 4 for Reliable Evaluation of Adversarial Transferability
Viaarxiv icon

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

Add code
Jun 11, 2023
Figure 1 for Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models
Figure 2 for Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models
Figure 3 for Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models
Figure 4 for Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models
Viaarxiv icon