Picture for Philip Torr

Philip Torr

PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning

Add code
Oct 11, 2024
Figure 1 for PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning
Figure 2 for PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning
Figure 3 for PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning
Figure 4 for PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning
Viaarxiv icon

Semantic Score Distillation Sampling for Compositional Text-to-3D Generation

Add code
Oct 11, 2024
Figure 1 for Semantic Score Distillation Sampling for Compositional Text-to-3D Generation
Figure 2 for Semantic Score Distillation Sampling for Compositional Text-to-3D Generation
Figure 3 for Semantic Score Distillation Sampling for Compositional Text-to-3D Generation
Figure 4 for Semantic Score Distillation Sampling for Compositional Text-to-3D Generation
Viaarxiv icon

Sparse Autoencoders Reveal Universal Feature Spaces Across Large Language Models

Add code
Oct 09, 2024
Figure 1 for Sparse Autoencoders Reveal Universal Feature Spaces Across Large Language Models
Figure 2 for Sparse Autoencoders Reveal Universal Feature Spaces Across Large Language Models
Figure 3 for Sparse Autoencoders Reveal Universal Feature Spaces Across Large Language Models
Figure 4 for Sparse Autoencoders Reveal Universal Feature Spaces Across Large Language Models
Viaarxiv icon

SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders

Add code
Oct 09, 2024
Figure 1 for SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders
Figure 2 for SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders
Figure 3 for SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders
Figure 4 for SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders
Viaarxiv icon

Towards Interpreting Visual Information Processing in Vision-Language Models

Add code
Oct 09, 2024
Figure 1 for Towards Interpreting Visual Information Processing in Vision-Language Models
Figure 2 for Towards Interpreting Visual Information Processing in Vision-Language Models
Figure 3 for Towards Interpreting Visual Information Processing in Vision-Language Models
Figure 4 for Towards Interpreting Visual Information Processing in Vision-Language Models
Viaarxiv icon

Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap

Add code
Oct 09, 2024
Figure 1 for Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap
Figure 2 for Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap
Figure 3 for Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap
Figure 4 for Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap
Viaarxiv icon

FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models

Add code
Oct 07, 2024
Figure 1 for FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models
Figure 2 for FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models
Figure 3 for FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models
Figure 4 for FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models
Viaarxiv icon

Flex3D: Feed-Forward 3D Generation With Flexible Reconstruction Model And Input View Curation

Add code
Oct 02, 2024
Figure 1 for Flex3D: Feed-Forward 3D Generation With Flexible Reconstruction Model And Input View Curation
Figure 2 for Flex3D: Feed-Forward 3D Generation With Flexible Reconstruction Model And Input View Curation
Figure 3 for Flex3D: Feed-Forward 3D Generation With Flexible Reconstruction Model And Input View Curation
Figure 4 for Flex3D: Feed-Forward 3D Generation With Flexible Reconstruction Model And Input View Curation
Viaarxiv icon

Multimodal Pragmatic Jailbreak on Text-to-image Models

Add code
Sep 27, 2024
Viaarxiv icon

DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer

Add code
Sep 12, 2024
Figure 1 for DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer
Figure 2 for DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer
Figure 3 for DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer
Figure 4 for DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer
Viaarxiv icon