Philip Torr

11 papers University of Oxford

• Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?
• Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
• Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models
• Large Language Models Miss the Multi-agent Mark
• MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents
• Measuring what Matters: Construct Validity in Large Language Model Benchmarks
• On the Coexistence and Ensembling of Watermarks
• Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers
• Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval
• Towards Reliable Identification of Diffusion-based Image Manipulations
• VIKI‑R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning