AI.info
Philip Torr
Explore Philip Torr on AI.info.
- PaperDoctor: Evidence-Grounded and Actionable Feedback for Scientific Papers in Progress
- VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
- Multimodal Model Diffing for Feature Discovery and Control
- Adversarial Fast-Moving Real-World Domains as Test Beds for Benchmarking AI Scientist Capabilities
- Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories
- Code2World: A GUI World Model via Renderable Code Generation
- Reliable and Responsible Foundation Models: A Comprehensive Survey
- Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models
- Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge
- VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?
- Permission Manifests for Web Agents
- EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing
- Computer-Use Agents as Judges for Generative User Interface
- VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation
- Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?
- LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference