Philip Torr
6 papers · Latest:
ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation
ActCam enables zero-shot joint 3D motion and camera control for video generation, improving fidelity and camera adherence with staged guidance.
StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
StraTA introduces strategic trajectory abstraction to agentic RL, improving LLM performance in long-horizon tasks by enhancing exploration and credit assignment.
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
This paper introduces a "levels x laws" taxonomy for agentic world models, synthesizing over 400 works and outlining a roadmap for future development.
LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning
LongCoT is a new benchmark with 2,500 expert-designed problems to measure long-horizon chain-of-thought reasoning in frontier language models.
ActionParty: Multi-Subject Action Binding in Generative Video Games
ActionParty is a new video world model that enables multi-subject action control in generative video games by disentangling subject states.
Res2Net: A New Multi-scale Backbone Architecture
Res2Net introduces a novel CNN building block that enhances multi-scale feature representation within a single residual block, improving performance across various vision tasks.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.