Philip H. S. Torr

Fudan University — China

Computer Science · Physical Sciences

63h-index16.2kcitations280works1.52yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Image and Video Retrieval Techniques(75), Advanced Vision and Imaging(56), Advanced Neural Network Applications(44), Human Pose and Action Recognition(34), Domain Adaptation and Few-Shot Learning(31)

Publications280 total

Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval
arXiv (Cornell University)·2025Open Access
h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning
arXiv (Cornell University)·2025Open Access
Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning
arXiv (Cornell University)·2025Open Access
Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers
arXiv (Cornell University)·2025Open Access
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
arXiv (Cornell University)·2025· 1 citedOpen Access
True Multimodal In-Context Learning Needs Attention to the Visual Context
arXiv (Cornell University)·2025Open Access
Implicit neural representations for chemical reaction paths
The Journal of Chemical Physics·2025· 1 citedOpen Access
BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset
arXiv (Cornell University)·2025Open Access
Rethinking Data Protection in the (Generative) Artificial Intelligence Era
arXiv (Cornell University)·2025Open Access
Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence
arXiv (Cornell University)·2025Open Access
PVUW 2025 Challenge Report: Advances in Pixel-Level Understanding of Complex Videos in the Wild
2025
VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning
arXiv (Cornell University)·2025Open Access
Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks
arXiv (Cornell University)·2025Open Access
Large Language Models Miss the Multi-Agent Mark
arXiv (Cornell University)·2025Open Access
Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers
arXiv (Cornell University)·2025Open Access
Hadamard product in deep learning: Introduction, Advances and Challenges
arXiv (Cornell University)·2025Open Access
Hadamard Product in Deep Learning: Introduction, Advances and Challenges
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025· 16 cited
Reliable Evaluation of Adversarial Transferability
2025· 1 cited
PSyDUCK: Training-Free Steganography for Latent Diffusion
arXiv (Cornell University)·2025Open Access
Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation
Lecture notes in computer science·2025
page 1 of 14Next →

Frequent Co-authors

Pushmeet Kohli(10), Ľubor Ladický(7), Roberto Cipolla(7), Andrew Zisserman(6), Björn Stenger(4), A. Thayananthan(4), Karteek Alahari(4), Luca Bertinetto(3), Manish Kumar(3), Paul Sturgess(3), Shimon Whiteson(3), Anthony Dick(3), Andrew Fitzgibbon(3), Sunando Sengupta(3), Matej Kristan(2), Aleš Leonardis(2), Jiřı́ Matas(2), Michael Felsberg(2), Roman Pflugfelder(2), Luka Čehovin Zajc(2)