PT
Philip Torr
cs.CVcs.LGcs.AIcs.CLstat.MLeess.IVcs.CRcs.ROcs.MAcs.CY
On Valency
published · living versionsW_va2zqy3n·v1 · currentpublished
Learning Dynamics of On-Policy Distillation
with Guan Zhe Hong, Sumeet Ramesh Motwani, Liang Chen, Yangchen Pan +3
1 version
W_kscrjsq8·v1published
W_wgtghpkh·v2published
W_t9xernyt·v1published
W_3xzyutkf·v2published
Preprints & journals
404 papers in the corpus · 2004–2026LLM Post-Training: A Deep Dive Into Reasoning Large Language Models.42550758 · Kumar, Komal, Ashraf, Tajamul, Thawakar, Omkar et al.2026 · 10 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(11):14968-14987
How Much Do Activation Monitors Benefit from Original Model Computations?2610.24613v1 · James Oldfield, Shawn Im, Jay J Culligan et al.2026 · 0 citationsarXivon Valency
Inside the Loop: A Mechanistic Study of Weight-Tied Transformers on Depth-Bound Algorithmic Tasks2610.24135v1 · Magnus Sesodia, Juil Sock, Philip Torr et al.2026 · 0 citationsarXiv
BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents2610.06748v1 · Ziyan Wang, Shuqing Shi, James Oldfield et al.2026 · 0 citationsarXiv
Towards Better Exploration in Sequential Test-Time Scaling2609.39632v2 · Joseph Rance, Fabio Pizzati, Juil Sock et al.2026 · 0 citationsarXiv
When Vision Meets Graphs: A Survey on Graph Reasoning and Learning2609.03816v1 · Xinjian Zhao, Wei Pang, Zhixuan Yu et al.2026 · 0 citationsarXiv
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning2608.26105v2 · Junxiang Xu, Ruisi Wang, Fanyi Pu et al.2026 · 0 citationsarXiv
Self-Supervised Visual On-Policy Distillation2608.14144v1 · Yijiang Li, Yijun Liang, Yunjie Tian et al.2026 · 0 citationsarXiv
Multimodal Model Diffing for Feature Discovery and Control2608.09928v1 · Hunar Batra, Lachin Naghashyar, Ashkan Khakzar et al.2026 · 0 citationsarXiv
LatticeMind: A Conflict-Aware Memory Primitive for Multi-Agent Systems2608.08236v1 · Heng Zhou, Lian Zhang, Yutao Fan et al.2026 · 0 citationsarXiv
Conformalized Large Language Models under Configuration Shift2608.01460v2 · Yuqicheng Zhu, Jialin Yu, Lin Li et al.2026 · 0 citationsarXiv
CurveShift: Is Agent Progress Scalar? Separating Level from Shape2608.00355v1 · Hanwen Xing, Pengyun Wang, BingXu Meng et al.2026 · 0 citationsarXiv
Technical Report on the CVPR 2026@AdvML Workshop Challenge2607.11560v1 · Tianyuan Zhang, Zonglei Jing, Jiangfan Liu et al.2026 · 0 citationsarXiv
SETA: Scaling Environments for Terminal Agents2607.10891v2 · Qijia Shen, Zhiqi Huang, Vamsidhar Kamanuru et al.2026 · 0 citationsarXiv
A Survey on Foundations and Frontiers of Multimodal Agentic Frameworks: Techniques and Applications2608.20379v1 · Neel Mokaria, Rishie Raj, Dheeraj Baiju et al.2026 · 0 citationsarXiv
Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks2606.27147v1 · Yunqi Xue, Zhijiang Li, Philip Torr et al.2026 · 0 citationsarXiv
MedGenesis: Toward a World Model for Autonomous Clinical and Translational Research10.64898/2026.06.14.26355612v1 · Xiao, H., Jiang, N., Zhang, T. et al.2026 · 0 citationsmedRxiv
SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks2606.15872v2 · Jingru Guo, Xiangyuan Xue, Lian Zhang et al.2026 · 0 citationsarXiv
Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories2606.11176v2 · Kevin Qinghong Lin, Batu EI, Yuhong Shi et al.2026 · 0 citationsarXiv
ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptation2605.30484v2 · Zeyuan He, Bowen Yang, Zhirui Fang et al.2026 · 0 citationsarXiv
-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation Signals2605.25893v2 · Aoxi Liu, Yupeng Chen, James Oldfield et al.2026 · 0 citationsarXiv
The Path Matters: Learning a Token-Commitment Policy for Diffusion Language Models2605.24697v1 · Bohang Sun, Max Zhu, Francesco Caso et al.2026 · 0 citationsarXiv
Retrieval-Augmented Linguistic Calibration2605.19344v2 · Yi-Fan Yeh, Linwei Tao, Minjing Dong et al.2026 · 0 citationsarXiv
Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning2605.16776v1 · Puning Yang, Junchi Yu, Qizhou Wang et al.2026 · 0 citationsarXiv
ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation2605.06667v1 · Omar El Khalifi, Thomas Rossi, Oscar Fossey et al.2026 · 0 citationsarXiv
World Model for Robot Learning: A Comprehensive Survey2605.00080v1 · Bohan Hou, Gen Li, Jindou Jia et al.2026 · 1 citationarXiv
Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding2604.26031v1 · Chang Liu, Henghui Ding, Nikhila Ravi et al.2026 · 0 citationsarXiv
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond2604.22748v3 · Meng Chu, Xuan Billy Zhang, Kevin Qinghong Lin et al.2026 · 0 citationsarXiv
AutoOR: Scalably Post-training LLMs to Autoformulate Operations Research Problems2604.16804v4 · Sumeet Ramesh Motwani, Chuan Du, Aleksander Petrov et al.2026 · 0 citationsarXiv
LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning2604.14140v1 · Sumeet Ramesh Motwani, Daniel Nichols, Charles London et al.2026 · 0 citationsarXiv
Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models2604.11576v1 · Songlong Xing, Weijie Wang, Zhengyu Zhao et al.2026 · 0 citationsarXiv
Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents2604.06753v1 · Heng Zhou, Zelin Tan, Zhemeng Zhang et al.2026 · 0 citationsarXiv
Improving Semantic Uncertainty Quantification in Language Model Question-Answering via Token-Level Temperature Scaling2604.07172v1 · Tom A. Lamb, Desi R. Ivanova, Philip H. S. Torr et al.2026 · 0 citationsarXiv
ActionParty: Multi-Subject Action Binding in Generative Video Games2604.02330v2 · Alexander Pondaven, Ziyi Wu, Igor Gilitschenski et al.2026 · 0 citationsarXiv
Detecting Multi-Agent Collusion Through Multi-Agent Interpretability2604.01151v5 · Aaron Rose, Carissa Cullen, Sahar Abdelnabi et al.2026 · 0 citationsarXiv
Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning2603.14811v1 · Heng Zhou, Li Kang, Yiran Qin et al.2026 · 0 citationsarXiv
Safer by Diffusion, Broken by Context: Diffusion LLM's Safety Blessing and Its Failure Mode2602.00388v2 · Zeyuan He, Yupeng Chen, Lang Lin et al.2026 · 0 citationsarXiv
The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer2602.02557v2 · Yupeng Chen, Junchi Yu, Aoxi Liu et al.2026 · 0 citationsarXiv
Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge2601.18733v1 · Li Kang, Heng Zhou, Xiufeng Song et al.2026 · 0 citationsarXiv
Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learning2512.10150v1 · Lama Alssum, Hani Itani, Hasan Abed Al Kader Hammoud et al.2025 · 1 citationarXiv
Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval2512.03276v1 · Constantin Venhoff, Ashkan Khakzar, Sonia Joseph et al.2025 · 0 citationsarXiv
AI Deception: Risks, Dynamics, and Controls2511.22619v2 · Boyuan Chen, Sitong Fang, Jiaming Ji et al.2025 · 0 citationsarXiv
Measuring what Matters: Construct Validity in Large Language Model Benchmarks2511.04703v1 · Andrew M. Bean, Ryan Othniel Kearns, Angelika Romanou et al.2025 · 7 citationsarXiv
Sensitivity Analysis for Climate Science with Generative Flow Models2511.00663v3 · Alex Dobra, Jakiw Pidstrigach, Tim Reichelt et al.2025 · 0 citationsarXiv
DEEDEE: Fast and Scalable Out-of-Distribution Dynamics Detection2510.21638v1 · Tala Aljaafari, Varun Kanade, Philip Torr et al.2025 · 0 citationsarXiv
CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards2510.08529v2 · Xiangyuan Xue, Yifan Zhou, Guibin Zhang et al.2025 · 1 citationarXiv
MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning2510.08567v3 · Tajamul Ashraf, Umair Nawaz, Abdelrahman M. Shaker et al.2025 · 0 citationsarXiv
h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning2510.07312v2 · Sumeet Ramesh Motwani, Alesia Ivanova, Ziyang Cai et al.2025 · 0 citationsarXiv
CAT+: Investigating and Enhancing Audio-Visual Understanding in Large Language Models.40560702 · Ye, Qilang, Yu, Zitong, Shao, Rui et al.2025 · 17 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(10):8674-8690
TraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Models2510.01274v1 · Shenxu Chang, Junchi Yu, Weixing Wang et al.2025 · 0 citationsarXiv
Career total: at least 757 works. 404 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.