3.5k citations · 14.1k across the 436 of their papers we have counts for
494 papers
Reading, Writing, Sharing, and Interacting with the World through Video
Shengqiong Wu, Meng Luo, Bobo Li +5
Video foundation models have advanced rapidly in understanding and generating visual sequences, while video world models seek to capture the underlying dynamics of the world they d…
How Much Do Activation Monitors Benefit from Original Model Computations?
James Oldfield, Shawn Im, Jay J Culligan +3
One powerful way to safeguard AI systems is to monitor their internal computations--where signs of undesirable behavior might be more easily detectable than from models' inputs and…
Inside the Loop: A Mechanistic Study of Weight-Tied Transformers on Depth-Bound Algorithmic Tasks
Magnus Sesodia, Juil Sock, Philip Torr +1
Solving algorithmic tasks with many sequential steps typically requires scaling up transformer depth or chain-of-thought length, incurring unfavorable parameter and inference-compu…
BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents
Ziyan Wang, Shuqing Shi, James Oldfield +5
In decentralized consumer-to-consumer (C2C) marketplaces, people list goods, negotiate with strangers, and rate one another, so trust rests on reputation. Large language model (LLM…
On-the-fly Weight Generation: A Hypernetwork Proof of Concept on ARC-1D
Fabio J. Fehr, Philip Torr
General-purpose models can adapt to many tasks from context, while specialised models can execute individual functions with less capacity. Yet obtaining such specialists requires t…
Towards Better Exploration in Sequential Test-Time Scaling
Joseph Rance, Fabio Pizzati, Juil Sock +4
Test-time scaling improves language model reasoning by spending additional compute at inference. However, both classes of existing methods often fail to continue improving over lon…
PartiCam: Camera Controlled Video Generation with Reward Guidance
Amine Ouasfi, Runjia Li, Junlin Han +3
We present PartiCam, a training-free Particle filtering rooted method for improved Camera controlled video generation. Generating videos that follow a precisely specified camera tr…
What if automating AI R&D triggers an intelligence explosion?
Alan Chan, Christoph Winter, Andrew Barto +19
In contrast to even a year ago, AI systems now write most of the code inside the companies that build them. As more of the AI research and development (R&D) pipeline is automated,…
Training Object Permanence in World Models
Haotian Zhang, Fengyuan Yu, Dezhi Luo +28
Object permanence and solidity are hallmarks of human cognitive priors. Recent studies show that video generation models, a paradigmatic class of current world models, have begun t…
Beyond Visual Quality: A Study of Test-Time Planning with World Action Models
Jianhao Yuan, Yu Yuan, Benjamin Ramtoula +5
World action models generate actions together with visual predictions of their consequences. These paired outputs create the potential for planning by sampling multiple actions fro…
MotionJEPA: Preventing Temporal Feature Collapse by Capturing Visual Changes in Latent Space
Markus Karmann, Shile Li, Christian Internò +10
Joint Embedding Predictive Architectures (JEPAs) are a promising paradigm for learning task-agnostic latent world models without visual reconstruction. However, standard JEPA train…
Procedural Pretraining for Molecular Property Prediction
Moritz Friedemann, Zachary Shinnick, Philip Torr +1
Molecular property prediction is often limited by the small size of labeled downstream datasets, motivating pretraining on large corpora of unlabeled molecules. In this work, we as…
PaperDoctor: Evidence-Grounded and Actionable Feedback for Scientific Papers in Progress
Kevin Qinghong Lin, Siyuan Hu, Pan Lu +14
Autoresearch agents are reshaping the research ecosystem, but they can also let flawed claims enter the literature at scale. Human advisors catch such issues in drafts through care…
Building Legal Reward Models for Grounding and Abstention
Rilton Franzone, Valentin Noël, Puyu Wang +2
Large language models are increasingly used in high-stakes domains such as law, where systems must ground their reasoning in retrieved evidence and abstain when that evidence is in…
When Rubrics Fail: Hallucinations Reveal Blind Spots in Medical AI Evaluation
Griffin Farrow, Lily Sijia Li, Jack Johnson +4
Hallucinations can undermine clinician trust in LLMs, making it important that evaluation methods capture clinically relevant errors. Rubric-based evaluation has become the leading…
RAP: Research Attention Prediction Reveals Target-Conditioned Evidence Acquisition Biases
Yingqian Wu, Jingcong Liang, Siyuan Wang +4
Large language models (LLMs) increasingly act as research agents, yet their ability to track shifts in research attention is difficult to evaluate because reviews and research idea…
Online Surrogate Repair: Decoupling High-Fidelity Feedback from Search Length in Closed-Loop Discovery
Xiaotang Feng, Philip Torr, Bruno Andreis
Closed-loop AI scientists can generate candidate designs at low marginal computational cost, whereas reliable feedback may require wet-lab synthesis, characterization, or high-fide…
FramingQA: Does the Question Shape the Answer? Measuring the Compositional Framing Effect
Hazel H. Kim, Andrew M. Bean, Guilherme Affonso Ferreira de Camargo +10
We introduce FramingQA, a benchmark that measures the model sensitivity to question framing across law, medicine, finance, and robotic simulations. Large language models (LLMs) oft…
Automatic Red Teaming for Implicit Vulnerabilities of Text-to-Image Models
Chang Ma, Junlin Han, Shuo Chen +3
Red-teaming Text-to-Image (T2I) models is essential for safe deployment, yet it remains particularly challenging against implicit adversarial prompts. Unlike explicit adversarial p…
When Vision Meets Graphs: A Survey on Graph Reasoning and Learning
Xinjian Zhao, Wei Pang, Zhixuan Yu +8
Graphs are a fundamental data structure underlying many problems in the natural and social sciences. Over the past decade, Graph Neural Networks (GNNs) have dominated graph machine…
Conformalized Large Language Models under Configuration Shift
Yuqicheng Zhu, Jialin Yu, Lin Li +7
Conformal prediction (CP) is a distribution-free framework for uncertainty quantification that has recently been adapted to large language models (LLMs), providing prediction sets…
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
Junxiang Xu, Ruisi Wang, Fanyi Pu +49
Native visual reasoning treats visual generation as the medium of reasoning itself: visual states (i.e. images and videos) are not merely inputs to be understood or outputs to be r…
Self-Supervised Visual On-Policy Distillation
Yijiang Li, Yijun Liang, Yunjie Tian +6
Visual on-policy distillation relies heavily on an informative teacher-student asymmetry, through either a larger, stronger teacher or privileged supervision, such as reference ans…
Multimodal Model Diffing for Feature Discovery and Control
Hunar Batra, Lachin Naghashyar, Ashkan Khakzar +4
Multimodal Large Language Models (MLLMs) exhibit strong visual understanding, yet the internal features that cause these behaviors remain difficult to identify, audit, or control.…