AI Research

Latest research papers from arXiv covering machine learning, computer vision, natural language processing, and more.

arXivPDF

Posterior Matching Distillation

Diffusion distillation accelerates image and video generation by compressing a pretrained teacher's iterative sampling process into a few network evaluations. Distribution-based methods achieve this by matching the student's output distribution to the teacher's. This matching is often driven by reve...

Hidir Yesiltepe, Julius Berner, Arash Vahdat
Nov 19, 2026
arXivPDF

RL Post-Training in Diffusion Transformers Is Activation Steering

Reinforcement learning (RL) post-training substantially improves the visual quality, text rendering, and compositional accuracy of diffusion transformers. Because capabilities such as rendering requested text or composing multiple objects are inherently prompt-dependent, a natural hypothesis is that...

Tuna Han Salih Meral, Kaan Oktay, Alec Helbling
Nov 19, 2026
arXivPDF

PlayCraft: Designing Engaging Games from Agent Play Experience

Recent AI agents can generate playable games, but these games are not necessarily engaging. Mastery is a key source of engagement, yet designing for it requires extensive human play and tuning. We propose PlayCraft, an automated framework that uses a vision-based agent to play games and draws on its...

Weihao Cheng
Nov 19, 2026
arXivPDF

ScaleWorld: High-Resolution World Generation through Shared Prediction and Refinement

High-resolution generation enables video world models to render fine-grained scene structures and textures, but directly generating high-resolution video incurs substantial computational and memory costs. We present ScaleWorld, a causal video model that unifies low-resolution world prediction and hi...

Yansong Qu, Wesker Zheng, Quanjian Song
Nov 19, 2026
arXivPDF

Bio-PM-Guided Synthetic IMU Generation

Collecting and labeling inertial measurement unit (IMU) data for human activity recognition (HAR) is expensive, and models trained on one group of subjects often fail to generalize to unseen individuals. Even with balanced data, classifiers struggle to distinguish dynamically similar activity classe...

Deepali Singh, Deepesh Parpani, Aviral Gupta
Nov 19, 2026
arXivPDF

Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depth

We present Depth Pro 2, an approach to estimating dense metric depth for images and video at full resolution. By analyzing prior methods for monocular depth estimation, we find that they commonly trade off temporal consistency and boundary sharpness: multi-frame methods favor consistency, single-fra...

Peiyun Hu, Marko Mihajlovic, Lyndon Duong
Nov 19, 2026
arXivPDF

SoK: Assessing the Evolution of LLM Capability in Software Vulnerability Research

LLM-based agents are becoming increasingly capable at discovering, validating and patching vulnerabilities in real software, and vendors and researchers report that this is already changing how vulnerabilities are found and fixed. These claims, however, are scattered across papers, vendor reports an...

Amine Lbath, Manan Suri, Aurelien Delaitre
Nov 19, 2026
arXivPDF

Active Feature Acquisition by Distilling an Oracle Teacher

Acquiring every feature of an instance is often costly: a measurement can carry a monetary price, a time delay, or a privacy cost. Active Feature Acquisition (AFA) addresses this by learning a policy that decides, per instance, which features to acquire under a budget. Existing AFA methods train thi...

Yang Meng, Zixin Ding, Robert L. Grossman
Nov 19, 2026
arXivPDF

PGX: Physically Grounded Execution for Long-Horizon Humanoid Loco-Manipulation

Robotic vision-language-action (VLA) models can execute diverse individual manipulation skills, yet they still struggle with long-horizon loco-manipulation tasks, where temporal structure, skills, and precision are tightly coupled within a monolithic model. We propose Physically Grounded Execution (...

Kai Lu, Chenyang Ma, Ioannis Havoutis
Nov 19, 2026
arXivPDF

Coda-DaVinci: Reimagining Video Generation with Code2Video

Code2Video uses agent-authored 3D proxies to guide video generation, enabling explicit control over structure and dynamics. However, how to construct proxies and prompts for optimal downstream quality remains underexplored, as do the capabilities and limitations of this paradigm. Through controlled ...

Yiyan Ji, Qixun Wang, Yang Shi
Nov 19, 2026

Data from arXiv.org • Updated hourly