HuggingFace
SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE
We present a zero-shot, training-free and optimization-free framework for generating 360 panoramic images and videos ...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
LUNA: Learning Universal 3D Human Animation Beyond Skinning
Creating photorealistic, animatable 3D human avatars from monocular images still largely depends on Linear Blend Skin...
arXiv
GR2 Technical Report
Industrial recommendation systems serve billions of users through a multi-stage funnel -- retrieval, early-stage rank...
arXiv
Amplifying Membership Signal Through Chained Regeneration
The tendency of large generative models to memorize training data makes sample verification critical for privacy audi...
arXiv
Radial Suppression Accelerates Algorithmic Generalization: A Geometric Analysis of Delayed Generalization
Why do neural networks memorize algorithmic training data long before they generalize? We present a geometric case st...
arXiv
Self-Study Reconsidered: The Hidden Fragility of Learning from Self-Generated QA
Language models are increasingly taught from synthetic question--answer (QA) supervision: a model generates questions...
arXiv
PolicyGuard: From Organizational Policies to Neuro-SymbolicCompliance Review Engines
Policy-grounded document review requires determining whether a target document complies with organization-specific po...
arXiv
AxDafny: Agentic Verified Code Generation in Dafny
We study agentic code generation in Dafny, where a model must generate both executable code and the proof artifacts f...
arXiv
TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning
Agentic reinforcement learning requires assigning credit to environment-facing actions such as searches, clicks, edit...
arXiv
FLORA: A deep learning approach to predict forest attributes from heterogeneous LiDAR data
Forest attributes are essential for national-scale resource monitoring. Airborne LiDAR metrics are among the auxiliar...
arXiv
AdaJEPA: An Adaptive Latent World Model
Latent world models enable planning from high-dimensional observations by predicting future states in a compact laten...
arXiv
Freeform Preference Learning for Robotic Manipulation
Reward design remains a central bottleneck for autonomous robot policy improvement, especially in long-horizon manipu...