HuggingFace
The Lattice of Transition Laws
Diffusion and autoregression (AR) have long been seen as different categories of generative models, with diffusion sp...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
ARC: A Reasoning Recipe for Robot Foundation Models
The prevailing approach to improving robot foundation models (RFMs) relies on larger models, more robot demonstration...
arXiv
GeoReform: Reflective Formalization Evolution for Multimodal Geometry Problem Solving
Multimodal large language models (MLLMs) often struggle to identify and use geometric relations in diagrams. Recent m...
arXiv
HRIL: Learning Multimodal Synergy via Higher-Order Tensor Modeling
Self-supervised multimodal representation learning has achieved remarkable success across diverse domains, yet captur...
arXiv
SpaceFlow: Locally Controllable 3D Generation
Current 3D generation methods lack explicit local control: geometric adherence is often defined by a global control s...
arXiv
LeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC
World action models (WAMs) predict actions and future observations, typically from a reconstruction-based representat...
arXiv
Searching for "Harmful Refusal": A Psychometric Audit of an AI Safety Benchmark
Safety benchmarks typically report one overall score for a suite of datasets, each of which may target one or more sa...
arXiv
Predicting Alignment Generalization with Value Representations
LLM developers post-train their models to exhibit prosocial values and behavioral traits, which are enumerated in an ...
arXiv
MAMHOI: Factorizing Scene-Aware Human-Object Interaction through Affordances
Generating realistic human-object interactions (HOI) in complex 3D scenes requires two complementary capabilities: re...
arXiv
RoboRSI: Stable, efficient, and reusable robot self-evolution in complex real-world environments
A generalist robot should not only perform diverse tasks but also improve through experience, turning what it learns ...
arXiv
Ecology of AI Agents: Collaboration Creates a Population Threshold for Takeoff
AI agents can now conduct real-world cyberattacks, scale up capabilities with the number of agents, and collectively ...
arXiv
Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception
Recent incidents have highlighted the challenge of monitoring LLM agents and the danger of models deceiving people. W...