arXiv
Towards Value-Constrained Credit Assignment in Fully Delegated AI Cooperatives
We propose a framework for reward allocation in fully delegated AI cooperatives where humans are represented by agent...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching
Flow Matching (FM) has achieved remarkable generative performance, yet it suffers from exposure bias due to discrepan...
arXiv
Govern the Repository, Not the Agent: Measuring Ecosystem-Level Risk in AI-Native Software
Autonomous coding agents now open and merge pull requests in shared repositories at scale, and the field evaluates th...
arXiv
How Width and Data Shape Generalization Scaling Laws in Quadratic Neural Networks
Understanding how performance scales jointly with model size and data is a central problem in modern machine learning...
arXiv
Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation
Test-time adaptation (TTA) has emerged as a promising paradigm for mitigating distribution shifts in deep models. How...
arXiv
Agent-Native Immune System: Architecture, Taxonomy, and Engineering
The transition from static chat bots to autonomous agents--equipped with persistent memory, tool-use protocols, and m...
arXiv
Parameter Efficient Hybrid Transformer (PEHT) for Network Traffic Prediction via Dynamic Urban Congestion Integration
Accurate network traffic prediction is a critical element for efficient resource allocation in dynamic urban cellular...
arXiv
Towards Automating Scientific Review with Google's Paper Assistant Tool
Artificial intelligence is driving a revolution in scientific discovery, accelerating everything from hypothesis gene...
arXiv
Agentic Hardware Design as Repository-Level Code Evolution
We present HORIZON, a self-evolving agent framework that treats hardware design as repository-level code evolution. A...
arXiv
Which Nash Equilibrium? Solver-Dependent Selection on Zero-Sum Nash Polytopes
Many two-player zero-sum games admit not a unique Nash equilibrium but a convex set of them: a polytope of profiles t...
arXiv
DexCompose: Reusing Dexterous Policies for Multi-Task Manipulation with a Single Hand
Dexterous manipulation policies can solve individual skills, but composing them to perform multiple tasks with a sing...
HuggingFace
PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation
Video generation models have emerged as a promising paradigm for embodied world simulation. However, both general-dom...