登录 注册
AMIGO: 代理多图像定位甲骨文基准
AMIGO: Agentic Multi-Image Grounding Oracle Benchmark
👁 13 📚 0
自我改进系统安全核查的信息理论限制
Information-Theoretic Limits of Safety Verification for Self-Improving Systems
👁 12 📚 0
AI驱动的Generative Phychologys尺度发展终极导师:将AIGNIE从其瓶子中取出
The Ultimate Tutorial for AI-driven Scale Development in Generative Psychometrics: Releasing AIGENIE...
👁 11 📚 0
通过强化学习实现动态视向距离,实现自主赛跑
Dynamic Lookahead Distance via Reinforcement Learning-Based Pure Pursuit for Autonomous Racing
👁 11 📚 0
分布在边缘的 Generative AI 推论
Trust-Aware Routing for Distributed Generative AI Inference at the Edge
👁 11 📚 0
临时信贷是免费的
Temporal Credit Is Free
👁 12 📚 0
停止探测, 开始编码: 为什么线性探测器和 Sparse 自动编码器在组成通用化中失败
Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generali...
👁 12 📚 0
在可转移超平面优化下反思语言模型缩放
Rethinking Language Model Scaling under Transferable Hypersphere Optimization
👁 16 📚 0
线性后退和线性神经网络中转移学习的预期出错
Expectation Error Bounds for Transfer Learning in Linear Regression and Linear Neural Networks
👁 14 📚 0
见"放入":以视觉-语言模式演进的宏定位
See it to Place it: Evolving Macro Placements with Vision-Language Models
👁 15 📚 0
GPU-加速优化变形器基于实时推论的神经网络
GPU-Accelerated Optimization of Transformer-Based Neural Networks for Real-Time Inference
👁 15 📚 0
功能性自然政策梯度
Functional Natural Policy Gradients
👁 13 📚 0
亚空间优化后传播-无持续测试-时间适应
Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptation
👁 15 📚 0
FL-PBM:联邦学习的后门培训前缓解
FL-PBM: Pre-Training Backdoor Mitigation for Federated Learning
👁 13 📚 0
在联邦学习中使用PPA和MiniMax游戏理论减轻后门攻击
Mitigating Backdoor Attacks in Federated Learning Using PPA and MiniMax Game Theory
👁 14 📚 0
线性马尔可夫决定过程的参数政策优化演员-批评
Optimistic Actor-Critic with Parametric Policies for Linear Markov Decision Processes
👁 14 📚 0
事后的有线电视新闻网自我解释
Post-hoc Self-explanation of CNNs
👁 14 📚 0
FEDMRA: 有动态记忆回放分配的联邦增量学习
FeDMRA: Federated Incremental Learning with Dynamic Memory Replay Allocation
👁 14 📚 0
Mixture-模型 (Model) Preference 学习 (Learning) for Many-Objective 贝叶斯 (Bayesian) 优化 (Optimization)
Mixture-Model Preference Learning for Many-Objective Bayesian Optimization
👁 14 📚 0
共通域分解:在无限-高维度噪声下M-估计器的确切风险
The Conjugate Domain Dichotomy: Exact Risk of M-Estimators under Infinite-Variance Noise in High Dim...
👁 15 📚 0
🌊