登录 注册
从相似性/多样性和对等性中学习
Learning from Similarity/Dissimilarity and Pairwise Comparison
👁 384 📚 42
差异隐私下的最小和可适应共变矩阵估计
Minimax and Adaptive Covariance Matrix Estimation under Differential Privacy
👁 25 📚 30
遗憾分析睡眠竞争强盗
Regret Analysis of Sleeping Competing Bandits
👁 52 📚 13
在扩展基因模型和Godel-Tarski-Lob Limits中减少返回
Diminishing Returns in Expanding Generative Models and Godel-Tarski-Lob Limits
👁 293 📚 11
由次级目标驱动的改进长范围 LLM代理的框架
A Subgoal-driven Framework for Improving Long-Horizon LLM Agents
👁 62 📚 29
基于本体学的知识模型和不确定性的室外空气质量评估
Ontology-Based Knowledge Modeling and Uncertainty-Aware Outdoor Air Quality Assessment Using Weighte...
👁 437 📚 19
GoAgent: 基于 LLM 的多代理系统的代理集团通信地形
GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems
👁 503 📚 30
ATHNA: 适应性测试-时间指导,用于改进传播模式中的精益求精
ATHENA: Adaptive Test-Time Steering for Improving Count Fidelity in Diffusion Models
👁 127 📚 47
Wasserstein 逆向传播的缩放- 依赖辐射几何和量子误差
Scale-Dependent Radial Geometry and Metric Mismatch in Wasserstein Propagation for Reverse Diffusion
👁 67 📚 3
经验是最佳教师:激励有效探索加强法学硕士课程的学习
Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMs
👁 203 📚 1
LoASR-Bench:评价语言家庭对低资源自动语音识别的大型语音模型
LoASR-Bench: Evaluating Large Speech Language Models on Low-Resource Automatic Speech Recognition Ac...
👁 376 📚 47
Bench:评估各个任务和领域的信息覆盖面
CoverageBench: Evaluating Information Coverage across Tasks and Domains
👁 429 📚 24
管弦人类-AI软件交付:三个软件现代化方案的回溯纵向实地研究
Orchestrating Human-AI Software Delivery: A Retrospective Longitudinal Field Study of Three Software...
👁 264 📚 29
脱钩-线克和R$-Probe: 脱钩功能 分级传播 MLLLM OCR
Detached Skip-Links and $R$-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM...
👁 467 📚 19
机器学习汉密尔顿人远程校正
Physics-Informed Long-Range Coulomb Correction for Machine-learning Hamiltonians
👁 320 📚 38
X-World:可控Ego-Centric 多卡梅拉可扩展端到端驱动世界模型
X-World: Controllable Ego-Centric Multi-Camera World Models for Scalable End-to-End Driving
👁 370 📚 43
推动用特定领域进行批判性思考
Promoting Critical Thinking With Domain-Specific Generative AI Provocations
👁 108 📚 31
Trojan's Whisper:通过注入的脚步引导来隐形地操纵 OpenClaw
Trojan's Whisper: Stealthy Manipulation of OpenClaw through Injected Bootstrapped Guidance
👁 301 📚 15
RAM: 恢复任何3D 人类运动在网络中
RAM: Recover Any 3D Human Motion in-the-Wild
👁 283 📚 29
Span-Level 机器翻译元评价
Span-Level Machine Translation Meta-Evaluation
👁 507 📚 25
🌊