会员服务
A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference
Arxiv
0+阅读 · 9月1日
Online Reinforcement Learning in the Met Office Unified Model through Distributed Model-Agent Coupling
Arxiv
0+阅读 · 9月2日
Train What You Deploy: Closing the MLP Reachability Gap in Low-Rank Clone Distillation
Arxiv
0+阅读 · 9月2日
Safe, Always-Valid Alpha-Investing Rules For Doubly Sequential Online Inference
Arxiv
0+阅读 · 9月1日
Behavioral calibration of mobile-phone GPS data for population-representative analyses
Arxiv
0+阅读 · 9月1日
Scaling Inference Prefill with High-Radix Photonic Interconnects
Arxiv
0+阅读 · 9月1日
TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models
Arxiv
0+阅读 · 9月1日
SwapRec: Warming Up Cold Items Through Training-Time Swaps
Arxiv
0+阅读 · 9月1日
Geometric Distillation from Rectified Stereo: Leveraging Epipolar Cues for Monocular Depth
Arxiv
0+阅读 · 9月2日
Gradient Prediction with Control Variates in the Cheap-Forward Regime
Arxiv
0+阅读 · 9月2日
Accelerating Unified Multimodal Models with Core-Expansion Routing and Unified Computation Scheduling
Arxiv
0+阅读 · 9月2日
A Top-Down Framework for Metric-Scale Athlete Localization from Single Broadcast Frames
Arxiv
0+阅读 · 9月2日
Propose to Learn, Learn to Propose: Evaluability-Aware Assistance under Bounded Rationality
Arxiv
0+阅读 · 9月2日
DESA-TTA: Dynamic EMA and Source Anchoring for Test-Time Adaptation
Arxiv
0+阅读 · 9月1日
Not All Agreement Counts as Corroboration: Provenance-Conserving Multi-View Fusion for Typed Action Admission in Human-Robot Collaboration
Arxiv
0+阅读 · 8月31日
参考链接
微信扫码咨询专知VIP会员
Top