会员服务
Scaling Enterprise Agent Routing: Degradation, Diagnosis, and Recovery
Arxiv
0+阅读 · 6月16日
When in Doubt, Plan It Out: Committed Small Language Model Deliberation for Reactive Reinforcement Learning
Arxiv
0+阅读 · 6月15日
ReQAT: Achieving Full-Precision Reasoning Accuracy with 4-bit Floating-Point Quantization-Aware Training
Arxiv
0+阅读 · 6月14日
Multi-Turn Reasoning When Context Arrives in Pieces: Scalable Sharding and Memory-Augmented RL
Arxiv
0+阅读 · 6月12日
UltraSketchLLM: Sub-1-Bit LLM Compression via Sketch and Hardware-Friendly Operators
Arxiv
0+阅读 · 6月12日
Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communities
Arxiv
0+阅读 · 5月29日
More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries
Arxiv
0+阅读 · 5月21日
Multidimensional Resilience for Electrical Power Systems: Systematic Review, Integrated Index, and Validation under Real-World Cyber-Physical Attack Scenarios
Arxiv
0+阅读 · 6月6日
A comprehensive evaluation of spatial co-execution on GPUs using MPS and MIG technologies
Arxiv
0+阅读 · 4月24日
Edge Radar Material Classification Under Geometry Shifts
Arxiv
0+阅读 · 3月24日
Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification
Arxiv
0+阅读 · 4月9日
Dense-Jump Flow Matching with Non-Uniform Time Scheduling for Robotic Policies: Mitigating Multi-Step Inference Degradation
Arxiv
0+阅读 · 3月2日
Accurate Failure Prediction in Agents Does Not Imply Effective Failure Prevention
Arxiv
0+阅读 · 2月3日
Bi-Anchor Interpolation Solver for Accelerating Generative Modeling
Arxiv
0+阅读 · 1月30日
A PAC-Bayesian Analysis of Channel-Induced Degradation in Edge Inference
Arxiv
0+阅读 · 1月16日
参考链接
微信扫码咨询专知VIP会员
Top