On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “Multi-exit”

Simulating multi-exit evacuation using deep reinforcement learningcs.LG

Deep RL model optimizes pedestrian evacuation in multi-exit scenarios.

problem Optimizing pedestrian evacuation in multi-exit indoor environments.

method MultiExit-DRL using Deep Reinforcement Learning with DQN and DNN.

result MultiExit-DRL reduces evacuation frames and optimizes exit utilization.

Deep Reinforcement Learning Pedestrian Evacuation Multi-exit Deep Q-Network Optimization

2020-07-11abs ↗pdf ↗

Multi-Exit Kolmogorov-Arnold Networks: enhancing accuracy and parsimonycs.LG

Enhances KANs for accuracy and interpretability with multi-exit architecture.

problem Unclear optimal depth for KANs and difficulty in optimization and interpretation.

method Introduces multi-exit KANs with each layer having its own prediction branch.

result Multi-exit KANs outperform single-exit versions on various datasets.

Kolmogorov-Arnold Networks interpretability machine learning scientific discovery model complexity

2025-06-03abs ↗pdf ↗

Intermittent Inference with Nonuniformly Compressed Multi-Exit Neural Network for Energy Harvesting Powered Devicescs.LG

This work optimizes DNN inference for energy-harvesting devices by compressing and selectively executing neural network exits.

problem Inference delays and energy inefficiency in energy-harvesting devices.

method Developed a power trace-aware and exit-guided network compression algorithm for multi-exit neural networks.

result Superior accuracy and reduced latency compared to state-of-the-art techniques.

energy harvesting DNN inference neural network compression microcontrollers exit-guided

2020-04-23abs ↗pdf ↗