resource-constrained environments
Settings in which computational resources (such as memory, processing power, and energy) are limited, often requiring AI algorithms to optimize performance under strict constraints.
- CAML: Collaborative Auxiliary Modality Learning for Multi-Agent Systems
- DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization
- Learn2Mix: Training Neural Networks Using Adaptive Data Integration
- LittleBit: Ultra Low-Bit Quantization via Latent Factorization
- Multi-Objective One-Shot Pruning for Large Language Models
- NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoning
- OASIS: One-Shot Federated Graph Learning via Wasserstein Assisted Knowledge Integration
- SEMPO: Lightweight Foundation Models for Time Series Forecasting
- Sim-LLM: Optimizing LLM Inference at the Edge through Inter-Task KV Reuse