paper-with-me

Papers

QuIDE: Mastering the Quantized Intelligence Trade-off via Active Optimization

2026-05-05 · Xiantao Jiang arxiv

There is currently no unified metric for evaluating the efficiency of quantized neural networks. We propose QuIDE, built around the Intelligence Index I = (C x P)/log_2(T+1), which collapses the compression-accuracy-latency trade-off into a single score. Experiments across six settings -- SimpleCNN (MNIST, CIFAR), ResNet-18 (ImageNet-1K), and Llama-3-8B -- show a task-dependent Pareto Knee. 4-bit quantization is optimal for MNIST and large LLMs, while 8-bit is the sweet spot for complex CNN tasks (ResNet-18 on ImageNet), where 4-bit PTQ collapses accuracy catastrophically. The accuracy-gated variant I' correctly flags these non-viable configurations that the raw I would reward. QuIDE provides a reproducible evaluation protocol and a ready-to-use fitness function for mixed-precision search.

📄 PDF Abstract BibTeX arXiv:2605.10959

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Grade Inflation in Generative Models

2024-12-31 · Phuc Nguyen, Miao Li, Alexandra Morgan, Rima Arnaout 외

Generative models hold great potential, but only if one can trust the evaluation of the data they generate. We show that many commonly used quality scores for comparing two-dimensional distributions of synthetic vs. grou…

EquiDexFlow: Contact-Grounded SE(3)-Equivariant Dexterous Grasp Generative Flows

2026-06-10 · Clinton Enwerem, John S. Baras, Calin Belta arxiv

Most learned dexterous grasp generators relegate contact forces to a downstream verification step, so a kinematically-plausible pose can still violate the conditions for a stable physical grasp. We address this with Equi…

ProMAS: Proactive Error Forecasting for Multi-Agent Systems Using Markov Transition Dynamics

2026-03-12 · Xinkui Zhao, Sai Liu, Yifan Zhang, Qingyu Ma 외 arxiv

The integration of Large Language Models into Multi-Agent Systems (MAS) has enabled the so-lution of complex, long-horizon tasks through collaborative reasoning. However, this collec-tive intelligence is inherently fragi…

Artificial Generals Intelligence: Mastering Generals.io with Reinforcement Learning

2025-07-09 · Matej Straka, Martin Schmid

We introduce a real-time strategy game environment built on Generals.io, a game that hosts thousands of active players each week across multiple game formats. Our environment is fully compatible with Gymnasium and Pettin…

GPUMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning

Can Large Language Models Master Complex Card Games?

2025-09-01 · Wei Wang, Fuqing Bie, Junzhe Chen, Dan Zhang 외 arxiv

Complex games have long been an important benchmark for testing the progress of artificial intelligence algorithms. AlphaGo, AlphaZero, and MuZero have defeated top human players in Go and Chess, garnering widespread soc…