The Flow has not summarised this story yet — read it at arXiv Machine Learning.
arXiv:2607. 02893v1 Announce Type: new Abstract: Low-bit quantization shrinks language models but treats precision as a single global hyper-parameter: every weight uses the same bit-width.
arXiv:2608.30564v1 Announce Type: cross Abstract: Mixed-precision quantization (MPQ) assigns a different bitwidth to each linear layer of a large language model (LLM) to minimize the quantization-ind...
The paper presents a Quadratic Constrained Binary Optimization (QCBO) framework that provides provable guarantees for training quantized neural networks. It characterizes the topology of zero‑loss level sets, compiles finite‑depth architectures into bounded QCBOs, and introduces a sample‑wise Decomposed Lower‑Bound Optimization (DLBO) to scale Ising‑based optimization. Experiments on a coherent Ising machine show high accuracy on binary Fashion‑MNIST at 1.1‑bit precision and validate the approach on multi‑class datasets.
arXiv:2605.11222v2 Announce Type: replace Abstract: Quantization is an effective strategy to reduce the storage and computation footprint of large language models (LLMs). Post-training quantization (...
Cross-Backend QIEO is a runtime core for quantum-inspired evolutionary optimization that unifies execution across OpenMP5, CUDA, HIP, and multiple high-level languages. It compiles a single C++ implementation per hardware target and dispatches to CPU, multi-core, NVIDIA, or AMD backends at runtime, adapting kernels to each device’s memory hierarchy. The framework is validated with real-world bindings: a Python neural‑network hyperparameter optimizer achieving 88.60 % MNIST accuracy, a MATLAB wind‑farm layout optimizer matching particle swarm results and outperforming genetic algorithms, and a Julia package that reduces mean SSE by 2.1× in Lotka–Volterra parameter estimation.
REAL-Q introduces a new post‑training quantization approach for large language models that replaces the traditional single closed‑form second‑order solver with a fine‑grained, dynamic block‑wise gradient descent applied after every 128‑column block. By aligning the surrogate loss with the end‑to‑end objective and using a sliding window for smooth cross‑layer transitions, REAL‑Q mitigates error propagation and information misalignment. Experiments on LLaMA‑3.1 and Qwen3 show up to ~49% reduction in end‑to‑end KL divergence compared to state‑of‑the‑art methods.