arXiv:2610. 22621v1 Announce Type: new Abstract: The training loss of binary and ternary neural networks, expanded as a multilinear polynomial over the discrete weights, is structurally equivalent to the energy of a hierarchical high-order Ising model.
arXiv:2606. 26650v1 Announce Type: cross Abstract: In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing and accelerating LLMs.
In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing and accelerating LLMs. Unlike existing state-of-the-art ternary quantization methods that rely on data-intensive and costly quantization-aware training to mitigate severe performance degradation, CAT-Q is a simple yet effective post-training quantization scheme that is readily applicable to LLMs with diverse architectures and model sizes.
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.
As large language model inference shifts toward lower precision, post-training quantization (PTQ) becomes increasingly brittle, making quantization-aware training (QAT) essential for preserving model...
arXiv:2610.29378v1 Announce Type: cross Abstract: Quantization-aware training (QAT) aims to recover reasoning capabilities in low-bit large language models (LLMs). Existing recipes typically supervis...
arXiv:2608. 13966v1 Announce Type: new Abstract: As large language model inference shifts toward lower precision, post-training quantization (PTQ) becomes increasingly brittle, making quantization-aware training (QAT) essential for preserving model quality.
arXiv:2606. 13054v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit exceptional general language processing capabilities, but their memory and compute costs hinder deployment.
arXiv:2610. 21808v1 Announce Type: new Abstract: Weight quantization below four bits shrinks memory and bandwidth at a perplexity that looks acceptable, but often at the cost of factual knowledge and task accuracy.
arXiv:2606. 08779v1 Announce Type: new Abstract: Reinforcement Learning (RL) has emerged as a pivotal post-training paradigm, yet it frequently suffers from unpredictable sub-optimum performance or even training collapses.
arXiv:2610.17531v1 Announce Type: cross Abstract: While it is known that quantization of large language models (LLMs) reduces memory usage via lower-bit weights, studies quantifying the resulting imp...
arXiv:2602. 03120v2 Announce Type: replace-cross Abstract: Post-Training Quantization (PTQ) is essential for deploying Large Language Models (LLMs) on memory-constrained devices, yet it renders models static and difficult to fine-tune.
The paper proposes two new 4‑bit quantization schemes for AdamW’s optimizer states, focusing on the rounding space of the second moment. Zero‑Inclusive Preconditioner‑space Stochastic Rounding (ZIP‑SR) keeps zero in the codebook and applies stochastic rounding in preconditioner space, while Zero‑Excluding EDEN (ZE‑EDEN) removes zero from the codebook and rescales the quantized block to reduce distortion. Experiments on GPT‑ and Llama‑style models from 130 M to 2.7 B parameters show that both methods close the validation‑loss gap to 32‑bit AdamW, achieving up to a 70 % reduction in the gap and outperforming TorchAO in fine‑tuning tasks.