HARP (Hadamard‑Preconditioned Adaptive Rotation Processor) is a learnable, structured two‑sided orthogonal processor that replaces fixed randomized Hadamard transforms in post‑training quantization of large language models. By representing rotations as sparse butterfly‑like block‑orthogonal stages and supporting mixed‑radix schedules, HARP adapts the quantization basis to each layer and calibration distribution while maintaining full‑precision equivalence. Across 2–4‑bit settings on Llama models from 1B to 70B, HARP consistently improves perplexity, delivers the strongest zero‑shot gains at 2 bits, and preserves deployment efficiency—achieving 128 tokens per second on Llama 2 7B at 2 bits, roughly 90% of RHT throughput and over twice the speed of FP16.
By Artur Zagitov, Gleb Molodtsov, Aleksandr Beznosikov
arXiv:2606. 02823v1 Announce Type: new Abstract: Two-bit weight quantization is attractive for memory-efficient LLM inference, but the standard W2 level set {-2,-1,0,+1} often collapses under aggressive W2A4/KV4 settings.
By Chi-Wei Huang, Chia-Chi Tsai
arXiv:2606. 31963v1 Announce Type: new Abstract: Modern LLM workflows move coordinate-indexed objects across checkpoints: steering vectors, sparse autoencoders, top-$k$ neuron sets, attribution lists, and merge alignments.
By John Sweeney
The paper surveys the use of linear, function‑preserving transforms in 4‑bit large‑language‑model (LLM) quantization, formalizing the underlying principle as the "Great Inversion"—the trade‑off between energy concentration favored by allocation‑flexible coding and within‑group flattening favored by grouped shared‑scale quantization. It reviews 200 works, classifies 43 transform methods by structure, data‑awareness, construction approach, and runtime cost, and examines how they interact with GPTQ rounding. The study also explores how different number formats (FP4, MXFP4, NVFP4) influence the optimal transform choice and outlines open research problems.
"whyItMatters":"The survey clarifies the conflicting objectives in transform‑based LLM quantization and provides a practical guide for selecting transforms based on deployment regime, thereby informing future research and deployment strategies."
By Ehsan Jokar
arXiv:2605. 28803v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models unify perception, reasoning, and control within a single policy, yet their multi-billion-parameter backbones and diffusion-based action heads make on-device deployment prohibitively expensive.
By Xinyu Wang, Mingze Li, Sicheng Lyu, Dongxiu Liu, Kaicheng Yang, Ziyu Zhao, Yufei Cui, Xiao-Wen Chang, Peng Lu
arXiv:2606. 24975v1 Announce Type: new Abstract: PaTH Attention showed that replacing RoPE's position-indexed rotations with accumulated data-dependent Householder reflections yields strong length extrapolation, though performance degrades at extreme context lengths.
By Mahesh Godavarti
arXiv:2608. 02947v1 Announce Type: new Abstract: The attention score with rotary position embeddings (RoPE) decomposes exactly into a sum over its 2D-rotation frequency pairs, and each pair's wavelength limits how far it can discriminate position.
By Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino, Takahiro Katagiri
arXiv:2607. 04302v1 Announce Type: cross Abstract: We present HiFA4, a post-training operator-level design that executes both QK^T and PV in FlashAttention as 4-bit HIF4 Cube GEMMs for LLM inference on Ascend NPUs, while maintaining the online softmax state in FP16.
By Hui Dong, Yanzhao Li, Jie Gao, Chunlu Li, Zhiyuan Zhang, Yupeng Sun, Zhenyuan Chen, Zhiqiang Zou
arXiv:2609.00066v1 Announce Type: cross
Abstract: NVFP4 is an efficient microscaling format for low-bit inference, but activation outliers can still degrade quantization accuracy within NVFP4 blocks....
By Yishan Yao, Binjun Li, Hanling Yi, Pengyu Li, Xiaoqing Liu, Zihan Yang, Xiaotian Yu, Zhiwen Yu
arXiv:2606. 01717v1 Announce Type: new Abstract: Instruction tuning aligns large language models, including multimodal ones, with diverse user intents, but scaling to heterogeneous mixtures is hindered by gradient interference and bandwidth-heavy synchronization.
By Minsik Choi, Geewook Kim
CORAM (Coherent Orthogonal Rotation for Model Merging) is a new method for combining fine‑tuned models without joint training or access to original data. It partitions each target weight matrix into row slices, represents each expert slice with its singular value decomposition in the base‑model SVD frame, and merges the task‑specific factors on their corresponding manifolds. The approach includes an amplification coefficient to counteract manifold averaging contraction, spread slicing to balance highly updated rows, and a residual pathway for non‑target layers, achieving improvements over existing orthogonal merging techniques across multiple model families and scales.
By Xinyi Sui, Ziran Liu, Nam Ling, Wei Wang, Wei Jiang
arXiv:2607. 05872v1 Announce Type: new Abstract: Memory-efficient optimizers such as GaLore train large language models by projecting gradients onto a rank-r subspace recomputed every T steps, assuming this subspace is a slowly drifting object that can be tracked.
By Noel Thomas