arXiv:2606. 04620v1 Announce Type: cross Abstract: LLMs have become the state-of-the-art algorithms for solving NLP tasks.
arXiv:2507. 07814v2 Announce Type: replace Abstract: We introduce a novel upper bound on the local Lipschitz constant of the dot-product self-attention block showing its dependence on the attention map distributions.
HyQuant introduces a hybrid-precision quantization framework for large language model (LLM) attention modules. It quantizes most attention states to low-bit formats while preserving a small set of vertical‑line tokens and local‑window states in full precision, guided by lightweight attention‑pattern signals. This design achieves near‑lossless accuracy across tasks while improving memory and hardware efficiency.
arXiv:2508.03351v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across diverse language tasks, motivating their extension to vision-la...
arXiv:2609.38166v1 Announce Type: cross Abstract: Recent LLMs increasingly adopt hybrid designs that replace standard attention with linear attention, such as Gated DeltaNet (GDN) and Kimi Delta Atte...
arXiv:2606. 00494v1 Announce Type: new Abstract: Post-Training Quantization (PTQ) and Low-Rank Adaptation (LoRA) constitute the standard pipeline for efficient Large Language Model (LLM) deployment.
The paper introduces DASH-Q, a post‑training quantization method that uses a diagonal Hessian approximation and iterative weighted least squares to reduce noise in curvature estimates. By discarding noisy cross‑channel dependencies, DASH‑Q preserves salient feature power and achieves superior performance in ultra low‑bit quantization. Across five large language models, it improves zero‑shot accuracy by an average of 7.01% and up to 14.01% over the strongest baselines, even with very small calibration datasets.
arXiv:2606. 04349v1 Announce Type: cross Abstract: Conventional Post-Training Quantization (PTQ) methods struggle with 4-bit Omni-modal Large Language Models (OLLMs) due to the extreme distribution heterogeneity and disparate outlier patterns across modalities.
The paper introduces a quantization technique for tabular foundation models that focuses on converting queries, keys, and values to FP8 and employing explicit FP8 matrix multiplication to accelerate attention calculations. It emphasizes aligning quantization errors between training and test rows to avoid accuracy loss, and demonstrates up to 1.7× speedup over 16‑bit kernels with no significant accuracy degradation on TabPFN‑v3 and TabICLv2 across TabArena and BeyondArena.
arXiv:2607. 08734v1 Announce Type: new Abstract: Post-training quantization is widely used to deploy large language models in resource-constrained settings, yet its evaluation relies almost exclusively on accuracy and perplexity.
arXiv:2602.04852v3 Announce Type: replace Abstract: Linear attention offers a computationally efficient yet expressive alternative to softmax attention. However, recent empirical results indicate tha...
The paper introduces OASIS, a method designed to stabilize dual‑normalized attention‑residual architectures by employing explicit null routing and token‑to‑depth null coupling. OASIS mitigates attention sinks and activation outliers, improving low‑bit quantization performance across several language‑model backbones. Empirical results show significant reductions in attention norms and perplexity, with notable gains on long‑context benchmarks.