LLM Compression

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

23 papers in the last four weeks, up 92% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 178

Oct 7, 2026cs.LG

OrBIT: Structure-Guided Embedding Compression

Embedding tables are among the largest components of modern language models. Most compression methods fix a coding geometry such as coordinate blocks, low-rank subspaces, or unrestricted codebooks, and optimize within it. We instead ask whether the coding geometry can itself be discovered. We introduce \emph{OrBIT}, a structure-guided embedding compression framework that learns reusable local geometry from orbit dynamics and uses it to constrain a small set of shared codewords. The global reconstruction residual then decides where the fixed coding budget is spent, while redundant overlapping charts let local errors compensate one another after gluing. Our theory shows how tight-chart geometry controls distortion, how the global residual directs sequential allocation, and how data-geometry-guided refinement improves the codec. The resulting orbit machinery is compiled away, leaving a compact decoder in which the learned structure governs what is stored, where capacity is allocated, and how local information is assembled globally. Across four LLM embedding tables, OrBIT achieves

37.9\times

compression on GPT-2 and over

23\times

on each 7B table relative to 16-bit storage, while delivering competitive rate-distortion performance against established quantization and low-rank baselines.

Yunied Puig, Amit Kumar Jaiswal

Jay Chaudhry Software Innovation Centre Indian Institute of Technology (BHU) Varanasi, India

Embedding Compression LLM Compression Vector Quantization

Oct 7, 2026cs.LG

SemanticFold: Latent Sequence Compression SeparatesLanguage Modeling, Decodability, and Reasoning

We study whether latent sequence compression of prompt prefixes preserves the capabilities that large language models rely on during inference. We introduce SemanticFold, a compression scheme that folds prefix hidden states at learned boundaries, and evaluate it across five model scales: Qwen3-1.7B, Qwen3-8B, SmolLM2-1.7B, Pythia-1.4B, and Pythia-6.9B. We use a fixed-target protocol: a frozen prefix is executed natively or compressed, and both arms teacher-force identical continuation tokens. This design rules out target-selection explanations for likelihood changes. We examine five endpoint families: fixed-target negative log-likelihood, finite-label reasoning accuracy, linear probe accessibility, open-ended generation, and systems-level memory and latency. We find that compression moves these endpoints non-monotonically and that they do not share a single compression threshold. On Qwen3-1.7B at compression ratio R=1.7, compressed-minus-native mean NLL decreases by 0.135 under paired bootstrap with 10000 draws. On SmolLM2 at R=1.2, the mean change is 0.013 higher than native. On both Pythia checkpoints, NLL is effectively unchanged. An NLL decomposition separating sequence shortening from the learned residual transform shows that the favorable Qwen likelihood is attributable primarily to residual adaptation rather than to shortening alone. MLP-only, which applies the transform without shortening, achieves 0.082 lower NLL than Full SemanticFold. Linear probe accuracy and macro AUC change by less than 0.03 in absolute value across conditions, with confidence intervals crossing zero. We conclude that preservation under latent compression has no single scalar certificate: language-model fit, decodability, and reasoning behavior answer different questions and can move in different directions under the same compression operation.

Mingyan Liu, Min Huang

LLM Compression LLM Inference LLM Reasoning

Oct 7, 2026cs.LG

Activation-Aware Weight Tensorization: A Calibration-Time Preconditioner for Tensor-Network LLM Compression

Post-training tensor-network compression replaces Transformer linear layers with Tensor Train (TT) or Tree Tensor Network (TTN) operators, but standard decompositions minimize weight-space Frobenius error rather than functional error under the layer's activation distribution. We propose Activation-aware Weight Tensorization (AWT), a training-free calibration wrapper that preconditions each weight matrix with a diagonal activation-derived scale before an unchanged TT/TTN solver and deploys the result with only an input-side elementwise rescaling. Across Llama 3.1 8B, Ministral 8B, and Qwen2.5 7B, AWT consistently improves vanilla TT/TTN tensorization at 2-6 times compression: under single-operator replacement, AWT closes 12-35% of the WikiText perplexity gap to the dense baseline across the three model families and 2-6 times compression settings; while under multi-operator Llama suffix replacement it closes 27-60% across attention-group and all-seven-matrix settings. The gains also transfer to downstream HellaSwag and ARC-Challenge evaluations. We further show that diagonal preconditioning is a robustness-modularity tradeoff rather than a diagonal-covariance assumption: a dense full-covariance oracle wins its own weighted objective in 80/81 cases, yet diagonal AWT gives better held-out functional fidelity in 53/81 cases. Together, these results position AWT as a principled, modular preconditioner for improving functional fidelity in fixed TT/TTN compression pipelines without modifying the decomposition solver.

Alessandro Beatini, Marco Maronese, Emanuele Rodolà

Sapienza University of Rome · Independent Researcher

LLM Compression Tensor Networks Tensor Decomposition TT Decomposition

Oct 7, 2026cs.LG

Shared Low-rank Basis Factorization for Data-free Mixture-of-Experts Compression

Mixture-of-Experts (MoE) large language models decouple capacity from compute through sparse routing, but their large parameter count creates storage and serving challenges. We analyze three MoE compression families: expert pruning, expert merging, and weight reconstruction, and derive structural error bounds showing that pruning and merging can incur non-vanishing errors tied to routing and expert heterogeneity. In contrast, weight reconstruction avoids these structural costs by preserving expert structure and routing. Motivated by the analysis, we propose Shared Low-rank Basis Factorization (SLBF), a data-free weight reconstruction method that uses rank-

k

bases shared among experts, enabling richer cross-expert sharing, faster convergence, and lower reconstruction error. A post-hoc gauge fixing removes redundant parameters at no representational cost. Across five MoE architectures spanning 16B to 122B parameters, SLBF consistently outperforms methods from all three compression families.

Tianxiao Cao, Jiahe Shao, Yuning Qiu +3

Kyoto University · The University of Tokyo · RIKEN AIP

LLM Compression Mixture-of-Experts Language Models Matrix Factorization Low-Rank Matrix Decomposition

Oct 6, 2026cs.LG

A Self-Pruning Transformer: Extreme KV-Cache Compression with Universal Attention

The large KV-cache size of modern LLMs creates a barrier to efficient deployment. Recent work has explored replacing attention layers' RoPE positional embeddings with alternative decay-based mechanisms, which can then be used to prune KV-cache during inference. However, these decay functions have limited expressivity, and in practice devolve into sliding-window-like eviction patterns. In this work, we propose a unifying framework for complementary and novel decay mechanisms, capturing complex key statistics and interactions while preserving expressive RoPE embeddings and Softmax attention. The resulting Universal Attention is a highly expressive and end-to-end trainable architecture, whose composite decay mechanism acts as a natural,

\textit{adaptive}

pruning criterion, removing tokens that contribute least to attention computation. Experimentally, Universal Attention achieves state-of-the-art

10\times

compression on natural language and synthetic task data, while

\textit{improving}

downstream performance compared to both state-of-the-art baselines and unpruned oracles. It further demonstrates superior long-context generalization with unprecedented

25\times

compression at length 16k.

Davis Wertheimer, Haochen Shen, Ahan Gupta +6

IBM Research, USA · SSAIL Lab, University of Illinois Urbana-Champaign

KV-Cache Compression Transformer Attention LLM Compression KV-Cache Pruning LLM Pruning

Oct 5, 2026cs.CL

Differentiable Bit-Widths: Co-optimizing Pruning and Quantization via SVD for Ultra-Efficient LLM Compression

SVD-based pruning and quantization have recently emerged as a promising strategy for the ultra-efficient compression of large language models. In these methods, compression is performed in two stages: components are first truncated, and the remaining ones are subsequently quantized. Although this decoupled pipeline benefits from both pruning and quantization, it requires separate optimization for each stage and fails to fully exploit their balance, which can lead to suboptimal performance under aggressive compression. To address this limitation, we propose a new LLM compression method that co-optimizes pruning and quantization in a unified framework. Our key idea is a differentiable method for learning component-wise bit-widths, allowing less important components to be assigned 0-bit precision and pruned away. Notably, our method performs favorably against two-stage baselines, even when subjected to extreme quantization settings (

1.61

bits) designed for ultra-efficiency. Code: https://github.com/MMAI-Laboratory/DBW.

Hankyul Kang, Jongbin Ryu

Ajou University

LLM Quantization LLM Pruning LLM Compression Neural Network Quantization Neural Network Compression

Oct 5, 2026cs.LG

The Optimization Landscape of Learning Compacted Context Models

Many works approach continual learning through the lens of infinite context windows. As an agent puts more observation into context (concretely the KV cache), compacting said context is akin to direct memory manipulation, without affecting the base model's weights. Many works pose KV compaction as an optimization problem: learn a smaller set of KV vectors that matches the behavior of the full KV cache. While this preserves base model behavior, optimizing through a frozen base model results in a highly nontrivial optimization problem with a brittle and flat loss landscape. In this paper, we characterize what makes these optimization problems difficult and demonstrate that a heavily simplified Perceiver-based architecture not only matches performance of a full Perceiver transformer in continuous context compaction, but outperforms baselines on compaction utility. Results are presented on MCQ tasks across Finance, Legal, Gutenberg, and Code.

Thomas Villeneuve, Alex Sandomirsky, Charles O'Neill +2

Base Labs

LLM Compression KV-Cache Compression

Oct 4, 2026cs.AI

The Functional Structure of Post-Compression Recovery in Low-Rank LLMs

Different low-rank compression methods can produce compressed LLMs that respond differently to the same post-compression recovery procedure, and relative advantages observed between methods at the compression endpoint may shrink, grow, or even reverse after recovery. We ask whether this recovery heterogeneity reflects functional structure beyond scalar loss evolution, and how that structure evolves throughout recovery. Our results establish that this heterogeneity reflects a reproducible compression-induced functional structure, which we formalize as recovery pressure. To characterize this structure consistently throughout recovery, we develop a standardized functional characterization within each backbone that is applicable across heterogeneous low-rank methods. The primary backward characterization reveals reproducible module-wise structure across independent probes, while a complementary forward-only characterization recovers related structure without loss or backpropagation. We further find that recovery pressure measured at the endpoint is associated with subsequent recovery response; during recovery, its module-wise structure is reorganized non-uniformly, and localized updates induce distributed responses beyond directly updated modules. Further evidence indicates that tracking this evolving structure provides a complementary functional view of recovery progress alongside scalar loss.

Zishan Shao, Liang Tian, Georgiy Zemlevskiy +10

Duke University · Wake Forest University · Carnegie Mellon University +2

LLM Compression Low-Rank Compression LLM Post-Training

Oct 1, 2026cs.AI

ITC-MoE: Importance-guided Token-aware Compression for MoE Diffusion Language Models

Mixture-of-Experts (MoE) Diffusion Language Models (DLMs) offer flexible parallel decoding and increased model capacity, but their large number of expert parameters incurs substantial computation and storage costs. Existing low-rank MoE compression methods largely rely on static factorization and fixed rank allocation, which overlook the distinctive properties of MoE DLMs. Specifically, we identify two properties: cross-mode non-uniform redundancy, where parameter redundancy and sensitivity to rank truncation vary across the input, output, and expert modes, and token-wise utilization variation, where hot and cold tokens exhibit distinct spectral characteristics and expert activation patterns. To address these challenges, we propose ITC-MoE, an Importance-guided Token-aware Compression framework for MoE DLMs. ITC-MoE consists of two complementary components. First, Importance-guided Adaptive Tucker Compression (IATC) incorporates activation and gradient importance into expert weight transformation, jointly factorizes expert weights across multiple modes, and adaptively allocates ranks under a fixed parameter budget. Second, Token-aware Compensation and Routing (TCR) applies lightweight low-rank compensation to compression-sensitive hot tokens and restricts the candidate expert set for cold tokens with concentrated routing patterns. By jointly adapting compression capacity and inference execution to both parameter redundancy and token-wise variation, ITC-MoE substantially reduces the computation and storage costs of MoE DLMs while preserving their generation quality. For example, on SDAR-30B-A3B-Chat-b32, ITC-MoE maintains an accuracy of 96.33% on MultiArith under a 30% compression budget, while achieving up to a 7.22x end-to-end speedup. The code is publicly available at https://github.com/lianjunl13-sudo/ITC-MoE.

Lianjun Liu, Shipeng Li, You Huang +5

Hainan University, Haikou, China · Xiamen University, Xiamen, China · Zhejiang Normal University, Jinhua, China

Mixture-of-Experts Language Models LLM Compression Mixture-of-Experts Inference Tensor Decomposition Diffusion Language Models

Sep 30, 2026cs.CL

Sequential Functional Structured Tucker Compression for Large Language Model Attentions

Post-training compression of LLM attention is often formulated as independent matrix approximation, ignoring both the shared structure among attention projections and the representation shift introduced by earlier compression. We propose FTC, a sequential structured compression framework that adapts the approximation to the current compressed model while jointly exploiting the native Q/K/V head structure under a fixed storage budget. The output projection is handled separately to account for the changed post-attention representation. FTC requires neither fine-tuning nor gradient-based recovery. Across seven decoder-only LLMs from 6B to 32B parameters, FTC achieves the lowest WikiText-2 perplexity among the compared methods at every tested keep ratio on five modern GQA models, with the largest gains under aggressive compression. The improvements transfer to downstream tasks and remain substantial at the 32B scale.

Jiangfeng Chen, Xinyu Wang, Tianshuo Yan +4

University of Manitoba · McGill University · Simpleway +2

LLM Compression Decoder-Only Language Models Tensor Decomposition Low-Rank Compression

Sep 30, 2026cs.CL

How Divergence Becomes Decision Flips in Compressed Language Models

Compression reports summarize how far a compressed language model moved from the dense one, usually by a KL divergence; a deployment that relies on the dense model's outputs needs to know how many of its decisions changed. We show that total variation, not KL, answers this directly. Across 802 compressed and perturbed copies of 19 open models on five corpora and nine mechanically unrelated perturbation families, the rate at which the arg-max token changes (the \emph{flip rate}) tracks total variation at a ratio with median

1.05

, with no fitted constant. KL converts into flips only through its square root and a factor that varies fourfold across models and corpora, because KL averages over tokens before the root is taken; first-order statistics averaged per token, such as Hellinger distance, avoid this, but reports rarely give them. As a result, of two compressors reported on different models and corpora whose flip rates differ by at least

10%

, KL assigns the smaller divergence to the one that changes more decisions in

11%

of cases, total variation in

1%

. Two pre-registered tests mark the limits: on a held-out code corpus the ratio held for all eight models while three predictions about KL each failed for half of them or more, and on three new models with real kernels it stayed in its band for 37 of 38 checkpoints but fell below one on code for two models. In vLLM speculative decoding, total variation measured under teacher forcing predicts greedy draft acceptance with a mean relative error of

1.1

--

2.4%

, without the task-specific calibration that KL needs.

Beatriz Almeida Felicio

Instituto de Informática (INF) Universidade Federal de Goiás (UFG)

LLM Evaluation LLM Compression Distribution Matching

Sep 30, 2026cs.LG

Learning Functional Subspaces for Neural Network Compression

Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factorization reduces both while keeping the matrices dense, and thus efficient on standard hardware. Existing methods, however, choose the subspace to remove from each weight matrix with local closed-form criteria: activation energy, layer-wise reconstruction error, or a quadratic approximation of the loss. These criteria ignore how errors propagate through the network, so at high compression the errors compound with depth and performance collapses. We introduce Learnable Subspace Projections (LSP), which instead learns the subspaces to discard end-to-end. Each linear layer, or tied group of layers that read the same activations, is assigned an orthogonal projector. All projectors are optimized jointly against a global objective--the KL divergence to the dense model's output distribution or the model's original training loss--while the pretrained weights remain frozen. Projectors are initialized from a whitened SVD truncation, and ranks are allocated by the output KL each projector induces per parameter saved. After training, the projectors merge into standard low-rank factors, with each tied group sharing one factor. In attention, this also lets the model cache one narrow latent in place of full keys and values. Across LLMs (OPT-125M/1.3B, Qwen3-4B, Llama-2-7B) and ViT-B/16, LSP outperforms baselines, and its advantage widens as compression increases. At -70% compression, LSP brings Llama-2-7B to 10.9 WikiText-2 perplexity and 42.2% mean zero-shot accuracy, versus 13.3 and 36.0% for the strongest baseline. The factorized model decodes up to 1.6x faster than the dense model at small batch sizes, and aching the shared latent shrinks the combined memory of weights and KV cache by 13.5x at a 128k-token context, versus at most 6.5x for untied baseline factorizations.

Massimo Bini, Anders Christensen, Stephan Alaniz +5

Helmholtz Munich · Technical University of Munich · MCML +6

LLM Compression Low-Rank Matrix Decomposition Low-Rank Compression Dimensionality Reduction Neural Network Compression

Sep 30, 2026cs.LG

IrekoGPT: Turning Structured Pruning into Post-Hoc Slimmable LLMs

We introduce IrekoGPT, a post-hoc method for converting pretrained LLMs into slimmable models whose width can be adjusted at inference time. Building on SliceGPT, we retain its projection matrices without pruning them, allowing a single model to expose nested subnetworks at different widths. We improve robustness by calibrating each layer across multiple compression ratios, and correct downstream linear layers through gradient-free ridge regression. Across Llama and Qwen models, preliminary results show improvements over naive PCA-based slimming, with the largest gains at high compression. Code is available at https://github.com/aimagelab/IrekoGPT

Pietro Moriello, Pietro Buzzega, Angelo Porrello +1

AImageLab, University of Modena and Reggio Emilia, Italy

LLM Compression LLM Inference Acceleration LLM Post-Training

Sep 30, 2026cs.LG

MoRA: MoE Pruning via Router Bias Learning and Expert Approximation

Mixture-of-Experts (MoE) models enable parameter scaling with limited per-token computation by activating only a small subset of experts for each token, but deploying them still requires loading the complete expert pool into memory. Structured expert pruning can effectively reduce the memory usage by removing experts. However, existing pruning methods either use expert ranking criteria that are not well aligned with model performance or rely on effective expert subset searching that is computationally expensive. Moreover, these methods typically overlook the routing-behavior redundancy among the retained experts. In this paper, we propose MoE Pruning via Router Bias Learning and Expert Approximation (MoRA), a framework for structured MoE expert pruning. We introduce a learnable router bias for each expert and optimize these biases by minimizing the language-modeling loss and a routing-diversity regularizer. The learned router biases sharpen the routing probability distributions to identify experts critical to model performance while encouraging the selection of experts with diverse routing preferences. In addition, we introduce an expert approximation mechanism as a post-pruning enhancement. It leverages the remaining experts to approximate the outputs of pruned experts by affine transformation, further improving the performance of the pruned model. We evaluate MoRA on Qwen3-30B-A3B, DeepSeek-V2-Lite, and Moonlight-16B-A3B, removing 25% and 50% of the routed experts in each MoE layer. Extensive experiments on nine zero-shot benchmarks show that MoRA outperforms state-of-the-art pruning algorithms. Our code will be released.

Yushuai Sun, Zikun Zhou, Lin Gao +2

Harbin Institute of Technology, Shenzhen

Mixture-of-Experts Pruning LLM Compression Expert Routing Mixture-of-Experts Models

Sep 29, 2026cs.CR

Security-Enhanced Seed-Based Weight Quantization for Large Language Models

Large language models (LLMs) incur substantial storage, memory-bandwidth and energy costs, motivating compact weight representations. Existing seed-based compression methods reconstruct weights from compact pseudo-random representations but do not explicitly account for the non-uniform sensitivity of model weights. We introduce Seed-Q, a security-enhanced sensitivity-aware seed-based weight compression framework that uses lightweight Linear Feedback Shift Register (LFSR)-based weight generation with non-uniform bit allocation. Our approach assigns larger representation budgets to sensitive weights while aggressively compressing less sensitive regions. Importantly, this non-uniform allocation requires no side-information: the decoder deterministically reconstructs the bit-allocation schedule, with no rung depending on the decoded weights, eliminating the need to store per-block metadata or use calibration data while preserving the baseline coding rate. Experiments across diverse LLMs show that Seed-Q matches 4-bit perplexity of SeedLM with fewer bits, while at the same 4 bits/weight it reduces both perplexity degradation and zero-shot accuracy loss relative to SeedLM. We also show that Seed-Q simultaneously achieves high security against bit-flip attacks on model parameters, as bit corruption affects multiple reconstructed weights, greatly amplifying its impact and making it easier to detect. We further implement Seed-Q in an ASIC-based accelerator and demonstrate modest hardware overhead compared to prior seed-based approaches.

Qiuyu Ren, Sudipta Paria, Aritra Dasgupta +1

Department of Electrical and Computer Engineering (ECE) University of Florida Gainesville, FL 32611, USA

LLM Quantization LLM Compression LLM Security Weight-Only Quantization Neural Network Compression

Sep 28, 2026cs.LG

Output-aware Residual Stream Pruning for Large Language Models

Residual stream pruning methods reduce inference cost by shrinking the model's hidden dimension, but existing approaches typically choose these dimensions by minimizing activation reconstruction error. This criterion implicitly treats all perturbation directions as equally important, ignoring the sensitivity of downstream layers. We introduce a sensitivity-aware approach to residual-stream pruning that directly accounts for this direction-dependent sensitivity. Using a second-order approximation to the output KL divergence, we characterize the effect of a residual-stream perturbation through both its activation covariance and the local sensitivity of the model output. The resulting subspace selection objective couples these two quantities, but is difficult to optimize directly. We derive a tractable spectral upper bound that reduces subspace selection to an eigendecomposition of a sensitivity-weighted covariance matrix, retaining the efficiency and structural simplicity of rotation-based pruning methods. Across several instruction-tuned language model families, our method consistently reduces calibration KL divergence relative to activation-only pruning and improves perplexity and downstream task performance over a range of compression levels. Our results show that preserving activation energy alone is insufficient for residual-stream pruning, and that explicitly accounting for how perturbations propagate to the model output provides a more effective criterion for selecting dimensions to remove.

Chayne Thrash, Kevin Chen, Soheil Kolouri

Department of Computer Science Vanderbilt University Nashville, TN 37235, USA

LLM Pruning LLM Compression Neural Network Pruning

Sep 28, 2026cond-mat.dis-nn

Pre-registered tests of solid-state-physics-inspired LLM compression: a cluster-level negative result at small-language-model scale

We report a three-month autonomous research-agent program testing five solid-state-physics-inspired compression mappings on pretrained language models, with predictions committed to git before any pilot data and a 3-sigma gate deciding PASS or SHELVE. The common anchor -- area-law / Kohn-nearsighted decay of the one-particle density matrix -- has a distance face (P001 Wannier, P002 tight-binding) and a rank face (P003 DMRG-truncated MLPs, P005 Wilson-RG, P011 tensor-train embeddings). P005 was pre-empted at Phase 1; three of four Phase-3 pilots were falsified. On the attention face, GPT-2-medium attention-versus-distance is best fit by a stretched exponential in 12 of 16 median-layer heads once probe padding is excluded, and a tight-binding cutoff costs +96% perplexity (P002); on Pythia-160M the Wannier sparsity 0.054 +/- 0.004 is indistinguishable from PCA, random-Haar and identity baselines (P001). On the rank face, per-token tensor-train bond dimension does not track surprisal (r = 0.016 vs a pre-registered 0.65) and the format inflates rather than compresses (P011). P003 is mixed: its scaling claim shelved (r = -0.434), its MPO premise died at stage-0, and its cross-paper check, r = 0.523 as first written, collapses to 0.047 under the same correction, leaving both cross-paper checks null. The results invert the pre-registered prediction that most attention heads behave like Kohn-nearsighted insulators, pointing instead to critical, glassy or heavy-tailed regimes; the inversion is specific to the <= 350M scale tested, while the rank-face no-gain result held to 7-8B. We contribute the pre-registration + 3-sigma + cluster-framing + append-only-catalogue discipline -- including why our own enforcement gate was designed but not deployed -- four pre-registered negative results with full data release, and the inversion. The catalogue holds eighteen concluded studies, seventeen negative.

Jun-qiang Lu

Department of Physics, University of Puerto Rico, Mayagüez, PR 00680, USA

Tensor Networks LLM Compression Low-Rank Compression

Sep 27, 2026cs.LG

GroupMask: Layer-Adaptive Group-wise Sparsity for Semi-Structured LLM Pruning

Semi-structured pruning compresses large language models (LLMs) while keeping a regular sparse structure, but the prevailing N:M pattern fixes the same local sparsity ratio in every layer. Layer-adaptive sparsity allocation improves unstructured pruning, yet it has been reported to be less effective under N:M sparsity, leaving open whether adaptive allocation is of limited value for semi-structured pruning in general or only under the fine-grained N:M pattern. We examine this question with group-level sparsity, which partitions each weight matrix into regular groups, retains or prunes each group as a whole, and allows each layer's sparsity ratio to vary under a global budget. We propose GroupMask, which generates the group selectors of all layers with a lightweight hypernetwork, relaxes them with a Gumbel-Sigmoid parameterization and a straight-through estimator, and learns them through sparsity-budget regularization and self-distillation while keeping the pretrained weights frozen. On LLaMA-2-7B at 50% sparsity with the same

1\times256

group size, learned layer-adaptive allocation reduces WikiText-2 perplexity from 10.02 to 8.30 and raises the average zero-shot accuracy from 0.455 to 0.496 relative to a uniform per-layer ratio. GroupMask obtains the lowest WikiText-2 perplexity on LLaMA-2-7B and the highest average zero-shot accuracy with Alpaca calibration among the evaluated baselines on five LLaMA and Qwen models. Our code is available at https://github.com/ZhengaoLi/GroupMask.

Zhengao Li, Shuoqiu Li, Xiaofang Zhang +7

Florida State University · University of Connecticut · College of William & Mary +1

LLM Pruning LLM Compression Structured Sparsity Neural Network Pruning

Sep 24, 2026cs.LG

RAZOR: Pruning Replaceable Experts in LLMs

Mixture-of-experts (MoE) models activate only a few experts per token but store the entire expert pool. Pruning this pool requires identifying experts whose removal preserves model behavior. Routing frequency and output magnitude do not fully describe deletion damage, which also depends on how the surviving and replacement experts compensate for the removed output. We introduce RAZOR, a training-free pruning method based on consensus residuals, the deviations of expert outputs from their original weighted mixture. At a fixed layer input, these residuals give the exact output change for a single deletion under survivor renormalization and router refill. RAZOR aggregates this damage by conditional root mean square and selects experts under a layerwise budget using forward computation alone, without gradients, subset search, or recovery training. Against frequency, activation-norm, and REAP baselines on GLM-4.7-Flash and Qwen3.6-35B-A3B at 25% and 50% expert removal, it attains the highest macro average over nine reasoning-intensive tasks in all four model-budget settings, gaining 2.12-5.59 points over REAP and lowering reverse KL in all four. On DeepSeek-V4-Flash-0731 and Hy3, it also achieves the highest macro average among the three residual criteria. Local exactness does not guarantee better joint pruning. Generation analyses show changes in diversity, formatting, and termination despite higher task scores.

Mingyang Song, Mao Zheng

Foundation Model Department, Tencent, China

Mixture-of-Experts Pruning LLM Pruning Mixture-of-Experts Language Models LLM Compression

Sep 23, 2026cs.CL

Distilling Sequential Computation in Transformer Language Models

Transformer language models process sequences token by token in an autoregressive manner, making growing contexts increasingly expensive. Yet many adjacent token spans are highly predictable or frequently occur as stable units, suggesting that their representations may be compressible. We introduce a method for distilling sequential computation by replacing spans of input tokens with collapsed representations, computed on the fly by a lightweight merge module. This module generates a single surrogate embedding from a sequence of static token embeddings that captures the functional role of the multiple tokens, allowing pretrained models to operate on compressed inputs without architectural changes or re-training. We apply this approach during inference to compress both prompts and intermediate decoding steps, using a rollback mechanism to substitute stored multi-token KV cache entries with their single-step surrogates. Experiments across diverse models show that the merge module can be used to reduce effective sequence length by up to 40% with minimal accuracy degradation across language modeling evaluations and downstream tasks, including question answering, summarization, commonsense reasoning, and long-form mathematical reasoning. Additional lightweight adaptation of the merge module further improves the accuracy-compression trade-off in selected settings. These results demonstrate that sequential token computation in Transformers can be effectively approximated through condensed surrogate representations that approximate the original behavior without model updating.

Zixuan Lan, Jessica Yang, Yanhong Li +2

The University of Chicago · Toyota Technological Institute at Chicago · Independent Researcher +1

LLM Compression Long-Context Language Model Inference LLM Inference Acceleration

Sep 16, 2026cs.LG

Higher-order pruning of experts in mixture-of-experts language models

Mixture-of-Experts (MoE) language models suffer from large parameter counts, which create a significant memory bottleneck. Expert pruning is the most direct approach for reducing this parameter count, yet existing methods make pruning decisions for each expert independently, and assume experts' contributions are purely additive. In reality, expert usage in MoEs is inherently cooperative. We derive HOPE (Higher-Order Pruning of Experts), a second-order pruning objective which provably minimizes an upper bound on the error resulting from pruning. We show that REAP (a state-of-the-art first-order pruning method) is a special case of HOPE where interaction terms are ignored. Across three frontier MoE models (up to 122B parameters), two distinct calibration sets, and multiple benchmarks (including math, instruction following, coding, and an agentic suite), we demonstrate that HOPE produces better pruning decisions than existing methods, and its advantage is most pronounced at high pruning rates and on challenging agentic workloads. At 50% pruning, HOPE outperforms all baselines and achieves an average rank of 1.58 out of 5 methods (versus 2.42 for the next-best method, REAP), with gains of up to +6.1% on agentic coding. Over all conditions, HOPE again achieves the best average rank and surpasses every other method in the majority of head-to-head comparisons. By preserving cooperative expert structure that first-order methods ignore, HOPE enables aggressive compression with minimal degradation, particularly on complex tasks where diverse expert combinations are invoked over long sequences.

Alex M. Tseng, Prannay Kaul, Luca Zancato +2

AI Fundamental Research AWS Agentic AI

Mixture-of-Experts Pruning Mixture-of-Experts Language Models LLM Compression Neural Network Pruning

Sep 16, 2026cs.LG

Layer-wise Curriculum Learning for Efficient LLM Compression

In this paper, we introduce layer-wise curriculum learning for efficient LLM compression. The proposed method facilitates the knowledge transfer from the teacher model to the student model, utilizing a curriculum learning approach that begins with easier optimization tasks and progressively tackles harder ones. In order to adopt the layer-wise learning in LLM compression, we partition the whole model into multiple segments consisting of layers, thereby enabling more computationally efficient knowledge transfer for LLMs. Based on our theoretical analysis of cumulative error phenomenon, layer-wise curriculum learning accelerates convergence while stabilizing the knowledge transfer process. In addition, we present a feature caching method with a multi-threading strategy to efficiently address feature misalignment across layers, maximizing GPU utilization. Consequently, our method exhibits advanced model compression performance, as well as high computational efficiency in terms of minimized memory usage and short training hours. Experiments on multiple datasets show that the proposed method achieves state-of-the-art performance while reducing GPU memory usage and training hours by more than 50% on BERT and GPT-2. Moreover, it outperforms the other pruning methods on LLaMA-family and Qwen models under the same training hours, with a lower GPU memory footprint.

Donggeon Lee, Dooyeon Na, Seungmin Oh +1

Ajou University, South Korea

LLM Compression Curriculum Learning Knowledge Distillation Memory-Efficient Training

Sep 14, 2026cs.AI

Breaking the 1.58-bit Barrier for Ternary LLMs

Ternary Large Language Models (LLM) store every weight as one of three symbols

\{-1,0,+1\}

, so the cost of a ternary model is conventionally referenced to the information-theoretic

\log_2 3 \approx 1.585

bits per weight. The prevailing deployment format packs five ternary weights into one byte (five-trit packing), and due to the power-of-two group sizes used in practice this rounds up to

1.625

bits per weight. This effective storage bit-width treats the three symbols

\{-1,0,+1\}

as equiprobable. We measure the actual symbol distribution of 29 ternary LLM models and find that zeros account for up to

51.5\%

of all weights. Motivated by this finding, we introduce BITCOS, a simple distribution-adaptive layout comprised of a dense presence bitmap plus a compacted sign vector, and costs

2 - z

bits per weight element given a zero density

z

in the model's weights. BITCOS stores weights more compactly than the five-trit packing in 26 of the 29 tested models, and reaches

1.485

bits per weight on the sparsest of them. BITCOS is amenable to efficient unpacking on modern processors and GPUs, and we present optimized unpacking sequences for AVX-512, AVX2 and Intel Xe2 GPUs. Measured against production state-of-the-art ternary matrix-vector multiplication kernels, at the zero densities real-world ternary models exhibit, the realized gain with our proposed layout is up to

1.28\times

. Finally, we illustrate end-to-end LLM inference results on 5 different platforms (client and server CPUs, integrated and discrete Xe2 GPUs) where decode throughput improves by up to

1.18\times

on CPUs and

1.27\times

on GPUs.

Evangelos Georganas, Alexander Heinecke, Pradeep Dubey

Intel Corporation

Ternary Quantization LLM Compression LLM Inference Acceleration

Sep 14, 2026cs.LG

Per-Matrix Optimality Is Not Enough: Three-Level Optimization for Low-Rank LLM Compression

Per-matrix singular value decomposition (SVD) truncation is Eckart-Young optimal in the whitened Frobenius norm, but errors from independently compressed matrices compound through the block's nonlinear forward pass. Inspired in part by hierarchical variational optimization in quantum many-body methods, we introduce a three-level chain that widens optimization scope from individual matrices to Transformer blocks to the full model: whitened SVD~(L1), block-level joint optimization~(L2), and end-to-end language-modeling loss refinement~(L3), all from 256 calibration sequences, with no instruction or recovery data. On LLaMA-7B at 60% compression, the chain reduces WikiText-2 perplexity from 42.1 to 19.1 to 11.4. The block-level stage acts as a regularizer: skipping it worsens Penn Treebank (PTB) perplexity by 24 points, a gap that additional end-to-end training did not close in our experiments. Perplexity gains hold across 20-80% compression, five architectures up to 13B parameters, and both in-distribution and out-of-distribution benchmarks, though the cross-architecture rows use architecture-specific configurations and the ratio sweep was not run under one common protocol. With more calibration data, skipping the block-level stage becomes competitive, revealing an offline compute--data trade-off. We therefore claim improvements only in perplexity and compression fidelity; downstream accuracy remains well below the dense model.

Huicheng Zhang, Xiyao Feng, Ze-Tong Li +6

Hong Kong University of Science and Technology (Guangzhou), Guangdong 511453, China · QudeLeap Research, Shanghai 200030, China

Model Compression LLM Compression Low-Rank Matrix Decomposition Low-Rank Compression Singular Value Decomposition

Sep 14, 2026cs.CL

To Each Language Its Tokenizer: Modular Tokenizers for Efficient Multilingual LLMs

Multilingual Large Language Models (LLMs) traditionally rely on a single vocabulary shared by all supported languages, which can lead to uneven compression across them. Moreover, their large embedding and output matrices increase memory usage and slow inference, notably for small-scale models. It is also wasteful as models are often used for only a subset of languages. To address these issues, we introduce a modular framework for multilingual model training. First, we propose methods to learn large modular BPE and Unigram tokenizers that enable extraction of subtokenizers tailored to any language subset. These subtokenizers achieve compression on par with monolingual tokenizers and improve cross-lingual fairness. Second, we design a pretraining strategy that samples subtokenizers to form batches, restricting predictions to the relevant vocabulary subset and allowing efficient training despite a large vocabulary. This supports efficient inference with any combination of language-specific vocabularies. Therefore, it reduces memory usage and speeds up inference in models without sacrificing performance.

Franck Signe, Hippolyte Pilchen, François Yvon +1

Kyutai, Paris · Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG, Grenoble · Sorbonne Université, CNRS, Institute of Intelligent Systems and Robotics, Paris

Multilingual Language Models LLM Compression LLM Inference Acceleration

Sep 14, 2026cs.CL

Dynamic Semantic Compression for Efficient Latent-Space Inference in Large Language Models

Large Language Models (LLMs) primarily perform inference at the token level, resulting in substantial memory overhead and compromised computational efficiency. In this paper, we propose a Dynamic Semantic Extraction and Inference (DSEI) framework, which achieves segment-level inference within the latent space through a two-stage training strategy. First, we construct a Dynamic Semantic Autoencoder (DSAE) via self-supervised learning. DSAE dynamically extracts segment-level semantics and compresses them into compact latent representations via adaptive semantic weighting and gated fusion. Subsequently, we integrate the DSAE into the LLM architecture and train the model to infer over dense latent space. DSEI substantially reduces both input and generation sequences and significantly enhances inference efficiency. Extensive experiments conducted on the Wanjuan dataset demonstrate that DSEI reduces perplexity by 48% compared to static sentence-level latent inference baseline. Furthermore, compared to standard LLMs using token-level inference, DSEI accelerates inference speed by 2.5

\times

and reduces memory overhead by 90%.

Peipei Li, Dongsen Zhang, Yuchen Liu +1

Beijing University of Posts and Telecommunications, Beijing, China

LLM Compression LLM Inference Efficient Language Model Inference

Sep 12, 2026cs.SD

X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation

Reducing audio-encoder depth lowers the inference cost of speech large language models, but removing complete blocks perturbs the embeddings consumed by the decoder and can cause deletion and premature end-of-sequence errors. We introduce X-AuT, a progressive framework that selects layer combinations through short behavioral probes and restores the pruned model through representation alignment, cross-scale distillation, scheduled student-policy supervision, and LoRA finetuning. The language-model backbone remains frozen, while attention LoRA adapters and the tied output embedding adapt during distillation. Training uses the highest-agreement tier from a transcript-consistency pipeline, followed by source reweighting during finetuning. On ten public Chinese--English benchmarks, compressing Qwen3-ASR-0.6B from 18 to 16 audio-encoder layers reduces macro-average error from 5.61% to 5.27%. The 14-layer model reaches 5.75% with 20.7% fewer audio-tower parameters. Under the matched recipe, the 1.7B teacher yields 5.55% mean error, compared with 8.45% for self-distillation, and progressive 18

\rightarrow

14 pruning outperforms direct pruning (5.75% vs. 6.73%). These single-run results establish two practical operating points and show that the accuracy effects vary across benchmarks. Project website: https://xpeng-ai.github.io/x-aut

Haojun Zhang, Yi Zou, Min Chen +7

XPeng Inc.

LLM Compression Language Model Distillation Speech Language Models Neural Network Pruning

Sep 11, 2026cs.LG

LILA: Calibration-Free Structured Pruning of Large Language Models via Latent Spectral Geometry

Structured pruning of large language models (LLMs) offers hardware-efficient compression, yet existing methods require calibration data, gradient computation, or large auxiliary policy networks at pruning time. LILA (\emph{Latent-Informed Layer Analysis}) scores neuron importance via the Kolmogorov--Smirnov (KS) distance between empirical singular value distributions of the full and neuron-ablated feed-forward network (FFN) weight matrix, providing a closed-form spectral rule requiring no training, calibration data, or auxiliary network. Without any fine-tuning, LILA surpasses PruneNet (45M-parameter RL policy) by 1.57~~pp in zero-shot accuracy on LLaMA-2-7B at 25% sparsity, and outperforms WikiText-2-calibrated SliceGPT by up to 6.0~~pp across all sparsity levels, while preserving the original architecture. After one epoch of LoRA recovery fine-tuning, LILA achieves highly competitive performance, matching the heavily calibrated SliceGPT baseline to within a 0.48~pp margin across LLaMA-2-7B and Phi-2, despite using zero calibration data. A Neural Tangent Kernel analysis confirms a 22

\times

reduction in functional distortion versus random pruning, providing theoretical grounding for the spectral importance criterion. Finally, extending LILA to dynamically allocate sparsity budgets via KS-scores yields state-of-the-art generative preservation at moderate compression, while uncovering fundamental single-layer architectural bottlenecks at higher compression regimes.

Sankar Behera, Dhruv Singh, Anshika Agnihotri +3

CSE, IIT Jammu · Mathematics, IIT Jammu · IT, EC Bikaner +1

LLM Pruning LLM Compression Structured Pruning Neural Network Pruning

Sep 10, 2026cs.LG

Scaling Post-Training Ternarisation to Qwen3-8B Capability Retention, Reproduction, Lossless Packing, and Packed Execution

Ultra-low-bit language models promise reductions in storage and memory traffic, but a nominal "1.58-bit" label does not specify the deployed representation or its execution cost. We study a scale-up of an aggressive post-training conversion pipeline from Qwen3-4B to Qwen3-8B. The conversion uses KOTMS rotation, E2M-ATQ adaptive ternarisation, and GPTQ-style error compensation in a weight-only A16 configuration. We do not claim these algorithms as new. Our contribution is the end-to-end scale-up characterisation: an external reproduction gate, matched 4B/8B capability analysis, cross-corpus perplexity, effective-bit accounting, lossless lattice-aware packing, and direct packed execution. The 8B model reaches a three-corpus perplexity ratio of 1.361x, with WikiText-2, C4, and PTB ratios of 1.318x, 1.393x, and 1.371x. On eight zero-shot tasks at n = 500, mean accuracy is 64.6% versus 72.4% for FP16, corresponding to 78.5% chance-corrected retention and a 7.8-point absolute cost. The matched 4B run retains 69.6%, yielding an 8.9-point 8B advantage. The packed checkpoint is 8.24 GiB and preserves the recorded perplexity to measurement precision. Direct packed execution reaches 15.52 tokens/s in 7.35 GiB, while a preliminary packed GEMV remains slower than FP16 cuBLAS. The result is a validated scale-up baseline: model size improves robustness to aggressive post-training discretisation, actual serialisation is solved for the measured artefact, and direct execution is feasible, while broader seeds, calibration distributions, and kernel optimisation remain open.

Anirudh Malik, M Sparsh Mehra, Poojith Devan

OneBit AI

LLM Quantization Ternary Quantization LLM Compression Weight-Only Quantization Post-Training Quantization

Sep 9, 2026cs.LG

OMP-MoE: Efficient Expert Pruning for Mixture-of-Experts LLMs via Orthogonal Matching Pursuit

Mixture-of-Experts (MoE) models enable efficient scaling of large language models but face critical deployment challenges due to massive memory requirements. Existing pruning methods either incur prohibitive search costs or neglect the dynamic interdependencies between experts. To address these challenges, we present OMP-MoE, a novel training-free compression framework for reducing expert redundancy in MoE-based LLMs. Based on observations of expert contribution patterns, we reformulate the pruning problem as a sparse signal reconstruction task solved through Orthogonal Matching Pursuit. Specifically, our method first treats individual expert contributions as dictionary atoms and selects experts that greedily minimize reconstruction error with linear computational complexity. Then, we optimize cross-layer expert allocation through a water-filling strategy that accounts for both reconstruction quality and routing stability. Finally, we introduce OMP-MoE†, an adaptive inference mechanism that dynamically adjusts expert activation based on energy prediction. Comprehensive experiments on Qwen, DeepSeek-V2, GPT-OSS, and Mixtral MoE demonstrate consistent improvements over existing methods at 25-50% pruning ratios. For Qwen3-30B-A3B at 50% compression, we retain 93.3% of original performance, achieving 33

\times

faster search and 1.55

\times

inference speedup. Codes will be available after acceptance.

Dezhi Li, Lujun Li, Qiyuan Zhu +4

The Hong Kong University of Science and Technology

Mixture-of-Experts Pruning Mixture-of-Experts Language Models LLM Compression LLM Inference Acceleration