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

Sep 2, 2026cs.LG

Scalable Kronecker-Fisher Approximation: Efficient Hessian Analysis for Billion-Parameter Language Models Compression

In this paper, we propose a scalable Kronecker-based approximation that captures cross-layer interactions without storing the entire Fisher matrix, enabling practical Hessian analysis for billion-parameter networks where full computation is infeasible. Our approach reveals consistent vulnerability patterns: value projection layers exhibit the highest sensitivity and strongest cross-layer correlations across multiple model families, while other components exhibit architecture-specific behaviors. Through extensive experiments on quantization, sparsification, inter-layer corruption, and post-corruption fine-tuning, we demonstrate that our approximation strongly correlates with both performance degradation and recovery. Our framework provides a practical, theoretically grounded tool for identifying fragile components in large models, opening new avenues for guided compression and optimization strategies, such as mixed-precision allocation, layer-wise sparsity, and adaptive low-rank decomposition across layers and even individual weight groups.

Viacheslav Yusupov, Daria Cherniuk, Evgeny Frolov

1HSE University · 2AXXX

LLM Compression Fisher Information Neural Network Pruning

Sep 2, 2026cs.LG

XMerge: Cross-Axis Selection and Reconstructive Layer Merging for LLM Depth Compression

Removing complete transformer layers preserves a standard serving architecture, but existing depth-compression methods can lose substantial quality, and the loss varies unpredictably across models. We introduce XMerge, a post-training method with two components. Cross-axis selection identifies a block with low relative-magnitude and angular hidden-state change, and local boundary reconstruction re-fits the adjacent surviving block to match the original two-block output. XMerge uses no task labels or end-to-end fine-tuning, and it introduces neither architectural changes nor additional inference-time parameters. Across seven Llama and Qwen backbones (0.5B-8B), five published baselines, and three layer-reduction levels, its advantage over baselines is largest at the most aggressive removal: at k=4 it ranks first on six of seven backbones on CORE (a 22-task aggregate) and, separately, on six of seven on MMLU (five of seven on both at once), while avoiding the large perplexity increases of several competing operators. In a task-level bootstrap, the 95% confidence intervals for the three largest CORE margins exclude zero; the remaining margins are consistent with ties. Across the 14 (model, regime) cells it is also the only evaluated operator that never collapses, ranking top-2 in both zero-shot and in-context regimes; on a first calibration probe (one backbone) it is the best-calibrated operator. Ablations show that local reconstruction provides most of the gain, while cross-axis fusion helps when the two selection axes disagree. The additional construction cost is recovered through per-token decode savings after roughly tens of thousands of requests.

Jundong Hu, Shekar Ramachandran

PayPal AI

LLM Compression Model Compression Neural Network Pruning

Sep 2, 2026cs.LG

Train What You Deploy: Closing the MLP Reachability Gap in Low-Rank Clone Distillation

A compressed student has two shapes that need not agree: the weight it deploys at inference and the weight family its training can reach. We show that a state-of-the-art weight-inheritance distiller, Low-Rank Clone (LRC), deploys a full-width student MLP but ties training to a teacher-induced slice, leaving 62.5-81.4% of each deployed matrix's independent linear degrees of freedom unreachable-paid for at inference, never trainable. Our principle is one line: train what you deploy. From the identical LRC warm start, we make the training object the entire deployed matrix, with no change in deployed shape, deployed parameter count, or inference FLOPs, via two mergeable realizations (Dense-LRC and CORE-LRC) that both collapse to one deployed weight. This recovers stranded capacity: taking the stronger realization per teacher, +2.36/+2.71/+10.45 Avg9 over matched-budget plain-LRC baselines across three teachers (Llama3.2-3B, Llama3.1-8B, Qwen2.5-3B), with the largest gain on the widest teacher (Qwen), where it reaches the original recipe's approx. 20B-token accuracy at 10B tokens (2x token efficiency); there the strictly same-lineage arm still recovers +6.39, the fully controlled figure. Controls strongly support attributing the gain to the enlarged reachable set, rather than to added parameters or the recipe. From approx. 10B distillation tokens plus a short SFT, a half-parameter 1.5B student matches its approx. 9T-token teacher's 9-task macro-average, within evaluation noise and with a residual MMLU deficit, and a 2.7B student beats Meta's own official compression of Llama3.1-8B at ~900x fewer compression tokens (a token count under unmatched recipes, not a compute claim). All results are from single-seed runs on the LRC backbone.

Wenhui Chen, Zhifeng Li, Jie Zhou +5

1Incept Labs, Houston, TX · 2Titan Holdings, San Francisco, CA

LLM Compression Language Model Distillation Knowledge Distillation

Sep 2, 2026cs.AI

Post-Training Ternarization of Qwen3-4B Capability, Effective Bit Budget, Storage Compression, and Deployment

Ultra-low-bit language models can reduce storage and memory bandwidth, but a nominal "1.58-bit" label does not fully describe the stored representation, retained capability, or runtime behavior. We study an end-to-end post-training conversion of Qwen, an instruction-tuned 4B-parameter model, using KOTMS rotation, E2M-ATQ ternarization, and GPTQ-style error compensation from TWLA. The experiment is weight-only: activations remain at 16-bit precision, so ILA-AMP is omitted. We evaluate effective bit accounting, task capability retention, perplexity, calibration sensitivity, checkpoint composition, and deployment behavior. The final conversion uses 1.641 effective bits per weight for quantized linear weights, with 81.62% of model parameters targeted. Across ten scored capability comparisons, accuracy falls from 64.5% to 54.7%. Degradation is uneven: BoolQ retains 84.6% chance-corrected teacher performance, while ARC-Challenge retains 43.8%. Perplexity rises from 13.639 to 18.748 on WikiText-2, 24.700 to 31.992 on PTB, and 19.831 to 28.966 on C4. A subsequent packing run preserves the ternary planes and scales, reducing reported model size from 8.29 GiB to 3.96 GiB with essentially unchanged perplexity. A separate third-party packing attempt was lossy and is excluded from the primary artifact claim. The packed artifact has not been benchmarked end-to-end for task accuracy or generation throughput. A preliminary Triton GEMV microbenchmark is 4.6x slower than FP16 cuBLAS on one tested shape. We therefore do not claim that compression alone yields faster inference.

Anirudh Malik, M Sparsh Mehra, Poojith Devan

OneBit AI

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

Sep 1, 2026cs.AI

Residual Sparsification via Output Importance for Compressing Mixture-of-Experts LLMs

Mixture-of-experts (MoE) architectures scale large language models efficiently, but they demand massive GPU memory. To cope with such demand, models are commonly compressed to reduce their memory footprint. Residual sparsification is a representative compression technique that decomposes each projection matrix of an expert into a shared base matrix and per-expert residual matrix, and then compresses the residuals. Existing sparsification methods compress each residual matrix independently by minimizing its compression error, thereby minimizing the error of each projection matrix. However, our analysis shows that this objective is misaligned with preserving model accuracy after compression. In an expert, the final output is produced through computations coupled across multiple projections and hidden representations. Therefore, even small errors in individual matrices can propagate through hidden representations and projection interactions, leading to large expert output errors and accuracy degradation. To address this misalignment, we propose PARSER, a new residual sparsification method that shifts the compression objective from minimizing isolated matrix errors to preserving the expert output error. PARSER achieves this by introducing output importance, which measures the actual contribution to the expert output error. Our experiments show that, compared with existing methods, PARSER narrows the accuracy gap to the uncompressed model by 1.41

\times

on Qwen and 1.44

\times

on DeepSeek, while achieving the same peak memory reduction. Our code is available at https://github.com/OSSS-KU/PARSER.

Seungwoo Jung, Dohyeok Kwon, Seungmin Cha +4

Department of Computer Science and Engineering, Korea University · Department of Computer Science and Artificial Intelligence, Dongguk University

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

Aug 31, 2026cs.CL

Every Token Leaves a Ripple in the Stream of Thought: Eliciting Model-Internal Token Saliency for Chain-of-Thought Compression

Chain-of-thought (CoT) reasoning improves multi-step problem solving, but long reasoning traces inflate inference cost. Token-level CoT compression reduces this cost by pruning full reasoning chains into shorter traces for model adaptation, making token selection the central challenge. Existing methods often rely on external scorers or heuristic signals only indirectly tied to the model's internal answer computation. We instead adopt a model-internal perspective: as the model forms an answer, each reasoning token induces a ripple in the residual stream whose effect on the answer reflects the token's contribution to the underlying computation. Building on this view, we propose \textsc{MIST} (Model-Internal Saliency for Token-level CoT compression), which defines token importance along two complementary axes: \emph{necessity}, the drop in answer likelihood when a token's internal contribution is removed, and \emph{sufficiency}, the gain in answer likelihood when that contribution alone is provided. Combining the two yields a unified importance score for pruning. Across four reasoning benchmarks and four models, \textsc{MIST} consistently outperforms baseline methods, suggesting that model-internal saliency provides an effective proxy for reasoning-token importance.

Tianyi Zhao, Yinhan He, Wendy Zheng +2

University of Virginia

LLM Compression Efficient Language Model Reasoning CoT Compression Large Reasoning Models

Aug 31, 2026cs.CL

TopoCompress: Long Context Compression via Graph-Wired Semantic Trajectories

Long-context compression is essential for reducing the cost and latency of large language model inference. However, existing methods can fragment important evidence, require additional training or alignment, and often depend on the target model for effective compression. We introduce TopoCompress, a training-free and model-agnostic framework that compresses long contexts by selecting coherent semantic spans. TopoCompress first scores each span using dense and lexical query relevance together with semantic acceleration. It then constructs a hybrid graph that connects spans based on semantic similarity and sequential adjacency, and propagates the query-guided relevance scores over the graph. Across five long-context tasks-HotpotQA, 2WikiMQA, MuSiQue, Qasper, and MultiFieldQA-en-TopoCompress consistently outperforms strong compression baselines. Notably, TopoCompress achieves performance comparable to the strongest baseline while using a 4x smaller compression budget, and provides a 1.41x smaller compression time over the fastest baseline.

Daniel Agyei Asante, Yang Li

1Iowa State University, United States

LLM Compression Long-Context QA LLM Inference Acceleration

Aug 31, 2026cs.LG

Tensor Methods for Language Models: From Token Representation to Training, Adaptation, Inference, Compression, and Interpretability

Large language models (LLMs) are built from structured high-dimensional objects such as token representations, weights, adaptation updates, caches, and activations, whose multilinear structure is underexploited by the conventional matrix-centric view. Tensor decompositions and tensor networks provide a principled algebraic language for this structure, yet the literature often treats them as isolated compression mechanisms. This survey organizes tensor methods for LLMs through two complementary views: a seven-stage lifecycle taxonomy covering tokenization, embeddings, pre-training, adaptation, compression, inference, and interpretability, and a component view covering embeddings, attention, and feed-forward networks. We provide unified notation and theoretical foundations, analyze tensorization strategies for individual Transformer components, and compare methods at each lifecycle stage while making differences in evaluation protocols and model scales explicit. We further connect tensor methods to neighboring efficiency techniques and probabilistic tensor networks. Finally, we synthesize open challenges and introduce

ρ_{\rm gap}

, a metric for the compression-realization gap between theoretical memory reduction and measured system-level speedup. By treating tensorization as a common structural principle, the survey provides a structured entry point to tensorized language models and clarifies when parameter savings can plausibly translate into memory efficiency, computational efficiency, or interpretability. The GitHub page dedicated to this paper is accessible at this https URL.

Matvei Tarasov, Salman Ahmadi-Asl, Andre L. F. de Almeida +1

Innopolis University, Innopolis 420500, Russia · Department of Teleinformatics Engineering, Federal University of Cear´a, Fortaleza 60455-760, Brazil · Systems Research Institute of Polish Academy of Science and Warsaw University of Technology, Poland

LLM Compression LLM Inference Acceleration Language Modeling

Aug 31, 2026cs.AI

LaMoC: Loss-Aware Modular Compression for LLMs

Modular compression has enabled considerable parameter reduction in LLMs while preserving strong language understanding and downstream task accuracy. However, existing joint modular compression methods primarily rely on activation statistics, leaving loss-sensitivity information and its module-level characterization underexplored. We investigate addressing this gap with LaMoC, a loss-aware modular compression methodology that blends activation and Empirical Fisher statistics through gradient-error alignment. LaMoC improves joint compression by selecting compression statistics that better align local module reconstruction error with the downstream loss. Our contributions are three-fold: (1) We characterize the Empirical Fisher as a module-level loss-aware proxy that can be blended with the activation statistics required for compression. (2) We reformulate joint modular compression as a two-tiered optimization problem that minimizes module reconstruction error while tuning the activation and gradient information blending rate. (3) We implement an empirically driven methodology with statistical validation to solve the resulting compression problem. We evaluate LaMoC across four model families spanning eight models. On the 4-8B models, LaMoC achieves an average 2.5% reduction in perplexity and a 1% relative improvement in task accuracy over state-of-the-art modular compression methods.

Mohanad Odema, Jacob Song

LG Electronics USA

Model Compression LLM Compression Modular Neural Networks

Aug 30, 2026cs.CL

Budget-Aware Compression Pipeline for Single-GPU LLM Inference: Methods, Trade-offs, and Coupling Effects

Single-GPU deployment of 70B-parameter language models on an NVIDIA GPU is constrained by device memory, long-context throughput, and engineering integration cost. We cast single-GPU inference as a budget-aware design problem over these three axes and study how pruning, quantization, and KV-cache compression interact under realistic execution. Controlled ablations show that layer-wise pruning makes weight quantization more robust. KV-cache sparsification complements INT8 KV quantization by reducing memory without hurting decoding speed, while static vector quantizers often conflict with dynamic caching. Guided by these coupling results and explicit budget tracking, we assembled a practical pipeline and compressed a 70B model to about 33 GB, sustained about 57 tokens/s on 10k token prompts on a single A40, and kept absolute accuracy within 5% on common and reasoning benchmarks. We contribute design rules and a reproducible evaluation protocol that jointly report quality, memory, and end-to-end speed, and we provide a foundation for automated pipeline search under realistic single-GPU constraints.

Hongyu Yu, Yifei Shen

Lenovo Research · University of Washington

LLM Quantization LLM Pruning LLM Compression KV-Cache Compression Efficient Language Model Inference

Aug 12, 2026cs.CL

Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed

Small Language Models (SLMs) have emerged as a more efficient alternative to traditional Large Language Models (LLMs), offering promising potential in resource-constrained scenarios. Existing approaches to building SLMs typically follow two paths: training compact models from scratch, or compressing larger pre-trained models using methods such as pruning, quantization, or distillation. As language models become increasingly integrated into real-world applications, ensuring their trustworthiness has become a critical concern. However, how to build trustworthy SLMs remains an underexplored question. In this work, we present a comprehensive evaluation of SLM trustworthiness across multiple dimensions, including fairness, robustness, privacy, and ethics. We first examine the effects of pruning and quantization, and find that quantization is significantly more effective in preserving trustworthiness compared to pruning. More importantly, we demonstrate that compressing a reliable large model via quantization can produce SLMs with superior trustworthiness and adaptability compared to using small models trained from scratch. Furthermore, knowledge distillation from trustworthy teacher models can further enhance the reliability of SLMs. We hope our findings provide practical guidance and a foundation for future research into the development and deployment of trustworthy small language models.

Haokun Lin, Kaijie Zhu, Haobo Xu +4

Institute of Automation, CAS Beijing, China · Tsinghua University Beijing, China · Harvard Medical School Boston, U.S. +1

LLM Quantization LLM Pruning LLM Compression Small Language Models Language Model Distillation

Aug 11, 2026cs.IR

Towards Efficient Reasoning in LLM-Based Recommender Systems via Model Merging

Large language model-based recommender systems are increasingly adopting slow-thinking models that generate step-by-step reasoning before making predictions, often achieving higher accuracy than fast-thinking models that predict directly. However, their reasoning traces are often unnecessarily verbose, increasing inference costs without commensurate accuracy gains. Existing training-based approaches to reasoning compression often incur substantial adaptation costs, while inference-time methods are brittle and difficult to scale. These limitations motivate model merging as a promising training-free direction for transferring specialised behaviours between models in a shared parameter space. In particular, merging a slow-thinking model with a fast-thinking counterpart provides a natural mechanism for balancing recommendation accuracy and reasoning conciseness. To this end, we propose, to our knowledge, the first model merging framework for reasoning compression in recommender systems. Unlike conventional merging methods that apply uniform merge coefficients across model components, our method performs fine-grained merging at the level of individual attention heads, capturing heterogeneous patterns in recommendation reasoning. Each attention head is assigned a distinct merge coefficient according to its contribution to critical reasoning evidence and its sensitivity to parameter change, enabling selective injection of the concise behaviour of the fast-thinking model into the slow-thinking model and reducing reasoning verbosity without compromising recommendation quality. Experiments on three benchmark datasets show that our method reduces reasoning length by up to 24.3% while outperforming competitive model merging baselines in maintaining recommendation accuracy. The code is available at https://github.com/linhledieu/REAM.

Linh Dieu Le, Tong Chen, Shazia Sadiq +3

The University of Queensland Brisbane, Australia · Griffith University Brisbane, Australia

LLM Compression Large Language Model-Based Recommendation Model Merging Efficient Language Model Inference

Aug 9, 2026cs.LG

LegoLM: Structured Weight Sharing for Large Language Models

We present \LegoLM{}, a structured weight-sharing compression framework for large language models grounded in a systematic study of why global weight sharing fails and how to fix it. We identify two distinct failure modes. Distributional mismatch: for vector blocks of dimension d <= 2, transformer layers with heterogeneous weight scales impose a scale-mismatch penalty that grows linearly with d and cannot be resolved by increasing K, producing perplexity in the millions.Outlier dominance: for scalar blocks, a fraction ~1/K of weights lies beyond the outermost Lloyd-Max decision threshold and cannot be represented by any centroid; their misrepresentation accumulates across layers, causing catastrophic quality loss. \LegoLM{} resolves both failure modes via three data-free adaptations: 1 scalar-block encoding to eliminate the

d

-linear mismatch component, 2 percentile-selective replacement that identifies and preserves outlier weights verbatim, and 3 boundary-layer protection for the first and last transformer blocks. Across GPT-2 small (124M) and Mistral-7B, \LegoLM{} achieves +0.03% PPL degradation at 4.41X compression on Mistral-7B - outperforming PTQ-8bit in both quality and compression ratio - and -0.02% at 2.67X. Downstream evaluation on LAMBADA and HellaSwag confirms that \LegoLM{} at K=64, p=99% preserves accuracy within noise at 5.12 X compression, exceeding PTQ-8bit's compression ratio while matching its accuracy. We further discover that outlier dominance grows with model scale: full replacement at K=128 degrades GPT-2 small by only +23% but catastrophically degrades Mistral-7B by +1,134,279%, while selective replacement at p=99% rescues both models to under +15%. A controlled ablation confirms that selective replacement is the dominant mechanism: adding it to per-layer K-means also yields near-lossless quality, matching \LegoLM{} within 0.02%.

Joseph Bingham

Deparment of Biology, Technion – Israel Institute of Technology

LLM Quantization LLM Compression Neural Network Quantization

Aug 9, 2026cs.AI

Understanding Calibration and Truncation Error Propagation in Training-Free Low-Rank Compression for LLMs

Training-free low-rank compression frameworks have been gaining prominence for LLM compression given their effectiveness in reducing model parameter count while maintaining task-level accuracy. However, existing SOTA frameworks share two key limitations: (1) residual errors in calibration data activations accumulate across layers during compression, causing misalignment between representations simulated at compression time and those experienced at inference; (2) the assumption that layer importance distribution is preserved post-compression does not hold. Together, these two effects introduce misalignment in the compression process in relation to the deployed model. We study these effects and propose a simple, training-free methodology compatible with existing frameworks to mitigate them, comprising: (1) Layer-by-Layer Compression with Calibration Correction; (2) Iterative Compression with Rank Allocation Correction. Implemented atop an existing SOTA decomposition framework, and evaluated on Llama and Qwen3 models across various benchmarks and compression rates, our approach demonstrates up to ~1-2.5 accuracy point improvements over per-weight and joint decomposition baselines on zero-shot tasks.

Mohanad Odema, Gabrielle De Micheli, Dayin Gou +3

LG Electronics, North America

Model Compression LLM Compression Low-Rank Compression Adaptive Rank Allocation

Aug 5, 2026cs.CL

Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt Compression

Hard prompt compression reduces long-context inference cost by independently scoring tokens, sentences, or chunks and retaining the highest-scoring units under a budget. We identify a structural failure in this procedure: independent selection can split dependent evidence pairs, retaining one member while deleting the other. When retained text contains an answer but deleted text defines the entity needed to interpret it, we call the result referential dangling. At a compression ratio of 0.30, Beaver, which ranks coherent chunks using Qwen3-0.6B embeddings, leaves the answer path incomplete in 34-54% of bridge examples across three multi-hop question answering datasets. On a shared HotpotQA bridge set, all six hard compressors we test exhibit dangling at rates up to 60%, and every document in LongBench-v2 Single-Document QA contains at least one dangling reference. On dangling examples evaluated with Qwen3-8B, reinserting the missing supporting paragraph while removing nonsupporting paragraphs to maintain the token budget improves accuracy by 29-34 percentage points (p < 0.0001), recovering at least 88% of the gap to contexts retaining both supporting paragraphs. Stronger answer models do not absorb the loss: on MuSiQue, GPT-5.5 is 8.8 points less accurate on compressed contexts than on contexts retaining both supporting paragraphs. Finally, we train a compact classifier to rank omitted sentences by whether they are needed to interpret retained text and reinsert the top-ranked candidates without support annotations at inference. On HotpotQA with Qwen3-8B, this automatic restoration improves accuracy by 4.7 points while changing the compression ratio only from 0.30 to 0.31. Hard compressors should optimize both relevance and referential completeness.

Zhengpei Hu, Kai Li, Dapeng Fu +5

School of Computer Technology and Application, Qinghai University · Tsinghua University · Ant Group Security and Intelligence Laboratory (SIL)

LLM Compression Long-Context Inference Prompt Compression

Aug 3, 2026cs.AI

When Compression Scores Cannot Decide: Information Boundaries for Group-Robust LLM Pruning

A stable compression score can still select the worse model. In our dense study, a split-half reliable path-quadratic score predicted a 16.1% gain, while the selected endpoints were 6.0--7.7% worse than two controls. We ask what a compression statistic can justify when deployment cares about the worst supplied group. We treat each statistic as an information interface. Its observation leaves a fiber of compatible endpoint-risk tables, and only orders fixed across that fiber are identified. Cone and fiber identities quantify the remaining uncertainty, while matched observations reverse endpoint order for pooled moments, group-local moments, and reference-path curvature. Sequential composition adds one state variable: the slack from each group risk to the current maximum. This vector determines every unrestricted one-step response, and a margin condition keeps the active group fixed along paths with bounded relative drift. The experiments follow the same ladder. Across three dense LLMs, an early-preserving allocation reduces worst-group perplexity inflation by 12.6--20.9%; target-matched complete-menu selection improves over its references by 2.7--8.0%. Across all 16 routed layers of OLMoE, pooled endpoint refresh lowers held-out worst-group teacher KL by 15.8% over the best static score. A compute-matched hard-max trajectory ends 32.7% worse than pooled, and neither adaptive trajectory improves excess NLL. Local evidence can narrow a menu. Complete endpoints rank that menu, while multistep claims also require control of the evolving active face and future candidates.

Andrew Zhang

KTH Royal Institute of Technology

Model Selection Mixture-of-Experts Pruning LLM Pruning LLM Compression Neural Network Pruning

Aug 3, 2026cs.LG

Wiring Beats Blending: Structure-Aware Compensation for Transformer Downscaling

Model families are trained size by size. Can a pretrained large model instead be converted into a smaller sibling? We study the 1.4B->410M conversion in Pythia end to end. Representations align strongly across sizes (ridge R^2=0.84); parameters align weakly. Dense weight projection is destructive; a bit-exact control places the fault in basis mixing, which breaks rotary, per-head, GELU, and LayerNorm structure. Residuals after the best-fit linear operator carry no learnable or transferable signal under shuffle controls, so conversion value lives in initialization. Matched-budget continued pre-training separates two independent levers: least-squares compensation (function lever, best zero-shot) and variance-preserving rescale (dynamics lever, best endpoints). Placement follows the architecture: compensation is well-posed exactly where no normalization sits between cut and read; norm-fronted paths take rescale. Compensation is a low-budget, token-efficiency win, not a universal one. At 30M tokens it beats the best subcloning variant on a width-reduced pair (84.0+-1.8 vs. 89.7+-3.7, 3/3 seeds) and a held-out depth-reduced pair (109.3 vs. 117.9, 3/3 seeds). Selection given the same activation statistics recovers under half of that gap (3/3 seeds): the gain is the re-fit, not the information. At 33x the budget the two reach parity (40.3+-0.3 vs. 40.3+-0.5, 3 seeds), both far ahead of from-scratch, which transfer always beats (up to 18x at low budget, narrowing at convergence and at the largest scale). At ~5x the donor scale (6.9B->1.4B) stacking both levers over-corrects, consistent with an ill-conditioned compensation solve at large width, pointing to dimension-aware regularization as a fix. The init also beats structured pruning plus distillation, the standard pipeline, at matched budget, and improves further combined with it. Code, checkpoints, and the frozen eval corpus are released.

Ravi Satya Durga Prasad Yenugula

Independent Researcher

LLM Compression Continued Pretraining

Aug 3, 2026cs.CL

ARCHead: Activation-Metric Residual Correction for Large Language Model Output Heads

Weight-only quantization substantially reduces the storage of large language model (LLM) transformer blocks, but practical backends often retain the final language-modeling head (LM-head) in BF16 or FP16. Quantizing this projection naively can strongly perturb the vocabulary-logit distribution. We present ARCHead, a packed LM-head compressor that combines a quantized low-rank core, group-wise INT4 residuals, and a low-rank correction fitted in an activation-derived metric. ARCHead stores no dense BF16 head and reduces persistent LM-head storage by 3.7-3.9x. On Qwen3-8B-Base, it uses 25.6% of BF16 head storage while attaining 1.007 relative perplexity; storage-matched naive INT4 yields 1.14-1.16. Replacing the BF16 head left by AWQ or bitsandbytes adds only 0.006-0.007 cross-entropy, with less than 2% throughput change in our measurements. ARCHead therefore complements block quantizers by compressing the large output projection they can leave untouched. Code is available at https://github.com/suayptalha/archead.

Şuayp Talha Kocabay, Talha Rüzgar Akkuş, Kamer Ali Yuksel

Independent Researcher · aiXplain, Inc.

LLM Quantization LLM Compression Low-Rank Compression Weight-Only Quantization

Aug 1, 2026cs.AI

F-WANDA: Fisher-Reweighted Post-Training Pruning for Sustainable Deployment of Large Language Models

One-shot post-training pruning is the most energy-frugal compression strategy for largelanguage models (LLMs), yet existing approaches trade either quality (WANDA) or compute cost (SPARSEGPT). We introduce F-WANDA, a drop-in modification of WANDA that reallocates the per-row keep budget across output neurons in proportion to the empirical Fisher information of the pre-activation. The Fisher signal is collected in a single additional backward pass over the same calibration corpus WANDA already uses; no weights are updated. On LLAMA-2-7B at 50 % unstructured sparsity, F-WANDA attains WikiText-2 perplexity of 6.85, matches WANDA fluency, and improves 5-shot MMLU by +1.6 pp over WANDA and +1.1 pp over SPARSEGPT, while incurring only one-third of SPARSEGPT pruning wall-clock and energy. The headline trade-off is achieved without extra calibration data or fine-tuning, placing F-WANDA on the Pareto frontier of quality versus pruning cost for sustainable LLM compression.

Himanshu Mishra

University of British Columbia

LLM Pruning LLM Compression Neural Network Pruning

Jul 30, 2026cs.CL

Fidelity Is Not Safety: Gently-Compressed LLMs Pass Every Data-Free Quality Guard Yet Invent Procedure Steps in Agentic Execution

Practitioners accept a compressed language model once it clears a stack of data-cheap quality guards: perplexity within a small factor of the original, downstream accuracy (for example MMLU) inside a confidence interval, and data-free output-fidelity signals that compare the compressed and original network's internal representations under random probe inputs. This stack has a blind spot. Across three model families, gently-compressed models clear every guard and then invent procedure steps that were never in the instructions when they run a standard operating procedure (SOP) as an agent. The effect is operator-specific: coherent low-rank (SVD) truncation induces it, and magnitude pruning matched to the same perplexity does not. One dissociation isolates the cause. The same compressed weights that CI-win a paired output-fidelity test CI-fail the invented-step canary. The governing axis is the coherence of the compression error times its rate; the magnitude of the damage does not predict it. The data-free fidelity probe is a fidelity oracle by construction, so it cannot see this axis. We characterize the blindspot and dissociation with paired confidence intervals on a pre-registered, powered canary across three architectures. Operator-specificity replicates on all three, and the perplexity-guard evasion appears where the model admits in-guard low-rank headroom. We then give a data-free screen: a two-axis statistic of the compression error (coherent-fraction and error-rate) that flags the failing builds with fixed thresholds across architectures and matches the coherence-times-rate mechanism. Perplexity, MMLU, and fidelity acceptance do not certify agent safety. Screen gently-compressed low-rank builds before agentic deployment

I. Kennedy, T. Kennedy

Model Compression AI Agent Reliability LLM Compression Language Model Safety Evaluation LLM Agent Verification Low-Rank Compression+2

Jul 28, 2026cs.CL

Every Time I Hire a Linguist, Inference Costs Go Down: On Linguistic Rules as Effective Prompt Compressors

Prompt compression shortens LLM input to reduce inference cost, yet existing methods score token importance through LM forward passes. It remains questionable whether such nuanced, costly token selection is necessary. Compression requires identifying informative content, a problem that linguistic research has long addressed through cues that can be operationalized as deterministic rules. We therefore ask: can \textbf{linguistic rules alone} serve as effective prompt compressors, without LM-based scoring at compression time? To address this, we conduct offline evolutionary search over lexical, syntactic, semantic, and discourse seeds to find competitive rule combinations. The resulting linguistic compressor requires no LM forward pass at deployment and uses only CPU-side processing for compression. We evaluate it with a dual-path protocol to balance compression quality and reconstruction fidelity. Across short passages, multi-document reasoning, and dialogue-memory QA datasets, evolved compressors achieve performance similar to that of recent advanced prompt-compression strategies. Performance is strongest under light-to-moderate compression and degrades as compression becomes more aggressive, while the Direct and Reconstruction paths exhibit distinct patterns. Evolutionary analysis reveals that effective compression fuses signals across linguistic levels and, as the compression ratio increases, rules shift from token pruning to sentence extraction.

Jianfei Ma, Zhaoxin Feng, Emmanuele Chersoni +1

The Hong Kong Polytechnic University

LLM Compression Efficient Language Model Inference Prompt Compression

Jul 24, 2026cs.LG

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization

Open-weight language models from different families exhibit complementary capabilities, motivating their consolidation into a compact student through on-policy distillation (OPD). However, full-vocabulary OPD typically assumes a shared tokenizer, while existing cross-tokenizer methods may discard teacher probability mass or assign it to student tokens with unrelated content. We introduce Byte-Prefix Marginalization (BPM), which re-expresses the teacher's next-token distribution over the student vocabulary in a shared byte space. Specifically, BPM assigns each teacher token's probability to the longest student token whose byte representation is a prefix of the teacher token's bytes, aggregates mass mapped to the same student token, and places otherwise unmatched mass in an explicit residual category. This produces a vocabulary-complete, byte-aligned, and mass-preserving target for dense OPD. The target exactly recovers the teacher-induced byte-prefix marginal when the relevant prefix does not span multiple teacher tokens (a condition satisfied at more than 99% of training positions) and uses a mass-preserving, chain-factorized lower bound otherwise. Across Qwen3-32B, GLM-Z1-9B-0414, and MiniMax-M2.7 as teachers, BPM consistently outperforms current cross-tokenizer methods on six mathematics and programming benchmarks, improving six-benchmark avg@8 by 3.7-6.6 points over the strongest baselines.

Hao Wang, Kun Yuan, Wenlin Zhong +4

University of Chinese Academy of Sciences · KwaiKAT Team · Zhejiang University +1

Cross-Tokenizer Knowledge Distillation LLM Compression Language Model Distillation On-Policy Distillation Knowledge Distillation

Jul 23, 2026cs.CL

Progressive Cramming: Reliable Token Compression and What It Reveals

Token cramming compresses sequences into learned embeddings with near-perfect reconstruction, but fixed token budgets and 99% accuracy thresholds leave it unclear whether residual errors reflect optimization failures or fundamental limits. We introduce progressive cramming, which grows the target prefix token-by-token, stopping only when reconstruction is no longer achievable within a fixed optimization budget. Progressive trajectories occupy low-dimensional structure in embedding space. Prepending a crammed embedding causes a moderate but consistent accuracy drop on multiple-choice benchmarks even with the original prefix in context, and collapses capability almost entirely under generative evaluation. Causal attention-knockout interventions trace this degradation to the embedding's interactions in the model's early layers. These results position progressive cramming as a tool for studying compression limits and show that perfect reconstruction - achievable through brittle steering rather than transferable semantics - is insufficient for meaningful compression.

Dmitrii Tarasov, Timofei Lashukov, Elizaveta Goncharova +1

FusionBrain Lab, AXXX, Moscow, Russia · HSE University, Moscow, Russia · Artificial Intelligence Institute, Innopolis University, Innopolis, Russia

LLM Compression Embedding Compression

Jul 20, 2026cs.LG

CoCurve: Cross-Module Co-Pruning Curvature for Training-Free Structured LLM Pruning

Structured pruning compresses large language models (LLMs) by removing whole computational units, such as attention heads and feed-forward (FFN) channel groups. Most training-free methods, however, rank these units independently, implicitly treating the loss from pruning a set as the sum of its individual losses. This view fails for Transformers, whose sublayers are coupled through a shared residual stream. Two individually weak units can thus be jointly indispensable, yet independent scoring is blind to such dependence and removes them together. We introduce CoCurve (Cross-Module Co-Pruning Curvature), a calibration-only, fine-tuning-free method that prunes attention and FFN units jointly. A second-order Taylor expansion of the token-level KL between the frozen model and its masked copy yields a single Fisher matrix whose diagonal is classical node saliency and whose off-diagonal entries are co-pruning curvature edges: the extra damage of removing two units together. Under a single-ablation additivity approximation this matrix reduces to a Gram product of single-unit ablation features, so the full M x M interaction is recovered from M forward passes, with no pairwise sweeps or gradients. Pruning then reduces to one budgeted quadratic program, solved in a single shot under a shared attention--FFN budget, with no labels, fine-tuning, or recovery.

Zhiren Gong, Zihao Zeng, Zijie Wang +3

College of Computing and Data Science, Nanyang Technological University, Singapore · Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore · School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore

LLM Pruning LLM Compression Structured Pruning Attention Head Pruning Neural Network Pruning

Jul 20, 2026cs.PF

SALT: Salience-Aware Lexical Trie for Long-Context Compression

As large language models (LLMs) process increasingly longer prompts, computation and KV-cache memory costs have emerged as major bottlenecks in inference systems. Existing input-level prompt compression methods address this, but rank each sentence by a scalar relevance score, treating the document as an unstructured pool of words and sentences. Under tight budgets, this causes theme collapse, where the dominant theme(s) of a document consumes the budget, discarding less-frequent yet task-relevant themes. Preserving thematic coverage instead requires allocating the budget across recurring themes rather than scoring sentences in isolation. To this end, we propose SALT, a model-agnostic extractive framework that organizes per-sentence keywords into a trie ordered by sentence frequency (SF), a lightweight, reusable proxy for document thematic structure. This trie-based organization smooths memory allocation and prevents dominant themes from monopolizing the budget. Multi-anchor retrieval activates trie nodes labeled by query keywords at any depth, and the trie persists across dialogue turns, supporting multi-turn use without re-encoding the document. By preserving document themes, SALT reduces the prefill computation and memory cost of long-context prompts while remaining composable with KV-cache methods that target decoding-time latency and memory.

Oteo Mamo, Hyunjin Yi, Joydhriti Choudhury +2

Florida State University

LLM Compression Long-Context Language Model Inference Prompt Compression

Jul 10, 2026cs.LG

A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design

The rapid expansion of large-scale AI models has led to significant performance breakthroughs across diverse domains, yet it has also raised critical concerns regarding computational costs, energy consumption, and environmental sustainability. This survey provides a comprehensive overview of the green development of large models, emphasizing resource-efficient architectures and full-stack hardware-software co-design. We systematically review recent advances in efficient model construction, including attention operator optimization, linear-complexity architectures, and model sparsification and merging, as well as training and deployment strategies such as data-efficient learning, parameter-efficient fine-tuning, and computational compression. Beyond algorithmic improvements, we explore energy-efficient AI hardware, including mainstream AI chips, memory optimization, cross-platform deployment, and sustainable infrastructure. Furthermore, we examine how large models are being applied to sustainability-critical domains such as DeepSeek, remote sensing interpretation, national-scale infrastructure, and global initiatives. Finally, we discuss key challenges and future directions, highlighting the need for continual learning paradigms, memory-centric hardware, and standardized evaluation protocols. This survey aims to offer a holistic roadmap toward sustainable, scalable, and socially responsible development of large models. Paper homepage: https://cje.ejournal.org.cn/article/doi/10.23919/cje.2025.00.438

Linhui Xiao, Guiping Cao, Mingyue Guo +6

1. Pengcheng Laboratory, Shenzhen 518066, China · 2. Harbin Institute of Technology (Shenzhen), Shenzhen 518055, China · 3. Peking University, Beijing 100080, China

LLM Compression Energy-Efficient ML Hardware-Software Co-Design Data-Efficient Learning

Jul 9, 2026cs.LG

SLORR: Simple and Efficient In-Training Low-Rank Regularization

Low-rank factorization is widely used to compress neural networks, but modern models are often not naturally amenable to aggressive factorization without significant accuracy loss. Existing training-time low-rank regularizers can improve compressibility, but they often require SVDs of large weight matrices, modify the model architecture (introducing additional trainable parameters), or rely on stateful cached quantities. To address these limitations, we introduce SLORR, a simple, stateless, and architecture-preserving framework for in-training low-rank regularization, instantiated with two main variants based on the Hoyer sparsity metric and the nuclear norm. SLORR directly regularizes the original weight matrices using GPU-friendly approximations for the forward and backward passes of the regularizers, for which we provide approximation guarantees. We first evaluate SLORR on ImageNet-1K across short-horizon continued training of ResNet-50, ViT-B/16, and ViT-L/16, and pretraining of ResNet-18, where SLORR induces compressibility while introducing less than 8% training overhead. We further evaluate SLORR-Hoyer in LLM pretraining at 135M and 560M scales: SLORR-trained compressed models preserve performance substantially better than unregularized models while adding less than 1% average training overhead.

David González-Martínez, Shiwei Liu

Max Planck Institute for Intelligent Systems · University of Tübingen · ELLIS Institute Tübingen +1

LLM Compression Low-Rank Matrix Decomposition Nuclear Norm Minimization Low-Rank Compression Low-Rank Approximation Neural Network Compression

Jul 9, 2026cs.LG

BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression

Large language models (LLMs) are increasingly constrained by memory capacity, weight bandwidth, and checkpoint storage during deployment. Existing low-bit compression methods mainly follow two directions. Scalar or group-wise quantization is simple and compatible with efficient low-precision kernels, but its representation capacity becomes limited when the target budget approaches 2 bits per weight. Vector-quantized weight compression provides a richer block-level representation, but usually introduces explicit codebooks, index lookup, and additional storage accounting. This paper presents BiSCo-LLM, a codebook-free binary spherical coding framework for extreme low-bit LLM weight compression. The core pipeline is built on three components. First, local weight chunks are mapped onto a unit hypersphere and binarized into compact spherical codes, so that the main payload is a bit-packed sign stream rather than explicit VQ centroids. Second, a residual BSQ stage encodes the reconstruction error left by the base spherical codec, providing an explicit rate-distortion path without stored codebooks. Third, category-wise recovery distillation is performed after replacing each Transformer module category, reducing the mismatch between local weight reconstruction and assembled model behavior. A small 8-bit protected-channel path is used as an auxiliary stabilization mechanism for sensitive channels and is counted separately from the BSQ payload. The reported storage budget includes binary codes, neural decoders, protected-channel payloads, LoRA adapters, and metadata.

Yuantian Shao, Peisong Wang, Zhilei Liu +6

Nanjing University of Science and Technology, Nanjing, China · Institute of Automation, Chinese Academy of Sciences, Beijing, China · Huawei, China

LLM Compression Weight-Only Quantization Low-Bit Quantization

Jul 9, 2026cs.CL

It Takes a MAESTRO To Prune Bad Experts

Sparsely-activated Mixture-of-Experts (MoE) language models achieve remarkable inference efficiency by activating only a small fraction of parameters per token, yet their full expert banks reside in memory at all times, creating a prohibitive deployment bottleneck. Existing structured pruning methods, largely designed for dense transformers, assess expert importance using locally derived heuristics that are blind to the interdependent nature of MoE routing. We introduce MAESTRO (Markov-chain Approximated Expert Sparsification via Transition-based ROuting), a structured pruning framework designed for MoE architectures that models autoregressive expert activation trajectories as Ergodic Markov chains whose stationary distributions encode cross-layer dependencies, yielding a globally aware importance heuristic. Evaluated across five diverse domains including Safety, Bias, and Ethics, MAESTRO outperforms state-of-the-art baselines by up to 10.61% in average performance retention under a strict 50% compression regime, while exhibiting substantially lower cross-task variance, indicating that global, routing-congruent pruning produces models that generalize more consistently across heterogeneous tasks.

Palaash Goel, Ayush Maheshwari, Tanmoy Chakraborty

Indian Institute of Technology Delhi, India · NVIDIA, India

Mixture-of-Experts Pruning LLM Pruning Mixture-of-Experts Language Models LLM Compression Activation Sparsity Structured Sparsity+1

Jul 9, 2026cs.CL

Structured Pruning of Large Language Models via Power Transformation and Sign-Preserving Score Aggregation with Adaptive Feature Retention

This paper proposes an improved structured pruning method for large language models (LLMs) that addresses key challenges in adapting Adaptive Feature Retention (AFR), an unstructured pruning technique, to structured pruning. When applying AFR to structured pruning, three major problems arise: distribution mismatch between heterogeneous pruning scores, loss of sign information indicating optimization direction consistency, and influence of outliers. To address these issues, we propose a unified approach combining power transformation for nonlinear distribution alignment, sign-preserving score aggregation, and percentile-based outlier removal. Experiments on Llama-3-8B, Vicuna-v1.5-13B, and LLaVA-v1.5-13B demonstrate that our method maintains accuracy comparable to unstructured pruning while achieving practical inference speedup through structured pruning.

Ryota Kobayashi, Tsubasa Hirakawa, Takayoshi Yamashita +4

1Chubu University · 2Panasonic Holdings Corporation

LLM Pruning LLM Compression LLM Inference Acceleration Structured Pruning