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

Jun 5, 2026cs.AI

Joint Structural Pruning and Mixed-Precision Quantization for LLM Compression

Recently, the efficiency of Large Language Models (LLMs) deployment has become a critical concern in practical applications. While post-training quantization (PTQ) and structural pruning are established techniques for reducing memory footprint and inference latency, most existing PTQ approaches optimize quantization errors on a per-layer basis, overlooking how errors accumulate and propagate through the network, often resulting in suboptimal solutions. Traditional pipelines also tend to apply pruning and quantization in isolation or sequentially, further compounding sub-optimality. We introduce a novel end-to-end framework that addresses these limitations in two key ways. First, we propose a novel mixed-precision PTQ strategy that directly minimizes global error propagation across the entire model, rather than isolating layer-wise errors. Building on this, we develop a novel joint optimization approach that simultaneously learns structural pruning decisions and mixed-precision quantization policies within a unified search space. Extensive experiments show that, at ultra-low precisions (1-3 bits), our quantization method reduces WikiText perplexity by up to 21% compared to state-of-the-art (SoTA) weight-activation quantization baselines. Against leading weight-only quantization methods, it achieves up to 59% and 85% lower perplexity on WikiText and C4, respectively. Compared to the SoTA joint pruning-and-quantization techniques, our proposed method delivers superior perplexity and reasoning performance at ultra-low bits.

Hoang-Loc La, Truong-Thanh Le, Amir Taherkordi +1

UiT The Arctic University of Norway · University of Oslo, Norway

Mixed-Precision Quantization LLM Quantization LLM Pruning LLM Compression Post-Training Quantization Neural Network Compression

Jun 5, 2026cs.CL

SigmaScale: LLM Compression with SVD-based Low-Rank Decomposition and Learned Scaling Matrices

We present SigmaScale, a method for learning auxiliary scaling matrices

S

to aid truncated Singular Value Decomposition (SVD) based Large Language Model (LLM) compression. Instead of deriving scaling matrices analytically, SigmaScale optimizes two sets of vectors that define diagonal row and column scaling transformations under an activation-aware compression loss. We show that learned scaling lowers the effective intrinsic rank of weight matrices, as reflected by reductions in effective-rank entropy, and that this reduction is strongly correlated with compression loss. Experiments on Llama 3.1 8B Instruct and Qwen3-8B show that SigmaScale is competitive with closely related state-of-the-art SVD-based compression methods across perplexity and zero-shot benchmarks. By using learned activation-aware transformations, SigmaScale explores a more flexible route to low-rank LLM compression by adapting to the structure of individual model weights. The advantage observed in specific tasks makes our approach a valid option for applications requiring a reduced LLM-inference computing cost.

Ernests Lavrinovics, Marco Letizia, Roy Janco +3

Department of Computer Science, Aalborg University Copenhagen, Denmark · MaLGa-DIBRIS, University of Genoa, Genoa, Italy · INFN, Sezione di Genova, Genoa, Italy +2

Model Compression LLM Compression Low-Rank Matrix Decomposition LLM Inference Acceleration Low-Rank Compression Low-Rank Approximation

Jun 4, 2026cs.CL

YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition

Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory overhead, which inflates infrastructure costs and throttles scalability. To address this, we propose YouZhi-LLM, a highly efficient financial LLM empowered by a comprehensive structural transition and training pipeline natively built on the Huawei Ascend ecosystem. At its algorithmic core, YouZhi-LLM features a layer-adaptive GQA-to-MLA transition framework that dynamically assigns per-layer FreqFold sizes, maximizing KV-cache compression while minimizing perplexity degradation. To recover representation capacity and inject domain expertise, the Ascend-based training pipeline seamlessly integrates generalized knowledge distillation with financial-specific supervised fine-tuning. Evaluations demonstrate the superiority of this systematic approach, with the adaptive transition reducing perplexity degradation by up to 35% over uniform baselines. Crucially, when evaluated on Ascend NPUs via vLLM-Ascend, the massive KV-cache reduction translates directly into deployment efficiency. Compared to their respective base models, YouZhi-7B yields a 12.3% improvement in average financial benchmark score alongside a 2.69

\times

increase in maximum concurrency; similarly, YouZhi-14B achieves a 7.0% accuracy gain and a 2.43

\times

concurrency boost, establishing a new paradigm for cost-effective, high-throughput financial inference.

PSBC LLM Team, Huawei LLM Team, Ruihan Long +56

LLM Compression LLM Inference Acceleration Language Modeling KV-Cache Compression

Jun 4, 2026cs.MM

LLMCodec: Adapting Video Codecs for Efficient Weight Compression of Large Language Models

The rapid development of large language models(LLMs) has led to remarkable advances in natural language processing. However, the increasing scale of these models introduces substantial challenges in terms of storage, transmission, and deployment. Though great efforts have been devoted to model compression and quantization, existing methods often rely on fine-tuning or calibration data, which exhibit limited generalization across different tensor types. In this paper, we argue that video codecs offer a promising solution for LLM compression, due to their inherent compatibility with matrix structured data, configurable compression strategies, and the availability of highly optimized, off-the-shelf implementations. Therefore, we present LLMCodec, a video codec-based LLM compression method that integrates affine quantization with the recent VVC/H.266 video codec. Beyond VVC, we further compare a range of video codecs and encoding profiles to evaluate their impact on compression performance. Experiments on different models demonstrate the robustness and generality of LLMCodec. Notably, on LLaMA-3-8B at 2-bit precision, LLMCodec reduces perplexity by over 1.5x and improves downstream task accuracy by 21% compared with the existing method.

Rui Wang, Yan Zhao, Li Song +1

Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University. Shanghai, China

Model Compression LLM Quantization LLM Compression Language Modeling

Jun 3, 2026cs.LG

Learned Subspace Compression for Communication-Efficient Pipeline Parallelism

Pipeline parallelism enables training of large language models that exceed single-device memory, yet inter-stage activation communication becomes the dominant bottleneck when trained on low-bandwidth networks. Recent work in this area has proposed using fixed orthogonal projections to compress activations. However, this still results in a significant performance degradation and requires a number of non-standard adaptations to constrain the optimization. A natural alternative is to learn a low rank projection for each pipeline stage, however maintaining the necessary orthogonality of these projectors during training remains a challenge. We present Manifold Aware Projection Learning (MAPL), a method that treats inter-stage compression as a learnable orthogonal projection under explicit Stiefel manifold (orthogonal matrices) constraints. Rather than prescribing a fixed global subspace, MAPL lets each pipeline stage discover and continuously adapt its own task-optimal compression subspace via manifold-constrained steepest descent. To recover token-specific signals at stage boundaries, we introduce per-stage factorized anchor embeddings that allow for full-rank activation reconstruction with negligible communication overhead. We further show that we can incorporate residual vector quantization after projection with a streaming codebook synchronization protocol that amortizes dictionary communication. Across LLaMA models from 150M to 1B parameters we show that MAPL can be easily applied to the existing pipeline and can achieve high compression with neglibile performance degradation with a drastically improved tradeoffs in performance vs. compression compared to Subspace Networks.

Paul Janson, Edouard Oyallon, Eugene Belilovsky

Concordia University · Mila Quebec AI Institute · CNRS, Sorbonne University

LLM Compression Communication-Efficient Distributed Training Low-Rank Compression Pipeline Parallelism Neural Network Compression

Jun 3, 2026cs.LG

TENP: Trapezoidal Expert Neuron Pruning For Mixture-of-Experts

Mixture-of-Experts large language models (LLMs) scale efficiently through sparse activation, yet their deployment is fundamentally constrained by the large static parameter footprint of experts. Existing compression approaches either remove entire experts, disrupting routing topology and harming performance, or rely on unstructured weight pruning with limited practical efficiency. To address the limitations, we propose TENP, a structured Trapezoidal ExpertNeuron Pruning framework. Using a few samples, we identify and retain important experts, while applying expert neuron pruning (ENP) to less important experts, reserving model parameters in a trapezoidal pattern from shallow to deep layers. When evaluating expert importance, we jointly consider both the magnitude of the expert output and its ability to change the direction of the input vector. For ENP, we measure each neuron's projected contribution to the expert output to identify and retain important neurons. We conduct extensive experiments on the Qwen and DeepSeek models. Under a routing expert sparsity of 40% and an average of 63.76% activated expert parameters, the DeepSeek model suffers only a 1-point drop in accuracy compared to the full-parameter model. Moreover, it outperforms the full-parameter model by 10% on code generation tasks.

Jiangyang He, Shaolin Zhu, Deyi Xiong

TJUNLP Lab, School of Computer Science and Technology, Tianjin University, China

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

Jun 2, 2026cs.CL

Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines

LLM pipelines waste substantial token budgets on low-information content: repeated context, verbose responses, and redundant boilerplate. We introduce Entropy Gate, a token compression framework applying entropy quenching

-

a thermodynamic process that progressively freezes out low-energy tokens while preserving semantic fidelity. Each token receives a multi-factor information energy

E(t)

combining statistical, structural, and positional components. An adaptive quenching schedule

T(τ) = T_0 / (1 + ατ)

removes tokens whose Boltzmann survival probability

p_i = \exp(-E_i / kT)

falls below threshold, with a fidelity gate halting compression when energy-weighted similarity drops below

θ

. We prove token selection by descending

E(t)

maximizes expected semantic preservation, that quenching produces nested survival sets, and that achievable compression approaches the information-theoretic limit

\text{CR} \to 1 - I(P; T)/H(P)

. A Phase 1 heuristic achieves 40-60% compression across five prompt categories while maintaining

S_E > 0.80

, with energy-squared amplification

E \to E^2

adding 10-25 percentage points. Context deduplication adds 50-70% savings on repeated blocks. Output-side quenching, motivated by findings that brevity improves accuracy, further reduces response overhead. Combined with external memory, reduction composes multiplicatively to 88-96% for agentic workloads. The framework is stateless, model-agnostic, and deploys as an OpenAI-compatible HTTP proxy.

Justice Owusu Agyemang, Jerry John Kponyo, Kwame Opuni-Boachie Obour Agyekum +3

1VIA Cybersecurity Lab, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana · 2Quantum and Assistive Technologies Lab, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana

LLM Compression Token Pruning LLM Context Management

Jun 2, 2026cs.LG

LLM Compression with Jointly Optimizing Architectural and Quantization choices

Deploying large language models (LLMs) is challenging due to their significant memory and computational requirements. While some methods address this by developing small or tiny language models from scratch, these approaches demand extensive GPU training. Compressing pre-trained LLMs for edge devices offers a compelling alternative. Beyond pruning and quantization, Neural Architecture Search (NAS) enables effective compression, yet prior NAS approaches often limit the search space and decouple architecture from quantization. We introduce a differentiable NAS framework that explores the entire space and jointly optimizes architectural configurations alongside mixed-precision quantization for linear layers of LLMs. Experiments demonstrate superior accuracy-latency trade-offs: our models achieve up to 1.4x faster inference than sequential NAS-then-quantization baselines at comparable accuracy, or up to 6% higher average accuracy across seven reasoning tasks at equivalent latency.

Hoang-Loc La, Truong-Thanh Le, Amir Taherkordi +1

UiT The Arctic University of Norway · University of Oslo, Norway

Mixed-Precision Quantization LLM Quantization On-Device Language Model Inference LLM Compression Neural Architecture Search

Jun 2, 2026cs.LG

Rethinking the Role of Tensor Decompositions in Post-Training LLM Compression

Post-training compression is essential for deploying large language models (LLMs) under tight resource constraints. Tensor decompositions have emerged as a promising direction, offering compact parameterizations well suited to Transformer weight structures. However, existing studies evaluate these methods in narrow settings, leaving unclear whether tensorization is effective at large-scale deployment. We systematically evaluate tensor compression across dense and MoE architectures, establishing performance trade-offs grounded in both empirical analysis and theoretical analysis. We identify a fundamental mismatch between the shared subspaces assumed by tensor decompositions and the heterogeneous representations learned by modern LLMs, thereby delineating their practical limits and clarifying their viable role in large-scale deployment. The code is available at https://github.com/brain-lab-research/TT-LLM.

Artur Zagitov, Alexander Miasnikov, Maxim Krutikov +5

BRAIn Lab, Moscow, Russia

LLM Compression Tensor Decomposition LLM Post-Training

Jun 2, 2026cs.LG

LiftQuant: Continuous Bit-Width LLM via Dimensional Lifting and Projection

Existing quantization methods are fundamentally limited by rigid, integer-based bit-widths (e.g., 2, 3-bit), resulting in a

deployment gap" where Large Language Models cannot be optimally fitted to specific memory budgets. To bridge this gap, we introduce LiftQuant, a novel framework that enables continuous bit-width control for true Pareto-optimal deployment. The core innovation is a

lift-then-project" mechanism which approximates low-dimensional weight vectors by projecting a simple 1-bit lattice from a higher-dimensional ``lifted" space. Crucially, the effective bit-width is determined simply by the ratio of the lifted dimension to the original dimension, which allows the bit-width to be tuned quasi-continuous as the dimension is a flexible structural parameter. This projection generates a structured yet non-uniform codebook, capturing the expressive power of Vector Quantization (VQ). While beneficial over VQ, LiftQuant's decoding path relies solely on linear transformations and 1-bit uniform quantizers, retaining hardware-friendly nature. This flexibility is transformative: LiftQuant enables a 70B LLM to be compressed to 2.4 bits to precisely fit a 24GB GPU, where its performance significantly surpasses state-of-the-art 2-bit models fitted on the same device. Our code and ckpt is available at https://github.com/Heliulu/LiftQuant.

Liulu He, XuanAng Liu, Juntao Liu +8

Nanjing University, China · China Mobile Research Institute, China · Xiaomi Corporation, China +2

LLM Quantization LLM Compression Weight-Only Quantization Low-Bit Quantization Neural Network Quantization

Jun 1, 2026cs.CL

From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression

Post-training compression of Large Language Models (LLMs) removes entire architectural components, either deleting them or replacing them with fitted modules. Existing replacement-based methods share two design constraints: full-layer granularity and contiguous selection. We argue that this is overly restrictive: in fact, redundancy in pretrained transformers is not confined to contiguous regions, nor does it evenly distribute between Attention and FeedForward outputs, implying that different strategies best approximate different submodule types and that removable components need not cluster within contiguous depth ranges. Based on this intuition, we introduce SubFit (Submodule-level Fitted residual replacement), which compresses LLMs at the submodule level: Attention and FeedForward submodules are selected non-contiguously, and each receives its own lightweight fitted residual bypass. SubFit operates post-training and requires only calibration data. Across ten LLMs (five base, five instruction-tuned), five sparsity levels from 12.5% to 37.5%, and four replacement-based baselines, SubFit achieves the best aggregate perplexity-accuracy trade-off across the evaluated sparsity levels, with larger gains under aggressive compression. At 25% sparsity, it retains 84.6% of dense downstream accuracy and incurs 2.42x perplexity degradation, against 81.6% and 4.34x for the strongest baselines, while delivering measurable inference speedup and KV-cache savings. Code is available at https://github.com/eliacunegatti/SubFit.

Elia Cunegatti, Marcus Vukojevic, Erik Nielsen +1

University of Trento

LLM Pruning LLM Compression Transformer LLM Inference Acceleration

Jun 1, 2026cs.LG

HMPO: Hybrid Median-length Policy Optimization for Chain-of-Thought Compression

Large language models achieve remarkable performance via extended chain-of-thought (CoT) reasoning, yet this lengthy process incurs substantial inference overhead. Existing CoT compression methods struggle with inflexible manual length budgets, computationally expensive multi-stage training pipelines, and fragile scalability restricted to small models. We propose HMPO (Hybrid Median-length Policy Optimization), a cost-effective, single-stage reinforcement learning framework. HMPO efficiently compresses CoT via three synergistic components: an adaptive median-based budget derived from successful rollouts to eliminate manual tuning, a cosine-decay token reward for smooth length penalization, and a multiplicative reward formulation that substantially mitigates trivial reward hacking by strictly prioritizing answer correctness. Trained exclusively on mathematical data, HMPO generalizes seamlessly across math, code, science, and instruction-following tasks. Extensive experiments scaling from 9B to 122B parameters across dense and Mixture-of-Experts (MoE) architectures demonstrate that HMPO achieves 19%--46% token compression with negligible accuracy degradation, all while drastically reducing training costs compared to existing multi-stage baselines.

Minghui Zheng, Hongxu Chen, Huimin Ren +8

Li Auto Inc.

LLM Compression RL for Language Model Reasoning LLM Inference Acceleration CoT Compression

Jun 1, 2026cs.AI

Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction

Model compression techniques such as quantization and pruning are widely used to reduce the deployment cost of large language models (LLMs), with existing evaluations focusing almost exclusively on accuracy preservation. However, in safety-critical applications, a model's ability to reliably quantify its own uncertainty is equally important. We ask: does compression preserve this ability? To answer this question, we benchmark 12 LLMs under various compression configurations across five NLP tasks, using conformal prediction to provide a rigorous, distribution-free measure of uncertainty. Our experiments reveal that: (I) compression frequently decouples accuracy from uncertainty; (II) larger models absorb compression-induced uncertainty far more effectively than smaller ones; and (III) uncertainty inflation is often threshold-like rather than gradual. These results suggest that accuracy-only evaluation is insufficient for assessing the deployment readiness of compressed LLMs, and that uncertainty-aware benchmarking should be a standard component of model compression pipelines.

Yujia Tong, Yuxi Wang, Yunyang Wan +3

Wuhan University of Technology · Nanyang Technological University

LLM Quantization LLM Evaluation LLM Pruning LLM Compression Confidence Estimation in Language Models LLM Reliability+1

Jun 1, 2026cs.LG

CRePE: Convolution-aware Relative Importance in Post-training Pruning with Efficient Search

Deploying Large Language Models (LLMs) in practice incurs substantial memory and computational costs. Post-training pruning (PTP) is an effective approach to reducing these costs by removing weights without additional training. Among existing methods, RIA introduces relative importance scores normalized by row and column sums, achieving state-of-the-art accuracy. However, RIA considers only 1D cross-shaped (row/column) directional information and assigns equal weight to row and column contributions. In this paper, we propose \textbf{CRePE}, which incorporates 2D local neighborhood context and adaptive coefficients into Relative Importance scoring. CRePE consistently outperforms existing PTP methods across diverse models and sparsity settings. However, identifying optimal adaptive coefficients via perplexity (PPL)-based hill climbing requires numerous PPL evaluations and approximately 11 hours of search time. To address this, we propose \textbf{PHO} (Proxy-based Hyperparameter Optimization), which eliminates the need for repeated PPL measurements and reduces the search time to approximately 20 minutes. Furthermore, the optimal hyperparameter configuration found by PHO on one model transfers well to other models, demonstrating strong generalization. Finally, we verify that CRePE can be orthogonally combined with existing techniques including Channel Permutation, non-uniform sparsity allocation, and re-pruning methods.

Cheonjun Park

Hankuk University of Foreign Studies

LLM Pruning LLM Compression Hyperparameter Optimization Neural Network Pruning

May 31, 2026cs.CL

LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning

As real-world applications increasingly require processing inputs of 100k+ tokens, the gap between context length and inference efficiency has become a critical bottleneck. Context compression offers a way to reduce prefill costs while preserving task accuracy. However, existing training-free attention-based methods leave substantial gaps in demanding long-context tasks such as code reasoning. We present LongAttnComp, a long-context adaptation of AttnComp that fine-tunes a lightweight cross-attention scoring layer and introduces tokenlevel chunking, a token-budget top-p algorithm, positional reordering, and a formatagnostic query parser. We further design a two-stage fine-tuning recipe for the compressor: Stage 1 builds a general retrieval foundation from NIAH-style data, and Stage 2 extends it with multi-hop and reasoning data for broader long-context task coverage. On InfiniteBench Code-Debug, LongAttnComp matches or exceeds full-context accuracy, substantially outperforms training-free baselines, and transfers across four target models from three families. On LongBench v2, the two-stage recipe largely closes the Stage 1 gap on multi-document reasoning while preserving Code-Debug performance.

Mengmeng Ji, Ravi Shanker Raju, Jonathan Lingjie Li +1

SambaNova Systems, Inc. San Jose, CA, USA

LLM Compression LLM Fine-Tuning LLM Inference Acceleration Long-Context Inference

May 29, 2026cs.LG

Cross-Layer Subspace Coupling for LLM Compression: A Unifying Framework and Its Empirical Limits

Recent SVD based compression methods for large language models like SVD LLM and Basis Sharing can be unified under one optimization problem. While mathematical proofs and tests on Pythia models show this unified approach improves weight reconstruction error by up to 46% percent it fails in practical tasks. Downstream metrics like perplexity and accuracy severely degrade compared to standard per layer SVD LLM. The authors explain this failure mechanistically. Although the bundle method mathematically couples adjacent layers the transformer residual stream actually decouples them during forward passes. Thus per layer optimality matters more than joint cross layer optimization. The paper concludes that weight space reconstruction is a flawed objective for cross layer compression and future methods must focus on per layer activation reconstruction instead.

Snigdha Chandan Khilar

Independent Researcher

Model Compression LLM Compression Low-Rank Compression

May 28, 2026cs.CL

Kronecker Embeddings: Byte-Level Structured Token Representations for Parameter-Efficient Language Models

Large language models route every input through a learned embedding table of shape |V| x d_model, consuming hundreds of millions to billions of trainable parameters at frontier scale. We introduce Kronecker Embeddings, a deterministic byte-level character-position factorization that replaces this table with a fixed encoder and a single learned projection, compatible with standard BPE tokenizers, eliminating 91--94% of input-side trainable parameters at frontier scale. We provide five contributions. First, a cross-model probe across six LMs (135M-671B parameters) shows trained input embeddings cluster typographic variants of the probe word far more than morphological relatives; Kronecker escapes this clustering at the embedding layer. Second, a controlled three-seed comparison on nanoGPT GPT-2 124M over 2.5B tokens of FineWeb-Edu shows Kronecker reaching 2.5 +- 0.2% lower validation loss than the BPE-tied baseline (gap 0.083 +- 0.007 nats, ~9% lower perplexity), needing ~1.43x fewer steps to reach BPE's converged loss. Third, a spelling-robustness probe over 110 clean/typo pairs shows Kronecker preserves the top-1 prediction on 55.5% of pairs vs. 47.3% for BPE (+8.2 pp) and lowers KL by 7.6%, winning or tying in 10 of 11 categories; a generation probe shows Kronecker echoes byte-novel strings and typos through generation where BPE forgets them. Fourth, BPE embedding norm drifts during training while Kronecker projection norm stays near 1.0, consistent with a stable representational target. Fifth, an on-the-fly runtime variant reconstructs embeddings from a 4.5 MB byte buffer rather than a 2.15 GB table at vocabulary 131,072, with 0.01--0.24% step-time overhead. Byte-level locality has a tradeoff: byte-similar but semantically distant pairs (compute/commute, nation/notion) cluster together, shifting disambiguation to early attention layers.

Rohan Shravan

The School of AI Bengaluru, India

Language Model Pretraining LLM Compression Word Embeddings Byte-Level Language Model

May 28, 2026cs.AI

ConMoE: Expert-Pool Consolidation via Prototype Reassignment for MoE Compression

Mixture-of-Experts (MoE) language models reduce per-token computation but still require storing and serving all experts, making deployment memory-intensive. Existing post-training compression methods mainly shrink this cost by pruning experts or merging their weights. We formulate post-training MoE compression as expert-pool consolidation: retaining a smaller set of pretrained experts as reusable prototypes and deterministically remapping each original expert reference to one selected prototype. This view separates the reduced expert pool from the reuse structure that represents the original expert slots, and allows prototype sharing within local layer scopes while preserving the original router interface. We propose ConMoE, a train-free prototype remapping framework that selects retained experts using calibration-based contribution and replaceability signals, then redirects original expert calls to the selected prototypes without weight updates or post-compression fine-tuning. Experiments on three pretrained MoE language models show that ConMoE matches or outperforms strong pruning and merging baselines in several settings, achieving the best average score on deepseek-moe-16b-base at both 25% and 50% routed-expert reduction, while remaining competitive on Qwen3-30B-A3B and OLMoE-1B-7B-0125. Ablations indicate that deterministic reassignment is the most stable component, whereas broader cross-layer sharing and post-hoc weight fusion are model-dependent.

Yilun Yao, Jiaming Pan, Elsie Dai +3

Peking University

Mixture-of-Experts Language Models LLM Compression

May 28, 2026cs.CL

Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization

Efficient Distillation (EDistill) compresses large language models (LLMs) by structured pruning parameters and tuning lightweight modules with high training efficiency. Although these EDistilled LLMs achieve state-of-the-art (SOTA) performance on general ability benchmarks relative to similarly sized LLMs, we identify a severe degradation in their multi-step reasoning ability, which we term reasoning collapse. We systematically analyze the geometric origins of reasoning collapse and show that the SOTA EDistill method based on width-reducing projection matrices suffers from eRank collapse, in which the effective rank (eRank) of hidden representations drops. We theoretically explain how singular values of randomly initialized projection matrices become unevenly distributed, leading to eRank collapse and thus token indistinguishability. To address this issue, we propose RED (Reasoning-preserved Efficient Distillation) for LLMs, which introduces activation-aware initialization to initialize projection matrices as channel-selection matrices, thus theoretically mitigating eRank collapse. Experiments on Llama and Qwen series demonstrate that RED substantially recovers reasoning while maintaining high training efficiency and SOTA general ability.

Junlin He, Yihong Tang, Tong Nie +5

The Hong Kong Polytechnic University, Hong Kong SAR, China · McGill University, Montreal, QC, Canada

LLM Pruning LLM Compression Language Model Distillation LLM Reasoning

May 27, 2026cs.LG

Apertus LLM Family Expansion via Distillation and Quantization

The wide adoption of LLMs has led to their use in great variety of applications and scenarios, such as chatbot assistants and data annotation, creating the need for the models to satisfy certain budget and hardware constraints. This has led to the trend of LLMs being released in batches consisting of similar models of various sizes for the family of models to adhere to as wide of a range of constraints as possible. In this paper, we validate distillation and quantization as a cost-effective way to expand model families to new sizes and hardware formats. Based on the open-recipe Apertus 8B LLM, we produce Apertus-v1.1 - a distilled family of models with up to 4B parameters trained on 1.7T permissive license tokens. We demonstrate cost-efficiency and strong accuracy performance of our approach for covering large ranges of hardware and systems requirements.

Andrei Panferov, Davit Melikidze, Martin Jaggi +1

ISTA · EPFL · ETH Zürich +1

LLM Quantization LLM Compression Small Language Models Language Model Distillation

May 27, 2026cs.LG

Knowledge Offloading: Decomposing LLMs into Sparse Backbones and Memory Modules

LLMs encode both general capabilities and domain-specific knowledge in a single set of parameters. We ask whether this capacity can be reorganized: keeping broadly useful computation in a shared backbone, while moving specialized knowledge into external memory modules. We propose \emph{knowledge offloading} (KOFF), a framework for decomposing a pretrained LLM into a sparse shared backbone and domain-specific memories. Starting from a frozen base model, we jointly learn a structured pruning mask and lightweight recovery modules, implemented as LoRA adapters and learned key-value caches. Across Llama and Qwen models from 3B to 8B, we find that non-trivial capacity can be moved out of the shared backbone without a large loss in model ability. At around 12% global sparsity, KOFF preserves much of the unpruned model's performance, while pruning the same frozen model without memories degrades sharply. Ablations show that LoRA and learned KV memories are complementary, and specialization analyses suggest that the learned decomposition is meaningful: language-specific neurons are preferentially removed while language-general neurons largely remain in the backbone. These results suggest that knowledge can be reallocated between a shared core and swappable external memories.

Karim Galliamov, Rochelle Choenni, Ivan Titov

University of Amsterdam · University of Edinburgh

LLM Pruning LLM Compression Memory-Augmented Language Models Parameter-Efficient Fine-Tuning

May 27, 2026cs.AI

Thinking as Compression: Your Reasoning Model is Secretly a Context Compressor

Context compression aims to shorten long context inputs with minimal information loss for LLM inference acceleration. While existing methods have shown promise, they typically rely on complex compression modules or compression-specific training, leaving the intrinsic capabilities of LLMs underexplored. In contrast, this work reveals that a thinking model itself can naturally compress long contexts by organizing task-relevant information. We thus derive Thinking as Compression (TaC), a new compression paradigm that treats thinking itself as compressed context. Without relying on specific dedicated compressor, TaC directly prompts the thinking model to generate thinking traces as the shortened context, already outperforming most representative compression methods. Further, given that raw thinking output may struggle with budget control and shortcut behaviors, we introduce Thinking as Compression Constrained (TaC-C), leveraging a simple reward-driven optimization framework to elicit intrinsic thinking as compact and controllable compressed context. Experiments across four long-context QA benchmarks demonstrate that TaC-C consistently outperforms existing baselines. At 4x and 8x compression ratios, it surpasses the strongest competitor by 17.4% and 23.4% in average F1, and by 15.7% and 21.7% in average Exact Match Score (EM), respectively.

Guoxin Ma, Yibing Liu, Chengzhengxu Li +7

Baidu Inc., Beijing, China · Xi’an Jiaotong University · City University of Hong Kong +1

LLM Compression Long-Context Inference Context Compression

May 27, 2026cs.CL

Pruning and Distilling Mixture-of-Experts into Dense Language Models

Mixture-of-Experts (MoE) is now the dominant architecture for frontier language models, yet it requires all expert parameters to be loaded in memory, making it less preferable for memory-constrained deployment. Existing compression methods reduce the number of experts but the output remains an MoE model with the same fundamental limitation. We present the first systematic framework for converting a trained MoE into a standard fully dense architecture: experts are scored, selected, and grouped, then concatenated into a dense FFN and refined by knowledge distillation from the MoE teacher. We evaluate 7 scoring, 5 grouping, and 2 magnitude scaling methods across a range of selected expert counts on Qwen3-30B-A3B, yielding 350 configurations. We find that the choice of scoring method is the most impactful, with our novel diversity-aware scoring consistently outperforming prior methods on Qwen3-30B-A3B, DeepSeek-V2-Lite, and GPT-OSS-20B. Under a controlled comparison at matched parameter count, MoE-to-dense outperforms dense-to-dense pruning by +6.3 pp in average downstream accuracy after ~4B-token distillation at 1.6x faster training wall-clock speed.

Junhyuck Kim, Jihun Yun, Haechan Kim +3

1KRAFTON · 2KAIST

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

May 27, 2026cs.AI

ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replay

Adaptive context compression is vital for scaling Large Language Models (LLMs) to complex, multi-turn agent tasks. However, rule-based compression methods may discard task-critical nuances, while Reinforcement Learning (RL) approaches usually struggle to balance information retention and token efficiency under the sparse rewards inherent to long-horizon workflows. To bridge this gap, we propose ZipRL, a novel adaptive compression framework tailored for Reinforcement Learning from Verifiable Rewards (RLVR). ZipRL features a multi-granularity compression mechanism for active, non-uniform information reduction, coupled with Hindsight Response Replay (HRR), a technique designed to densify training signals during RLVR optimization. Theoretically, we prove ZipRL's superior task-relevant utility over uniform methods. Concretely, ZipRL utilizes coarse-to-fine prompts for macro-compression and incorporates HRR into GRPO via generalized advantage reshaping. Multiple models of varying versions and parameter scales validate the effectiveness of our approach. Benchmarks on five agent tasks show ZipRL outperforms state-of-the-art approaches by 27.9% and 34.7% across Qwen3-4B and Qwen3-8B models, while maintaining exceptional token efficiency and robustness under extreme 256-turn extrapolation stress tests.

Zhexin Hu, Li Wang, Xiaohan Wang +4

1Meituan · Institute of Software, Chinese Academy of Sciences

LLM Compression Reinforcement Learning with Verifiable Rewards RL for LLM Agents

May 27, 2026cs.CL

Extracting Small Translation Specialists from LLMs by Aggressively Pruning Experts

Modern large language models (LLMs) achieve state-of-the-art machine translation performance, but they do so as broad generalists largely trained for many tasks and capabilities unrelated to translation. Thus, they are heavily overparameterized for this task, resulting in excessive memory and compute requirements. In this paper, we present a method for aggressively pruning experts from modern mixture-of-experts LLMs while incurring negligible degradation in translation quality. Our approach exploits expert specialization and the separability of multilingual capabilities in LLMs to identify experts irrelevant to translation. And because of the modular nature of MoEs, these can be easily pruned without any training. Without retraining, we are able to prune half of all experts with negligible degradation and 70% with only minor losses. With a very short SFT, we prune 75% of experts while recovering baseline performance, and in some settings remove nearly 90% while maintaining reasonable translation quality. Overall, our results show that translation requires only a fraction of the LLM, enabling substantial compression of the MoE blocks that contain over 90% of parameters.

Liu O. Martin, Lucas Bandarkar, Nanyun Peng

University of California, Los Angeles

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

May 27, 2026cs.LG

Locality-Aware Redundancy Pruning for LLM Depth Compression

Large language models are known to contain representational redundancy across network depth, making depth pruning an effective approach for improving inference efficiency. Existing one-shot pruning methods rely on local layer importance or fixed redundancy assumptions across architectures. We propose Locality-Aware Redundancy Pruning (LoRP), a training-free one-shot depth pruning framework guided by representation locality. We show that inter-layer redundancy can be either localized or globally distributed depending on the LLM architecture. To characterize this phenomenon, we introduce Representation Locality Score (RLS), derived from global inter-layer hidden-state similarity. Using a small calibration set, LoRP computes pairwise layer similarity, clusters layers by representational similarity, and allocates pruning according to residual intra-cluster redundancy. Experiments across diverse LLM families show improvements in both perplexity and downstream task accuracy. Official github repository: https://github.com/daniel-eai/LoRP-Locality-Aware-Redundancy-Pruning/

Vincent-Daniel Yun, Youngrae Kim, Woosang Lim +3

University of Southern California, United States · Neural Superintelligence Lab, MODULABS, Republic of Korea · Seoul National University, Republic of Korea +1

LLM Pruning LLM Compression LLM Inference Acceleration

May 26, 2026cs.CL

Pair-In, Pair-Out: Latent Multi-Token Prediction for Efficient LLMs

Long chain-of-thought reasoning has made autoregressive decoding the dominant inference cost of modern large language models. Existing methods target either the input side (latent compression) or the output side (speculative decoding and multi-token prediction, MTP), but the two lines of work have been pursued independently. Moreover, output-side methods must incur an expensive verifier pass to validate the unreliable draft tokens predicted by MTP. To address these issues, we propose \textbf{Pair-In, Pair-Out (PIPO)}, which unifies both sides by viewing a latent compressor and an MTP head as mirror-image operations: the compressor folds two input tokens into one latent representation, while the MTP head unfolds one hidden state into one additional output token. To remove the verifier cost without sacrificing reliability, PIPO trains a lightweight confidence head that decides whether draft tokens should be accepted. We observe that On-Policy Distillation (OPD) naturally matches the rejection-sampling criterion of speculative decoding, so the confidence head can be trained alongside OPD with negligible extra cost. Experiments on AIME 2025, GPQA-Diamond, LiveCodeBench v6, and LongBench v2 with Qwen3.5-4B and 9B backbones show that PIPO improves pass@4 over regular decoding by up to

+7.15

points, while delivering up to

2.64\times

first-token-latency and

2.07\times

per-token-latency speedups. Project Page: GitHub.com/RedAI-Infra/PIPO.

Wenhui Tan, Minghao Li, Xiaoqian Ma +5

Gaoling School of Artificial Intelligence, Renmin University of China · AI Platform, Xiaohongshu Inc. · University of Electronic Science and Technology of China +1

Multi-Token Prediction LLM Compression Speculative Decoding LLM Inference Acceleration

May 26, 2026cs.AI

AGORA: Adapter-Grounded Observation-Action Retention for Inference-Free Prompt Compression in LLM Agents

The token-level extractive compressors widely used for general LM context are structurally inappropriate for LLM agents: across 17 (env, backbone, method) cells spanning two independent token-level method families, every cell collapses to mean reward <= 0.05 despite 1.3-13.3x realized compression. We name and characterize this failure mode as action-grammar destruction -- the tokens carrying action semantics (identifiers, brackets, action verbs) are exactly those self-information ranks lowest, so a general-purpose compressor reliably removes them and the environment rejects the residual. The diagnosis points to step-granularity compression. We introduce AGORA, an inference-free step-level compressor combining a structural prompt parser, an always-keep floor for format- and recency-critical content, and a 125M-parameter relevance scorer trained on counterfactual next-action-change labels (~2ms/step, zero per-step LLM toll). Across the compared inference-free and LLM-based methods, AGORA is the only one retaining >= 75% uncompressed performance in 8 of 9 cells (with the lone exception at 73%); a four-way component ablation isolates the structural floor as the dominant quality lever and the learned scorer as the source of 1.0-11.5x adaptive end-to-end compression from a single fixed keep ratio.

Haoran Zhang, Zhaohua Sun

AI Agent Technologies (Hong Kong) Limited · Department of Mechanical Engineering, The University of Hong Kong

LLM Compression LLM Agents Prompt Compression

May 26, 2026cs.LG

Dense2MoE: Pushing the Pareto Frontier of On-Device LLMs via Unified Pruning and Upcycling

The Mixture of Experts MoE architecture is highly promising for resource constrained on device deployments yet training these models from scratch incurs prohibitive costs Current methods attempt to alleviate this by upcycling dense models into MoEs however they often introduce parameter redundancy that degrades inference efficiency Alternatively standard layer pruning mitigates redundancy but inevitably compromises model accuracy To resolve this dilemma we propose Dense2MoE a novel framework that unifies pruning and upcycling through Layer Fusion UpCycling LF UC Guided by hardware Roofline theory Dense2MoE systematically overcomes the inference memory wall by pruning bandwidth heavy attention modules from redundant layers while repurposing their Multi Layer Perceptrons MLPs into MoE experts This structural innovation preserves the models core capabilities and strictly limits active parameters via selective token routing With a modest continual pre training budget Dense2MoE efficiently converts publicly available dense LLMs into on device ready MoE models Extensive experiments demonstrate that Dense2MoE significantly advances the Pareto frontier for on device inference latency versus model accuracy outperforming dense baselines state of the art compression and standard upcycling methods

Fengfa Li, Hongjin Ji, Yifeng Ding +2

Li Auto · The Chinese University of Hong Kong, Shenzhen

Mixture-of-Experts Pruning LLM Pruning On-Device Language Model Inference LLM Compression Mixture-of-Experts Inference

May 25, 2026cs.LG

The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works

Knowledge distillation (KD) transfers knowledge from a large teacher model to a smaller student. In language modeling, the student is trained either on tokens sampled from the teacher (hard labels) or the teacher's full next-token distribution (soft labels). Despite soft labels appear strictly richer, we find that mixing hard and soft labels consistently yields better results. Crucially, we show that this gain cannot be explained by closer teacher matching during training. Instead, it comes from reduced exposure bias, the mismatch between training and inference distributions. To explain this phenomenon, we introduce the Bridge-Garden Decomposition theory, which categorizes generation steps into two types: Bridges, where the next token must be exact, and Gardens, where it can be flexible. We show that hard-only KD excels in Bridges by avoiding risky deviations, while soft-only KD preserves diversity in Gardens. A hybrid strategy handles both cases and, as a result, reduces exposure bias across the sequence. Guided by this theory, we develop a family of Bridge-Garden hybrid supervision methods that adaptively balance hard and soft labels. Across a primary suite of seven teacher-student pairs (including Qwen, Llama, Gemma, and DeepSeek) and benchmarks in reasoning and coding, our approach outperforms divergence-based and on-policy KD baselines while reducing training cost by 9.7x, enabling efficient model compression. Code is available at https://github.com/ghwang-s/bridge_garden_hybrid_kd_release.

Guanghui Wang, Kaiwen Lv Kacuila, Zhiyong Yang +5

School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China · Alibaba Group, Hangzhou, China · State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China +2

LLM Compression Language Model Distillation Knowledge Distillation