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

• URL: http://arxiv.org/abs/2609.15338v1
• Date: Mon, 14 Sep 2026 10:24:16 GMT
• Title: Dynamic Semantic Compression for Efficient Latent-Space Inference in Large Language Models
• Abstract summary: Large Language Models (LLMs) primarily perform inference at the token level, resulting in substantial memory overhead and compromised computational efficiency.<n>We propose a Dynamic Semantic Extraction and Inference framework, which achieves segment-level inference within the latent space through a two-stage training strategy.
• Score: 11.004177856497085
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) primarily perform inference at the token level, resulting in substantial memory overhead and compromised computational efficiency. In this paper, we propose a Dynamic Semantic Extraction and Inference (DSEI) framework, which achieves segment-level inference within the latent space through a two-stage training strategy. First, we construct a Dynamic Semantic Autoencoder (DSAE) via self-supervised learning. DSAE dynamically extracts segment-level semantics and compresses them into compact latent representations via adaptive semantic weighting and gated fusion. Subsequently, we integrate the DSAE into the LLM architecture and train the model to infer over dense latent space. DSEI substantially reduces both input and generation sequences and significantly enhances inference efficiency. Extensive experiments conducted on the Wanjuan dataset demonstrate that DSEI reduces perplexity by 48% compared to static sentence-level latent inference baseline. Furthermore, compared to standard LLMs using token-level inference, DSEI accelerates inference speed by 2.5$\times$ and reduces memory overhead by 90%.

Related papers

• Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs [18.457250148137494]
  We present an Adaptive Depth Sparse Framework (AdaDSF) that converts off-the-shelf pre-trained large language models into depth-sparse models without retraining.<n>On GPT-NeoX and Qwen2.5 over language modeling and commonsense reasoning, AdaDSF substantially reduces inference FLOPs while preserving performance close to dense counterparts.
  arXiv  Detail & Related papers  (2026-07-23T13:13:04Z)
• Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs [58.719964942364356]
  Lychee-FD is a native end-to-end full-to-end full SLMs framework.<n>Lychee-FD decouples conflicting modalities while preserving cross-modality coherence.<n>Our method significantly remains the state of the art.
  arXiv  Detail & Related papers  (2026-07-07T17:43:36Z)
• Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs [17.167595029948576]
  We introduce three metrics to characterize how training paradigms allocate entropy reduction between the speech encoder and the LLM.<n>We propose a principled multi-stage training strategy grounded in capability-boundary awareness, optimizing parameter efficiency and robustness hallucination.<n> Experiments on Mandarin and English benchmarks show that our method achieves competitive performance with state-of-the-art models using only 2.3B parameters.
  arXiv  Detail & Related papers  (2026-04-09T09:07:52Z)
• MemDLM: Memory-Enhanced DLM Training [56.40248490616793]
  Diffusion Language Models (DLMs) offer attractive advantages over Auto-Regressive (AR) models.<n>They suffer from a notable train-inference mismatch.<n>We propose MemDLM (Memory-Enhanced DLM), which embeds a simulated denoising process into training.
  arXiv  Detail & Related papers  (2026-03-23T17:39:56Z)
• SLIM-Brain: A Data- and Training-Efficient Foundation Model for fMRI Data Analysis [16.923310176195766]
  Foundation models are emerging as a powerful paradigm for fMRI analysis.<n>Current approaches face a dual bottleneck of data- and training-efficiency.<n>SLIM-Brain is a new atlas-free foundation model that simultaneously improves both data- and training-efficiency.
  arXiv  Detail & Related papers  (2025-12-26T06:10:31Z)
• Exploring Structural Degradation in Dense Representations for Self-supervised Learning [84.52554180480037]
  We observe a counterintuitive phenomenon in self-supervised learning (SSL): longer training may impair the performance of dense prediction tasks.<n>We refer to this phenomenon as Self-supervised Dense Degradation (SDD) and demonstrate its consistent presence across sixteen state-of-the-art SSL methods.<n>We introduce a Dense representation Structure Estimator (DSE) composed of a class-relevance measure and an effective dimensionality measure.
  arXiv  Detail & Related papers  (2025-10-20T08:40:16Z)
• Beyond Fixed: Training-Free Variable-Length Denoising for Diffusion Large Language Models [74.15250326312179]
  Diffusion Large Language Models offer efficient parallel generation and capable global modeling.<n>The dominant application ofDLLMs is hindered by the need for a statically predefined generation length.<n>We introduce DAEDAL, a novel training-free denoising strategy that enables Dynamic Adaptive Length Expansion.
  arXiv  Detail & Related papers  (2025-08-01T17:56:07Z)
• Saliency-driven Dynamic Token Pruning for Large Language Models [32.903622070917194]
  Saliency-driven Dynamic Token Pruning (SDTP)<n>A lightweight saliency-driven prediction module is designed to estimate the importance score of each token with its hidden state.<n>A ranking-based optimization strategy is proposed to minimize the ranking divergence of the saliency score and the predicted importance score.
  arXiv  Detail & Related papers  (2025-04-06T15:15:07Z)
• Efficient Redundancy Reduction for Open-Vocabulary Semantic Segmentation [36.46163240168576]
  Open-vocabulary semantic segmentation (OVSS) is an open-world task that aims to assign each pixel within an image to a specific class defined by arbitrary text descriptions.<n>Recent advancements in large-scale vision-language models have demonstrated their open-vocabulary understanding capabilities.<n>This study introduces ERR-Seg, a novel framework that effectively reduces redundancy to balance accuracy and efficiency.
  arXiv  Detail & Related papers  (2025-01-29T13:24:53Z)
• Accelerating LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with LITE [62.13435256279566]
  Large Language Models (LLMs) have achieved remarkable performance across a wide variety of natural language tasks. However, their large size makes their inference slow and computationally expensive. We show that it enables these layers to acquire 'good' generation ability without affecting the generation ability of the final layer.
  arXiv  Detail & Related papers  (2023-10-28T04:07:58Z)
• Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of Semantics and Depth [83.94528876742096]
  We tackle the MTL problem of two dense tasks, ie, semantic segmentation and depth estimation, and present a novel attention module called Cross-Channel Attention Module (CCAM) In a true symbiotic spirit, we then formulate a novel data augmentation for the semantic segmentation task using predicted depth called AffineMix, and a simple depth augmentation using predicted semantics called ColorAug. Finally, we validate the performance gain of the proposed method on the Cityscapes dataset, which helps us achieve state-of-the-art results for a semi-supervised joint model based on depth and semantic
  arXiv  Detail & Related papers  (2022-06-21T17:40:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.