Papers Semantic Compression
“Semantic Compression” 태그가 달린 논문 60편 · 필터 해제
SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
Retrieval-augmented Generation (RAG) extends large language models (LLMs) with external knowledge but faces key challenges: restricted effective context length and redundancy in retrieved documents. Pure compression-base…
Evidence SelectionRAGRerankingRetrieval+4Agentic Semantic Control for Autonomous Wireless Space Networks: Extending Space-O-RAN with MCP-Driven Distributed Intelligence
Lunar surface operations impose stringent requirements on wireless communication systems, including autonomy, robustness to disruption, and the ability to adapt to environmental and mission-driven context. While Space-O-…
Decision MakingSemantic CompressionLatent Diffusion Model Based Denoising Receiver for 6G Semantic Communication: From Stochastic Differential Theory to Application
In this paper, a novel semantic communication framework empowered by generative artificial intelligence (GAI) is proposed, to enhance the robustness against both channel noise and transmission data distribution shifts. A…
DenoisingSemantic CommunicationSemantic CompressionZero-shot GeneralizationMachine Mirages: Defining the Undefined
As multimodal machine intelligence systems started achieving average animal-level and average human-level fluency in many measurable tasks in processing images, language, and sound, they began to exhibit a new class of c…
Causal InferenceHallucinationSemantic CompressionSemantics-Guided Generative Image Compression
Advancements in text-to-image generative AI with large multimodal models are spreading into the field of image compression, creating high-quality representation of images at extremely low bit rates. This work introduces …
DecoderImage CompressionSemantic CompressionSemantic SegmentationTAG-INSTRUCT: Controlled Instruction Complexity Enhancement through Structure-based Augmentation
High-quality instruction data is crucial for developing large language models (LLMs), yet existing approaches struggle to effectively control instruction complexity. We present TAG-INSTRUCT, a novel framework that enhanc…
Semantic CompressionTAGSemantic Compression of 3D Objects for Open and Collaborative Virtual Worlds
Traditional methods for 3D object compression operate only on structural information within the object vertices, polygons, and textures. These methods are effective at compression rates up to 10x for standard object size…
ObjectSemantic CompressionFrom Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
Humans organize knowledge into compact categories through semantic compression by mapping diverse instances to abstract representations while preserving meaning (e.g., robin and blue jay are both birds; most birds can fl…
Semantic CompressionHypernym Mercury: Token Optimization Through Semantic Field Constriction And Reconstruction From Hypernyms. A New Text Compression Method
Compute optimization using token reduction of LLM prompts is an emerging task in the fields of NLP and next generation, agentic AI. In this white paper, we introduce a novel (patent pending) text representation scheme an…
Semantic CompressionSemantic SimilaritySemantic Textual SimilarityText Compression+1Fair Resource Allocation in UAV-based Semantic Communication System with Fluid Antenna
In this paper, the problem of maximization of the minimum equivalent rate in a unmanned-aerial-vehicle (UAV)-based multi-user semantic communication system is investigated. In the considered model, a multi-antenna UAV em…
Semantic CommunicationSemantic CompressionEditID: Training-Free Editable ID Customization for Text-to-Image Generation
We propose EditID, a training-free approach based on the DiT architecture, which achieves highly editable customized IDs for text to image generation. Existing text-to-image models for customized IDs typically focus more…
Image GenerationSemantic CompressionText to Image GenerationText-to-Image GenerationThe Best of Both Worlds: Integrating Language Models and Diffusion Models for Video Generation
Recent advancements in text-to-video (T2V) generation have been driven by two competing paradigms: autoregressive language models and diffusion models. However, each paradigm has intrinsic limitations: language models st…
Semantic CompressionVideo GenerationStatistical Mechanics of Semantic Compression
The basic problem of semantic compression is to minimize the length of a message while preserving its meaning. This differs from classical notions of compression in that the distortion is not measured directly at the lev…
Semantic CompressionSemantic SimilaritySemantic Textual SimilarityHierarchical Semantic Compression for Consistent Image Semantic Restoration
The emerging semantic compression has been receiving increasing research efforts most recently, capable of achieving high fidelity restoration during compression, even at extremely low bitrates. However, existing semanti…
Feature CompressionSemantic CompressionVideo CompressionUAV Cognitive Semantic Communications Enabled by Knowledge Graph for Robust Object Detection
Unmanned aerial vehicles (UAVs) are widely used for object detection. However, the existing UAV-based object detection systems are subject to severe challenges, namely, their limited computation, energy and communication…
Objectobject-detectionObject DetectionRobust Object Detection+2Efficient Transmission of Radiomaps via Physics-Enhanced Semantic Communications
Enriching information of spectrum coverage, radiomap plays an important role in many wireless communication applications, such as resource allocation and network optimization. To enable real-time, distributed spectrum ma…
Edge-computingFederated LearningNovel ConceptsSemantic Communication+1SMIC: Semantic Multi-Item Compression based on CLIP dictionary
Semantic compression, a compression scheme where the distortion metric, typically MSE, is replaced with semantic fidelity metrics, tends to become more and more popular. Most recent semantic compression schemes rely on t…
Semantic CompressionRodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions
Recent advancements in Transformer-based large language models (LLMs) have set new standards in natural language processing. However, the classical softmax attention incurs significant computational costs, leading to a $…
Semantic CompressionFree-VSC: Free Semantics from Visual Foundation Models for Unsupervised Video Semantic Compression
Unsupervised video semantic compression (UVSC), i.e., compressing videos to better support various analysis tasks, has recently garnered attention. However, the semantic richness of previous methods remains limited, due …
Semantic CompressionExpediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding
Large language models (LLMs) have demonstrated remarkable capabilities in tasks requiring reasoning and multi-step problem-solving through the use of chain-of-thought (CoT) prompting. However, generating the full CoT pro…
Contrastive LearningLanguage ModelingLanguage ModellingLarge Language Model+3