Imagen de Portada

CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Makhov, Denis, Shopkhoev, Dmitriy, Zhussip, Magauiya, Ali, Ammar, Lefkimmiatis, Stamatios
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Share Your Attention: Transformer Weight Sharing via Matrix-based Dictionary Learning
por: Zhussip, Magauiya, et al.
Publicado: (2025)

ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression
por: Ali, Ammar, et al.
Publicado: (2026)

COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression
por: Makhov, Denis, et al.
Publicado: (2026)

ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization
por: Shopkhoev, Dmitriy, et al.
Publicado: (2025)

Speak, Edit, Repeat: High-Fidelity Voice Editing and Zero-Shot TTS with Cross-Attentive Mamba
por: Mohammad, Baher, et al.
Publicado: (2025)

A Modular Conditional Diffusion Framework for Image Reconstruction
por: Zhussip, Magauiya, et al.
Publicado: (2024)

SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks
por: Christopoulou, Fenia, et al.
Publicado: (2024)

Double-Calibration: Towards Reliable LLMs via Calibrating Knowledge and Reasoning Confidence
por: Lu, Yuyin, et al.
Publicado: (2026)

Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training
por: Si, Jianfeng, et al.
Publicado: (2025)

SpaRC and SpaRP: Spatial Reasoning Characterization and Path Generation for Understanding Spatial Reasoning Capability of Large Language Models
por: Rizvi, Md Imbesat Hassan, et al.
Publicado: (2024)

Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning
por: Volovikova, Zoya, et al.
Publicado: (2026)

CoDi: Conversational Distillation for Grounded Question Answering
por: Huber, Patrick, et al.
Publicado: (2024)

Beyond Label Attention: Transparency in Language Models for Automated Medical Coding via Dictionary Learning
por: Wu, John, et al.
Publicado: (2024)

Jailbreaking LLMs via Calibration
por: Lu, Yuxuan, et al.
Publicado: (2026)

Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control
por: Xiao, Yuxin, et al.
Publicado: (2024)

Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging
por: Liu, Deyuan, et al.
Publicado: (2024)

Advancing Arabic Reverse Dictionary Systems: A Transformer-Based Approach with Dataset Construction Guidelines
por: Sibaee, Serry, et al.
Publicado: (2025)

CRoCoDiL: Continuous and Robust Conditioned Diffusion for Language
por: Uziel, Roy, et al.
Publicado: (2026)

Improving Low-Resource Translation with Dictionary-Guided Fine-Tuning and RL: A Spanish-to-Wayuunaiki Study
por: Mosquera, Manuel, et al.
Publicado: (2025)

Dictionaries to the Rescue: Cross-Lingual Vocabulary Transfer for Low-Resource Languages Using Bilingual Dictionaries
por: Sakajo, Haruki, et al.
Publicado: (2025)

Atomic Calibration of LLMs in Long-Form Generations
por: Zhang, Caiqi, et al.
Publicado: (2024)

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression
por: Hong, Junyuan, et al.
Publicado: (2024)

CoDiQ: Test-Time Scaling for Controllable Difficult Question Generation
por: Peng, Zhongyuan, et al.
Publicado: (2026)

Generating Concept Lexicalizations via Dictionary-Based Cross-Lingual Sense Projection
por: Basil, David, et al.
Publicado: (2026)

Calibration Across Layers: Understanding Calibration Evolution in LLMs
por: Joshi, Abhinav, et al.
Publicado: (2025)

Continual Learning via Sparse Memory Finetuning
por: Lin, Jessy, et al.
Publicado: (2025)

A Survey of Calibration Process for Black-Box LLMs
por: Xie, Liangru, et al.
Publicado: (2024)

Compactor: Calibrated Query-Agnostic KV Cache Compression with Approximate Leverage Scores
por: Chari, Vivek, et al.
Publicado: (2025)

Parse Trees Guided LLM Prompt Compression
por: Mao, Wenhao, et al.
Publicado: (2024)

Mechanistic Knobs in LLMs: Retrieving and Steering High-Order Semantic Features via Sparse Autoencoders
por: Zhang, Ruikang, et al.
Publicado: (2026)

Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Survey
por: Bilal, Ahsan, et al.
Publicado: (2025)

TokenSkip: Controllable Chain-of-Thought Compression in LLMs
por: Xia, Heming, et al.
Publicado: (2025)

ODKE+: Ontology-Guided Open-Domain Knowledge Extraction with LLMs
por: Khorshidi, Samira, et al.
Publicado: (2025)

Towards Compositional Generalization of LLMs via Skill Taxonomy Guided Data Synthesis
por: Wei, Yifan, et al.
Publicado: (2026)

DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning
por: Parekh, Tanmay, et al.
Publicado: (2025)

CoT-Valve: Length-Compressible Chain-of-Thought Tuning
por: Ma, Xinyin, et al.
Publicado: (2025)

WordAlchemy: A transformer-based Reverse Dictionary
por: Madaswar, Kanhaiya, et al.
Publicado: (2022)

Accelerating Prefilling for Long-Context LLMs via Sparse Pattern Sharing
por: Peng, Dan, et al.
Publicado: (2025)

Problem-Solving Logic Guided Curriculum In-Context Learning for LLMs Complex Reasoning
por: Ma, Xuetao, et al.
Publicado: (2025)

Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs
por: Zhang, Zhuoxuan, et al.
Publicado: (2025)