Imagen de Portada

Haiku to Opus in Just 10 bits: LLMs Unlock Massive Compression Gains

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Rinberg, Roy, Carrell, Annabelle Michael, Henniger, Simon, Carlini, Nicholas, Warr, Keri
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence Information Theory
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

DiFR: Inference Verification Despite Nondeterminism
por: Karvonen, Adam, et al.
Publicado: (2025)

Rich-ARQ: From 1-bit Acknowledgment to Rich Neural Coded Feedback
por: Chen, Enhao, et al.
Publicado: (2026)

A SER-based Device Selection Mechanism in Multi-bits Quantization Federated Learning
por: Sun, Pengcheng, et al.
Publicado: (2024)

The Token Games: Evaluating Language Model Reasoning with Puzzle Duels
por: Henniger, Simon, et al.
Publicado: (2026)

From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
por: Shani, Chen, et al.
Publicado: (2025)

Exploiting Deep Reinforcement Learning for Edge Caching in Cell-Free Massive MIMO Systems
por: Zhang, Yu, et al.
Publicado: (2022)

CAnet: Uplink-aided Downlink Channel Acquisition in FDD Massive MIMO using Deep Learning
por: Guo, Jiajia, et al.
Publicado: (2021)

CSRv2: Unlocking Ultra-Sparse Embeddings
por: Guo, Lixuan, et al.
Publicado: (2026)

Fibbinary-Based Compression and Quantization for Efficient Neural Radio Receivers
por: Fiandaca, Roberta, et al.
Publicado: (2025)

Broadcast Channel Cooperative Gain: An Operational Interpretation of Partial Information Decomposition
por: Tian, Chao, et al.
Publicado: (2025)

Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs
por: Ayonrinde, Kola, et al.
Publicado: (2024)

Fed-PELAD: Communication-Efficient Federated Learning for Massive MIMO CSI Feedback with Personalized Encoders and a LoRA-Adapted Shared Decoder
por: Zhou, Yixiang, et al.
Publicado: (2025)

Optimizing Learned Image Compression on Scalar and Entropy-Constraint Quantization
por: Borzechowski, Florian, et al.
Publicado: (2025)

Solomonoff-Inspired Hypothesis Ranking with LLMs for Prediction Under Uncertainty
por: Barber, Josh, et al.
Publicado: (2025)

Can Complexity and Uncomputability Explain Intelligence? SuperARC: A Test for Artificial Super Intelligence Based on Recursive Compression
por: Hernández-Espinosa, Alberto, et al.
Publicado: (2025)

Forget BIT, It is All about TOKEN: Towards Semantic Information Theory for LLMs
por: Bai, Bo
Publicado: (2025)

Belief Information based Deep Channel Estimation for Massive MIMO Systems
por: Xu, Jialong, et al.
Publicado: (2024)

Compressing Chemistry Reveals Functional Groups
por: Sharma, Ruben, et al.
Publicado: (2025)

Distributed and Rate-Adaptive Feature Compression
por: Deshmukh, Aditya, et al.
Publicado: (2024)

Causality-Driven Reinforcement Learning for Joint Communication and Sensing
por: Roy, Anik, et al.
Publicado: (2024)

Multi-agent Reinforcement Learning for Energy Saving in Multi-Cell Massive MIMO Systems
por: Cai, Tianzhang, et al.
Publicado: (2024)

AlphaZip: Neural Network-Enhanced Lossless Text Compression
por: Narashiman, Swathi Shree, et al.
Publicado: (2024)

A Low-Overhead Incorporation-Extrapolation based Few-Shot CSI Feedback Framework for Massive MIMO Systems
por: Zhou, Binggui, et al.
Publicado: (2023)

Energy Saving for Cell-Free Massive MIMO Networks: A Multi-Agent Deep Reinforcement Learning Approach
por: Wang, Qichen, et al.
Publicado: (2026)

A General Error-Theoretical Analysis Framework for Constructing Compression Strategies
por: Zhang, Boyang, et al.
Publicado: (2025)

BERT4MIMO: A Foundation Model using BERT Architecture for Massive MIMO Channel State Information Prediction
por: Catak, Ferhat Ozgur, et al.
Publicado: (2025)

Test-Time Steering for Lossless Text Compression via Weighted Product of Experts
por: Zhang, Qihang, et al.
Publicado: (2025)

FibQuant: Universal Vector Quantization for Random-Access KV-Cache Compression
por: Lee, Namyoon, et al.
Publicado: (2026)

Flexible Variational Information Bottleneck: Achieving Diverse Compression with a Single Training
por: Kudo, Sota, et al.
Publicado: (2024)

Deep Learning-based Compressive Beam Alignment in mmWave Vehicular Systems
por: Wang, Yuyang, et al.
Publicado: (2021)

GeoIB: Geometry-Aware Information Bottleneck via Statistical-Manifold Compression
por: Wang, Weiqi, et al.
Publicado: (2026)

DiffPace: Diffusion-based Plug-and-play Augmented Channel Estimation in mmWave and Terahertz Ultra-Massive MIMO Systems
por: Hu, Zhengdong, et al.
Publicado: (2025)

Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws
por: Pan, Zhixuan, et al.
Publicado: (2025)

Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data
por: Heurtel-Depeiges, David, et al.
Publicado: (2024)

Pay Less But Get More: A Dual-Attention-based Channel Estimation Network for Massive MIMO Systems with Low-Density Pilots
por: Zhou, Binggui, et al.
Publicado: (2023)

Co-learning-aided Multi-modal-deep-learning Framework of Passive DOA Estimators for a Heterogeneous Hybrid Massive MIMO Receiver
por: Bai, Jiatong, et al.
Publicado: (2024)

Low-Overhead Channel Estimation via 3D Extrapolation for TDD mmWave Massive MIMO Systems Under High-Mobility Scenarios
por: Zhou, Binggui, et al.
Publicado: (2024)

Language Modeling Is Compression
por: Delétang, Grégoire, et al.
Publicado: (2023)

Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gain
por: Liu, Wei, et al.
Publicado: (2026)

Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning
por: Samuelson, Jeremy J
Publicado: (2026)