Image de couverture de livre

Tiled Bit Networks: Sub-Bit Neural Network Compression Through Reuse of Learnable Binary Vectors

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gorbett, Matt, Shirazi, Hossein, Ray, Indrakshi
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Label-Free Reinforcement Learning via Cross-Model Entropy
par: Gorbett, Matt, et autres
Publié: (2026)

Cross-Silo Federated Learning Across Divergent Domains with Iterative Parameter Alignment
par: Gorbett, Matt, et autres
Publié: (2023)

BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook
par: Gu, Hao, et autres
Publié: (2025)

A&B BNN: Add&Bit-Operation-Only Hardware-Friendly Binary Neural Network
par: Ma, Ruichen, et autres
Publié: (2024)

Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression
par: Zhang, Xi, et autres
Publié: (2025)

SplitQuant: Layer Splitting for Low-Bit Neural Network Quantization
par: Song, Jaewoo, et autres
Publié: (2025)

Diagonal-Tiled Mixed-Precision Attention for Efficient Low-Bit MXFP Inference
par: Ding, Yifu, et autres
Publié: (2026)

Verification of Bit-Flip Attacks against Quantized Neural Networks
par: Zhang, Yedi, et autres
Publié: (2025)

LittleBit-2: Maximizing the Spectral Energy Gain in Sub-1-Bit LLMs via Latent Geometry Alignment
par: Lee, Banseok, et autres
Publié: (2026)

FP=xINT:Representing Neural Networks via Low-Bit Series Basis Functions
par: Zhang, Boyang, et autres
Publié: (2024)

Unlocking the Theory Behind Scaling 1-Bit Neural Networks
par: Daliri, Majid, et autres
Publié: (2024)

From Arithmetic to Logic: The Resilience of Logic and Lookup-Based Neural Networks Under Parameter Bit-Flips
par: Bacellar, Alan T. L., et autres
Publié: (2026)

Point Cloud Compression with Bits-back Coding
par: Hieu, Nguyen Quang, et autres
Publié: (2024)

Q-Palette: Fractional-Bit Quantizers Toward Optimal Bit Allocation for Efficient LLM Deployment
par: Lee, Deokjae, et autres
Publié: (2025)

UltraSketchLLM: Saliency-Driven Sketching for Ultra-Low Bit LLM Compression
par: Zou, Sunan, et autres
Publié: (2025)

BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization
par: Zhao, Jiayu, et autres
Publié: (2026)

LittleBit: Ultra Low-Bit Quantization via Latent Factorization
par: Lee, Banseok, et autres
Publié: (2025)

Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators
par: Blumenfeld, Yaniv, et autres
Publié: (2024)

Normalized Architectures are Natively 4-Bit
par: Fishman, Maxim, et autres
Publié: (2026)

Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Lehman Go Indifferent
par: Kummer, Lorenz, et autres
Publié: (2023)

Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression
par: Sakai, Akira, et autres
Publié: (2026)

On the Probabilistic Learnability of Compact Neural Network Preimage Bounds
par: Marzari, Luca, et autres
Publié: (2025)

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache
par: Son, Donghyun, et autres
Publié: (2025)

More Than Bits: Multi-Envelope Double Binary Factorization for Extreme Quantization
par: Ichikawa, Yuma, et autres
Publié: (2025)

PATCH: Learnable Tile-level Hybrid Sparsity for LLMs
par: Hourri, Younes, et autres
Publié: (2025)

Human-aligned Chess with a Bit of Search
par: Zhang, Yiming, et autres
Publié: (2024)

Boosting Graph Neural Network Expressivity with Learnable Lanczos Constraints
par: Azizi, Niloofar, et autres
Publié: (2024)

Towards Efficient and Accurate Spiking Neural Networks via Adaptive Bit Allocation
par: Yao, Xingting, et autres
Publié: (2025)

Müntz-Szász Networks: Neural Architectures with Learnable Power-Law Bases
par: N'guessan, Gnankan Landry Regis
Publié: (2025)

Physics-Informed Neural Networks with Learnable Loss Balancing and Transfer Learning
par: Pirayeshshirazinezhad, Reza
Publié: (2026)

Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips
par: Galil, Ido, et autres
Publié: (2025)

Self-Compressing Neural Networks
par: Cséfalvay, Szabolcs, et autres
Publié: (2023)

To be Continuous, or to be Discrete, Those are Bits of Questions
par: Wang, Yiran, et autres
Publié: (2024)

Skill Reuse as Compression in Agentic RL
par: Xu, Zhikun, et autres
Publié: (2026)

Depth-Adaptive Graph Neural Networks via Learnable Bakry-'Emery Curvature
par: Hevapathige, Asela, et autres
Publié: (2025)

AdaQAT: Adaptive Bit-Width Quantization-Aware Training
par: Gernigon, Cédric, et autres
Publié: (2024)

On Exact Bit-level Reversible Transformers Without Changing Architectures
par: Zhang, Guoqiang, et autres
Publié: (2024)

Safe Transformer: An Explicit Safety Bit For Interpretable And Controllable Alignment
par: Feng, Jingyuan, et autres
Publié: (2026)

Attn-QAT: 4-Bit Attention With Quantization-Aware Training
par: Zhang, Peiyuan, et autres
Publié: (2026)

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference
par: Zhao, Yushu, et autres
Publié: (2025)