Imagen de Portada

CafeQ: Calibration-free Quantization via Learned Transformations and Adaptive Rounding

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sun, Ziteng, Benton, Adrian, Kushnir, Samuel, Trockman, Asher, Singh, Vikas, Diggavi, Suhas, Suresh, Ananda Theertha
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Multi-Mixer Models: Flexible Sequence Modeling with Shared Representations
por: Li, Kevin Y., et al.
Publicado: (2026)

The importance of feature preprocessing for differentially private linear optimization
por: Sun, Ziteng, et al.
Publicado: (2023)

Subset-Based Instance Optimality in Private Estimation
por: Dick, Travis, et al.
Publicado: (2023)

Private federated discovery of out-of-vocabulary words for Gboard
por: Sun, Ziteng, et al.
Publicado: (2024)

Exploring and Improving Drafts in Blockwise Parallel Decoding
por: Kim, Taehyeon, et al.
Publicado: (2024)

Asymptotics of Language Model Alignment
por: Yang, Joy Qiping, et al.
Publicado: (2024)

CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization
por: Kwon, Soo Min, et al.
Publicado: (2026)

SpecTr: Fast Speculative Decoding via Optimal Transport
por: Sun, Ziteng, et al.
Publicado: (2023)

In-Context Credit Assignment via the Core
por: Harris, Keegan, et al.
Publicado: (2026)

Coupling without Communication and Drafter-Invariant Speculative Decoding
por: Daliri, Majid, et al.
Publicado: (2024)

On Robust Hypothesis Testing with respect to the Hellinger Distance
por: Modak, Eeshan, et al.
Publicado: (2025)

Mean estimation in the add-remove model of differential privacy
por: Kulesza, Alex, et al.
Publicado: (2023)

Mimetic Initialization of MLPs
por: Trockman, Asher, et al.
Publicado: (2026)

ICQuant: Index Coding enables Low-bit LLM Quantization
por: Li, Xinlin, et al.
Publicado: (2025)

An Information-Theoretic Approach to Understanding Transformers' In-Context Learning of Variable-Order Markov Chains
por: Zhou, Ruida, et al.
Publicado: (2024)

Block Verification Accelerates Speculative Decoding
por: Sun, Ziteng, et al.
Publicado: (2024)

Rate of Model Collapse in Recursive Training
por: Suresh, Ananda Theertha, et al.
Publicado: (2024)

SPIRE: Conditional Personalization for Federated Diffusion Generative Models
por: Ozkara, Kaan, et al.
Publicado: (2025)

Multi-Group Fairness Evaluation via Conditional Value-at-Risk Testing
por: Paes, Lucas Monteiro, et al.
Publicado: (2023)

Reframing Data Value for Large Language Models Through the Lens of Plausibility
por: Rammal, Mohamad Rida, et al.
Publicado: (2024)

Efficient Language Model Architectures for Differentially Private Federated Learning
por: Ro, Jae Hun, et al.
Publicado: (2024)

Robust Federated Personalised Mean Estimation for the Gaussian Mixture Model
por: Managoli, Malhar A., et al.
Publicado: (2025)

Common Information Dimension
por: Hanna, Osama, et al.
Publicado: (2023)

ADEPT: Hierarchical Bayes Approach to Personalized Federated Unsupervised Learning
por: Ozkara, Kaan, et al.
Publicado: (2024)

Effect of Pre‐ and Post‐Milling Processing Techniques on the Physico‐Chemical, Functional, and Pasting Properties of Sorghum
por: Theertha DP, et al.
Publicado: (2025)

InfAlign: Inference-aware language model alignment
por: Balashankar, Ananth, et al.
Publicado: (2024)

Normalized Narrow Jump To Conclusions: Normalized Narrow Shortcuts for Parameter Efficient Early Exit Transformer Prediction
por: Seshadri, Amrit Diggavi
Publicado: (2024)

Hierarchical Retrieval: The Geometry and a Pretrain-Finetune Recipe
por: You, Chong, et al.
Publicado: (2025)

One Jump Is All You Need: Short-Cutting Transformers for Early Exit Prediction with One Jump to Fit All Exit Levels
por: Seshadri, Amrit Diggavi
Publicado: (2025)

Revisiting Adaptive Rounding with Vectorized Reparameterization for LLM Quantization
por: Zhou, Yuli, et al.
Publicado: (2026)

On the optimal regret of collaborative personalized linear bandits
por: Huang, Bruce, et al.
Publicado: (2025)

Mimetic Initialization Helps State Space Models Learn to Recall
por: Trockman, Asher, et al.
Publicado: (2024)

FrameQuant: Flexible Low-Bit Quantization for Transformers
por: Adepu, Harshavardhan, et al.
Publicado: (2024)

Efficient and Asymptotically Unbiased Constrained Decoding for Large Language Models
por: Ye, Haotian, et al.
Publicado: (2025)

CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization
por: Cha, Seohyeon, et al.
Publicado: (2026)

Theoretical guarantees on the best-of-n alignment policy
por: Beirami, Ahmad, et al.
Publicado: (2024)

Failure of the local-global principle for isotropy of quadratic forms over function fields
por: Auel, Asher, et al.
Publicado: (2017)

AT-2FF: Adaptive Type-2 Fuzzy Filter for De-noising Images Corrupted with Salt-and-Pepper
por: Singh, Vikas
Publicado: (2023)

AdpQ: A Zero-shot Calibration Free Adaptive Post Training Quantization Method for LLMs
por: Ghaffari, Alireza, et al.
Publicado: (2024)

LoopQ: Quantization for Recursive Transformers
por: Fang, Rui, et al.
Publicado: (2026)