Imagen de Portada

Extending Puzzle for Mixture-of-Experts Reasoning Models with Application to GPT-OSS Acceleration

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Bercovich, Akhiad, Ailon, Nir, Anisimov, Vladimir, Asida, Tomer, Assaf, Nave, Dabbah, Mohammad, Galil, Ido, Geifman, Amnon, Geifman, Yonatan, Golan, Izhak, Koren, Roi, Levy, Itay, Moshe, Zach, Molchanov, Pavlo, Nabwani, Najeeb, Patwary, Mostofa, Puny, Omri, Ronen, Tomer, Schen, Itamar, Segal, Elad, Shahaf, Ido, Tropp, Oren, Zilberstein, Ran, El-Yaniv, Ran
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

FFN Fusion: Rethinking Sequential Computation in Large Language Models
por: Bercovich, Akhiad, et al.
Publicado: (2025)

Puzzle: Distillation-Based NAS for Inference-Optimized LLMs
por: Bercovich, Akhiad, et al.
Publicado: (2024)

Changing Base Without Losing Pace: A GPU-Efficient Alternative to MatMul in DNNs
por: Ailon, Nir, et al.
Publicado: (2025)

Controlling the Inductive Bias of Wide Neural Networks by Modifying the Kernel's Spectrum
por: Geifman, Amnon, et al.
Publicado: (2023)

Hierarchical Selective Classification
por: Goren, Shani, et al.
Publicado: (2024)

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation
por: Goren, Shani, et al.
Publicado: (2026)

Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips
por: Galil, Ido, et al.
Publicado: (2025)

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

Efficient Video Sampling: Pruning Temporally Redundant Tokens for Faster VLM Inference
por: Bagrov, Natan, et al.
Publicado: (2025)

SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
por: Abramovich, Talor, et al.
Publicado: (2026)

Star Elastic: Many-in-One Reasoning LLMs with Efficient Budget Control
por: Taghibakhshi, Ali, et al.
Publicado: (2026)

LatentMoE: Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts
por: Elango, Venmugil, et al.
Publicado: (2026)

Maternal Anemia and Offspring Outcomes in India: A Scoping Review
por: Melissa T. Benavente, et al.
Publicado: (2025)

Implementation of a quantum linear solver for the Vlasov-Ampere equation
por: Goldfriend, Tomer, et al.
Publicado: (2025)

FormulaOne: Measuring the Depth of Algorithmic Reasoning Beyond Competitive Programming
por: Beniamini, Gal, et al.
Publicado: (2025)

Artificial Expert Intelligence through PAC-reasoning
por: Shalev-Shwartz, Shai, et al.
Publicado: (2024)

Multi-Review Fusion-in-Context
por: Slobodkin, Aviv, et al.
Publicado: (2024)

From Euler to AI: Unifying Formulas for Mathematical Constants
por: Raz, Tomer, et al.
Publicado: (2025)

The symbol length for elementary type pro-$p$ groups and Massey products
por: Efrat, Ido
Publicado: (2022)

Mild Pro-$p$ Groups and Ordered Monoids
por: Efrat, Ido
Publicado: (2026)

Cohomology and the Combinatorics of Words for Magnus Formations
por: Efrat, Ido
Publicado: (2022)

Failure of an higher analogue of Mho
por: Feldman, Ido
Publicado: (2024)

Measuring the Data
por: Cohen, Ido
Publicado: (2025)

Koopman Regularization
por: Cohen, Ido
Publicado: (2024)

The Elementary Type Conjecture for Maximal Pro-p Galois groups
por: Efrat, Ido
Publicado: (2025)

Linking Invariants for Valuations and Orderings on Fields
por: Efrat, Ido
Publicado: (2024)

Chapter B: Supporting Systems Architecture – An Integrative Concept for Implementing Neural Bypass in ALS
por: Tomer, Roi
Publicado: (2026)

Cape May Warbler in Oklahoma
por: Tomer, John S
Publicado: (1956)

On the Presence of Angular-Velocity Offsets in Disk Galaxies
por: Zimmerman, Tomer
Publicado: (2025)

Prophet Inequality from Samples: Is the More the Merrier?
por: Ezra, Tomer
Publicado: (2024)

A very short proof of the Figiel-Lindenstrauss-Milman theorem
por: Milo, Tomer
Publicado: (2025)

The Universe as a Learning System
por: Shushi, Tomer
Publicado: (2024)

Instance-optimal estimation of L2-norm
por: Adar, Tomer
Publicado: (2026)

On the Figiel-Lindenstrauss-Milman inequality
por: Milo, Tomer
Publicado: (2025)

Measuring the speed of quantum particles without a round-trip under non-synchronized quantum clocks
por: Shushi, Tomer
Publicado: (2024)

Wolf-Rayet stars
por: Shenar, Tomer
Publicado: (2024)

Observational constraints on massive binaries
por: Shenar, Tomer
Publicado: (2024)

Tight simulation of a distribution using conditional samples
por: Adar, Tomer
Publicado: (2025)

Asymptotics for face numbers of certain Hanner polytopes, with applications
por: Milo, Tomer
Publicado: (2026)

A general statistical approach to quantum algorithms in a circuit model based on the expectation and standard deviation of each gate separately
por: Shushi, Tomer
Publicado: (2024)