Copertina

Spectra 1.1: Scaling Laws and Efficient Inference for Ternary Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Vaidhya, Tejas, Kaushal, Ayush, Jain, Vineet, Harpin, Francis Couture, Shishodia, Prashant, Behbahani, Majid, Nevmyvaka, Yuriy, Rish, Irina
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale
di: Kaushal, Ayush, et al.
Pubblicazione: (2024)

Graph Partitioning With Limited Moves
di: Behbahani, Majid, et al.
Pubblicazione: (2024)

Small Vocabularies, Big Gains: Pretraining and Tokenization in Time Series Models
di: Roger, Alexis, et al.
Pubblicazione: (2025)

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting
di: Riachi, Roland, et al.
Pubblicazione: (2025)

Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference
di: Riemer, Matthew, et al.
Pubblicazione: (2024)

Deep Generative Sampling in the Dual Divergence Space: A Data-efficient & Interpretative Approach for Generative AI
di: Garg, Sahil, et al.
Pubblicazione: (2024)

Hiding in Plain Text: Detecting Concealed Jailbreaks via Activation Disentanglement
di: Farzam, Amirhossein, et al.
Pubblicazione: (2026)

Speculative Sampling for Parametric Temporal Point Processes
di: Biloš, Marin, et al.
Pubblicazione: (2025)

A Mechanistic Study of Tabular Foundation Models
di: Biloš, Marin, et al.
Pubblicazione: (2026)

Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning
di: Mircea, Andrei, et al.
Pubblicazione: (2025)

Breaking the $n^{1.5}$ Additive Error Barrier for Private and Efficient Graph Sparsification via Private Expander Decomposition
di: Aamand, Anders, et al.
Pubblicazione: (2025)

Carotenoid‐Fortified Lard Mimics Cow Ghee in Raman Spectra
di: Vineet Sharma, et al.
Pubblicazione: (2026)

Scaling Laws for Emulation of Stellar Spectra
di: Różański, Tomasz, et al.
Pubblicazione: (2025)

Warming Up for Zeroth-Order Federated Pre-Training with Low Resource Clients
di: Legate, Gwen, et al.
Pubblicazione: (2025)

Towards ethical multimodal systems
di: Roger, Alexis, et al.
Pubblicazione: (2023)

Quantifying the Jet Energy Loss in Pb+Pb collisions at LHC
di: Kumar, Vineet, et al.
Pubblicazione: (2024)

Chart-RVR: Reinforcement Learning with Verifiable Rewards for Explainable Chart Reasoning
di: Sinha, Sanchit, et al.
Pubblicazione: (2025)

Variational Schrödinger Momentum Diffusion
di: Rojas, Kevin, et al.
Pubblicazione: (2025)

Technical Report: Full-Stack Fine-Tuning for the Q Programming Language
di: Hogan, Brendan R., et al.
Pubblicazione: (2025)

Non-Linear Analysis of RC Building Considering Soil Structure Interaction
di: Prashant Amaragol, et al.
Pubblicazione: (2020)

Detecting Causality with Symplectic Quandles
di: Jain, Ayush
Pubblicazione: (2023)

(Table 1) Description of sediments from DSDP Site 20-196
di: Couture, Rex A
Pubblicazione: (1977)

(Table 1) Description of sediments from DSDP Site 17-164
di: Couture, Rex A
Pubblicazione: (1977)

Scaling laws for learning with real and surrogate data
di: Jain, Ayush, et al.
Pubblicazione: (2024)

Weighted Bergman Kernels on Planar Domains
di: Jain, Aakanksha, et al.
Pubblicazione: (2022)

Weighted Kernel Functions on Planar Domains
di: Jain, Aakanksha, et al.
Pubblicazione: (2025)

Weighted Szegő Kernels on Planar Domains
di: Jain, Aakanksha, et al.
Pubblicazione: (2023)

Data Supplementing the Article 'Relaxation Dynamics of Entangled Linear Polymer Melts via Molecular Dynamics Simulations', Macromolecules 2025, 58, 1, 767–786
di: Foroozani Behbahani, Alireza, et al.
Pubblicazione: (2026)

Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching
di: Jain, Arnav Kumar, et al.
Pubblicazione: (2024)

Stress Relaxation in Monodisperse Entangled Polymer Melts: Correlation Between Viscoelastic Response and Single-Chain Relaxation via Molecular Dynamics Simulations
di: Behbahani, Alireza F.
Pubblicazione: (2026)

Bitnet.cpp: Efficient Edge Inference for Ternary LLMs
di: Wang, Jinheng, et al.
Pubblicazione: (2025)

Towards Interpretable and Trustworthy Time Series Reasoning: A BlueSky Vision
di: Ning, Kanghui, et al.
Pubblicazione: (2025)

Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting
di: Schuchardt, Jan, et al.
Pubblicazione: (2025)

$\textbf{S}^2$IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting
di: Pan, Zijie, et al.
Pubblicazione: (2024)

Bedgraphs from TGIRT-Seq datasets in different species (1/3) and total jobs submitted throughout snoBIRD's development
di: Fafard-Couture, Étienne
Pubblicazione: (2025)

Knowledge Distillation for Federated Learning: a Practical Guide
di: Mora, Alessio, et al.
Pubblicazione: (2022)

Image Tiling for High-Resolution Reasoning: Balancing Local Detail with Global Context
di: de Margerie, Anatole Jacquin, et al.
Pubblicazione: (2025)

On the Adversarial Robustness of Discrete Image Tokenizers
di: Bhagwatkar, Rishika, et al.
Pubblicazione: (2026)

Neural Neural Scaling Laws
di: Hu, Michael Y., et al.
Pubblicazione: (2026)

Influence Functions for Efficient Data Selection in Reasoning
di: Humane, Prateek, et al.
Pubblicazione: (2025)