93 citations · 588 across the 20 of their papers we have counts for
21 papers
The Llama 4 Herd: Architecture, Training, Evaluation, and Deployment Notes
Redacted by arXiv
This document consolidates publicly reported technical details about Metas Llama 4 model family. It summarizes (i) released variants (Scout and Maverick) and the broader herd conte…
Efficient Speculative Decoding for Llama at Scale: Challenges and Solutions
Bangsheng Tang, Carl Chengyan Fu, Fei Kou +35
Speculative decoding is a standard method for accelerating the inference speed of large language models. However, scaling it for production environments poses several engineering c…
From KMMLU-Redux to KMMLU-Pro: A Professional Korean Benchmark Suite for LLM Evaluation
Seokhee Hong, Sunkyoung Kim, Guijin Son +3
The development of Large Language Models (LLMs) requires robust benchmarks that encompass not only academic domains but also industrial fields to effectively evaluate their applica…
Dialect Normalization using Large Language Models and Morphological Rules
Antonios Dimakis, John Pavlopoulos, Antonios Anastasopoulos
Natural language understanding systems struggle with low-resource languages, including many dialects of high-resource ones. Dialect-to-standard normalization attempts to tackle thi…
ZeroSumEval: An Extensible Framework For Scaling LLM Evaluation with Inter-Model Competition
Hisham A. Alyahya, Haidar Khan, Yazeed Alnumay +2
We introduce ZeroSumEval, a dynamic, competition-based, and evolving evaluation framework for Large Language Models (LLMs) that leverages competitive games. ZeroSumEval encompasses…
Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study
Menglong Cui, Pengzhi Gao, Wei Liu +2
Large language models (LLMs) have shown continuously improving multilingual capabilities, and even small-scale open-source models have demonstrated rapid performance enhancement. I…
When Every Token Counts: Optimal Segmentation for Low-Resource Language Models
Bharath Raj, Garvit Suri, Vikrant Dewangan +1
Traditional greedy tokenization methods have been a critical step in Natural Language Processing (NLP), influencing how text is converted into tokens and directly impacting model p…
LLäMmlein: Transparent, Compact and Competitive German-Only Language Models from Scratch
Jan Pfister, Julia Wunderle, Andreas Hotho
We create two German-only decoder models, LLäMmlein 120M and 1B, transparently from scratch and publish them, along with the training data, for the German NLP research community to…
Context Parallelism for Scalable Million-Token Inference
Amy Yang, Jingyi Yang, Aya Ibrahim +6
We present context parallelism for long-context large language model inference, which achieves near-linear scaling for long-context prefill latency with up to 128 H100 GPUs across…
The Llama 3 Herd of Models
Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri +556
Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models th…
BFKL Spectrum of N=4 SYM: non-Zero Conformal Spin
Mikhail Alfimov, Nikolay Gromov, Grigory Sizov
We developed a general non-perturbative framework for the BFKL spectrum of planar N=4 SYM, based on the Quantum Spectral Curve (QSC). It allows one to study the spectrum in the who…
Integrability of Conformal Fishnet Theory
Nikolay Gromov, Vladimir Kazakov, Gregory Korchemsky +2
We study integrability of fishnet-type Feynman graphs arising in planar four-dimensional bi-scalar chiral theory recently proposed in arXiv:1512.06704 as a special double scaling l…
New Construction of Eigenstates and Separation of Variables for SU(N) Quantum Spin Chains
Nikolay Gromov, Fedor Levkovich-Maslyuk, Grigory Sizov
We conjecture a new way to construct eigenstates of integrable XXX quantum spin chains with SU(N) symmetry. The states are built by repeatedly acting on the vacuum with a single op…
NNLO BFKL Pomeron eigenvalue in N=4 SYM
Nikolay Gromov, Fedor Levkovich-Maslyuk, Grigory Sizov
We obtain an analytical expression for the Next-to-Next-to-Leading order of the Balitsky-Fadin-Kuraev-Lipatov (BFKL) Pomeron eigenvalue in planar SYM N=4 using Quantum Spectral Cur…
Quantum Spectral Curve and the Numerical Solution of the Spectral Problem in AdS5/CFT4
Nikolay Gromov, Fedor Levkovich-Maslyuk, Grigory Sizov
We developed an efficient numerical algorithm for computing the spectrum of anomalous dimensions of the planar Super-Yang--Mills at finite coupling. The method is base…
Exact Slope and Interpolating Functions in ABJM Theory
Nikolay Gromov, Grigory Sizov
Using the Quantum Spectral Curve approach we compute exactly an observable (called slope function) in the planar ABJM theory in terms of an unknown interpolating function h(λ) whic…
Quantum Spectral Curve at Work: From Small Spin to Strong Coupling in N=4 SYM
Nikolay Gromov, Fedor Levkovich-Maslyuk, Grigory Sizov +1
We apply the recently proposed quantum spectral curve technique to the study of twist operators in planar N=4 SYM theory. We focus on the small spin expansion of anomalous dimensio…
Algebraic Curve for a Cusped Wilson Line
Grigory Sizov, Saulius Valatka
We consider the classical limit of the recently obtained exact result for the anomalous dimension of a cusped Wilson line with the insertion of an operator with L units of R-charge…
Analytic Solution of Bremsstrahlung TBA II: Turning on the Sphere Angle
Nikolay Gromov, Fedor Levkovich-Maslyuk, Grigory Sizov
We find an exact analytical solution of the Y-system describing a cusped Wilson line in the planar limit of N=4 SYM. Our explicit solution describes anomalous dimensions of this fa…
CSW-like Expansion for Einstein Gravity
Brenda Penante, Sayeh Rajabi, Grigory Sizov
Using the recent formula presented by He and Cachazo-Mason-Skinner for the link representation of tree-level N=8 supergravity amplitudes, we derived a CSW-like expansion for the Ne…
Parity Symmetry and Soft Limit for the Cachazo-Geyer Gravity Amplitude
Brenda Penante, Sayeh Rajabi, Grigory Sizov
In this note, we prove that the recent proposal for the tree-level n-particle N=8 supergravity amplitudes by Cachazo and Geyer satisfies parity symmetry and soft limit behavior exp…