wovepaper — the arXiv observatory

The paper measures the production rates and momentum spectra of the doubly‑strange baryons Xi⁻/anti‑Xi⁺ in jets from Z → hadrons decays using DELPHI open data, and compares their y…

#z boson decays#jet fragmentation#baryon production#strange baryons

cs.CL2023

Massively Multilingual Shallow Fusion with Large Language Models

Ke Hu, Tara N. Sainath, Bo Li +7

cs.CL2022

Building Machine Translation Systems for the Next Thousand Languages

Ankur Bapna, Isaac Caswell, Julia Kreutzer +21

cs.LG2020

Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout

Zhao Chen, Jiquan Ngiam, Yanping Huang +4

cs.LG2025

Autellix: An Efficient Serving Engine for LLM Agents as General Programs

Michael Luo, Xiaoxiang Shi, Colin Cai +8

cs.AI2015

Learning Efficient Representations for Reinforcement Learning

Yanping Huang

Publications (44)

SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs

Partitioning Large Scale Deep Belief Networks Using Dropout

GSPMD: General and Scalable Parallelization for ML Computation Graphs

Direct Meissner Effect Observation of Superconductivity in Compressed H2S

Controlled Decoding from Language Models

Discovery of a Glueball-like particle X(2370) at BESIII

Stylus: Automatic Adapter Selection for Diffusion Models

Do CNNs Encode Data Augmentations?

Gemini: A Family of Highly Capable Multimodal Models

GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Measurements of decay branching fractions of the Higgs boson to hadronic final states at the CEPC

New Physics Search at the CEPC: a General Perspective

AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving

Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning

Regularized Evolution for Image Classifier Architecture Search

Expected H→I^¼+I^¼− measurement precision with e+e−→Z(qqˉ​)H production at the CEPC

ChirpCast: Data Transmission via Audio

Determination of Strong Coupling Constant from Inclusive Semileptonic Decays of Charmed Mesons

Research on PM emission and energy consumption of mixed traffic flow based on cellular automata FI model

Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling

Flavor Physics at the CEPC: a General Perspective

PaLM 2 Technical Report

Double Dome and Reemergence of Superconductivity in Pristine 6R-TaS2 under Pressure

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Mixture-of-Experts with Expert Choice Routing

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding

Lifelong Language Pretraining with Distribution-Specialized Experts

BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition

GLaM: Efficient Scaling of Language Models with Mixture-of-Experts

Brainformers: Trading Simplicity for Efficiency

ST-MoE: Designing Stable and Transferable Sparse Expert Models

LaMDA: Language Models for Dialog Applications

Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference

Scaling Instruction-Finetuned Language Models

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

DeepSeek-V3 Technical Report

Measurement of I^−/I^ˉ+ production in jets from Z boson decays with the DELPHI open data

Massively Multilingual Shallow Fusion with Large Language Models

Building Machine Translation Systems for the Next Thousand Languages

Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout

Autellix: An Efficient Serving Engine for LLM Agents as General Programs

Learning Efficient Representations for Reinforcement Learning

Expected $H \to I^¼^{+} I^¼^{-}$ measurement precision with $e^{+} e^{-} \to Z (q q ˉ) H$ production at the CEPC

Measurement of $I^^{-} / I^ˉ ^{+}$ production in jets from $Z$ boson decays with the DELPHI open data