Find the people behind AI papers and projects.
/
Search public work, explore its connections, and check the sources. How coverage works
4,006 saved profiles
Matching saved profiles. Coverage and source-listed affiliations may be incomplete or historical.
Search results
1–80 of 549
- Adolfo VictoriaAffiliation: Not recordedWork: Efficient Speculative Decoding for Llama at Scale: Challenges and Solutions
- Andrew MayneAffiliation: InterdimensionalWork: Advanced Prompt Design for GPT-3: How to make a prompt 20x more efficient
- Andy DauAffiliation: Not recordedWork: Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
- Atri RudraAffiliation: University at Buffalo, The State University of New YorkWork: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
- Branislav StojkovicAffiliation: MetaWork: Applied Federated Learning: Architectural Design for Robust and Efficient Learning in Privacy Aware Settings
- Changkyu KimAffiliation: Meta Platforms, Inc. (Meta)Work: Efficient Speculative Decoding for Llama at Scale: Challenges and Solutions
- Ching-Hsiang ChuAffiliation: NVIDIAWork: Scaling Llama 3 Training with Efficient Parallelism Strategies
- Evgenii ZheltonozhskiiAffiliation: Technion – Israel Institute of TechnologyWork: StarCoder: may the source be with you!
- Guna LakshminarayananAffiliation: Not recordedWork: Disaggregated Multi-Tower: Topology-aware Modeling Technique for Efficient Large-Scale Recommendation
- Hunter GoldmanAffiliation: Not recordedWork: Scaling Llama 3 Training with Efficient Parallelism Strategies
- Jason ParkAffiliation: MetaWork: Efficient Speculative Decoding for Llama at Scale: Challenges and Solutions
- Jiawen LiuAffiliation: MetaWork: Efficient Speculative Decoding for Llama at Scale: Challenges and Solutions
- Jongsoo ParkAffiliation: MetaWork: Scaling Llama 3 Training with Efficient Parallelism Strategies
- Krzysztof MaziarzAffiliation: Microsoft ResearchWork: Chemist-aligned retrosynthesis by ensembling diverse inductive bias models
- Lailin ChenAffiliation: Not recordedWork: RangeAugment: Efficient Online Augmentation with Range Learning
- Liang LuoAffiliation: MetaWork: Disaggregated Multi-Tower: Topology-aware Modeling Technique for Efficient Large-Scale Recommendation
- Logan HowardAffiliation: Not recordedWork: Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
- Manohar PaluriAffiliation: MetaWork: Detect-and-Track: Efficient Pose Estimation in Videos
- Narjes TorabiAffiliation: Not recordedWork: Bean Machine: A Declarative Probabilistic Programming Language For Efficient Programmable Inference
- Rachad AlaoAffiliation: CohereWork: Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations
- Raj AgarwalAffiliation: Not recordedWork: Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
- Ravi RamamoorthiAffiliation: University of California, San DiegoWork: An Efficient Representation for Irradiance Environment Maps
- Samyam RajbhandariAffiliation: SnowflakeWork: Arctic Inference with Shift Parallelism: Fast and Efficient Open Source Inference System for Enterprise AI
- Tianhe LiAffiliation: Not recordedWork: The Llama 3 Herd of Models
- Tri DaoAffiliation: Princeton UniversityWork: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
- Wenchen WangAffiliation: MetaWork: Sparse Forcing: Native Trainable Sparse Attention for Real-time Autoregressive Diffusion Video Generation
- Xilun WuAffiliation: Not recordedWork: Backpropagation with Continuation Callbacks: Foundations for Efficient and Expressive Differentiable Programming
- Xinfeng XieAffiliation: Not recordedWork: CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization
- Yaelle GoldschlagAffiliation: MetaWork: OpenZL: Using Graphs to Compress Smaller and Faster
- Yanli ZhaoAffiliation: MetaWork: Disaggregated Multi-Tower: Topology-aware Modeling Technique for Efficient Large-Scale Recommendation
- Yuchen HaoAffiliation: MetaWork: Scaling Llama 3 Training with Efficient Parallelism Strategies
- Yunlu LiAffiliation: Not recordedWork: Efficient Speculative Decoding for Llama at Scale: Challenges and Solutions
- Zach RaitAffiliation: Not recordedWork: Leveraging AI for efficient incident response
- Zhiwei ZhaoAffiliation: Not recordedWork: Efficient Speculative Decoding for Llama at Scale: Challenges and Solutions
- Hao WuAffiliation: Not recordedWork: MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks
- Du LiAffiliation: Not recordedWork: DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale
- Nan DuAffiliation: Not recordedWork: GLaM: Efficient Scaling of Language Models with Mixture-of-Experts
- Tian LinAffiliation: Not recordedWork: Doubly Sparse: Sparse Mixture of Sparse Experts for Efficient Softmax Inference
- Xiao BiAffiliation: Not recordedWork: DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
- Yawen WeiAffiliation: Not recordedWork: An Efficient Scheme for Securing XOR Network Coding against Pollution Attacks
- Jie WangAffiliation: Not recordedWork: Scaling Llama 3 Training with Efficient Parallelism Strategies
- Tianrun LiAffiliation: Not recordedWork: ADvaNCE - Efficient and Scalable Approximate Density-Based Clustering Based on Hashing
- Dennis DuanAffiliation: Not recordedWork: Gemini: A Family of Highly Capable Multimodal Models
- Keqin BaoAffiliation: Not recordedWork: TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation
- Kun ZhangAffiliation: Not recordedWork: GLaM: Efficient Scaling of Language Models with Mixture-of-Experts
- Linda FrisoAffiliation: Not recordedWork: STLight: A Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal Joint Processing
- Andy DavisAffiliation: GoogleWork: EQuARX: Efficient Quantized AllReduce in XLA for Distributed Machine Learning Acceleration
- Denis VnukovAffiliation: Not recordedWork: EQuARX: Efficient Quantized AllReduce in XLA for Distributed Machine Learning Acceleration
- Heewoo JunAffiliation: Not recordedWork: Efficient Training of Language Models to Fill in the Middle
- Martin BölleAffiliation: Not recordedWork: Efficient training techniques for generative model based response systems
- Matan EyalAffiliation: Not recordedWork: ECLeKTic: a Novel Challenge Set for Evaluation of Cross-Lingual Knowledge Transfer
- Aliya AhmadAffiliation: Not recordedWork: AISI Frontier AI Trends Report (2025)
- Cody Hao YuAffiliation: Not recordedWork: Efficient Memory Management for Large Language Model Serving with PagedAttention
- Graeme NailAffiliation: Not recordedWork: Efficient Machine Translation with Model Pruning and Quantization
- Isha ArkatkarAffiliation: Not recordedWork: Gemini: A Family of Highly Capable Multimodal Models
- Sherjil OzairAffiliation: Not recordedWork: Generative Adversarial Networks
- Chris X. CaiAffiliation: Not recordedWork: Scaling Llama 3 Training with Efficient Parallelism Strategies
- Maxim KrikunAffiliation: Not recordedWork: GLaM: Efficient Scaling of Language Models with Mixture-of-Experts
- Rui HouAffiliation: MetaWork: Llama 2: Open Foundation and Fine-Tuned Chat Models
- Sam ShleiferAffiliation: Not recordedWork: HuggingFace's Transformers: State-of-the-art Natural Language Processing
- Evan SmothersAffiliation: Not recordedWork: The Llama 3 Herd of Models
- Ionuț GeorgescuAffiliation: Not recordedWork: Self-consistent phonons revisited. II. A general and efficient method for computing free energies and vibrational spectra of molecules and clusters
- Lakshman YagatiAffiliation: Not recordedWork: Gemini: A Family of Highly Capable Multimodal Models
- Lev KurilenkoAffiliation: Not recordedWork: Universal Checkpointing: A Flexible and Efficient Distributed Checkpointing System for Large-Scale DNN Training with Reconfigurable Parallelism
- Lianmin ZhengAffiliation: Not recordedWork: SGLang: Efficient Execution of Structured Language Model Programs
- Marcin KardasAffiliation: Not recordedWork: MultiFiT: Efficient Multi-lingual Language Model Fine-tuning
- Nithya AttaluriAffiliation: Not recordedWork: Efficient and Accurate Abnormality Mining from Radiology Reports with Customized False Positive Reduction
- Noa NabeshimaAffiliation: Not recordedWork: The Pile: An 800GB Dataset of Diverse Text for Language Modeling
- Richard TanburnAffiliation: Not recordedWork: Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
- Sarthak JauhariAffiliation: Not recordedWork: Compute-Efficient Churn Reduction for Conversational Agents
- Xuancheng RenAffiliation: Not recordedWork: Qwen Technical Report
- Yanping HuangAffiliation: Not recordedWork: Agentix: An Efficient Serving Engine for LLM Agents as General Programs
- Feng TianAffiliation: MetaWork: Scaling Llama 3 Training with Efficient Parallelism Strategies
- Mrinank SharmaAffiliation: Not recordedWork: Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
- Praveen KrishnanAffiliation: Not recordedWork: HWNet v2: An Efficient Word Image Representation for Handwritten Documents
- Samuel AndermattAffiliation: Not recordedWork: CP2K: An Electronic Structure and Molecular Dynamics Software Package — Quickstep: Efficient and Accurate Electronic Structure Calculations
- Thibaut LavrilAffiliation: Not recordedWork: LLaMA: Open and Efficient Foundation Language Models
- Dhruv ChoudharyAffiliation: Not recordedWork: The Llama 3 Herd of Models
- Mahesh PasupuletiAffiliation: Not recordedWork: Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations
- Ammar Ahmad AwanAffiliation: Not recordedWork: DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale