Base44
Mini toolsPapers
-
Mixtral of Experts
-
Autonomous Procedural Operations (ProcOps
-
Speech Translation with Large Language Models: An Industrial Practice
-
VideoPoet: A Large Language Model for Zero-Shot Video Generation
-
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
-
Knowledge Diffusion for Distillation
-
Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision
-
Diffusion Models Without Attention
-
Towards Making the Most of ChatGPT for Machine Translation
-
VOYAGER: An Open-Ended Embodied Agent with Large Language Models
-
Eureka: Human-Level Reward Design via Coding Large Language Models
-
BitNet: Scaling 1-bit Transformers for Large Language Models
-
SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds
-
CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules
-
Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
-
Solving Olympiad Geometry without Human Demonstrations (AlphaGeometry)
-
Deep Industrial Image Anomaly Detection: A Survey
-
Mistral 7B
-
mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration
-
SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF
-
LRM: Large Reconstruction Model for Single Image to 3D
-
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
-
Qwen Technical Report
-
Qwen Technical Report
-
Connecting Speech Encoder and Large Language Model for ASR
-
SWE-Agent: Agent-Computer Interfaces Enable Automated Software EngineeringPrinceton University
-
PaLM 2 Technical Report
-
Phi-2: A Small Language Model with Reasoning Capability
-
Efficient Memory Management for Large Language Model Serving with PagedAttentionStanford University, University of California, Berkeley
-
Textbooks Are All You Need
-
Graph of Thoughts: Solving Elaborate Problems with Large Language ModelsEidgenössische Technische Hochschule Zürich
-
3D Gaussian Splatting for Real-Time Radiance Field RenderingINRIA, Université Côte d’Azur
-
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
-
RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
-
Differentially Private Heavy Hitter Detection using Federated Analytics
-
Llama 2: Open Foundation and Fine-Tuned Chat Models
-
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
-
Neuralangelo: High-Fidelity Neural Surface Reconstruction
-
Orca: Progressive Learning from Complex Explanation Traces of GPT-4
-
AWQ: Activation-aware Weight Quantization for LLM Compression and AccelerationMassachusetts Institute of Technology
-
TransAct: Transformer-based Realtime User Action Model for Recommendation at Pinterest
-
IMAGEBIND: One Embedding Space To Bind Them Al
-
ReWOO: Decoupling Reasoning from Observation for Efficient LLM Reasoning
-
Voyager: An Open-Ended Embodied Agent with Large Language Models
-
QLoRA: Efficient Finetuning of Quantized LLMsUniversity of Washington
-
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
-
Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
-
Segment Anything
-
Sequential Attention: Making AI Models Leaner and Faster Without Sacrificing Accuracy
-
DAMO-YOLO : A Report on Real-Time Object Detection Design
