Skip to content

PaperCodex

Subscribe
WebLLM: Run Large Language Models Entirely in the Browser—No Server, No Cloud, Full Privacy

WebLLM: Run Large Language Models Entirely in the Browser—No Server, No Cloud, Full Privacy 16945

Imagine running powerful large language models (LLMs)—like Llama 3, Mistral, or Phi 3—directly inside a user’s web browser, with no…

12/12/202512/13/2025Client-side LLM, In-browser Inference, Privacy-preserving AI
TradingAgents: A Multi-Agent LLM Framework That Mirrors Real Trading Desks for Smarter Financial Decisions

TradingAgents: A Multi-Agent LLM Framework That Mirrors Real Trading Desks for Smarter Financial Decisions 26486

Automated financial trading has long relied on rule-based systems or single-agent machine learning models that struggle to capture the nuanced,…

12/12/2025Financial Trading, LLM-based Decision-making, Multi-agent Systems
Verl: A Flexible, High-Performance RLHF Framework for Aligning Large Language Models at Scale

Verl: A Flexible, High-Performance RLHF Framework for Aligning Large Language Models at Scale 17406

Verl (short for Volcano Engine Reinforcement Learning) is an open-source, production-ready framework designed specifically for Reinforcement Learning from Human Feedback…

12/12/2025Large Language Model Alignment, Multi-modal Reinforcement Learning, Reinforcement Learning From Human Feedback (RLHF)
Open-Sora: Build Commercial-Quality AI Videos for $200K — Fully Open-Source and Production-Ready

Open-Sora: Build Commercial-Quality AI Videos for $200K — Fully Open-Source and Production-Ready 28098

Open-Sora is a groundbreaking open-source initiative that makes high-quality AI video generation accessible, efficient, and affordable. With the release of…

12/12/2025Image-to-Video Animation, Text-to-Video Generation, Video-to-Video Editing
Paper2Code: Automatically Turn Machine Learning Research Papers into Ready-to-Run Code Repositories

Paper2Code: Automatically Turn Machine Learning Research Papers into Ready-to-Run Code Repositories 3875

Reproducing results from machine learning (ML) research papers is often a frustrating experience. Despite the surge in published work, a…

12/11/2025Automated Implementation, Code Generation, Research Reproducibility
R&D-Agent: Automate End-to-End AI Development with a Dual-Agent Framework That Tops MLE-Bench

R&D-Agent: Automate End-to-End AI Development with a Dual-Agent Framework That Tops MLE-Bench 9745

Building high-performing, data-driven AI solutions remains a labor-intensive, iterative process—even for seasoned machine learning engineers. From brainstorming novel modeling ideas…

12/11/202512/11/2025AI Agent for Data Science, Automated Machine Learning, End-to-end Model Development
MobileAgent: Cross-Platform GUI Automation That Understands and Acts Like a Human

MobileAgent: Cross-Platform GUI Automation That Understands and Acts Like a Human 6632

Imagine giving a natural language instruction like “Book a round-trip flight from Beijing to Paris on Skyscanner for September 18–21”…

12/11/2025Cross-platform Agent, GUI Automation, Multimodal Reasoning
Moshi: A Real-Time, Full-Duplex Speech-to-Speech Foundation Model for Natural Human-Like Dialogue

Moshi: A Real-Time, Full-Duplex Speech-to-Speech Foundation Model for Natural Human-Like Dialogue 9165

Traditional spoken dialogue systems—like those used in virtual assistants or customer service bots—rely on a cascade of disconnected components: voice…

12/11/2025Full-duplex Dialogue, Speech-to-speech Generation, Spoken Language Modeling
Spark-TTS: Zero-Shot, Controllable Text-to-Speech with a Single LLM—No Vocoder, No Flow Matching

Spark-TTS: Zero-Shot, Controllable Text-to-Speech with a Single LLM—No Vocoder, No Flow Matching 10840

Overview In the rapidly evolving landscape of AI-powered speech synthesis, complexity has long been the price of quality. Traditional text-to-speech…

12/11/2025Controllable Speech Generation, Text-to-Speech Synthesis, Zero-Shot Voice Cloning
Trae Agent: Resolve Real-World Software Issues with LLM-Powered, Repository-Aware AI Automation

Trae Agent: Resolve Real-World Software Issues with LLM-Powered, Repository-Aware AI Automation 10232

Overview Software engineering is increasingly becoming a collaboration between humans and intelligent tools. Yet, many developers still face persistent challenges:…

12/11/2025LLM-based Agent Reasoning, Repository-level Code Understanding, Software Issue Resolution

Posts pagination

Previous 1 … 40 41 42 43 Next
Copyright © 2026 PaperCodex.
  • Facebook
  • YouTube
  • Twitter

PaperCodex