PaperCodex

DeepResearcher: Train AI Research Agents That Think, Verify, and Adapt in the Real Web Environment 621

In today’s AI landscape, many organizations rely on large language models (LLMs) to automate complex research tasks—such as competitive analysis,…

01/05/2026Autonomous Research Agents, Reinforcement Learning For Information Retrieval, Web-grounded Reasoning

LLM×MapReduce: Generate Coherent Long-Form Articles from Extremely Long Inputs Using LLMs Efficiently 814

If you’ve ever tried using a large language model (LLM) to synthesize a detailed technical report from hundreds of research…

01/05/2026Document Synthesis, Long-context Reasoning, Long-form Generation

Waver: Generate Lifelike, High-Motion Videos in 1080p with One Unified Model 588

In the rapidly evolving world of generative AI, video generation has remained a particularly challenging frontier—especially when it comes to…

01/05/2026Image-to-Video Synthesis, Multimodal Generative Modeling, Text-to-Video Generation

VGGT-Long: Scalable Monocular 3D Reconstruction for Kilometer-Scale Real-World Sequences Without Retraining or Calibration 552

Monocular 3D reconstruction has seen rapid advances thanks to foundation models capable of inferring rich geometric structure from single images.…

01/05/2026Large-scale SLAM, Monocular 3D Reconstruction, Vision Foundation Models

SimpleVLA-RL: Boost Robotic Task Performance with Minimal Data Using Reinforcement Learning 762

Building capable robotic systems that understand vision, language, and action—commonly referred to as Vision-Language-Action (VLA) models—has become a central goal…

01/05/2026Reinforcement Learning, Robotic Manipulation, Vision-Language-Action Modeling

PUSA: Generate High-Quality Video from Text or Images for $500—Not $100,000 645

Video generation has long been bottlenecked by two stubborn realities: astronomical training costs and rigid temporal modeling. Most state-of-the-art image-to-video…

01/05/2026Image-to-Video Synthesis, Multi-condition Video Diffusion, Text-to-Video Generation

Decoupled DMD: Unlock Ultra-Fast, High-Quality Image Generation with 8-Step Distillation 8234

If you’re building or evaluating text-to-image systems that demand both speed and visual fidelity, Decoupled DMD offers a breakthrough in…

01/04/2026Diffusion Model Distillation, Few-step Image Synthesis, Text-to-Image Generation

Causal-Learn: Discover True Cause-and-Effect Relationships from Observational Data in Python 1521

In many real-world scenarios—whether you’re analyzing patient outcomes in healthcare, consumer behavior in economics, or system failures in engineering—you can’t…

01/04/2026Causal Discovery, Causal Inference, Structure Learning

Kimi-Dev: Solve Real Software Bugs with a Test-Passing, Open-Source Coding LLM 1075

Kimi-Dev is a state-of-the-art open-source large language model (LLM) purpose-built for software engineering tasks. Unlike generic coding assistants that generate…

01/04/2026Automated Bug Fixing, Software Engineering Agents, Test-aware Code Generation

Vizier: Production-Grade Black-Box Optimization for Reliable Hyperparameter Tuning and System Configuration 1616

Optimizing complex systems—whether machine learning models, database configurations, or compiler flags—often feels like navigating a dark room: you know the…

01/04/2026Automated Machine Learning, Black-box Optimization, Hyperparameter Optimization