PaperCodex

DeepCode: Turn Research Papers and Text into Production-Ready Code—Faster Than Human Experts 12706

Imagine being able to feed a research paper, a technical specification, or even a rough product description into a system—and…

12/26/2025Agentic AI, Code Generation, Research Reproduction

aiXcoder-7B: High-Accuracy Code Completion in a Lightweight 7B Model for Real-Time Developer Workflows 2274

aiXcoder-7B is a 7-billion-parameter open-source large language model (LLM) purpose-built for code processing. Unlike larger models that trade inference speed…

12/26/2025Code Completion, Code Generation, Fill-in-the-middle

Mini-Omni: Real-Time, End-to-End Speech AI Without ASR or TTS Latency 3492

In today’s landscape of conversational AI, most voice-enabled systems rely on a pipeline of separate components: automatic speech recognition (ASR)…

12/26/2025End-to-end Voice Interaction, Real-time Conversational AI, Speech-to-speech Synthesis

Puppeteer: Dynamic Multi-Agent Orchestration for Efficient, Adaptive LLM Collaboration 27888

Managing complex tasks with large language models (LLMs) often hits a ceiling: while single models excel at narrow tasks, scaling…

12/26/2025Dynamic Orchestration, Multi-agent Systems, Reinforcement Learning For LLMs

Elixir: Train Large Language Models Efficiently on Small GPU Clusters Without Expert-Level Tuning 41294

Training large language models (LLMs) has traditionally been the domain of well-resourced AI labs with access to massive GPU clusters…

12/26/2025Distributed Deep Learning, Large Language Model Training, Memory-efficient Training

UniLM: One Model for Both Understanding and Generating Natural Language 21874

In the evolving landscape of natural language processing (NLP), teams often find themselves juggling separate models—one for understanding tasks like…

12/26/2025Natural Language Generation, Natural Language Understanding, Sequence-to-sequence Modeling

Megatron-LM: Train Billion-Parameter Transformer Models Efficiently on NVIDIA GPUs at Scale 14515

If you’re building or scaling large language models (LLMs) and have access to NVIDIA GPU clusters, Megatron-LM—developed by NVIDIA—is one…

12/26/2025Distributed Deep Learning, Large Language Model Training, Mixture-of-Experts

MiDaS: Robust Monocular Depth Estimation from a Single Image—No Special Hardware Required 5267

In today’s world of intelligent systems—from autonomous robots to immersive AR experiences—depth perception is essential. Yet most cameras only capture…

12/26/2025Dense Prediction, Monocular Depth Estimation, Zero-shot Transfer

MedSAM: Accurate, Prompt-Based Medical Image Segmentation Out of the Box 3980

Medical image segmentation—the process of delineating anatomical structures or pathologies in scans like CT, MRI, or ultrasound—is foundational to diagnosis,…

12/26/20253D Medical Video Segmentation, Medical Image Segmentation, Prompt-based Segmentation

3D-Speaker: High-Accuracy Speaker Verification and Diarization Made Accessible for Real-World Applications 2648

In the landscape of spoken language processing, accurately identifying who is speaking—across recordings, meetings, or voice-based interfaces—remains a critical yet…

12/26/2025Language Identification, Speaker Diarization, Speaker Verification