For teams building or fine-tuning large language models (LLMs), one of the biggest bottlenecks is the scarcity of high-quality, diverse…
TTRL: Boost LLM Reasoning Without Labels Using Test-Time Reinforcement Learning 836
Imagine being able to improve a large language model’s (LLM) reasoning capabilities after deployment, using only unlabeled test data—no ground-truth…
RecAI: Prevent Out-of-Domain Recommendations with Plug-and-Play LLM Integration for Accurate, Explainable, and Interactive Systems 913
Large Language Models (LLMs) have unlocked new possibilities for recommender systems—enabling natural-language interactions, personalized explanations, and dynamic user control. Yet…
FinTeam: A Multi-Agent Financial Intelligence System That Generates Human-Accepted Reports and Outperforms GPT-4o 779
Financial analysis is rarely a solo endeavor. In real-world institutions—from investment banks to asset management firms—complex tasks like producing quarterly…
MAGI-1: Autoregressive Video Generation at Scale with Constant Memory and Real-Time Streaming 530
MAGI-1 is a breakthrough world model designed for autoregressive video generation at scale. Unlike conventional video diffusion or transformer-based approaches…
HiDream-I1: Generate and Edit High-Quality Images in Seconds with Sparse Diffusion Transformer 777
The rapid evolution of AI-driven image generation has unlocked incredible creative potential—but often at a steep cost: slow inference, massive…
ZipVoice-Dialog: Generate Realistic Spoken Dialogues Instantly—No Fine-Tuning, No Templates 662
Creating natural-sounding spoken dialogues between two people has long been a pain point in AI-driven voice applications. Traditional approaches either…
YOLOv13: Boost Real-Time Object Detection Accuracy Without Sacrificing Speed or Efficiency 827
For engineers, researchers, and product teams building real-time vision systems—whether for surveillance cameras, autonomous drones, or mobile apps—achieving high detection…
UniAnimate-DiT: High-Fidelity Human Animation from a Single Image and Pose Sequence – No Full Retraining Needed 797
Animating a static human image into a realistic, temporally coherent video used to require massive datasets, complex pipelines, or retraining…
360-LLaMA-Factory: Plug-and-Play Sequence Parallelism for Long-Context SFT and DPO Without Rewriting Your Workflow 571
Training large language models (LLMs) on long sequences—whether for document-level instruction tuning, multi-modal reasoning, or complex alignment tasks—has long been…