SOTAVerified

The Open Verification Layer for ML Research

Community benchmark tracking and reproducibility verification. Built for researchers and autonomous research agents.

510,095 papers251,776 code links4,818 tasks

Papers

Showing 476–500 of 177341 papers

TitleStatusHype
MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio SynthesisCode7
AniSora: Exploring the Frontiers of Animation Video Generation in the Sora EraCode7
Better than classical? The subtle art of benchmarking quantum machine learning modelsCode7
Ichigo: Mixed-Modal Early-Fusion Realtime Voice AssistantCode7
GenAD: Generalized Predictive Model for Autonomous DrivingCode7
FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual OdometryCode7
aiXcoder-7B: A Lightweight and Effective Large Language Model for Code ProcessingCode7
AgentOrchestra: A Hierarchical Multi-Agent Framework for General-Purpose Task SolvingCode7
MAGI-1: Autoregressive Video Generation at ScaleCode7
Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese UnderstandingCode7
ComfyUI-Copilot: An Intelligent Assistant for Automated Workflow DevelopmentCode7
Kimi-Audio Technical ReportCode7
Bilateral Reference for High-Resolution Dichotomous Image SegmentationCode7
EvoGP: A GPU-accelerated Framework for Tree-based Genetic ProgrammingCode7
AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied SystemsCode7
StarCoder 2 and The Stack v2: The Next GenerationCode7
Mini-Omni: Language Models Can Hear, Talk While Thinking in StreamingCode7
Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning SystemsCode7
Neural Codec Language Models are Zero-Shot Text to Speech SynthesizersCode7
DocETL: Agentic Query Rewriting and Evaluation for Complex Document ProcessingCode7
Intent-based Prompt Calibration: Enhancing prompt optimization with synthetic boundary casesCode7
Improving Sample Quality of Diffusion Models Using Self-Attention GuidanceCode7
EasyAnimate: A High-Performance Long Video Generation Method based on Transformer ArchitectureCode7
HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple CharactersCode7
MagicQuill: An Intelligent Interactive Image Editing SystemCode7
Show:102550
← PrevPage 20 of 7094Next →