SOTAVerified

The Open Verification Layer for ML Research

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

474,278 papers248,326 code links4,818 tasks

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 474278 papers

TitleStatusHype
OpenHands: An Open Platform for AI Software Developers as Generalist AgentsCode16
YOLOv9: Learning What You Want to Learn Using Programmable Gradient InformationCode16
MinerU: An Open-Source Solution for Precise Document Content ExtractionCode16
Docling Technical ReportCode16
DeepSeek-V3 Technical ReportCode16
AutoGen Studio: A No-Code Developer Tool for Building and Debugging Multi-Agent SystemsCode16
Mem0: Building Production-Ready AI Agents with Scalable Long-Term MemoryCode16
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversionCode15
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement LearningCode15
LightRAG: Simple and Fast Retrieval-Augmented GenerationCode14
Optimizing Instructions and Demonstrations for Multi-Stage Language Model ProgramsCode14
Assisting in Writing Wikipedia-like Articles From Scratch with Large Language ModelsCode14
TradingAgents: Multi-Agents LLM Financial Trading FrameworkCode14
ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All ToolsCode14
From Local to Global: A Graph RAG Approach to Query-Focused SummarizationCode14
1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUsCode14
FLUX that Plays MusicCode14
Chatbot Arena: An Open Platform for Evaluating LLMs by Human PreferenceCode14
UI-TARS: Pioneering Automated GUI Interaction with Native AgentsCode14
Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200kCode14
Relevance Isn't All You Need: Scaling RAG Systems With Inference-Time Compute Via Multi-Criteria RerankingCode14
Autonomous Agents for Collaborative Task under Information AsymmetryCode14
Qwen3 Technical ReportCode14
Qwen2.5 Technical ReportCode13
Qwen2 Technical ReportCode13
R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint OptimizationCode13
Open-Sora: Democratizing Efficient Video Production for AllCode13
Bitnet.cpp: Efficient Edge Inference for Ternary LLMsCode13
MiniCPM-V: A GPT-4V Level MLLM on Your PhoneCode12
Zep: A Temporal Knowledge Graph Architecture for Agent MemoryCode12
OmniParser for Pure Vision Based GUI AgentCode12
SAM 2: Segment Anything in Images and VideosCode12
FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precisionCode12
SmolVLA: A Vision-Language-Action Model for Affordable and Efficient RoboticsCode12
Qwen3-Coder-Next Technical Report—11
DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints—11
EAP4EMSIG -- Experiment Automation Pipeline for Event-Driven Microscopy to Smart Microfluidic Single-Cells AnalysisCode11
NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive SecurityCode11
WebWalker: Benchmarking LLMs in Web TraversalCode11
Gymnasium: A Standard Interface for Reinforcement Learning EnvironmentsCode11
F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow MatchingCode11
Eagle and Finch: RWKV with Matrix-Valued States and Dynamic RecurrenceCode11
HunyuanVideo: A Systematic Framework For Large Video Generative ModelsCode11
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any ResolutionCode11
KAN 2.0: Kolmogorov-Arnold Networks Meet ScienceCode11
KAN: Kolmogorov-Arnold NetworksCode11
Absolute Zero: Reinforced Self-play Reasoning with Zero DataCode11
USP: A Unified Sequence Parallelism Approach for Long Context Generative AICode11
AgentScope: A Flexible yet Robust Multi-Agent PlatformCode11
Qwen2.5-Coder Technical ReportCode11
Show:102550
← PrevPage 1 of 9486Next →