SOTAVerified

The Open Verification Layer for ML Research

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

661,570 papers248,326 code links4,818 tasks

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 5001–5050 of 661570 papers

TitleStatusHype
Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial DefectsCode2
MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group QuantizationCode2
Open Source Planning & Control System with Language Agents for Autonomous Scientific DiscoveryCode2
MoFE-Time: Mixture of Frequency Domain Experts for Time-Series Forecasting ModelsCode2
AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMsCode2
Feed-Forward SceneDINO for Unsupervised Semantic Scene CompletionCode2
Omni-Video: Democratizing Unified Video Understanding and GenerationCode2
High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement LearningCode2
Modern Methods in Associative MemoryCode2
Differentiable Reward Optimization for LLM based TTS systemCode2
GTA1: GUI Test-time Scaling AgentCode2
T-LoRA: Single Image Diffusion Model Customization Without OverfittingCode2
RIPE: Reinforcement Learning on Unlabeled Image Pairs for Robust Keypoint ExtractionCode2
Neural-Driven Image EditingCode2
any4: Learned 4-bit Numeric Representation for LLMsCode2
Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document RestorationCode2
Learning Robust Stereo Matching in the Wild with Selective Mixture-of-ExpertsCode2
BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated LearningCode2
MambaFusion: Height-Fidelity Dense Global Fusion for Multi-modal 3D Object DetectionCode2
PresentAgent: Multimodal Agent for Presentation Video GenerationCode2
GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph LearningCode2
Flow-Anchored Consistency ModelsCode2
Meta SecAlign: A Secure Foundation LLM Against Prompt Injection AttacksCode2
DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal AlignmentCode2
SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature AlignmentCode2
AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-benchCode2
Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics EmulationCode2
MathOptAI.jl: Embed trained machine learning predictors into JuMP modelsCode2
MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech EnhancementCode2
NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous EnvironmentsCode2
Advancing Learnable Multi-Agent Pathfinding Solvers with Active Fine-TuningCode2
DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real WorldCode2
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement LearningCode2
VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and CollisionsCode2
MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow EstimationCode2
R1-Track: Direct Application of MLLMs to Visual Object Tracking via Reinforcement LearningCode2
EAMamba: Efficient All-Around Vision State Space Model for Image RestorationCode2
The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT ImprovementsCode2
LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMsCode2
Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement LearningCode2
WAFT: Warping-Alone Field Transforms for Optical FlowCode2
ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo MatchingCode2
Spatial Mental Modeling from Limited ViewsCode2
EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing CorporaCode2
Learning to See in the Extremely DarkCode2
BMFM-DNA: A SNP-aware DNA foundation model to capture variant effectsCode2
KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding ModelCode2
DBConformer: Dual-Branch Convolutional Transformer for EEG DecodingCode2
HumanOmniV2: From Understanding to Omni-Modal Reasoning with ContextCode2
Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and TrendsCode2
Show:102550
← PrevPage 101 of 13232Next →