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

Showing 24262450 of 661570 papers

TitleStatusHype
Discrete Diffusion in Large Language and Multimodal Models: A SurveyCode3
Vine Copulas as Differentiable Computational GraphsCode3
AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-TuningCode3
ANIRA: An Architecture for Neural Network Inference in Real-Time Audio ApplicationsCode3
A Comprehensive Survey of Deep Research: Systems, Methodologies, and ApplicationsCode3
FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented GenerationCode3
Spurious Rewards: Rethinking Training Signals in RLVRCode3
The Diffusion DualityCode3
TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity TreeCode3
AniMaker: Automated Multi-Agent Animated Storytelling with MCTS-Driven Clip GenerationCode3
Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation ModelsCode3
MagCache: Fast Video Generation with Magnitude-Aware CacheCode3
JAFAR: Jack up Any Feature at Any ResolutionCode3
G-Memory: Tracing Hierarchical Memory for Multi-Agent SystemsCode3
Real-Time Execution of Action Chunking Flow PoliciesCode3
Highly Compressed Tokenizer Can Generate Without TrainingCode3
Hierarchical Lexical Graph for Enhanced Multi-Hop RetrievalCode3
Generalized Trajectory Scoring for End-to-end Multimodal PlanningCode3
When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented GenerationCode3
SupeRANSAC: One RANSAC to Rule Them AllCode3
FlashDMoE: Fast Distributed MoE in a Single KernelCode3
HtFLlib: A Comprehensive Heterogeneous Federated Learning Library and BenchmarkCode3
INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual LearningCode3
A Smart Multimodal Healthcare Copilot with Powerful LLM ReasoningCode3
Ultra-High-Resolution Image Synthesis: Data, Method and EvaluationCode3
Show:102550
← PrevPage 98 of 26463Next →