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 87018750 of 661570 papers

TitleStatusHype
Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Multi-modal Text RecognitionCode2
Advancing Spiking Neural Networks for Sequential Modeling with Central Pattern GeneratorsCode2
Not All Language Model Features Are LinearCode2
DreamText: High Fidelity Scene Text SynthesisCode2
Flatten Anything: Unsupervised Neural Surface ParameterizationCode2
Agent Planning with World Knowledge ModelCode2
RoPINN: Region Optimized Physics-Informed Neural NetworksCode2
Mamba-R: Vision Mamba ALSO Needs RegistersCode2
AnalogCoder: Analog Circuit Design via Training-Free Code GenerationCode2
Metric Flow Matching for Smooth Interpolations on the Data ManifoldCode2
Calibrated Self-Rewarding Vision Language ModelsCode2
Drones Help Drones: A Collaborative Framework for Multi-Drone Object Trajectory Prediction and BeyondCode2
Fast-DDPM: Fast Denoising Diffusion Probabilistic Models for Medical Image-to-Image GenerationCode2
TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving ScenesCode2
Improved Canonicalization for Model Agnostic EquivarianceCode2
RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging RadarCode2
Model Editing as a Robust and Denoised variant of DPO: A Case Study on ToxicityCode2
Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid ModelingCode2
Dense Connector for MLLMsCode2
FedCache 2.0: Federated Edge Learning with Knowledge Caching and Dataset DistillationCode2
Vikhr: Constructing a State-of-the-art Bilingual Open-Source Instruction-Following Large Language Model for RussianCode2
xRAG: Extreme Context Compression for Retrieval-augmented Generation with One TokenCode2
ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous VehiclesCode2
What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence FunctionsCode2
Fine-tuned In-Context Learning Transformers are Excellent Tabular Data ClassifiersCode2
VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal GroundingCode2
BrainMorph: A Foundational Keypoint Model for Robust and Flexible Brain MRI RegistrationCode2
Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam GenerationCode2
Context and Geometry Aware Voxel Transformer for Semantic Scene CompletionCode2
Learning Diffusion Priors from Observations by Expectation MaximizationCode2
A General Framework for Jersey Number Recognition in Sports VideoCode2
I2I-Mamba: Multi-modal medical image synthesis via selective state space modelingCode2
FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept CompositionCode2
LightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from VideosCode2
CViT: Continuous Vision Transformer for Operator LearningCode2
Large Language Models Meet NLP: A SurveyCode2
Mamba in Speech: Towards an Alternative to Self-AttentionCode2
KPConvX: Modernizing Kernel Point Convolution with Kernel AttentionCode2
RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor SearchCode2
ProtT3: Protein-to-Text Generation for Text-based Protein UnderstandingCode2
SirLLM: Streaming Infinite Retentive LLMCode2
Reducing Transformer Key-Value Cache Size with Cross-Layer AttentionCode2
The future of cosmological likelihood-based inference: accelerated high-dimensional parameter estimation and model comparisonCode2
FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher informationCode2
Wav-KAN: Wavelet Kolmogorov-Arnold NetworksCode2
LLM Processes: Numerical Predictive Distributions Conditioned on Natural LanguageCode2
GarmentDreamer: 3DGS Guided Garment Synthesis with Diverse Geometry and Texture DetailsCode2
Large-Scale Multi-Center CT and MRI Segmentation of Pancreas with Deep LearningCode2
Imp: Highly Capable Large Multimodal Models for Mobile DevicesCode2
DATR: Unsupervised Domain Adaptive Detection Transformer with Dataset-Level Adaptation and Prototypical AlignmentCode2
Show:102550
← PrevPage 175 of 13232Next →