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 11001–11050 of 661570 papers

TitleStatusHype
Execution Guided Line-by-Line Code GenerationCode2
SEMv3: A Fast and Robust Approach to Table Separation Line DetectionCode2
GO-SLAM: Global Optimization for Consistent 3D Instant ReconstructionCode2
Interpreting the Weight Space of Customized Diffusion ModelsCode2
HugNLP: A Unified and Comprehensive Library for Natural Language ProcessingCode2
UNeXt: MLP-based Rapid Medical Image Segmentation NetworkCode2
FrontierNet: Learning Visual Cues to ExploreCode2
POTATO: The Portable Text Annotation ToolCode2
LLaVAction: evaluating and training multi-modal large language models for action recognitionCode2
Multi-Agent Reinforcement Learning is a Sequence Modeling ProblemCode2
Convergence Analysis of Probability Flow ODE for Score-based Generative ModelsCode2
From Hours to Minutes: Lossless Acceleration of Ultra Long Sequence Generation up to 100K TokensCode2
E3x: E(3)-Equivariant Deep Learning Made EasyCode2
An Economic Framework for 6-DoF Grasp DetectionCode2
Discrete Diffusion Modeling by Estimating the Ratios of the Data DistributionCode2
REINFORCE++: A Simple and Efficient Approach for Aligning Large Language ModelsCode2
Fine-tuned In-Context Learning Transformers are Excellent Tabular Data ClassifiersCode2
Three Bricks to Consolidate Watermarks for Large Language ModelsCode2
NeuRBF: A Neural Fields Representation with Adaptive Radial Basis FunctionsCode2
SINDy-RL: Interpretable and Efficient Model-Based Reinforcement LearningCode2
High-Performance Transformers for Table Structure Recognition Need Early ConvolutionsCode2
mbrs: A Library for Minimum Bayes Risk DecodingCode2
DeepAAT: Deep Automated Aerial Triangulation for Fast UAV-based MappingCode2
Text2Light: Zero-Shot Text-Driven HDR Panorama GenerationCode2
MTLoRA: Low-Rank Adaptation Approach for Efficient Multi-Task LearningCode2
Zeus: Understanding and Optimizing GPU Energy Consumption of DNN TrainingCode2
Retriever-and-Memory: Towards Adaptive Note-Enhanced Retrieval-Augmented GenerationCode2
GUI Odyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile DevicesCode2
Blind Video Deflickering by Neural Filtering with a Flawed AtlasCode2
4Hammer: a board-game reinforcement learning environment for the hour long time frameCode2
WeKws: A production first small-footprint end-to-end Keyword Spotting ToolkitCode2
OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-AllocationCode2
RoCo: Dialectic Multi-Robot Collaboration with Large Language ModelsCode2
Towards a Unified Multi-Dimensional Evaluator for Text GenerationCode2
Mass-Editing Memory in a TransformerCode2
[Reproducibility Report] Path Planning using Neural A* SearchCode2
BitDecoding: Unlocking Tensor Cores for Long-Context LLMs Decoding with Low-Bit KV CacheCode2
Graph Data Augmentation for Graph Machine Learning: A SurveyCode2
PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical DocumentsCode2
VampNet: Music Generation via Masked Acoustic Token ModelingCode2
TextBox: A Unified, Modularized, and Extensible Framework for Text GenerationCode2
Generative Image as Action ModelsCode2
DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable DiffusionCode2
Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question AnsweringCode2
DataComp: In search of the next generation of multimodal datasetsCode2
Do We Need Domain-Specific Embedding Models? An Empirical InvestigationCode2
MACE: An Efficient Model-Agnostic Framework for Counterfactual ExplanationCode2
EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-TrainingCode2
EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the WildCode2
P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and TasksCode2
Show:102550
← PrevPage 221 of 13232Next →