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 19851–19900 of 474278 papers

TitleStatusHype
TI-PREGO: Chain of Thought and In-Context Learning for Online Mistake Detection in PRocedural EGOcentric VideosCode1
LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph GenerationCode1
Revisiting K-mer Profile for Effective and Scalable Genome Representation LearningCode1
Improving Steering Vectors by Targeting Sparse Autoencoder FeaturesCode1
Expanding Sparse Tuning for Low Memory UsageCode1
Context-Informed Machine Translation of Manga using Multimodal Large Language ModelsCode1
On Targeted Manipulation and Deception when Optimizing LLMs for User FeedbackCode1
Can Language Models Learn to Skip Steps?Code1
The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant UnitsCode1
Multi-Transmotion: Pre-trained Model for Human Motion PredictionCode1
TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for NetworkCode1
Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence ChallengeCode1
Continual LLaVA: Continual Instruction Tuning in Large Vision-Language ModelsCode1
VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector QuantizationCode1
Classifier-guided Gradient Modulation for Enhanced Multimodal LearningCode1
Polar R-CNN: End-to-End Lane Detection with Fewer AnchorsCode1
ROAD-Waymo: Action Awareness at Scale for Autonomous DrivingCode1
Activating Self-Attention for Multi-Scene Absolute Pose RegressionCode1
EDformer: Transformer-Based Event Denoising Across Varied Noise LevelsCode1
Conditional Controllable Image FusionCode1
Large-Scale Multi-Robot Coverage Path Planning on Grids with Path DeconflictionCode1
Co-clustering for Federated Recommender SystemCode1
FactorizePhys: Matrix Factorization for Multidimensional Attention in Remote Physiological SensingCode1
GraphXForm: Graph transformer for computer-aided molecular designCode1
LinRec: Linear Attention Mechanism for Long-term Sequential Recommender SystemsCode1
Rethinking Weight Decay for Robust Fine-Tuning of Foundation ModelsCode1
Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LMCode1
HeightMapNet: Explicit Height Modeling for End-to-End HD Map LearningCode1
Task-Aware Harmony Multi-Task Decision Transformer for Offline Reinforcement LearningCode1
MonoPlane: Exploiting Monocular Geometric Cues for Generalizable 3D Plane ReconstructionCode1
Leveraging LLM and Text-Queried Separation for Noise-Robust Sound Event DetectionCode1
Test-Time Adaptation in Point Clouds: Leveraging Sampling Variation with Weight AveragingCode1
CmdCaliper: A Semantic-Aware Command-Line Embedding Model and Dataset for Security ResearchCode1
Visual Fourier Prompt TuningCode1
Use Digital Twins to Support Fault Diagnosis From System-level Condition-monitoring DataCode1
AutoPT: How Far Are We from the End2End Automated Web Penetration Testing?Code1
Fast and Memory-Efficient Video Diffusion Using Streamlined InferenceCode1
What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind AttacksCode1
TaxaBind: A Unified Embedding Space for Ecological ApplicationsCode1
Beyond Utility: Evaluating LLM as RecommenderCode1
PatternBoost: Constructions in Mathematics with a Little Help from AICode1
MetaMetrics-MT: Tuning Meta-Metrics for Machine Translation via Human Preference CalibrationCode1
LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban SimulationCode1
Abstracted Shapes as Tokens -- A Generalizable and Interpretable Model for Time-series ClassificationCode1
LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language ModelsCode1
Attention Tracker: Detecting Prompt Injection Attacks in LLMsCode1
Self-Evolved Reward Learning for LLMsCode1
C2A: Client-Customized Adaptation for Parameter-Efficient Federated LearningCode1
Constant Acceleration FlowCode1
Contrasting with Symile: Simple Model-Agnostic Representation Learning for Unlimited ModalitiesCode1
Show:102550
← PrevPage 398 of 9486Next →