benchmark datasets
Standard datasets that are widely used in the AI community to evaluate and compare the performance of algorithms, ensuring consistency in research results.
- A Closer Look at Graph Transformers: Cross-Aggregation and Beyond
- A Difference-of-Convex Functions Approach to Energy-Based Iterative Reasoning
- A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning
- A Reinforcement Learning-based Bidding Strategy for Data Consumers in Auction-based Federated Learning
- A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
- ACT as Human: Multimodal Large Language Model Data Annotation with Critical Thinking
- Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning
- Analogy-based Multi-Turn Jailbreak against Large Language Models
- Anchor-based Maximum Discrepancy for Relative Similarity Testing
- Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks
- BlurDM: A Blur Diffusion Model for Image Deblurring
- Coloring Learning for Heterophilic Graph Representation
- Conditional Diffusion Anomaly Modeling on Graphs
- Credal Prediction based on Relative Likelihood
- Curriculum Model Merging: Harmonizing Chemical LLMs for Enhanced Cross-Task Generalization
- DIFFSSR: Stereo Image Super-resolution Using Differential Transformer
- DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigm
- Dataset Distillation of 3D Point Clouds via Distribution Matching
- Diffusing DeBias: Synthetic Bias Amplification for Model Debiasing
- Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation
- Diffusion-Guided Graph Data Augmentation
- Domain Adaptive Hashing Retrieval via VLM Assisted Pseudo-Labeling and Dual Space Adaptation
- Dynamic Masking and Auxiliary Hash Learning for Enhanced Cross-Modal Retrieval
- Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients
- Efficient Training-Free Online Routing for High-Volume Multi-LLM Serving
- Enhanced Cyclic Coordinate Descent Methods for Elastic Net Penalized Linear Models
- Epistemic Uncertainty Estimation in Regression Ensemble Models with Pairwise Epistemic Estimators
- Error Broadcast and Decorrelation as a Potential Artificial and Natural Learning Mechanism
- Event-Driven Dynamic Scene Depth Completion
- Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation
- Gaussian Processes for Shuffled Regression
- Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective
- GraphLand: Evaluating Graph Machine Learning Models on Diverse Industrial Data
- HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models
- HoloScene: Simulation‑Ready Interactive 3D Worlds from a Single Video
- How Benchmark Prediction from Fewer Data Misses the Mark
- How Classifier Features Transfer to Downstream: An Asymptotic Analysis in a Two-Layer Model
- How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning
- Hybrid-Collaborative Augmentation and Contrastive Sample Adaptive-Differential Awareness for Robust Attributed Graph Clustering
- IA-GGAD: Zero-shot Generalist Graph Anomaly Detection via Invariant and Affinity Learning
- Incomplete Multi-view Deep Clustering with Data Imputation and Alignment
- Incremental Sequence Classification with Temporal Consistency
- K-DeCore: Facilitating Knowledge Transfer in Continual Structured Knowledge Reasoning via Knowledge Decoupling
- Knowledge Distillation of Uncertainty using Deep Latent Factor Model
- LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups
- Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need
- LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching
- Learn2Mix: Training Neural Networks Using Adaptive Data Integration
- Learning Source-Free Domain Adaptation for Visible-Infrared Person Re-Identification
- Learning from Disjoint Views: A Contrastive Prototype Matching Network for Fully Incomplete Multi-View Clustering
- Learning to Clean: Reinforcement Learning for Noisy Label Correction
- Long-Tailed Recognition via Information-Preservable Two-Stage Learning
- Meta Guidance: Incorporating Inductive Biases into Deep Time Series Imputers
- Meta-D2AG: Causal Graph Learning with Interventional Dynamic Data
- Metropolis-Hastings Sampling for 3D Gaussian Reconstruction
- Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning
- MoFo: Empowering Long-term Time Series Forecasting with Periodic Pattern Modeling
- MolVision: Molecular Property Prediction with Vision Language Models
- More Than Just Functional: LLM-as-a-Critique for Efficient Code Generation
- Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting
- NoBOOM: Chemical Process Datasets for Industrial Anomaly Detection
- Optimistic Query Routing in Clustering-based Approximate Maximum Inner Product Search
- Oryx: a Scalable Sequence Model for Many-Agent Coordination in Offline MARL
- Pairwise Optimal Transports for Training All-to-All Flow-Based Condition Transfer Model
- PhysDiff: A Physically-Guided Diffusion Model for Multivariate Time Series Anomaly Detection
- Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
- RUAGO: Effective and Practical Retain-Free Unlearning via Adversarial Attack and OOD Generator
- ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAG
- Reliably detecting model failures in deployment without labels
- RoMa: A Robust Model Watermarking Scheme for Protecting IP in Diffusion Models
- RrED: Black-box Unsupervised Domain Adaptation via Rectifying-reasoning Errors of Diffusion
- SMARTraj$^2$: A Stable Multi-City Adaptive Method for Multi-View Spatio-Temporal Trajectory Representation Learning
- Self-Perturbed Anomaly-Aware Graph Dynamics for Multivariate Time-Series Anomaly Detection
- Semantic-KG: Using Knowledge Graphs to Construct Benchmarks for Measuring Semantic Similarity
- Semi-Supervised Regression with Heteroscedastic Pseudo-Labels
- Size-adaptive Hypothesis Testing for Fairness
- Spatiotemporal Consensus with Scene Prior for Unsupervised Domain Adaptive Person Search
- Subgraph Federated Learning via Spectral Methods
- TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link Prediction
- TARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAE
- TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs
- Think before Recommendation: Autonomous Reasoning-enhanced Recommender
- TimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series Forecasting
- Towards Unsupervised Training of Matching-based Graph Edit Distance Solver via Preference-aware GAN
- Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning
- Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning
- Training Robust Graph Neural Networks by Modeling Noise Dependencies
- Trans-EnV: A Framework for Evaluating the Linguistic Robustness of LLMs Against English Varieties
- Uncertainty-Aware Multi-Objective Reinforcement Learning-Guided Diffusion Models for 3D De Novo Molecular Design
- UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation
- You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep Clustering