experimental validation
Experimental validation is the process of confirming that a model or algorithm performs as expected against various benchmarks and data sets, ensuring reliability and practical applicability.
- Accelerated Evolving Set Processes for Local PageRank Computation
- AlignedGen: Aligning Style Across Generated Images
- Approximately Aligned Decoding
- Boosting the Uniqueness of Neural Networks Fingerprints with Informative Triggers
- Diffusion on Demand: Selective Caching and Modulation for Efficient Generation
- Diversity-oriented Deep Multi-modal Clustering
- Evolving and Regularizing Meta-Environment Learner for Fine-Grained Few-Shot Class-Incremental Learning
- Extragradient Method for $(L_0, L_1)$-Lipschitz Root-finding Problems
- Fourier Analysis Network
- L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models
- Memory Injection Attacks on LLM Agents via Query-Only Interaction
- Multilevel neural simulation-based inference
- Partition-Then-Adapt: Combating Prediction Bias for Reliable Multi-Modal Test-Time Adaptation
- Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalization
- Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization
- Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates
- Revisiting 1-peer exponential graph for enhancing decentralized learning efficiency
- Tackling Biased Evaluators in Dueling Bandits
- The Rise of Parameter Specialization for Knowledge Storage in Large Language Models
- Time-o1: Time-Series Forecasting Needs Transformed Label Alignment
- Understanding Generalization in Physics Informed Models through Affine Variety Dimensions