model generalization
Model generalization is the ability of a machine learning model to perform well on unseen data, beyond the data it was trained on. It is a critical aspect, as a model that generalizes well can reliably make predictions and decisions in real-world applications.
- A Generalist Intracortical Motor Decoder
- An Investigation of Memorization Risk in Healthcare Foundation Models
- Boosting Resilience of Large Language Models through Causality-Driven Robust Optimization
- Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation
- C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models
- Cyclic Counterfactuals under Shift–Scale Interventions
- DAAC: Discrepancy-Aware Adaptive Contrastive Learning for Medical Time series
- FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies
- Graph Few-Shot Learning via Adaptive Spectrum Experts and Cross-Set Distribution Calibration
- Learning Chern Numbers of Multiband Topological Insulators with Gauge Equivariant Neural Networks
- Long-tailed Recognition with Model Rebalancing
- MindGYM: What Matters in Question Synthesis for Thinking-Centric Fine-Tuning?
- On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity
- On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity
- Policy Optimized Text-to-Image Pipeline Design
- Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning
- Probing Neural Combinatorial Optimization Models
- Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning
- RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers
- RoFt-Mol: Benchmarking Robust Fine-tuning with Molecular Graph Foundation Models
- SEMPO: Lightweight Foundation Models for Time Series Forecasting
- The Emergence of Abstract Thought in Large Language Models Beyond Any Language
- UniMotion: A Unified Motion Framework for Simulation, Prediction and Planning