model capacity
The ability of a model to represent and comprehend complex functions or patterns, typically determined by the number of parameters and structure within the model.
- Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models
- Compute-Optimal Scaling for Value-Based Deep RL
- DP²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution
- Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the Role of Model Complexity
- Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via $\textit{In-the-wild}$ Cascading Flow Optimization
- EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval
- Fair Deepfake Detectors Can Generalize
- Horizon Reduction Makes RL Scalable
- Is Your Diffusion Model Actually Denoising?
- Long-tailed Recognition with Model Rebalancing
- On the sample complexity of semi-supervised multi-objective learning
- Soft Task-Aware Routing of Experts for Equivariant Representation Learning
- Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties
- Turning the Tables: Enabling Backward Transfer via Causal-Aware LoRA in Continual Learning
- UMA: A Family of Universal Models for Atoms