real-world tasks
Practical applications of AI models that reflect challenges faced in everyday scenarios, such as image recognition for automated tagging, natural language processing for chatbots, or autonomous navigation, emphasizing the need for robustness and generalization in deployed systems.
- Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective
- On the $O(\frac{\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\ell_1$ Norm
- RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks
- SimSort: A Data-Driven Framework for Spike Sorting by Large-Scale Electrophysiology Simulation
- Variational Uncertainty Decomposition for In-Context Learning
- What Expressivity Theory Misses: Message Passing Complexity for GNNs