AI
Mechanistic Tomography: Designed Measurement for Control-Oriented Interpretability
Researchers have developed a new method called Mechanistic Tomography to improve the interpretabilit...
AI
Does Marginal Coverage Guarantee Class-Conditional Safety for Zero-Shot VLMs Under Shift?
Researchers have investigated whether using marginal coverage can ensure that zero-shot vision-langu...
AI
Fairness-Aware Network Embeddings: Methods, Applications, and Challenges
Researchers have proposed various fairness-aware network embedding methods to address biases in grap...
AI
Concentrated Liquidity Provision: a Reinforcement Learning Perspective
Researchers have applied reinforcement learning to improve the way liquidity is provided in decentra...
AI
HYDRA: A Heterogeneous Chiplet DSE Framework for Serving Dynamic Hybrid LLM Workloads
Researchers have developed HYDRA, a framework that explores the design space of ...
AI
HiRA-CAM: Preserving Fine-Grained Spatial Relevance in Gradient-Based Visual Explanations
Researchers have proposed an improved method called HiRA-CAM for creating visual...
AI
SCAPE: Scenario-Conditioned Simulation-Augmented Policy Evaluation
Researchers have developed SCAPE, a framework for evaluating robot-learning poli...
AI
Longitudinal Bayesian Learning of Continuous Disease Position across the Alzheimer's Disease Continuum
Researchers have developed a new AI framework called Disease Continuum Positioni...