Class imbalance significantly degrades classification performance, yet its effects are rarely analyzed from a unified theoretical perspective. We propose a prin...
As world models gain momentum in Embodied AI, an increasing number of works explore using video foundation models as predictive world models for downstream embo...
Large Language Models (LLMs) encode vast amounts of parametric knowledge during pre-training. As world knowledge evolves, effective deployment increasingly depe...
Satellites continuously generate massive volumes of data, particularly for Earth observation, including satellite image time series (SITS). However, most deep l...
GUI agents that interact with graphical interfaces on behalf of users represent a promising direction for practical AI assistants. However, training such agents...
Automated blood morphology analysis can support hematological diagnostics in low- and middle-income countries (LMICs) but remains sensitive to dataset shifts fr...
Optimal control of obstacle problems arises in a wide range of applications and is computationally challenging due to its nonsmoothness, nonlinearity, and bilev...
The PSO-X framework incorporates dozens of modules that have been proposed for solving single-objective continuous optimization problems using particle swarm op...
'Reinforcement learning gyms' train agents on the many low-level tasks that they must chain together to execute customer requests....
Language models often show a preference for using information from specific positions in the input regardless of semantic relevance. While positional bias has b...
Large Multimodal Models (LMMs) have demonstrated impressive capabilities in video reasoning via Chain-of-Thought (CoT). However, the robustness of their reasoni...
Mixture-of-Experts (MoE) models facilitate edge deployment by decoupling model capacity from active computation, yet their large memory footprint drives the nee...
