arXiv:2509.16188v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in diverse cultural environments, evaluating their cultural understanding capability has become essential for ensuring trustworthy and culturally aligned applications. However, most existing benchmarks lack comprehensiveness and are…
arXiv:2509.15230v1 Announce Type: cross Abstract: Foundation models have transformed multimedia analysis by enabling robust and transferable representations across diverse modalities and tasks. However, their static deployment conflicts with growing societal and regulatory demands — particularly the need to unlearn specific…
arXiv:2501.11447v2 Announce Type: replace Abstract: We introduce a novel framework for decomposing interventional causal effects into synergistic, redundant, and unique components, building on the intuition of Partial Information Decomposition (PID) and the principle of M”obius inversion. While recent work has…
arXiv:2509.15236v1 Announce Type: cross Abstract: We present ChannelFlow-Tools, a configuration-driven framework that standardizes the end-to-end path from programmatic CAD solid generation to ML-ready inputs and targets for 3D obstructed channel flows. The toolchain integrates geometry synthesis with feasibility checks, signed…
arXiv:2506.02918v2 Announce Type: replace Abstract: Tool use in stateful environments presents unique challenges for large language models (LLMs), where existing test-time compute strategies relying on repeated trials in the environment are impractical. We propose dynamics modelling (DyMo), a method that…
arXiv:2509.15238v1 Announce Type: cross Abstract: Belief-Desire-Intention (BDI) is a framework for modelling agents based on their beliefs, desires, and intentions. Plans are a central component of BDI agents, and define sequences of actions that an agent must undertake to achieve…
arXiv:2509.15246v1 Announce Type: cross Abstract: CAD programs, structured as parametric sequences of commands that compile into precise 3D geometries, are fundamental to accurate and efficient engineering design processes. Generating these programs from nonparametric data such as point clouds and meshes…
arXiv:2408.03591v2 Announce Type: replace-cross Abstract: Accurate fixation depth estimation is essential for applications in extended reality (XR), robotics, and human-computer interaction. However, current methods heavily depend on user-specific calibration, which limits their scalability and usability. We introduce FOVAL, a robust…
arXiv:2509.15248v1 Announce Type: cross Abstract: We introduce Synthetic Bootstrapped Pretraining (SBP), a language model (LM) pretraining procedure that first learns a model of relations between documents from the pretraining dataset and then leverages it to synthesize a vast new corpus…
arXiv:2509.15249v1 Announce Type: cross Abstract: Existing 3D scene generation methods often struggle to model the complex logical dependencies and physical constraints between objects, limiting their ability to adapt to dynamic and realistic environments. We propose CausalStruct, a novel framework that…
