GBC: Generalized Behavior-Cloning Framework for Whole-Body Humanoid Imitation
arXiv:2508.09960v1 Announce Type: cross Abstract: The creation of human-like humanoid robots is hindered by a fundamental fragmentation: data processing and…
Human Motion Capture from Loose and Sparse Inertial Sensors with Garment-aware Diffusion Models
arXiv:2506.15290v2 Announce Type: replace-cross Abstract: Motion capture using sparse inertial sensors has shown great promise due to its portability and…
One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learning
arXiv:2508.01561v2 Announce Type: replace Abstract: Generalizing to complex and temporally extended task objectives and safety constraints remains a critical challenge…
Explaining Caption-Image Interactions in CLIP Models with Second-Order Attributions
arXiv:2408.14153v4 Announce Type: replace-cross Abstract: Dual encoder architectures like Clip models map two types of inputs into a shared embedding…
RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussians
arXiv:2508.09830v1 Announce Type: cross Abstract: In this paper, we present a generalizable method for 3D surface reconstruction from raw point…
Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation
arXiv:2508.07981v2 Announce Type: replace-cross Abstract: Visual effects (VFX) are essential visual enhancements fundamental to modern cinematic production. Although video generation…
Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments
arXiv:2508.08791v1 Announce Type: cross Abstract: Effective tool use is essential for large language models (LLMs) to interact meaningfully with their…
TechOps: Technical Documentation Templates for the AI Act
arXiv:2508.08804v1 Announce Type: cross Abstract: Operationalizing the EU AI Act requires clear technical documentation to ensure AI systems are transparent,…
Cut2Next: Generating Next Shot via In-Context Tuning
arXiv:2508.08244v2 Announce Type: replace-cross Abstract: Effective multi-shot generation demands purposeful, film-like transitions and strict cinematic continuity. Current methods, however, often…
Topos Theory for Generative AI and LLMs
arXiv:2508.08293v1 Announce Type: new Abstract: We propose the design of novel categorical generative AI architectures (GAIAs) using topos theory, a…