RoboLayout: Differentiable 3D Scene Generation for Embodied Agents
arXiv:2603.05522v1 Announce Type: new Abstract: Recent advances in vision language models (VLMs) have shown strong potential for spatial reasoning and…
RoboPocket: Improve Robot Policies Instantly with Your Phone
arXiv:2603.05504v2 Announce Type: replace-cross Abstract: Scaling imitation learning is fundamentally constrained by the efficiency of data collection. While handheld interfaces…
CLAIRE: Compressed Latent Autoencoder for Industrial Representation and Evaluation — A Deep Learning Framework for Smart Manufacturing
arXiv:2603.06361v1 Announce Type: cross Abstract: Accurate fault detection in high-dimensional industrial environments remains a major challenge due to the inherent…
Dynamic Chunking Diffusion Transformer
arXiv:2603.06351v1 Announce Type: cross Abstract: Diffusion Transformers process images as fixed-length sequences of tokens produced by a static $textit{patchify}$ operation.…
Simulating Meaning, Nevermore! Introducing ICR: A Semiotic-Hermeneutic Metric for Evaluating Meaning in LLM Text Summaries
arXiv:2603.04413v2 Announce Type: replace-cross Abstract: Meaning in human language is relational, context dependent, and emergent, arising from dynamic systems of…
SkillNet: Create, Evaluate, and Connect AI Skills
arXiv:2603.04448v1 Announce Type: new Abstract: Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement…
Bielik-Q2-Sharp: A Comparative Study of Extreme 2-bit Quantization Methods for a Polish 11B Language Model
arXiv:2603.04162v2 Announce Type: replace-cross Abstract: We present Bielik-Q2-Sharp, the first systematic academic evaluation of extreme 2-bit quantization applied to a…
Federated Causal Discovery Across Heterogeneous Datasets under Latent Confounding
arXiv:2603.05149v1 Announce Type: cross Abstract: Causal discovery across multiple datasets is often constrained by data privacy regulations and cross-site heterogeneity,…
Recurrent Graph Neural Networks and Arithmetic Circuits
arXiv:2603.05140v1 Announce Type: cross Abstract: We characterise the computational power of recurrent graph neural networks (GNNs) in terms of arithmetic…