RAY-TOLD: Ray-Based Latent Dynamics for Dense Dynamic Obstacle Avoidance with TDMPC
arXiv:2604.27450v1 Announce Type: cross Abstract: Dense, dynamic crowds pose a persistent challenge for autonomous mobile robots. Purely reactive planning methods,…
CheXthought: A global multimodal dataset of clinical chain-of-thought reasoning and visual attention for chest X-ray interpretation
arXiv:2604.26288v2 Announce Type: replace-cross Abstract: Chest X-ray interpretation is one of the most frequently performed diagnostic tasks in medicine and…
Compositional Meta-Learning for Mitigating Task Heterogeneity in Physics-Informed Neural Networks
arXiv:2604.26999v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) approximate solutions of partial differential equations (PDEs) by embedding physical laws…
Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models
arXiv:2604.25313v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) models frequently produce answers grounded in parametric memory rather than the retrieved…
Causal Learning with Neural Assemblies
arXiv:2604.26919v1 Announce Type: cross Abstract: Can Neural Assemblies — groups of neurons that fire together and strengthen through co-activation —…
Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models
arXiv:2604.26951v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) offer parallel decoding and bidirectional context, but state-of-the-art dLLMs require…
The Surprising Effectiveness of Canonical Knowledge Distillation for Semantic Segmentation
arXiv:2604.25530v2 Announce Type: replace-cross Abstract: Recent knowledge distillation (KD) methods for semantic segmentation introduce increasingly complex hand-crafted objectives, yet are…