Articles & Guides

A new arXiv paper proposes a slice-wise data synthesis pipeline to help 2D-pretrained medical multimodal large language models reason over 3D scans. The approach turns volumetric reading into structured, interpretable reasoning traces.

SPyCE proposes a training framework where a multimodal agent’s policy and skill library improve together. Instead of treating trajectories only as rewards or static memories, it distills them into reusable execution and workflow skills.

A new arXiv paper introduces Quantum Topological Data Encoding (QTDE), a framework for encoding geometric and topological structure into quantum states through topology-driven quantum evolution. Early experiments on clique-complex classification suggest that these quantum representations can outperform a baseline based on direct Laplacian comparisons.

A new arXiv paper introduces HTFM, a flow-matching framework that models heavy-tailed sources as Gaussian mixtures conditioned on random clock paths. The goal is to make generative models better aligned with rare events, long-tail classes, and extreme-value data.

A new arXiv paper examines how German companies are integrating generative AI and predictive analytics into human resource management. The study finds that while AI can strengthen HR analytics, adoption is often driven by efficiency and rationalisation goals.

NodeImport reframes class-imbalanced node classification as a question of which nodes actually improve unbiased performance. The framework filters labeled, unlabeled, and synthetic nodes using an importance signal derived from a balanced meta-set.

A new arXiv paper proposes Recursive ArUco markers, a fiducial marker design intended to help UAVs recognize landing pads from both distant and close viewpoints. The approach embeds complete markers inside the black and white bit regions of a parent marker, enabling recursive detection without relying on the center being visible.

A new arXiv paper presents a fully automated multimodal framework for assessing pancreatic ductal adenocarcinoma resectability. The system combines 3D contrast-enhanced CT with structured clinical variables to classify patients into NCCN resectability categories.

TCAM-Diff proposes a triplane-aware diffusion pipeline for high-resolution 3D medical image generation. Instead of modeling dense volumes directly, it learns compact triplane features and decodes them back into 3D volumes.

A new arXiv paper introduces Spatial Texture-Atlas Splatting, a representation that bakes high-frequency, view-independent texture detail into compact atlases. The authors report up to a fivefold speedup over 3DGS while preserving state-of-the-art visual fidelity and enabling real-time 4K rendering at 60 FPS on consumer hardware.

AspectCLIP addresses a subtle weakness in CLIP-style training: images contain many possible semantic aspects, while captions usually describe only one. The method uses text-guided attribute clusters to apply consistency where it is semantically appropriate.

RainDancer targets video deraining by combining RGB frames with event-camera cues, while avoiding naive cross-modal fusion. Its central idea is to decompose rain and background components before letting the two modalities interact.

A new arXiv paper introduces TA-RS, a certified defense for LLM-based intrusion detection systems. Instead of perturbing every feature, it injects Gaussian noise only into traffic features a remote attacker can directly control.

A new arXiv study examines which inputs in chest radiograph classification are prospectively available and which are post-hoc artifacts. It finds that Clinical Indication is highly predictive, while report sections such as Findings and Impression can create substantial label leakage.

The arXiv paper “CAS I: A Geometric Coding Theorem” proposes a group-theoretic analogue of the classical Coding Theorem by measuring how likely a symmetry is to isolate a binary string as its unique fixed point.

EgoProceVQA introduces a benchmark for evaluating procedural reasoning in egocentric video question answering. The work also presents EgoProceGen for data generation and EgoProceAgent, a self-skill-exploration framework for procedural understanding.

A new arXiv paper reframes regularity through a communication-complexity lens: split an input word between Alice and Bob, then ask whether a constant amount of communication is enough to compute the function. The goal is to unify Nerode-style characterizations across different output domains.

A new arXiv paper applies Neural Spline Flows to a mono-Z dark matter search using CMS Run 2015D open data. The study reports no evidence for dark matter, but highlights how likelihood-ratio scoring in high-dimensional phase space could reshape particle-physics analyses.

A new arXiv paper introduces Kaleido, an algorithm-hardware co-design for video diffusion transformers that exploits channel-wise spatiotemporal correlations in latent space.

A new arXiv paper introduces MxGPS, a multiplex graph transformer designed to reduce topology overfitting in power-grid GNNs. By jointly training on static state estimation and AC power flow, the model aims to generalize better to unseen grid topologies.

A new arXiv paper studies how post-training methods alter confidence signals before, during and after chain-of-thought generation. Its key message: confidence in reasoning models is useful only when matched to the right stage and position.