arXiv:2604.11835v2 Announce Type: replace-cross Abstract: Machine learning for tabular data remains constrained by poor schema generalization, a challenge rooted in the lack of semantic understanding of structured variables. This challenge is particularly acute in domains like clinical medicine, where electronic health record (EHR) schemas vary significantly. To solve this problem, we propose Schema-Adaptive Tabular Representation […]
Visualizing Critic Match Loss Landscapes for Interpretation of Online Reinforcement Learning Control Algorithms
arXiv:2603.14535v2 Announce Type: replace-cross Abstract: Reinforcement learning has proven its power on various occasions. However, its performance is not always guaranteed when system dynamics change. Instead, it largely relies on users’ empirical experience. For reinforcement learning algorithms with an actor-critic structure, the critic neural network reflects the approximation and optimization process in the RL algorithm. […]
CellxPert: Inference-Time MCMC Steering of a Multi-Omics Single-Cell Foundation Model for In-Silico Perturbation
arXiv:2605.00930v1 Announce Type: new Abstract: In this work, we introduce CellxPert, a scalable multimodal foundation model that unifies single-cell and spatial multi-omics within a common representation space. CellxPert jointly encodes transcriptomic (scRNA-seq), chromatin-accessibility (ATAC-seq), and surface-proteomic (CITE-seq) measurements, while directly incorporating MERFISH and imaging mass-cytometry data as 2D or 3D spatial-visual layers. CellxPert facilitates four […]
Accelerating battery research with an AI interface between FINALES and Kadi4Mat
arXiv:2605.00909v1 Announce Type: new Abstract: The time-consuming formation process critically impacts the longevity of sodium-ion coin cells and End Of Life (EOL) performance. This study aims to optimize formation protocols for duration efficiency, targeting high-performance outcomes while minimizing the number of experiments to reduce resource consumption and accelerate discovery. Specifically, we consider two potentially competing […]
ClinicBot: A Guideline-Grounded Clinical Chatbot with Prioritized Evidence RAG and Verifiable Citations
arXiv:2605.00846v1 Announce Type: new Abstract: Clinical diagnosis requires answers that are accurate, verifiable, and explicitly grounded in official guidelines. While large language models excel at natural language processing, their tendency to hallucinate undermines their utility in high-stakes medical contexts where precision is essential. Existing retrieval-augmented generation (RAG) systems treat all evidence equally, producing noisy context […]
Understanding Emergent Misalignment via Feature Superposition Geometry
arXiv:2605.00842v1 Announce Type: new Abstract: Emergent misalignment, where fine-tuning on narrow, non-harmful tasks induces harmful behaviors, poses a key challenge for AI safety in LLMs. Despite growing empirical evidence, its underlying mechanism remains unclear. To uncover the reason behind this phenomenon, we propose a geometric account based on the geometry of feature superposition. Because features […]
Time-series forecasting through the lens of dynamics
arXiv:2507.15774v2 Announce Type: replace-cross Abstract: While deep learning is facing an homogenization across modalities led by Transformers, they are still challenged by shallow linear models in the time-series forecasting task. Our hypothesis is that models should learn a direct link from past to future data points, which we identify as a learning dynamics capability. We […]
Argumentation for Explainable and Globally Contestable Decision Support with LLMs
arXiv:2603.14643v2 Announce Type: replace Abstract: Large language models (LLMs) exhibit strong general capabilities, but their deployment in high-stakes domains is hindered by their opacity and unpredictability. Recent work has taken meaningful steps towards addressing these issues by augmenting LLMs with post-hoc reasoning based on computational argumentation, providing faithful explanations and enabling users to contest incorrect […]
NaviGNN: Multi-Agent Reinforcement Learning and Graph Neural Network for Sustainable Mobility in Futuristic Smart Cities
arXiv:2507.15143v3 Announce Type: replace Abstract: This paper investigates the feasibility of human mobility in extreme urban morphologies characterized by high-density vertical structures and linear city layouts. To assess whether agents can navigate efficiently within such unprecedented topologies, we develop a hybrid simulation framework integrating agent-based modeling, reinforcement learning (RL), supervised learning, and graph neural networks […]
Fuzzy Fingerprinting Encoder Pre-trained Language Models for Emotion Recognition in Conversations: Human Assessment and Validity Study
arXiv:2605.02665v1 Announce Type: cross Abstract: In Emotion Recognition in Conversations (ERC), model decisions should align with nuanced human perception and ideally provide insights on the classification process. Standard encoder pre-trained language models (PLMs) are the state-of-the-art at these tasks but offer little insight into why a certain prediction is made. This is especially problematic in […]
When Attention Collapses: Residual Evidence Modeling for Compositional Inference
arXiv:2605.02323v1 Announce Type: cross Abstract: Compositional inference – the decomposition of observations into an unknown number of latent components – is central to perception and scientific data analysis. Attention-based models perform well when components are approximately separable, as in object-centric vision. Under additive superposition, however – where multiple components contribute to every observation – we […]
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
arXiv:2604.28123v2 Announce Type: replace-cross Abstract: The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiable rewards (RLVR). However, SFT introduces distributional drift that neither preserves the model’s original capabilities nor faithfully matches the supervision distribution. This problem is further amplified in multimodal reasoning, […]