arXiv:2604.08203v1 Announce Type: cross Abstract: Medical Vision-Language Models (VLMs) hold immense promise for complex clinical tasks, but their reasoning capabilities are often constrained by text-only paradigms that fail to ground inferences in visual evidence. This limitation not only curtails performance on tasks requiring fine-grained visual analysis but also introduces risks of visual hallucination in safety-critical […]
Can Vision Language Models Judge Action Quality? An Empirical Evaluation
arXiv:2604.08294v1 Announce Type: cross Abstract: Action Quality Assessment (AQA) has broad applications in physical therapy, sports coaching, and competitive judging. Although Vision Language Models (VLMs) hold considerable promise for AQA, their actual performance in this domain remains largely uncharacterised. We present a comprehensive evaluation of state-of-the-art VLMs across activity domains (e.g. fitness, figure skating, diving), […]
Dead Weights, Live Signals: Feedforward Graphs of Frozen Language Models
arXiv:2604.08335v1 Announce Type: cross Abstract: We present a feedforward graph architecture in which heterogeneous frozen large language models serve as computational nodes, communicating through a shared continuous latent space via learned linear projections. Building on recent work demonstrating geometric compatibility between independently trained LLM latent spaces~citearmstrong2026thinking, we extend this finding from static two-model steering to […]
ADAPTive Input Training for Many-to-One Pre-Training on Time-Series Classification
arXiv:2604.08398v1 Announce Type: cross Abstract: Recent work on time-series models has leveraged self-supervised training to learn meaningful features and patterns in order to improve performance on downstream tasks and generalize to unseen modalities. While these pretraining methods have shown great promise in one-to-many scenarios, where a model is pre-trained on one dataset and fine-tuned on […]
A Quasi-Regression Method for the Mediation Analysis of Zero-Inflated Single-Cell Data
arXiv:2604.08507v1 Announce Type: cross Abstract: Recent advances in single-cell technologies have advanced our understanding of gene regulation and cellular heterogeneity at single-cell resolution. Single-cell data contain both gene expression levels and the proportion of expressing cells, which makes them structurally different from bulk data. Currently, methodological work on causal mediation analysis for single-cell data remains […]
Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts
arXiv:2604.08541v1 Announce Type: cross Abstract: Multimodal Mixture-of-Experts (MoE) models have achieved remarkable performance on vision-language tasks. However, we identify a puzzling phenomenon termed Seeing but Not Thinking: models accurately perceive image content yet fail in subsequent reasoning, while correctly solving identical problems presented as pure text. Through systematic analysis, we first verify that cross-modal semantic […]
Emergent complexity and rhythms in evoked and spontaneous dynamics of human whole-brain models after tuning through analysis tools
arXiv:2509.12873v2 Announce Type: replace Abstract: The simulation of whole-brain dynamics should reproduce realistic spontaneous and evoked neural activity across different scales, including emergent rhythms, spatio-temporal activation patterns, and macroscale complexity. Once a mathematical model is selected, its configuration must be determined by properly setting its parameters. A critical preliminary step in this process is defining […]
Rhizome OS-1: Rhizome’s Semi-Autonomous Operating System for Small Molecule Drug Discovery
arXiv:2604.07512v1 Announce Type: new Abstract: We introduce a semi-autonomous discovery system in which multi-modal AI agents function as a multi-disciplinary discovery team, acting as computational chemists, medicinal chemists, and patent agents, writing and executing analysis code, visually evaluating molecular candidates, assessing patentability, and adapting generation strategy from empirical screening feedback, while r1, a 246M-parameter Graph […]
DSCA: Dynamic Subspace Concept Alignment for Lifelong VLM Editing
arXiv:2604.07965v1 Announce Type: cross Abstract: Model editing aims to update knowledge to add new concepts and change relevant information without retraining. Lifelong editing is a challenging task, prone to disrupting previously learned concepts, especially for Vision Language Models (VLMs), because sequential edits can lead to degraded reasoning and cross modal misalignment. Existing VLM knowledge editing […]
DQA: Diagnostic Question Answering for IT Support
arXiv:2604.05350v2 Announce Type: replace-cross Abstract: Enterprise IT support interactions are fundamentally diagnostic: effective resolution requires iterative evidence gathering from ambiguous user reports to identify an underlying root cause. While retrieval-augmented generation (RAG) provides grounding through historical cases, standard multi-turn RAG systems lack explicit diagnostic state and therefore struggle to accumulate evidence and resolve competing hypotheses […]
Employing Deep Neural Operators for PDE control by decoupling training and optimization
arXiv:2506.04742v3 Announce Type: replace-cross Abstract: Neural networks have been applied to control problems, typically by combining data, differential equation residuals, and objective costs in the training loss or by incorporating auxiliary architectural components. Instead, we propose a streamlined approach that decouples the control problem from the training process, rendering these additional layers of complexity unnecessary. […]
DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs
arXiv:2601.07994v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) increasingly operate over long-form dialogues with frequent topic shifts. While recent LLMs support extended context windows, efficient management of dialogue history in practice is needed due to inference cost and latency constraints. We present DyCP, a lightweight context management method implemented outside the LLM that dynamically […]