arXiv:2601.04505v3 Announce Type: replace Abstract: Generating accurate circuit schematics from high-level natural language descriptions remains a persistent challenge in electronic design automation (EDA), as large language models (LLMs) frequently hallucinate components, violate strict physical constraints, and produce non-machine-readable outputs. To address this, we present CircuitLM, a multi-agent pipeline that translates user prompts into structured, visually […]
In Search of the Ingredients of Open-Endedness: Replicating Picbreeder with Large Vision-Language Models
arXiv:2605.23908v2 Announce Type: replace Abstract: We are in the midst of large-scale industrial and academic efforts to automate the processes of scientific, technological and creative production through AI-driven assistants. Historically, a fundamental property of these processes in their human form has been their open-endedness: their capacity for generating a seemingly endless supply of novel and […]
La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching
arXiv:2507.09466v2 Announce Type: replace-cross Abstract: Recently, many generative models for de novo protein structure design have emerged. Yet, only few tackle the difficult task of directly generating fully atomistic structures jointly with the underlying amino acid sequence. This is challenging, for instance, because the model must reason over side chains that change in length during […]
A Sheaf-Theoretic and Topological Perspective on Complex Network Modeling and Attention Mechanisms in Graph Neural Models
arXiv:2601.21207v3 Announce Type: replace-cross Abstract: Combinatorial and topological structures, such as graphs, simplicial complexes, and cell complexes, form the foundation of geometric and topological deep learning (GDL and TDL) architectures. These models aggregate signals over such domains, integrate local features, and generate representations for diverse real-world applications. However, the distribution and diffusion behavior of GDL […]
Speaking of Language: Reflections on Metalanguage Research in NLP
arXiv:2604.02645v2 Announce Type: replace-cross Abstract: This work aims to shine a spotlight on the topic of metalanguage. We first define metalanguage, link it to NLP and LLMs, and then discuss our two labs’ metalanguage-centered efforts. Finally, we discuss four dimensions of metalanguage and metalinguistic tasks, offering a list of understudied future research directions.
Case-Aware Medical Image Classification with Multimodal Knowledge Graphs and Reliability-Guided Refinement
arXiv:2605.22547v2 Announce Type: replace-cross Abstract: Deep learning has brought significant progress to medical image classification, yet most existing methods still rely on isolated visual evidence and cannot effectively leverage similar cases or external knowledge. In clinical practice, diagnosis is typically supported by similar historical cases and their associated symptoms. To explicitly model this evidence-based diagnostic […]
Extracting Small Translation Specialists from LLMs by Aggressively Pruning Experts
arXiv:2605.28042v1 Announce Type: cross Abstract: Modern large language models (LLMs) achieve state-of-the-art machine translation performance, but they do so as broad generalists largely trained for many tasks and capabilities unrelated to translation. Thus, they are heavily overparameterized for this task, resulting in excessive memory and compute requirements. In this paper, we present a method for […]
Hybrid Neural World Models
arXiv:2605.28317v1 Announce Type: cross Abstract: Neural surrogates promise large speedups over classical solvers for physical dynamics but fail silently at sharp dynamical events such as shocks, fronts, and contact. We present hybrid neural world models for physical dynamics: a recipe for training and deploying multi-horizon surrogates in physical state space, where a single network with […]
Mining Multi-Modality Spatio-Temporal Cues for Video Important Person Identification
arXiv:2605.28604v1 Announce Type: cross Abstract: Identifying key individuals in video scenes is essential for applications such as automated video editing and intelligent surveillance. Current methods primarily focus on static images and immediate visual cues, overlooking the rich spatio-temporal information in videos. This leads to the phenomenon of Temporal Importance Shift (TIS), wherein individuals deemed significant […]
Rethinking Memory as Continuously Evolving Connectivity
arXiv:2605.28773v1 Announce Type: cross Abstract: Existing memory-augmented LLM agents often treat memory as a static repository with pre-defined representations and fixed retrieval pipelines, which is brittle in dynamic agentic environments where feedback, task variation, and heterogeneous signals continuously reshape what should be remembered and how it should be connected. To address this, we propose FluxMem, […]
A Comparative Study of Rule-Based and Data-Driven Approaches in Industrial Monitoring
arXiv:2509.15848v2 Announce Type: replace Abstract: Industrial monitoring systems, especially when deployed in Industry 4.0 environments, are experiencing a shift in paradigm from traditional rule-based architectures to data-driven approaches leveraging machine learning and artificial intelligence. This study presents a comparison between these two methodologies, analyzing their respective strengths, limitations, and application scenarios, and proposes a basic […]
COOP$^2$: Defining, Observing, and Repairing Cooperation in LLM Multi-Agent Systems
arXiv:2603.00349v2 Announce Type: replace Abstract: Many complex tasks require extended effort, diverse capabilities, or coordinated actions beyond what a single agent can provide. However, simply adding more agents does not guarantee better performance, as effective cooperation depends on how agents interact with each other and with task structure to satisfy evolving constraints over time. This […]