arXiv:2506.01158v2 Announce Type: replace-cross Abstract: Simulation-free training frameworks have been at the forefront of the generative modelling revolution in continuous spaces, leading to large-scale diffusion and flow matching models. However, such modern generative models suffer from expensive inference, inhibiting their use in numerous scientific applications like Boltzmann Generators (BGs) for molecular conformations that require fast […]
Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study
arXiv:2506.13464v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown impressive capabilities across tasks such as mathematics, coding, and reasoning, yet their learning ability, which is crucial for adapting to dynamic environments and acquiring new knowledge, remains underexplored. In this work, we address this gap by introducing a framework inspired by cognitive psychology and […]
DSDE: Dynamic Speculative Decoding with KLD Stability for Real-World Serving
arXiv:2509.01083v3 Announce Type: replace-cross Abstract: Speculative decoding accelerates large language model inference, but its reliance on a fixed speculation length is suboptimal in large-batch serving environments with diverse requests. This paper explores a new direction for dynamic adaptation by investigating a novel class of post-hoc, diagnostic signals. We propose Dynamic Speculative Decoding Engine (DSDE), a […]
Epistemic Diversity and Knowledge Collapse in Large Language Models
arXiv:2510.04226v4 Announce Type: replace-cross Abstract: Large language models (LLMs) tend to generate lexically, semantically, and stylistically homogenous texts. This poses a risk of knowledge collapse, where homogenous LLMs mediate a shrinking in the range of accessible information over time. Existing works on homogenization are limited by a focus on closed-ended multiple-choice setups or fuzzy semantic […]
Integrating Genomics into Multimodal EHR Foundation Models
arXiv:2510.23639v2 Announce Type: replace-cross Abstract: This paper introduces an innovative Electronic Health Record (EHR) foundation model that integrates Polygenic Risk Scores (PRS) as a foundational data modality, moving beyond traditional EHR-only approaches to build more holistic health profiles. Leveraging the extensive and diverse data from the All of Us (AoU) Research Program, this multimodal framework […]
Simulating and Experimenting with Social Media Mobilization Using LLM Agents
arXiv:2510.26494v1 Announce Type: cross Abstract: Online social networks have transformed the ways in which political mobilization messages are disseminated, raising new questions about how peer influence operates at scale. Building on the landmark 61-million-person Facebook experiment citepbond201261, we develop an agent-based simulation framework that integrates real U.S. Census demographic distributions, authentic Twitter network topology, and […]
On the number of non-degenerate canalizing Boolean functions
arXiv:2510.26556v1 Announce Type: cross Abstract: Canalization is a key organizing principle in complex systems, particularly in gene regulatory networks. It describes how certain input variables exert dominant control over a function’s output, thereby imposing hierarchical structure and conferring robustness to perturbations. Degeneracy, in contrast, captures redundancy among input variables and reflects the complete dominance of […]
ResMatching: Noise-Resilient Computational Super-Resolution via Guided Conditional Flow Matching
arXiv:2510.26601v1 Announce Type: cross Abstract: Computational Super-Resolution (CSR) in fluorescence microscopy has, despite being an ill-posed problem, a long history. At its very core, CSR is about finding a prior that can be used to extrapolate frequencies in a micrograph that have never been imaged by the image-generating microscope. It stands to reason that, with […]
Process Integrated Computer Vision for Real-Time Failure Prediction in Steel Rolling Mill
arXiv:2510.26684v1 Announce Type: cross Abstract: We present a long-term deployment study of a machine vision-based anomaly detection system for failure prediction in a steel rolling mill. The system integrates industrial cameras to monitor equipment operation, alignment, and hot bar motion in real time along the process line. Live video streams are processed on a centralized […]
ExpertFlow: Adaptive Expert Scheduling and Memory Coordination for Efficient MoE Inference
arXiv:2510.26730v1 Announce Type: cross Abstract: The expansion of large language models is increasingly limited by the constrained memory capacity of modern GPUs. To mitigate this, Mixture-of-Experts (MoE) architectures activate only a small portion of parameters during inference, significantly lowering both memory demand and computational overhead. However, conventional MoE inference approaches, which select active experts independently […]