arXiv:2502.17773v5 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used to simulate survey responses, but synthetic data can be misaligned with the human population, leading to unreliable inference. We develop a general framework that converts LLM-simulated responses into reliable confidence sets for population parameters of human responses, quantifying the uncertainty induced by the […]
Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory
arXiv:2602.06025v2 Announce Type: replace-cross Abstract: Memory is increasingly central to Large Language Model (LLM) agents operating beyond a single context window, yet most existing systems rely on offline, query-agnostic memory construction that can be inefficient and may discard query-critical information. Although runtime memory utilization is a natural alternative, prior work often incurs substantial overhead and […]
Speech Enhancement Based on Drifting Models
arXiv:2604.24199v3 Announce Type: replace-cross Abstract: We propose Speech Enhancement based on Drifting Models (DriftSE), a novel generative framework that formulates denoising as an equilibrium problem. Rather than relying on iterative sampling, DriftSE natively achieves one-step inference by evolving the pushforward distribution of a mapping function to directly match the clean speech distribution. This evolution is […]
JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation
arXiv:2605.04128v2 Announce Type: replace-cross Abstract: We present JoyAI-Image, a unified multimodal foundation model for visual understanding, text-to-image generation, and instruction-guided image editing. JoyAI-Image couples a spatially enhanced Multimodal Large Language Model (MLLM) with a Multimodal Diffusion Transformer (MMDiT), allowing perception and generation to interact through a shared multimodal interface. Around this architecture, we build a […]
Component-Aware Structure-Preserving Style Transfer for Satellite Visual Sim2Real Data Construction
arXiv:2605.19624v2 Announce Type: replace-cross Abstract: For camera-based satellite visual sensing, Sim2Real data construction requires images that approach real-domain sensor appearance while retaining the annotations inherited from simulation. Real sensor images of satellite targets with reliable pose labels and component-level masks are difficult to acquire at scale, whereas synthetic rendering provides exact geometric annotations but suffers […]
Large-Step Training Dynamics of a Two-Factor Linear Transformer Model
arXiv:2605.21292v1 Announce Type: cross Abstract: Gradient-flow analyses show that simplified linear transformers can learn the in-context linear-regression algorithm, but they do not explain the finite-step behavior of gradient descent at large learning rates. Motivated by empirical work on high-learning-rate transformer instabilities and by the cubic-map phase diagram for quadratic regression, we study an exactly reducible […]
Stdlib or Third-Party? Empirical Performance and Correctness of LLM-Assisted Zero-Dependency Python Libraries
arXiv:2605.21405v1 Announce Type: cross Abstract: Third-party Python libraries introduce dependency management overhead, supply chain risk, and deployment friction in constrained environments. A natural question is how much of this ecosystem can be replicated using only Python’s standard library — and at what correctness and performance cost. We address this empirically through zerodep, a growing collection […]
Design of an Automated Ethanol Vapor Generating System for Alcohol Use Disorder(AUD) Animal Studies
arXiv:2502.07860v2 Announce Type: replace Abstract: Alcohol Use Disorder (AUD) is a prevalent addictive disorder affecting an estimated 29.5 million Americans. It is characterized by impaired control over alcohol consumption despite negative consequences. The number of diagnostic criteria met by an individual typically determines the severity of AUD. Research into AUD focuses on understanding individual susceptibility […]
MARS: Modular Agent with Reflective Search for Automated AI Research
arXiv:2602.02660v3 Announce Type: replace Abstract: A critical bottleneck in automating AI research is the execution of complex machine learning engineering (MLE) tasks. MLE differs from general software engineering due to computationally expensive evaluation (e.g., model training) and opaque performance attribution. Current LLM-based agents struggle here, often generating monolithic scripts that ignore execution costs and causal […]
Behavior Cue Reasoning: Monitorable Reasoning Improves Efficiency and Safety through Oversight
arXiv:2605.07021v2 Announce Type: replace Abstract: Reasoning in Large Language Models (LLMs) poses a challenge for oversight as many misaligned behaviors do not surface until reasoning concludes. To address this, we introduce Behavior Cue Reasoning for making LLM reasoning more controllable and monitorable. Behavior Cues are special token sequences that a model is trained to emit […]
Optical Quantum Mixed-State Reconstruction With Multiple Deep Learning Approaches
arXiv:2407.01734v4 Announce Type: replace-cross Abstract: Quantum state tomography is a crucial technique for characterizing the state of a quantum system, which is essential for many applications in quantum technologies. In recent years, there has been growing interest in leveraging neural networks to enhance the efficiency and accuracy of quantum state tomography. However, versatile methods that […]
M3: Conversational LLMs Simplify Secure Clinical Data Access, Understanding, and Analysis
arXiv:2507.01053v4 Announce Type: replace-cross Abstract: Large-scale clinical databases offer opportunities for medical research, but their complexity creates barriers to effective use. The Medical Information Mart for Intensive Care (MIMIC-IV), one of the world’s largest open-source electronic health record databases, traditionally requires both SQL proficiency and clinical domain expertise. We introduce M3, a system that enables […]