arXiv:2604.25847v1 Announce Type: cross Abstract: Optimization modeling underpins real-world decision-making in logistics, manufacturing, energy, and public services, but reliably solving such problems from natural-language requirements remains challenging for current large language models (LLMs). In this paper, we propose emphAgora-Opt, a modular agentic framework for optimization modeling that combines decentralized debate with a read-write memory bank. […]
A Comparative Study in Surgical AI: Datasets, Foundation Models, and Barriers to Med-AGI
arXiv:2603.27341v2 Announce Type: replace Abstract: Recent Artificial Intelligence (AI) models have matched or exceeded human experts in several benchmarks of biomedical task performance, but surgical benchmarks in particular are often missing from prominent medical benchmark suites (specifically, those requiring visual recognition). Since surgery requires integrating disparate tasks, generally-capable AI models could be particularly attractive as […]
At the Edge of the Heart: ULP FPGA-Based CNN for On-Device Cardiac Feature Extraction in Smart Health Sensors for Astronauts
arXiv:2604.25799v1 Announce Type: cross Abstract: The convergence of accelerating human spaceflight ambitions and critical terrestrial health monitoring demands is driving unprecedented requirements for reliable, real-time feature extraction on extremely resource-constrained wearable health sensors. We present an ultra-low-power (ULP) Field-Programmable Gate Array (FPGA) based solution for real-time Seismocardiography (SCG) feature classification using Convolutional Neural Networks (CNNs). […]
How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum
arXiv:2604.25907v1 Announce Type: cross Abstract: Adapting reasoning models to new tasks during post-training with only output-level supervision stalls under reinforcement learning from verifiable rewards (RLVR) when the initial success probability $p_0$ is small. Using the Tsallis $q$-logarithm, we define a loss family $J_Q$ that interpolates between RLVR (at $q=0$, the exploitation pole) and the log-marginal-likelihood […]
DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA
arXiv:2603.29844v2 Announce Type: replace-cross Abstract: The development of Vision-Language-Action (VLA) models has been significantly accelerated by pre-trained Vision-Language Models (VLMs). However, most existing end-to-end VLAs treat the VLM primarily as a multimodal encoder, directly mapping vision-language features to low-level actions. This paradigm underutilizes the VLM’s potential in high-level decision making and introduces training instability, frequently […]
K-SENSE: A Knowledge-Guided Self-Augmented Encoder for Neuro-Semantic Evaluation of Mental Health Conditions on Social Media
arXiv:2604.23493v2 Announce Type: replace-cross Abstract: Early detection of mental health conditions, particularly stress and depression, from social media text remains a challenging open problem in computational psychiatry and natural language processing. Automated systems must contend with figurative language, implicit emotional expression, and the high noise inherent in user-generated content. Existing approaches either leverage external commonsense […]
From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models
arXiv:2510.18030v2 Announce Type: replace-cross Abstract: Structured pruning is a practical approach to deploying large language models (LLMs) efficiently, as it yields compact, hardware-friendly architectures. However, the dominant local paradigm is task-agnostic: by optimizing layer-wise reconstruction rather than task objectives, it tends to preserve perplexity or generic zero-shot behavior but fails to capitalize on modest task-specific […]
Learning Unified Control of Intrinsic Nonlinear Spin Dynamics in Atomic Qudits for Magnetometry
arXiv:2603.28421v2 Announce Type: replace-cross Abstract: Generating and preserving metrologically useful quantum states is a central challenge in quantum-enhanced metrology. In low-field atomic magnetometry with multilevel atoms, the nonlinear Zeeman (NLZ) effect is both a resource and a limitation. It can generate internal spin squeezing within a single atomic qudit, but under fixed readout it also […]
LLM-ReSum: A Framework for LLM Reflective Summarization through Self-Evaluation
arXiv:2604.25665v1 Announce Type: cross Abstract: Reliable evaluation of large language model (LLM)-generated summaries remains an open challenge, particularly across heterogeneous domains and document lengths. We conduct a comprehensive meta-evaluation of 14 automatic summarization metrics and LLM-based evaluators across seven datasets spanning five domains, covering documents from short news articles to long scientific, governmental, and legal […]
Zoom In, Reason Out: Efficient Far-field Anomaly Detection in Expressway Surveillance Videos via Focused VLM Reasoning Guided by Bayesian Inference
arXiv:2604.23724v2 Announce Type: replace-cross Abstract: Expressway video anomaly detection is essential for safety management. However, identifying anomalies across diverse scenes remains challenging, particularly for far-field targets exhibiting subtle abnormal vehicle motions. While Vision-Language Models (VLMs) demonstrate strong semantic reasoning capabilities, processing global frames causes attention dilution for these far-field objects and incurs prohibitive computational costs. […]
CORAL: Adaptive Retrieval Loop for Culturally-Aligned Multilingual RAG
arXiv:2604.25676v1 Announce Type: cross Abstract: Multilingual retrieval-augmented generation (mRAG) is often implemented within a fixed retrieval space, typically via query or document translation or multilingual embedding vector representations. However, this approach may be inadequate for culturally grounded queries, in which retrieval-condition misalignment may occur. Even strong retrievers and generators may struggle to produce culturally relevant […]
Spreadsheet Modeling Experiments Using GPTs on Small Problem Statements and the Wall Task
arXiv:2604.25689v1 Announce Type: cross Abstract: This paper investigates how GPT-based tools can assist in building reusable analytical spreadsheet models. After a screening, we evaluate five GPT extensions and select Excel AI by pulsrai.com for detailed testing. Through structured experiments on simple problem statements, we assess Excel AI’s performance against the ERFR criteria (each input in […]