LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning
arXiv:2604.02338v1 Announce Type: new Abstract: MoE-PEFT methods combine Mixture of Experts with parameter-efficient fine-tuning for multi-task adaptation, but require separate adapters per expert causing trainable parameters to scale linearly with expert count and limiting applicability to adapter-based architectures. We propose...
What oral argument told us in the birthright citizenship case
Empirical SCOTUS is a recurring series by Adam Feldman that looks at Supreme Court data, primarily in the form of opinions and oral arguments, to provide insights into the justices’ decision making and […]The postWhat oral argument told us in...
Robust Graph Representation Learning via Adaptive Spectral Contrast
arXiv:2604.01878v1 Announce Type: new Abstract: Spectral graph contrastive learning has emerged as a unified paradigm for handling both homophilic and heterophilic graphs by leveraging high-frequency components. However, we identify a fundamental spectral dilemma: while high-frequency signals are indispensable for encoding...
A Reliability Evaluation of Hybrid Deterministic-LLM Based Approaches for Academic Course Registration PDF Information Extraction
arXiv:2604.00003v1 Announce Type: cross Abstract: This study evaluates the reliability of information extraction approaches from KRS documents using three strategies: LLM only, Hybrid Deterministic - LLM (regex + LLM), and a Camelot based pipeline with LLM fallback. Experiments were conducted...
Beyond Logit Adjustment: A Residual Decomposition Framework for Long-Tailed Reranking
arXiv:2604.01506v1 Announce Type: new Abstract: Long-tailed classification, where a small number of frequent classes dominate many rare ones, remains challenging because models systematically favor frequent classes at inference time. Existing post-hoc methods such as logit adjustment address this by adding...
Sven: Singular Value Descent as a Computationally Efficient Natural Gradient Method
arXiv:2604.01279v1 Announce Type: new Abstract: We introduce Sven (Singular Value dEsceNt), a new optimization algorithm for neural networks that exploits the natural decomposition of loss functions into a sum over individual data points, rather than reducing the full loss to...
Decision-Centric Design for LLM Systems
arXiv:2604.00414v1 Announce Type: new Abstract: LLM systems must make control decisions in addition to generating outputs: whether to answer, clarify, retrieve, call tools, repair, or escalate. In many current architectures, these decisions remain implicit within generation, entangling assessment and action...
Transformer self-attention encoder-decoder with multimodal deep learning for response time series forecasting and digital twin support in wind structural health monitoring
arXiv:2604.01712v1 Announce Type: new Abstract: The wind-induced structural response forecasting capabilities of a novel transformer methodology are examined here. The model also provides a digital twin component for bridge structural health monitoring. Firstly, the approach uses the temporal characteristics of...
Human-in-the-Loop Control of Objective Drift in LLM-Assisted Computer Science Education
arXiv:2604.00281v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly embedded in computer science education through AI-assisted programming tools, yet such workflows often exhibit objective drift, in which locally plausible outputs diverge from stated task specifications. Existing instructional responses...
Who is driving the conversation at the Supreme Court?
Empirical SCOTUS is a recurring series by Adam Feldman that looks at Supreme Court data, primarily in the form of opinions and oral arguments, to provide insights into the justices’ decision making and […]The postWho is driving the conversation at...
Court appears sympathetic to death-row inmate’s attempt to challenge racial discrimination in jury selection
The Supreme Court on Tuesday seemed sympathetic to a Mississippi man who argues that a district attorney violated the Constitution’s ban on racial discrimination in jury selection. Terry Pitchford is […]The postCourt appears sympathetic to death-row inmate’s attempt to challenge...
Two-Stage Optimizer-Aware Online Data Selection for Large Language Models
arXiv:2604.00001v1 Announce Type: cross Abstract: Gradient-based data selection offers a principled framework for estimating sample utility in large language model (LLM) fine-tuning, but existing methods are mostly designed for offline settings. They are therefore less suited to online fine-tuning, where...
Court to hear argument on claim of racial discrimination in jury selection
The Supreme Court will hear oral argument on Tuesday in Pitchford v. Cain, the case of a Mississippi man who contends that he was sentenced to death in violation of […]The postCourt to hear argument on claim of racial discrimination...
Berta: an open-source, modular tool for AI-enabled clinical documentation
arXiv:2603.23513v1 Announce Type: new Abstract: Commercial AI scribes cost \$99-600 per physician per month, operate as opaque systems, and do not return data to institutional infrastructure, limiting organizational control over data governance, quality improvement, and clinical workflows. We developed Berta,...
S-Path-RAG: Semantic-Aware Shortest-Path Retrieval Augmented Generation for Multi-Hop Knowledge Graph Question Answering
arXiv:2603.23512v1 Announce Type: new Abstract: We present S-Path-RAG, a semantic-aware shortest-path Retrieval-Augmented Generation framework designed to improve multi-hop question answering over large knowledge graphs. S-Path-RAG departs from one-shot, text-heavy retrieval by enumerating bounded-length, semantically weighted candidate paths using a hybrid...
MDKeyChunker: Single-Call LLM Enrichment with Rolling Keys and Key-Based Restructuring for High-Accuracy RAG
arXiv:2603.23533v1 Announce Type: new Abstract: RAG pipelines typically rely on fixed-size chunking, which ignores document structure, fragments semantic units across boundaries, and requires multiple LLM calls per chunk for metadata extraction. We present MDKeyChunker, a three-stage pipeline for Markdown documents...
StateLinFormer: Stateful Training Enhancing Long-term Memory in Navigation
arXiv:2603.23571v1 Announce Type: new Abstract: Effective navigation intelligence relies on long-term memory to support both immediate generalization and sustained adaptation. However, existing approaches face a dilemma: modular systems rely on explicit mapping but lack flexibility, while Transformer-based end-to-end models are...
Probabilistic Geometric Alignment via Bayesian Latent Transport for Domain-Adaptive Foundation Models
arXiv:2603.23783v1 Announce Type: new Abstract: Adapting large-scale foundation models to new domains with limited supervision remains a fundamental challenge due to latent distribution mismatch, unstable optimization dynamics, and miscalibrated uncertainty propagation. This paper introduces an uncertainty-aware probabilistic latent transport framework...
Off-Policy Safe Reinforcement Learning with Constrained Optimistic Exploration
arXiv:2603.23889v1 Announce Type: new Abstract: When safety is formulated as a limit of cumulative cost, safe reinforcement learning (RL) aims to learn policies that maximize return subject to the cost constraint in data collection and deployment. Off-policy safe RL methods,...
AgriPestDatabase-v1.0: A Structured Insect Dataset for Training Agricultural Large Language Model
arXiv:2603.22777v1 Announce Type: new Abstract: Agricultural pest management increasingly relies on timely and accurate access to expert knowledge, yet high quality labeled data and continuous expert support remain limited, particularly for farmers operating in rural regions with unstable/no internet connectivity....
AI Mental Models: Learned Intuition and Deliberation in a Bounded Neural Architecture
arXiv:2603.22561v1 Announce Type: new Abstract: This paper asks whether a bounded neural architecture can exhibit a meaningful division of labor between intuition and deliberation on a classic 64-item syllogistic reasoning benchmark. More broadly, the benchmark is relevant to ongoing debates...
Benchmarking Multi-Agent LLM Architectures for Financial Document Processing: A Comparative Study of Orchestration Patterns, Cost-Accuracy Tradeoffs and Production Scaling Strategies
arXiv:2603.22651v1 Announce Type: new Abstract: The adoption of large language models (LLMs) for structured information extraction from financial documents has accelerated rapidly, yet production deployments face fundamental architectural decisions with limited empirical guidance. We present a systematic benchmark comparing four...
Intelligence Inertia: Physical Principles and Applications
arXiv:2603.22347v1 Announce Type: new Abstract: While Landauer's principle establishes the fundamental thermodynamic floor for information erasure and Fisher Information provides a metric for local curvature in parameter space, these classical frameworks function effectively only as approximations within regimes of sparse...
STEM Agent: A Self-Adapting, Tool-Enabled, Extensible Architecture for Multi-Protocol AI Agent Systems
arXiv:2603.22359v1 Announce Type: new Abstract: Current AI agent frameworks commit early to a single interaction protocol, a fixed tool integration strategy, and static user models, limiting their deployment across diverse interaction paradigms. To address these constraints, we introduce STEM Agent...
Separating Diagnosis from Control: Auditable Policy Adaptation in Agent-Based Simulations with LLM-Based Diagnostics
arXiv:2603.22904v1 Announce Type: new Abstract: Mitigating elderly loneliness requires policy interventions that achieve both adaptability and auditability. Existing methods struggle to reconcile these objectives: traditional agent-based models suffer from static rigidity, while direct large language model (LLM) controllers lack essential...
HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature
arXiv:2603.23136v1 Announce Type: new Abstract: Automated knowledge graph (KG) construction is essential for navigating the rapidly expanding body of scientific literature. However, existing approaches struggle to recognize long multi-word entities, often fail to generalize across domains, and typically overlook the...
Where can AI be used? Insights from a deep ontology of work activities
arXiv:2603.20619v1 Announce Type: new Abstract: Artificial intelligence (AI) is poised to profoundly reshape how work is executed and organized, but we do not yet have deep frameworks for understanding where AI can be used. Here we provide a comprehensive ontology...
Profit is the Red Team: Stress-Testing Agents in Strategic Economic Interactions
arXiv:2603.20925v1 Announce Type: new Abstract: As agentic systems move into real-world deployments, their decisions increasingly depend on external inputs such as retrieved content, tool outputs, and information provided by other actors. When these inputs can be strategically shaped by adversaries,...
LLM-Driven Heuristic Synthesis for Industrial Process Control: Lessons from Hot Steel Rolling
arXiv:2603.20537v1 Announce Type: new Abstract: Industrial process control demands policies that are interpretable and auditable, requirements that black-box neural policies struggle to meet. We study an LLM-driven heuristic synthesis framework for hot steel rolling, in which a language model iteratively...