FMI@SU ToxHabits: Evaluating LLMs Performance on Toxic Habit Extraction in Spanish Clinical Texts
arXiv:2604.06403v1 Announce Type: new Abstract: The paper presents an approach for the recognition of toxic habits named entities in Spanish clinical texts. The approach was developed for the ToxHabits Shared Task. Our team participated in subtask 1, which aims to...
ART: Attention Replacement Technique to Improve Factuality in LLMs
arXiv:2604.06393v1 Announce Type: new Abstract: Hallucination in large language models (LLMs) continues to be a significant issue, particularly in tasks like question answering, where models often generate plausible yet incorrect or irrelevant information. Although various methods have been proposed to...
Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
arXiv:2604.06210v1 Announce Type: new Abstract: As LLMs are globally deployed, aligning their cultural value orientations is critical for safety and user engagement. However, existing benchmarks face the Construct-Composition-Context ($C^3$) challenge: relying on discriminative, multiple-choice formats that probe value knowledge rather...
The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning
arXiv:2604.06427v1 Announce Type: new Abstract: The viability of chain-of-thought (CoT) monitoring hinges on models being unable to reason effectively in their latent representations. Yet little is known about the limits of such latent reasoning in LLMs. We test these limits...
Scoring Edit Impact in Grammatical Error Correction via Embedded Association Graphs
arXiv:2604.06573v1 Announce Type: new Abstract: A Grammatical Error Correction (GEC) system produces a sequence of edits to correct an erroneous sentence. The quality of these edits is typically evaluated against human annotations. However, a sentence may admit multiple valid corrections,...
Illocutionary Explanation Planning for Source-Faithful Explanations in Retrieval-Augmented Language Models
arXiv:2604.06211v1 Announce Type: new Abstract: Natural language explanations produced by large language models (LLMs) are often persuasive, but not necessarily scrutable: users cannot easily verify whether the claims in an explanation are supported by evidence. In XAI, this motivates a...
State-of-the-Art Arabic Language Modeling with Sparse MoE Fine-Tuning and Chain-of-Thought Distillation
arXiv:2604.06421v1 Announce Type: new Abstract: This paper introduces Arabic-DeepSeek-R1, an application-driven open-source Arabic LLM that leverages a sparse MoE backbone to address the digital equity gap for under-represented languages, and establishes a new SOTA across the entire Open Arabic LLM...
Limits of Difficulty Scaling: Hard Samples Yield Diminishing Returns in GRPO-Tuned SLMs
arXiv:2604.06298v1 Announce Type: new Abstract: Recent alignment work on Large Language Models (LLMs) suggests preference optimization can improve reasoning by shifting probability mass toward better solutions. We test this claim in a resource-constrained setting by applying GRPO with LoRA to...
Hallucination as output-boundary misclassification: a composite abstention architecture for language models
arXiv:2604.06195v1 Announce Type: new Abstract: Large language models often produce unsupported claims. We frame this as a misclassification error at the output boundary, where internally generated completions are emitted as if they were grounded in evidence. This motivates a composite...
The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models
arXiv:2604.06374v1 Announce Type: new Abstract: Latent reasoning via continuous chain-of-thoughts (Latent CoT) has emerged as a promising alternative to discrete CoT reasoning. Operating in continuous space increases expressivity and has been hypothesized to enable superposition: the ability to maintain multiple...
Astropad’s Workbench reimagines remote desktop for AI agents, not IT support
Astropad’s Workbench lets users remotely monitor and control AI agents on Mac Minis from iPhone or iPad, with low-latency streaming and mobile access.
Dynamic Agentic AI Expert Profiler System Architecture for Multidomain Intelligence Modeling
arXiv:2604.05345v1 Announce Type: new Abstract: In today's artificial intelligence driven world, modern systems communicate with people from diverse backgrounds and skill levels. For human-machine interaction to be meaningful, systems must be aware of context and user expertise. This study proposes...
ActivityEditor: Learning to Synthesize Physically Valid Human Mobility
arXiv:2604.05529v1 Announce Type: new Abstract: Human mobility modeling is indispensable for diverse urban applications. However, existing data-driven methods often suffer from data scarcity, limiting their applicability in regions where historical trajectories are unavailable or restricted. To bridge this gap, we...
Memory Dial: A Training Framework for Controllable Memorization in Language Models
arXiv:2604.05074v1 Announce Type: new Abstract: Memorization in language models is widely studied but remains difficult to isolate and control. Understanding when and what models memorize is essential for explaining their predictions, yet existing approaches are post-hoc: they can detect memorization...
CODESTRUCT: Code Agents over Structured Action Spaces
arXiv:2604.05407v1 Announce Type: new Abstract: LLM-based code agents treat repositories as unstructured text, applying edits through brittle string matching that frequently fails due to formatting drift or ambiguous patterns. We propose reframing the codebase as a structured action space where...
Extending Tabular Denoising Diffusion Probabilistic Models for Time-Series Data Generation
arXiv:2604.05257v1 Announce Type: new Abstract: Diffusion models are increasingly being utilised to create synthetic tabular and time series data for privacy-preserving augmentation. Tabular Denoising Diffusion Probabilistic Models (TabDDPM) generate high-quality synthetic data from heterogeneous tabular datasets but assume independence between...
Optimal-Transport-Guided Functional Flow Matching for Turbulent Field Generation in Hilbert Space
arXiv:2604.05700v1 Announce Type: new Abstract: High-fidelity modeling of turbulent flows requires capturing complex spatiotemporal dynamics and multi-scale intermittency, posing a fundamental challenge for traditional knowledge-based systems. While deep generative models, such as diffusion models and Flow Matching, have shown promising...
DualDiffusion: A Speculative Decoding Strategy for Masked Diffusion Models
arXiv:2604.05250v1 Announce Type: new Abstract: Masked Diffusion Models (MDMs) offer a promising alternative to autoregressive language models by enabling parallel token generation and bidirectional context modeling. However, their inference speed is significantly limited by the inability to cache key-value pairs...
FastDiSS: Few-step Match Many-step Diffusion Language Model on Sequence-to-Sequence Generation--Full Version
arXiv:2604.05551v1 Announce Type: new Abstract: Self-conditioning has been central to the success of continuous diffusion language models, as it allows models to correct previous errors. Yet its ability degrades precisely in the regime where diffusion is most attractive for deployment:...
Instruction-Tuned LLMs for Parsing and Mining Unstructured Logs on Leadership HPC Systems
arXiv:2604.05168v1 Announce Type: new Abstract: Leadership-class HPC systems generate massive volumes of heterogeneous, largely unstructured system logs. Because these logs originate from diverse software, hardware, and runtime layers, they exhibit inconsistent formats, making structure extraction and pattern discovery extremely challenging....
Channel-wise Retrieval for Multivariate Time Series Forecasting
arXiv:2604.05543v1 Announce Type: new Abstract: Multivariate time series forecasting often struggles to capture long-range dependencies due to fixed lookback windows. Retrieval-augmented forecasting addresses this by retrieving historical segments from memory, but existing approaches rely on a channel-agnostic strategy that applies...
Bypassing the CSI Bottleneck: MARL-Driven Spatial Control for Reflector Arrays
arXiv:2604.05162v1 Announce Type: new Abstract: Reconfigurable Intelligent Surfaces (RIS) are pivotal for next-generation smart radio environments, yet their practical deployment is severely bottlenecked by the intractable computational overhead of Channel State Information (CSI) estimation. To bypass this fundamental physical-layer barrier,...
From Governance Norms to Enforceable Controls: A Layered Translation Method for Runtime Guardrails in Agentic AI
arXiv:2604.05229v1 Announce Type: new Abstract: Agentic AI systems plan, use tools, maintain state, and produce multi-step trajectories with external effects. Those properties create a governance problem that differs materially from single-turn generative AI: important risks emerge dur- ing execution, not...
A mathematical theory of evolution for self-designing AIs
arXiv:2604.05142v1 Announce Type: new Abstract: As artificial intelligence systems (AIs) become increasingly produced by recursive self-improvement, a form of evolution may emerge, in which the traits of AI systems are shaped by the success of earlier AIs in designing and...
Training Without Orthogonalization, Inference With SVD: A Gradient Analysis of Rotation Representations
arXiv:2604.05414v1 Announce Type: new Abstract: Recent work has shown that removing orthogonalization during training and applying it only at inference improves rotation estimation in deep learning, with empirical evidence favoring 9D representations with SVD projection. However, the theoretical understanding of...
Controllable Image Generation with Composed Parallel Token Prediction
arXiv:2604.05730v1 Announce Type: new Abstract: Conditional discrete generative models struggle to faithfully compose multiple input conditions. To address this, we derive a theoretically-grounded formulation for composing discrete probabilistic generative processes, with masked generation (absorbing diffusion) as a special case. Our...
Territory Paint Wars: Diagnosing and Mitigating Failure Modes in Competitive Multi-Agent PPO
arXiv:2604.04983v1 Announce Type: new Abstract: We present Territory Paint Wars, a minimal competitive multi-agent reinforcement learning environment implemented in Unity, and use it to systematically investigate failure modes of Proximal Policy Optimisation (PPO) under self-play. A first agent trained for...
Bivariate Causal Discovery Using Rate-Distortion MDL: An Information Dimension Approach
arXiv:2604.05829v1 Announce Type: new Abstract: Approaches to bivariate causal discovery based on the minimum description length (MDL) principle approximate the (uncomputable) Kolmogorov complexity of the models in each causal direction, selecting the one with the lower total complexity. The premise...
Multi-Drafter Speculative Decoding with Alignment Feedback
arXiv:2604.05417v1 Announce Type: new Abstract: Speculative decoding (SD) accelerates large language model (LLM) inference by using a smaller model to draft future tokens, which are then verified by the target LLM. This preserves generation quality by accepting only aligned tokens....
ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning
arXiv:2604.05355v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning improves large language model performance on complex tasks, but often produces excessively long and inefficient reasoning traces. Existing methods shorten CoTs using length penalties or global entropy reduction, implicitly assuming that low...