arXiv:2603.22325v1 Announce Type: cross Abstract: Recurrent neural networks (RNNs) and self-attention are both widely used sequence-mixing layers that maintain an internal memory. However, this memory is constructed using two orthogonal mechanisms: RNNs compress the entire past into a fixed-size state, whereas self-attention’s state stores every past time step growing its state (the KV cache) linearly […]
Computational Arbitrage in AI Model Markets
arXiv:2603.22404v1 Announce Type: new Abstract: Consider a market of competing model providers selling query access to models with varying costs and capabilities. Customers submit problem instances and are willing to pay up to a budget for a verifiable solution. An arbitrageur efficiently allocates inference budget across providers to undercut the market, thus creating a competitive […]
Biased Error Attribution in Multi-Agent Human-AI Systems Under Delayed Feedback
arXiv:2603.23419v1 Announce Type: cross Abstract: Human decision-making is strongly influenced by cognitive biases, particularly under conditions of uncertainty and risk. While prior work has examined bias in single-step decisions with immediate outcomes and in human interaction with a single autonomous agent, comparatively little attention has been paid to decision-making under delayed outcomes involving multiple AI […]
Causal Direct Preference Optimization for Distributionally Robust Generative Recommendation
arXiv:2603.22335v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) guides large language models (LLMs) to generate recommendations aligned with user historical behavior distributions by minimizing preference alignment loss. However, our systematic empirical research and theoretical analysis reveal that DPO tends to amplify spurious correlations caused by environmental confounders during the alignment process, significantly undermining the […]
Subspace Tensor Orthogonal Rotation Model (STORM) for Batch Alignment, Cell Type Deconvolution, and Gene Imputation in Spatial Transcriptomic Data
arXiv:2603.22477v1 Announce Type: new Abstract: Spatial transcriptomics data analysis integrates cellular transcriptional activity with spatial coordinates to identify spatial domains, infer cell-type dynamics, and characterize gene expression patterns within tissues. Despite recent advances, significant challenges remain, including the treatment of batch effects, the handling of mixed cell-type signals, and the imputation of poorly measured or […]
WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement
arXiv:2603.22352v1 Announce Type: cross Abstract: Recent progress in reinforcement learning with verifiable rewards (RLVR) offers a practical path to self-improvement of language models, but existing methods face a key trade-off: endogenous self-play can drift over iterations, while corpus-grounded approaches rely on curated data environments. We present textbfWIST, a textbfWeb-grounded textbfIterative textbfSelf-play textbfTree framework for domain-targeted […]
Morphology-Aware Peptide Discovery via Masked Conditional Generative Modeling
arXiv:2509.02060v4 Announce Type: replace Abstract: Peptide self-assembly prediction offers a powerful bottom-up strategy for designing biocompatible, low-toxicity materials for large-scale synthesis in a broad range of biomedical and energy applications. However, screening the vast sequence space for categorization of aggregate morphology remains intractable. We introduce PepMorph, an end-to-end peptide discovery pipeline that generates novel sequences […]
Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents
arXiv:2602.02050v3 Announce Type: replace Abstract: Tool-using agents based on Large Language Models (LLMs) excel in tasks such as mathematical reasoning and multi-hop question answering. However, in long trajectories, agents often trigger excessive and low-quality tool calls, increasing latency and degrading inference performance, making managing tool-use behavior challenging. In this work, we conduct entropy-based pilot experiments […]
Modelling SARS-CoV-2 epidemics via compartmental and cellular automaton SEIRS model with temporal immunity and vaccination
arXiv:2603.22498v1 Announce Type: new Abstract: We consider the SEIRS epidemiology model with such features of the COVID-19 outbreak as: abundance of unidentified infected individuals, limited time of immunity and a possibility of vaccination. The control of the pandemic dynamics is possible by restricting the transmission rate, increasing identification and isolation rate of infected individuals, and […]
FAAR: Format-Aware Adaptive Rounding for NVFP4
arXiv:2603.22370v1 Announce Type: cross Abstract: Deploying large language models (LLMs) on edge devices requires extremely low-bit quantization. Ultra-low precision formats such as NVFP4 offer a promising solution for reducing memory footprint and accelerating computation. However, existing quantization methods typically rely on conventional rounding strategies and fail to account for the non-uniformity of the NVFP4 numerical […]
Towards Intelligent Geospatial Data Discovery: a knowledge graph-driven multi-agent framework powered by large language models
arXiv:2603.20670v2 Announce Type: replace Abstract: The rapid growth in the volume, variety, and velocity of geospatial data has created data ecosystems that are highly distributed, heterogeneous, and semantically inconsistent. Existing data catalogs, portals, and infrastructures still rely largely on keyword-based search with limited semantic support, which often fails to capture user intent and leads to […]
Abnormalities and Disease Detection in Gastro-Intestinal Tract Images
arXiv:2603.22378v1 Announce Type: cross Abstract: Gastrointestinal (GI) tract image analysis plays a crucial role in medical diagnosis. This research addresses the challenge of accurately classifying and segmenting GI images for real-time applications, where traditional methods often struggle due to the diversity and complexity of abnormalities. The high computational demands of this domain require efficient and […]