One Size Does Not Fit All: Token-Wise Adaptive Compression for KV Cache
arXiv:2603.04411v1 Announce Type: new Abstract: Despite the remarkable progress of Large Language Models (LLMs), the escalating memory footprint of the Key-Value (KV) cache remains a critical bottleneck for efficient inference. While dimensionality reduction offers a promising compression avenue, existing approaches...
The Thinking Boundary: Quantifying Reasoning Suitability of Multimodal Tasks via Dual Tuning
arXiv:2603.04415v1 Announce Type: new Abstract: While reasoning-enhanced Large Language Models (LLMs) have demonstrated remarkable advances in complex tasks such as mathematics and coding, their effectiveness across universal multimodal scenarios remains uncertain. The trend of releasing parallel "Instruct" and "Thinking" models...
Do Mixed-Vendor Multi-Agent LLMs Improve Clinical Diagnosis?
arXiv:2603.04421v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems have emerged as a promising approach for clinical diagnosis, leveraging collaboration among agents to refine medical reasoning. However, most existing frameworks rely on single-vendor teams (e.g., multiple agents from...
Generating Realistic, Protocol-Compliant Maritime Radio Dialogues using Self-Instruct and Low-Rank Adaptation
arXiv:2603.04423v1 Announce Type: new Abstract: VHF radio miscommunication remains a major safety risk in maritime operations, with human factors accounting for over 58% of recorded incidents in Europe between 2014 and 2023. Despite decades of operational use, VHF radio communications...
Induced Numerical Instability: Hidden Costs in Multimodal Large Language Models
arXiv:2603.04453v1 Announce Type: new Abstract: The use of multimodal large language models has become widespread, and as such the study of these models and their failure points has become of utmost importance. We study a novel mode of failure that...
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning
arXiv:2603.04597v1 Announce Type: new Abstract: Large language models (LLMs) typically receive diverse natural language (NL) feedback through interaction with the environment. However, current reinforcement learning (RL) algorithms rely solely on scalar rewards, leaving the rich information in NL feedback underutilized...
Detection of Illicit Content on Online Marketplaces using Large Language Models
arXiv:2603.04707v1 Announce Type: new Abstract: Online marketplaces, while revolutionizing global commerce, have inadvertently facilitated the proliferation of illicit activities, including drug trafficking, counterfeit sales, and cybercrimes. Traditional content moderation methods such as manual reviews and rule-based automated systems struggle with...
TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings
arXiv:2603.04772v1 Announce Type: new Abstract: Despite the exceptional reasoning capabilities of Multimodal Large Language Models (MLLMs), their adaptation into universal embedding models is significantly impeded by task conflict. To address this, we propose TSEmbed, a universal multimodal embedding framework that...
Autoscoring Anticlimax: A Meta-analytic Understanding of AI's Short-answer Shortcomings and Wording Weaknesses
arXiv:2603.04820v1 Announce Type: new Abstract: Automated short-answer scoring lags other LLM applications. We meta-analyze 890 culminating results across a systematic review of LLM short-answer scoring studies, modeling the traditional effect size of Quadratic Weighted Kappa (QWK) with mixed effects metaregression....
SinhaLegal: A Benchmark Corpus for Information Extraction and Analysis in Sinhala Legislative Texts
arXiv:2603.04854v1 Announce Type: new Abstract: SinhaLegal introduces a Sinhala legislative text corpus containing approximately 2 million words across 1,206 legal documents. The dataset includes two types of legal documents: 1,065 Acts dated from 1981 to 2014 and 141 Bills from...
Free Lunch for Pass@$k$? Low Cost Diverse Sampling for Diffusion Language Models
arXiv:2603.04893v1 Announce Type: new Abstract: Diverse outputs in text generation are necessary for effective exploration in complex reasoning tasks, such as code generation and mathematical problem solving. Such Pass@$k$ problems benefit from distinct candidates covering the solution space. However, traditional...
Can LLMs Capture Expert Uncertainty? A Comparative Analysis of Value Alignment in Ethnographic Qualitative Research
arXiv:2603.04897v1 Announce Type: new Abstract: Qualitative analysis of open-ended interviews plays a central role in ethnographic and economic research by uncovering individuals' values, motivations, and culturally embedded financial behaviors. While large language models (LLMs) offer promising support for automating and...
AILS-NTUA at SemEval-2026 Task 3: Efficient Dimensional Aspect-Based Sentiment Analysis
arXiv:2603.04933v1 Announce Type: new Abstract: In this paper, we present AILS-NTUA system for Track-A of SemEval-2026 Task 3 on Dimensional Aspect-Based Sentiment Analysis (DimABSA), which encompasses three complementary problems: Dimensional Aspect Sentiment Regression (DimASR), Dimensional Aspect Sentiment Triplet Extraction (DimASTE),...
When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger
arXiv:2603.04968v1 Announce Type: new Abstract: Preference alignment is an essential step in adapting large language models (LLMs) to human values, but existing approaches typically depend on costly human annotations or large-scale API-based models. We explore whether a weak LLM can...
MPCEval: A Benchmark for Multi-Party Conversation Generation
arXiv:2603.04969v1 Announce Type: new Abstract: Multi-party conversation generation, such as smart reply and collaborative assistants, is an increasingly important capability of generative AI, yet its evaluation remains a critical bottleneck. Compared to two-party dialogue, multi-party settings introduce distinct challenges, including...
Thin Keys, Full Values: Reducing KV Cache via Low-Dimensional Attention Selection
arXiv:2603.04427v1 Announce Type: new Abstract: Standard transformer attention uses identical dimensionality for queries, keys, and values ($d_q = d_k = d_v = \dmodel$). Our insight is that these components serve fundamentally different roles, and this symmetry is unnecessary. Queries and...
Flowers: A Warp Drive for Neural PDE Solvers
arXiv:2603.04430v1 Announce Type: new Abstract: We introduce Flowers, a neural architecture for learning PDE solution operators built entirely from multihead warps. Aside from pointwise channel mixing and a multiscale scaffold, Flowers use no Fourier multipliers, no dot-product attention, and no...
ZorBA: Zeroth-order Federated Fine-tuning of LLMs with Heterogeneous Block Activation
arXiv:2603.04436v1 Announce Type: new Abstract: Federated fine-tuning of large language models (LLMs) enables collaborative tuning across distributed clients. However, due to the large size of LLMs, local updates in federated learning (FL) may incur substantial video random-access memory (VRAM) usage....
Learning Unified Distance Metric for Heterogeneous Attribute Data Clustering
arXiv:2603.04458v1 Announce Type: new Abstract: Datasets composed of numerical and categorical attributes (also called mixed data hereinafter) are common in real clustering tasks. Differing from numerical attributes that indicate tendencies between two concepts (e.g., high and low temperature) with their...
VSPrefill: Vertical-Slash Sparse Attention with Lightweight Indexing for Long-Context Prefilling
arXiv:2603.04460v1 Announce Type: new Abstract: The quadratic complexity of self-attention during the prefill phase impedes long-context inference in large language models. Existing sparse attention methods face a trade-off among context adaptivity, sampling overhead, and fine-tuning costs. We propose VSPrefill, a...
Understanding the Dynamics of Demonstration Conflict in In-Context Learning
arXiv:2603.04464v1 Announce Type: new Abstract: In-context learning enables large language models to perform novel tasks through few-shot demonstrations. However, demonstrations per se can naturally contain noise and conflicting examples, making this capability vulnerable. To understand how models process such conflicts,...
Activity Recognition from Smart Insole Sensor Data Using a Circular Dilated CNN
arXiv:2603.04477v1 Announce Type: new Abstract: Smart insoles equipped with pressure sensors, accelerometers, and gyroscopes offer a non-intrusive means of monitoring human gait and posture. We present an activity classification system based on a circular dilated convolutional neural network (CDCNN) that...
Standing on the Shoulders of Giants: Rethinking EEG Foundation Model Pretraining via Multi-Teacher Distillation
arXiv:2603.04478v1 Announce Type: new Abstract: Pretraining for electroencephalogram (EEG) foundation models has predominantly relied on self-supervised masked reconstruction, a paradigm largely adapted from and inspired by the success of vision and language foundation models. However, unlike images and text, EEG...
An LLM-Guided Query-Aware Inference System for GNN Models on Large Knowledge Graphs
arXiv:2603.04545v1 Announce Type: new Abstract: Efficient inference for graph neural networks (GNNs) on large knowledge graphs (KGs) is essential for many real-world applications. GNN inference queries are computationally expensive and vary in complexity, as each involves a different number of...
A Late-Fusion Multimodal AI Framework for Privacy-Preserving Deduplication in National Healthcare Data Environments
arXiv:2603.04595v1 Announce Type: new Abstract: Duplicate records pose significant challenges in customer relationship management (CRM)and healthcare, often leading to inaccuracies in analytics, impaired user experiences, and compliance risks. Traditional deduplication methods rely heavily on direct identifiers such as names, emails,...
PDE foundation model-accelerated inverse estimation of system parameters in inertial confinement fusion
arXiv:2603.04606v1 Announce Type: new Abstract: PDE foundation models are typically pretrained on large, diverse corpora of PDE datasets and can be adapted to new settings with limited task-specific data. However, most downstream evaluations focus on forward problems, such as autoregressive...
When Sensors Fail: Temporal Sequence Models for Robust PPO under Sensor Drift
arXiv:2603.04648v1 Announce Type: new Abstract: Real-world reinforcement learning systems must operate under distributional drift in their observation streams, yet most policy architectures implicitly assume fully observed and noise-free states. We study robustness of Proximal Policy Optimization (PPO) under temporally persistent...
Engineering Regression Without Real-Data Training: Domain Adaptation for Tabular Foundation Models Using Multi-Dataset Embeddings
arXiv:2603.04692v1 Announce Type: new Abstract: Predictive modeling in engineering applications has long been dominated by bespoke models and small, siloed tabular datasets, limiting the applicability of large-scale learning approaches. Despite recent progress in tabular foundation models, the resulting synthetic training...
The Untold Story of the Proto-Smith Era: Justice O’Connor’s Papers and the Court’s Free Exercise Revolution
Justice O’Connor’s recently released Supreme Court papers reveal the untold story of how the Court systematically dismantled religious accommodation protections in the decade leading up to Employment Division v. Smith. While Smith’s abandonment of strict scrutiny for neutral, generally applicable...