Projection-Free Evolution Strategies for Continuous Prompt Search
arXiv:2603.13786v1 Announce Type: new Abstract: Continuous prompt search offers a computationally efficient alternative to conventional parameter tuning in natural language processing tasks. Nevertheless, its practical effectiveness can be significantly hindered by the black-box nature and the inherent high-dimensionality of the...
Knowledge Distillation for Large Language Models
arXiv:2603.13765v1 Announce Type: new Abstract: We propose a resource-efficient framework for compressing large language models through knowledge distillation, combined with guided chain-of-thought reinforcement learning. Using Qwen 3B as the teacher and Qwen 0.5B as the student, we apply knowledge distillation...
LiveWeb-IE: A Benchmark For Online Web Information Extraction
arXiv:2603.13773v1 Announce Type: new Abstract: Web information extraction (WIE) is the task of automatically extracting data from web pages, offering high utility for various applications. The evaluation of WIE systems has traditionally relied on benchmarks built from HTML snapshots captured...
Agent-Based User-Adaptive Filtering for Categorized Harassing Communication
arXiv:2603.13288v1 Announce Type: new Abstract: We propose an agent-based framework for personalized filtering of categorized harassing communication in online social networks. Unlike global moderation systems that apply uniform filtering rules, our approach models user-specific tolerance levels and preferences through adaptive...
GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent
arXiv:2603.13875v1 Announce Type: new Abstract: Many large language model applications require conditioning on long contexts. Transformers typically support this by storing a large per-layer KV-cache of past activations, which incurs substantial memory overhead. A desirable alternative is ompressive memory: read...
sebis at ArchEHR-QA 2026: How Much Can You Do Locally? Evaluating Grounded EHR QA on a Single Notebook
arXiv:2603.13962v1 Announce Type: new Abstract: Clinical question answering over electronic health records (EHRs) can help clinicians and patients access relevant medical information more efficiently. However, many recent approaches rely on large cloud-based models, which are difficult to deploy in clinical...
FLUX: Data Worth Training On
arXiv:2603.13972v1 Announce Type: new Abstract: Modern large language model training is no longer limited by data availability, but by the inability of existing preprocessing pipelines to simultaneously achieve massive scale and high data quality. Current approaches are forced to sacrifice...
Selective Fine-Tuning of GPT Architectures for Parameter-Efficient Clinical Text Classification
arXiv:2603.14183v1 Announce Type: new Abstract: The rapid expansion of electronic health record (EHR) systems has generated large volumes of unstructured clinical narratives that contain valuable information for disease identification, patient cohort discovery, and clinical decision support. Extracting structured knowledge from...
Vavanagi: a Community-run Platform for Documentation of the Hula Language in Papua New Guinea
arXiv:2603.14210v1 Announce Type: new Abstract: We present Vavanagi, a community-run platform for Hula (Vula'a), an Austronesian language of Papua New Guinea with approximately 10,000 speakers. Vavanagi supports crowdsourced English-Hula text translation and voice recording, with elder-led review and community-governed data...
Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring
arXiv:2603.14251v1 Announce Type: new Abstract: Large Reasoning Language Models (LRLMs) demonstrate impressive capabilities on complex tasks by utilizing long Chain-of-Thought reasoning. However, they are prone to overthinking, which generates redundant reasoning steps that degrade both performance and efficiency. Recently, early-exit...
Motivation in Large Language Models
arXiv:2603.14347v1 Announce Type: new Abstract: Motivation is a central driver of human behavior, shaping decisions, goals, and task performance. As large language models (LLMs) become increasingly aligned with human preferences, we ask whether they exhibit something akin to motivation. We...
Extending Minimal Pairs with Ordinal Surprisal Curves and Entropy Across Applied Domains
arXiv:2603.14400v1 Announce Type: new Abstract: The minimal pairs paradigm of comparing model probabilities for contrasting completions has proven useful for evaluating linguistic knowledge in language models, yet its application has largely been confined to binary grammaticality judgments over syntactic phenomena....
Creative Convergence or Imitation? Genre-Specific Homogeneity in LLM-Generated Chinese Literature
arXiv:2603.14430v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in narrative generation. However, they often produce structurally homogenized stories, frequently following repetitive arrangements and combinations of plot events along with stereotypical resolutions. In this paper, we...
Echoes Across Centuries: Phonetic Signatures of Persian Poets
arXiv:2603.14443v1 Announce Type: new Abstract: This study examines phonetic texture in Persian poetry as a literary-historical phenomenon rather than a by-product of meter or a feature used only for classification. The analysis draws on a large corpus of 1,116,306 mesras...
PARSA-Bench: A Comprehensive Persian Audio-Language Model Benchmark
arXiv:2603.14456v1 Announce Type: new Abstract: Persian poses unique audio understanding challenges through its classical poetry, traditional music, and pervasive code-switching - none captured by existing benchmarks. We introduce PARSA-Bench (Persian Audio Reasoning and Speech Assessment Benchmark), the first benchmark for...
Continual Fine-Tuning with Provably Accurate and Parameter-Free Task Retrieval
arXiv:2603.13235v1 Announce Type: new Abstract: Continual fine-tuning aims to adapt a pre-trained backbone to new tasks sequentially while preserving performance on earlier tasks whose data are no longer available. Existing approaches fall into two categories which include input- and parameter-adaptation....
Federated Personal Knowledge Graph Completion with Lightweight Large Language Models for Personalized Recommendations
arXiv:2603.13264v1 Announce Type: new Abstract: Personalized recommendation increasingly relies on private user data, motivating approaches that can adapt to individuals without centralizing their information. We present Federated Targeted Recommendations with Evolving Knowledge graphs and Language Models (FedTREK-LM), a framework that...
CAMEL-CLIP: Channel-aware Multimodal Electroencephalography-text Alignment for Generalizable Brain Foundation Models
arXiv:2603.13272v1 Announce Type: new Abstract: Electroencephalography (EEG) foundation models have shown promise for learning generalizable representations, yet they remain sensitive to channel heterogeneity, such as changes in channel composition or ordering. We propose channel-aware multimodal EEG-text alignment contrastive language-image pretraining...
Learning from Partial Chain-of-Thought via Truncated-Reasoning Self-Distillation
arXiv:2603.13274v1 Announce Type: new Abstract: Reasoning-oriented language models achieve strong performance by generating long chain-of-thought traces at inference time. However, this capability comes with substantial and often excessive computational cost, which can materialize in redundant or inefficient reasoning. We study...
FedUAF: Uncertainty-Aware Fusion with Reliability-Guided Aggregation for Multimodal Federated Sentiment Analysis
arXiv:2603.13291v1 Announce Type: new Abstract: Multimodal sentiment analysis in federated learning environments faces significant challenges due to missing modalities, heterogeneous data distributions, and unreliable client updates. Existing federated approaches often struggle to maintain robust performance under these practical conditions. In...
MS2MetGAN: Latent-space adversarial training for metabolite-spectrum matching in MS/MS database search
arXiv:2603.13342v1 Announce Type: new Abstract: Database search is a widely used approach for identifying metabolites from tandem mass spectra (MS/MS). In this strategy, an experimental spectrum is matched against a user-specified database of candidate metabolites, and candidates are ranked such...
AI-Driven Predictive Maintenance with Real-Time Contextual Data Fusion for Connected Vehicles: A Multi-Dataset Evaluation
arXiv:2603.13343v1 Announce Type: new Abstract: Most vehicle predictive maintenance systems rely exclusively on internal diagnostic signals and are validated on deterministic synthetic data, limiting the credibility of reported metrics. This paper presents a simulation-validated proof-of-concept framework for V2X-augmented predictive maintenance,...
Thermal Robustness of Retrieval in Dense Associative Memories: LSE vs LSR Kernels
arXiv:2603.13350v1 Announce Type: new Abstract: Understanding whether retrieval in dense associative memories survives thermal noise is essential for bridging zero-temperature capacity proofs with the finite-temperature conditions of practical inference and biological computation. We use Monte Carlo simulations to map the...
Elon Musk's xAI sued for turning three girls' real photos into AI CSAM
Discord user led cops to Grok-generated CSAM of real girls, lawsuit says.
Jensen Huang just put Nvidia’s Blackwell and Vera Rubin sales projections into the $1 trillion stratosphere
Nvidia CEO Jensen Huang said he expects $1 trillion worth of orders for the chips.
Elon Musk’s xAI faces child porn lawsuit from minors Grok allegedly undressed
The three plaintiffs are seeking to represent anyone who had real images of them as a minor altered into sexual content by Grok.
How to watch Jensen Huang’s Nvidia GTC 2026 keynote — and what to expect
GTC is Nvidia's flagship annual event, where the chipmaker typically announces new products, partnerships, and its vision for the future of computing. Huang's keynote will focus on Nvidia's role in the future of computing and AI.
Fuse raises $25M to disrupt aging loan origination systems used by US credit unions
The startup also announced a $5 million "rescue fund" to help credit unions ditch legacy software for its AI-native platform.
AI Model Modulation with Logits Redistribution
arXiv:2603.12755v1 Announce Type: new Abstract: Large-scale models are typically adapted to meet the diverse requirements of model owners and users. However, maintaining multiple specialized versions of the model is inefficient. In response, we propose AIM, a novel model modulation paradigm...
An ethical framework for conversational AI in higher education: toward an evidence-based ethical governance