Are Large Language Models Truly Smarter Than Humans?
arXiv:2603.16197v1 Announce Type: new Abstract: Public leaderboards increasingly suggest that large language models (LLMs) surpass human experts on benchmarks spanning academic knowledge, law, and programming. Yet most benchmarks are fully public, their questions widely mirrored across the internet, creating systematic...
Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning
arXiv:2603.16127v1 Announce Type: new Abstract: We investigate the role of learning rate scheduling in the large-scale pre-training of large language models, focusing on its influence on downstream performance after supervised fine-tuning (SFT). Decay-based learning rate schedulers are widely used to...
SciZoom: A Large-scale Benchmark for Hierarchical Scientific Summarization across the LLM Era
arXiv:2603.16131v1 Announce Type: new Abstract: The explosive growth of AI research has created unprecedented information overload, increasing the demand for scientific summarization at multiple levels of granularity beyond traditional abstracts. While LLMs are increasingly adopted for summarization, existing benchmarks remain...
PyPhonPlan: Simulating phonetic planning with dynamic neural fields and task dynamics
arXiv:2603.16299v1 Announce Type: new Abstract: We introduce PyPhonPlan, a Python toolkit for implementing dynamical models of phonetic planning using coupled dynamic neural fields and task dynamic simulations. The toolkit provides modular components for defining planning, perception and memory fields, as...
PashtoCorp: A 1.25-Billion-Word Corpus, Evaluation Suite, and Reproducible Pipeline for Low-Resource Language Development
arXiv:2603.16354v1 Announce Type: new Abstract: We present PashtoCorp, a 1.25-billion-word corpus for Pashto, a language spoken by 60 million people that remains severely underrepresented in NLP. The corpus is assembled from 39 sources spanning seven HuggingFace datasets and 32 purpose-built...
IndexRAG: Bridging Facts for Cross-Document Reasoning at Index Time
arXiv:2603.16415v1 Announce Type: new Abstract: Multi-hop question answering (QA) requires reasoning across multiple documents, yet existing retrieval-augmented generation (RAG) approaches address this either through graph-based methods requiring additional online processing or iterative multi-step reasoning. We present IndexRAG, a novel approach...
VQKV: High-Fidelity and High-Ratio Cache Compression via Vector-Quantization
arXiv:2603.16435v1 Announce Type: new Abstract: The growing context length of Large Language Models (LLMs) enlarges the Key-Value (KV) cache, limiting deployment in resource-limited environments. Prior training-free approaches for KV cache compression typically rely on low-rank approximation or scalar quantization, which...
DynHD: Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learning
arXiv:2603.16459v1 Announce Type: new Abstract: Diffusion large language models (D-LLMs) have emerged as a promising alternative to auto-regressive models due to their iterative refinement capabilities. However, hallucinations remain a critical issue that hinders their reliability. To detect hallucination responses from...
AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents
arXiv:2603.16496v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external memory to support long-horizon interaction, personalized assistance, and multi-step reasoning. However, existing memory systems still face three core challenges: they often rely too heavily on semantic...
DanceHA: A Multi-Agent Framework for Document-Level Aspect-Based Sentiment Analysis
arXiv:2603.16546v1 Announce Type: new Abstract: Aspect-Based Sentiment Intensity Analysis (ABSIA) has garnered increasing attention, though research largely focuses on domain-specific, sentence-level settings. In contrast, document-level ABSIA--particularly in addressing complex tasks like extracting Aspect-Category-Opinion-Sentiment-Intensity (ACOSI) tuples--remains underexplored. In this work, we...
Alternating Reinforcement Learning with Contextual Rubric Rewards
arXiv:2603.15646v1 Announce Type: new Abstract: Reinforcement Learning with Rubric Rewards (RLRR) is a framework that extends conventional reinforcement learning from human feedback (RLHF) and verifiable rewards (RLVR) by replacing scalar preference signals with structured, multi-dimensional, contextual rubric-based evaluations. However, existing...
Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning
arXiv:2603.15842v1 Announce Type: new Abstract: Modern machine learning systems increasingly rely on sensitive data, creating significant privacy, security, and regulatory risks that existing privacy-preserving machine learning (ppML) techniques, such as Differential Privacy (DP) and Homomorphic Encryption (HE), address only at...
Federated Learning for Privacy-Preserving Medical AI
arXiv:2603.15901v1 Announce Type: new Abstract: This dissertation investigates privacy-preserving federated learning for Alzheimer's disease classification using three-dimensional MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Existing methodologies often suffer from unrealistic data partitioning, inadequate privacy guarantees, and insufficient benchmarking,...
Auto Researching, not hyperparameter tuning: Convergence Analysis of 10,000 Experiments
arXiv:2603.15916v1 Announce Type: new Abstract: When LLM agents autonomously design ML experiments, do they perform genuine architecture search -- or do they default to hyperparameter tuning within a narrow region of the design space? We answer this question by analyzing...
Discovery of interaction and diffusion kernels in particle-to-mean-field multi-agent systems
arXiv:2603.15927v1 Announce Type: new Abstract: We propose a data-driven framework to learn interaction kernels in stochastic multi-agent systems. Our approach aims at identifying the functional form of nonlocal interaction and diffusion terms directly from trajectory data, without any a priori...
Collaborative Temporal Feature Generation via Critic-Free Reinforcement Learning for Cross-User Sensor-Based Activity Recognition
arXiv:2603.16043v1 Announce Type: new Abstract: Human Activity Recognition using wearable inertial sensors is foundational to healthcare monitoring, fitness analytics, and context-aware computing, yet its deployment is hindered by cross-user variability arising from heterogeneous physiological traits, motor habits, and sensor placements....
Functorial Neural Architectures from Higher Inductive Types
arXiv:2603.16123v1 Announce Type: new Abstract: Neural networks systematically fail at compositional generalization -- producing correct outputs for novel combinations of known parts. We show that this failure is architectural: compositional generalization is equivalent to functoriality of the decoder, and this...
InterventionLens: A Multi-Agent Framework for Detecting ASD Intervention Strategies in Parent-Child Shared Reading
arXiv:2603.13710v1 Announce Type: new Abstract: Home-based interventions like parent-child shared reading provide a cost-effective approach for supporting children with autism spectrum disorder (ASD). However, analyzing caregiver intervention strategies in naturalistic home interactions typically relies on expert annotation, which is costly,...
Early Rug Pull Warning for BSC Meme Tokens via Multi-Granularity Wash-Trading Pattern Profiling
arXiv:2603.13830v1 Announce Type: new Abstract: The high-frequency issuance and short-cycle speculation of meme tokens in decentralized finance (DeFi) have significantly amplified rug-pull risk. Existing approaches still struggle to provide stable early warning under scarce anomalies, incomplete labels, and limited interpretability....
The AI Fiction Paradox
arXiv:2603.13545v1 Announce Type: new Abstract: AI development has a fiction dependency problem: models are built on massive corpora of modern fiction and desperately need more of it, yet they struggle to generate it. I term this the AI-Fiction Paradox and...
vla-eval: A Unified Evaluation Harness for Vision-Language-Action Models
arXiv:2603.13966v1 Announce Type: new Abstract: Vision Language Action VLA models are typically evaluated using per benchmark scripts maintained independently by each model repository, leading to duplicated code, dependency conflicts, and underspecified protocols. We present vla eval, an open source evaluation...
How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing
arXiv:2603.13259v1 Announce Type: new Abstract: When a language model is fed a wrong answer, what happens inside the network? Current understanding treats truthfulness as a static property of individual-layer representations-a direction to be probed, a feature to be extracted. Less...
Intelligent Materials Modelling: Large Language Models Versus Partial Least Squares Regression for Predicting Polysulfone Membrane Mechanical Performance
arXiv:2603.13834v1 Announce Type: new Abstract: Predicting the mechanical properties of polysulfone (PSF) membranes from structural descriptors remains challenging due to extreme data scarcity typical of experimental studies. To investigate this issue, this study benchmarked knowledge-driven inference using four large language...
Privacy Preserving Topic-wise Sentiment Analysis of the Iran Israel USA Conflict Using Federated Transformer Models
arXiv:2603.13655v1 Announce Type: new Abstract: The recent escalation of the Iran Israel USA conflict in 2026 has triggered widespread global discussions across social media platforms. As people increasingly use these platforms for expressing opinions, analyzing public sentiment from these discussions...
Benchmarking Large Language Models on Reference Extraction and Parsing in the Social Sciences and Humanities
arXiv:2603.13651v1 Announce Type: new Abstract: Bibliographic reference extraction and parsing are foundational for citation indexing, linking, and downstream scholarly knowledge-graph construction. However, most established evaluations focus on clean, English, end-of-document bibliographies, and therefore underrepresent the Social Sciences and Humanities (SSH),...
A Dual-Path Generative Framework for Zero-Day Fraud Detection in Banking Systems
arXiv:2603.13237v1 Announce Type: new Abstract: High-frequency banking environments face a critical trade-off between low-latency fraud detection and the regulatory explainability demanded by GDPR. Traditional rule-based and discriminative models struggle with "zero-day" attacks due to extreme class imbalance and the lack...
TheraAgent: Multi-Agent Framework with Self-Evolving Memory and Evidence-Calibrated Reasoning for PET Theranostics
arXiv:2603.13676v1 Announce Type: new Abstract: PET theranostics is transforming precision oncology, yet treatment response varies substantially; many patients receiving 177Lu-PSMA radioligand therapy (RLT) for metastatic castration-resistant prostate cancer (mCRPC) fail to respond, demanding reliable pre-therapy prediction. While LLM-based agents have...
Executable Archaeology: Reanimating the Logic Theorist from its IPL-V Source
arXiv:2603.13514v1 Announce Type: new Abstract: The Logic Theorist (LT), created by Allen Newell, J. C. Shaw, and Herbert Simon in 1955-1956, is widely regarded as the first artificial intelligence program. While the original conceptual model was described in 1956, it...
The ARC of Progress towards AGI: A Living Survey of Abstraction and Reasoning
arXiv:2603.13372v1 Announce Type: new Abstract: The Abstraction and Reasoning Corpus (ARC-AGI) has become a key benchmark for fluid intelligence in AI. This survey presents the first cross-generation analysis of 82 approaches across three benchmark versions and the ARC Prize 2024-2025...
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...