arXiv:2401.07386v5 Announce Type: cross Abstract: This study expands on previous work that introduced the AIcon2abs method (AI from Concrete to Abstract: Demystifying Artificial Intelligence to the general public), an innovative approach designed to increase public understanding of machine learning (ML) across diverse age groups, including K-12 students, and aims to evaluate its effectiveness. AIcon2Abs employs […]
CodegenBench: Can LLMs Write Efficient Code Across Architectures?
arXiv:2606.04023v1 Announce Type: cross Abstract: While large language models (LLMs) have been extensively evaluated on code generation tasks for general-purpose programming and GPU-accelerated environments (e.g., PyTorch, CUDA), their capabilities in CPU-oriented high-performance computing (HPC) across diverse architectures remain underexplored. To bridge this gap, we introduce CodegenBench, a comprehensive benchmark suite designed to evaluate the generation […]
Bayes-Sufficient Representations in Supervised Learning
arXiv:2606.04045v1 Announce Type: cross Abstract: Representation learning is often described as preserving the information in an input that is relevant for prediction. This work asks what relevance means for a fixed supervised decision problem. A representation is defined to be Bayes-sufficient for a joint distribution and loss if some prediction head can use it to […]
LLM Compression with Jointly Optimizing Architectural and Quantization choices
arXiv:2606.04063v1 Announce Type: cross Abstract: Deploying large language models (LLMs) is challenging due to their significant memory and computational requirements. While some methods address this by developing small or tiny language models from scratch, these approaches demand extensive GPU training. Compressing pre-trained LLMs for edge devices offers a compelling alternative. Beyond pruning and quantization, Neural […]
Fog of Love: Engineering Virtuous Agent Behavior with Affinity-based Reinforcement Learning in a Game Environment
arXiv:2606.04750v1 Announce Type: new Abstract: Instilling virtuous behavior in artificial intelligence has seen increasing interest. One of the techniques proposed is known as affinity-based reinforcement learning, which uses policy regularization on the objective function to incentivize virtuous actions without being fully dependent on the reward function design. Thus far, this technique has been demonstrated to […]
AIP: A Graph Representation for Learning and Governing Agent Skills
arXiv:2606.04781v1 Announce Type: new Abstract: Agent Skills today consist largely of free-form prose requiring the agent to read, interpret, and re-derive how to act in every session. This imposes two compounding costs: reduced reliability on implementation-heavy tasks, and difficulty in skill creation and improvement, since editing prose is a fragile process that both humans and […]
AICompanionBench: Benchmarking LLMs-as-Judges for AI Companion Safety
arXiv:2606.04867v1 Announce Type: new Abstract: As AI companion platforms such as Replika and Character.AI rapidly grow, concerns about unsafe human-AI interactions have intensified. This study introduces AICompanionBench, to our knowledge the first publicly available benchmark dataset of human-AI companion conversations annotated with fine-grained safety risk categories. The dataset contains 2,123 real-world Replika conversations collected from […]
Knowledge Index of Noah’s Ark
arXiv:2606.05104v1 Announce Type: new Abstract: Knowledge benchmarks for LLMs face three issues: scaling-driven designs that do not operationalize disciplinary representativeness; flat-payment annotation that permits lazy consensus; and unaudited ranking instability under bounded test budgets. We introduce KINA, an 899-item benchmark across 261 fine-grained disciplines, with two formal results. First, we cast representativeness as a coverage-style […]
SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification
arXiv:2605.13672v1 Announce Type: cross Abstract: Few-shot classification (FSC) is widely used for learning from limited labeled data, yet most evaluations implicitly assume that target concepts are independent of contextual cues. In real-world settings, however, examples often appear within rich contexts, allowing models to exploit spurious correlations between foreground content and background signals. While such effects […]
MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models
arXiv:2606.04027v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) generate text by iteratively denoising partially masked sequences under bidirectional context, exposing a safety surface distinct from autoregressive LLMs. Because mask tokens are native inputs and tokens are committed by confidence rather than position, harmful content can be induced through infilling and outside the monitored […]
Beyond Static Priors: Dynamic Neural Guidance for Large-Scale Ant Colony Optimization
arXiv:2606.04039v1 Announce Type: cross Abstract: Neural-guided Ant Colony Optimization (ACO) suffers from a fundamental training-inference misalignment: policies are typically trained to generate static priors (e.g., heatmaps), yet deployed to guide iterative, long-horizon search processes. In this paper, we present DyNACO, a novel framework that achieves dynamic neural guidance by periodically observing the pheromone distribution and […]
Unlocking Feature Learning in Gated Delta Networks at Scale
arXiv:2606.04048v1 Announce Type: cross Abstract: Training and scaling Large Language Models demand enormous computational resources, motivating both efficient sub-quadratic architectures and principled hyperparameter tuning methods. While the Maximal Update Parametrization ($mu$P) has enabled zero-shot hyperparameter transfer for standard Transformers, its extension to linear models, particularly those with structured state transitions and complicated architectures, remains largely […]