arXiv:2605.25293v1 Announce Type: cross Abstract: Autonomous driving perception demands accurate and efficient processing of three-dimensional sensor data under strict power constraints. Traditional convolutional neural networks achieve strong detection accuracy but are computationally intensive, limiting their suitability for deployment on resource-constrained neuromorphic platforms. Spiking neural networks offer a compelling alternative through event-driven sparse computation, yet their […]
SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction
arXiv:2605.23440v2 Announce Type: replace-cross Abstract: Joint Entity and Relation Extraction (JERE) is highly susceptible to weak generalization due to low-quality training data. Data augmentation is a common strategy to enhance model generalization across different domains. However, existing data augmentation methods often overlook text relevance and may disrupt semantic structures and dependencies, making it difficult to […]
QUIET: A Multi-Blank Cascaded Story Cloze Benchmark for LLM Creative Generation Capability
arXiv:2605.25955v1 Announce Type: cross Abstract: Large language models (LLMs) face a dual challenge in creative capability evaluation: existing benchmarks (e.g., Story Cloze Test, HellaSwag) measure models’ discriminative ability over narrative continuation using multiple-choice recognition paradigms, rather than directly measuring creative generation capability; rubric-based scoring and LLM-as-Judge methods rely on subjective dimension assessment or natural language […]
Contractual Skills: A GovernSpec Design Framework for Enterprise AI Agents
arXiv:2605.22634v2 Announce Type: replace-cross Abstract: Skills have become a practical packaging mechanism for agent instructions, workflows, scripts, and reference materials. In enterprise settings, however, a skill often needs to express more than task guidance: goals, input boundaries, permissions, human approval points, evidence requirements, output contracts, quality criteria, verification steps, and handoff rules. This paper proposes […]
Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare
arXiv:2509.07961v2 Announce Type: replace Abstract: We develop new experimental paradigms for measuring welfare in language models. We compare verbal reports of models about their preferences with preferences expressed through behavior when navigating a virtual environment and selecting conversation topics. We also test how costs and rewards affect behavior and whether responses to an eudaimonic welfare […]
Positivity in classical enumerative geometry: a case study in synchronized AI-assisted mathematics
arXiv:2605.25271v1 Announce Type: cross Abstract: We study the symmetric polynomial $prod_alphain A_n,dbigl(1+alpha_1 x_1+cdots+alpha_n x_nbigr)$ where $A_n,d:=\alphainmathbbZ_ge 0^n:$, which is the total Chern class of $mathrmSym^d(mathbbC^n)$, viewed as a torus representation whose Chern roots are the weights $alpha_1 x_1+cdots+alpha_n x_n$ for $alphain A_n,d$. Its homogeneous degree-$k$ part $c_k(n,d)$ is the $k$-th Chern class of $mathrmSym^d(mathbbC^n)$. These […]
When Skills Don’t Help: A Negative Result on Procedural Knowledge for Tool-Grounded Agents in Offensive Cybersecurity
arXiv:2605.20023v2 Announce Type: replace Abstract: Agent Skills, structured packages of procedural knowledge loaded into an LLM agent at inference time, are widely reported to improve task pass rates by an average of 16.2~percentage points across diverse domains. Yet the same benchmarks show wide variance, with 16 of 84 tasks suffering negative deltas when Skills are […]
Action with Visual Primitives
arXiv:2605.22183v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for generalist robotic manipulation. A common design in current architectures maps language instructions and visual observations to actions in a single forward pass. While conceptually simple, this formulation entangles instruction comprehension, spatial scene understanding, and motor control within a single learning […]
Membership Inference Attacks on Tokenizers of Large Language Models
arXiv:2510.05699v4 Announce Type: replace-cross Abstract: Membership inference attacks (MIAs) are widely used to assess the privacy risks associated with machine learning models. However, when these attacks are applied to pre-trained large language models (LLMs), they encounter significant challenges, including mislabeled samples, distribution shifts, and discrepancies in model size between experimental and real-world settings. To address […]
Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning
arXiv:2605.25267v1 Announce Type: cross Abstract: Safe in-context reinforcement learning (ICRL) adapts online from interaction history without test-time parameter updates while controlling episode cost under a safety budget. Under out-of-distribution (OOD) deployment shifts, pretraining-only safe ICRL can give poor reward-safety tradeoffs because the remaining budget affects behavior only through frozen policy conditioning, not an explicit action-level […]
Multimodal Crystal Flow: Any-to-Any Modality Generation for Unified Crystal Modeling
arXiv:2602.20210v3 Announce Type: replace-cross Abstract: Crystal modeling spans a family of conditional and unconditional generation tasks, including crystal structure prediction (CSP) and de novo generation (DNG). While recent deep generative models have shown promising performance, they remain largely task-specific, lacking a unified framework that shares crystal representations across tasks. To address this limitation, we propose […]
Ordering Matters: Rank-Aware Selective Fusion for Blended Emotion Recognition
arXiv:2605.21417v2 Announce Type: replace-cross Abstract: Blended emotion recognition is challenging because emotions are often expressed as mixtures of subtle and overlapping multimodal cues rather than a single dominant signal. We propose a rank-aware multi-encoder framework that selectively combines complementary representations from diverse pre-extracted video and audio encoders. Our method projects heterogeneous encoder features into a […]