arXiv:2604.14128v2 Announce Type: replace-cross Abstract: Rhetorical questions are asked not to seek information but to persuade or signal stance. How large language models internally represent them remains unclear. We analyze rhetorical questions in LLM representations using linear probes on two social-media datasets with different discourse contexts, and find that rhetorical signals emerge early and are […]
Self-Awareness before Action: Mitigating Logical Inertia via Proactive Cognitive Awareness
arXiv:2604.20413v1 Announce Type: new Abstract: Large language models perform well on many reasoning tasks, yet they often lack awareness of whether their current knowledge or reasoning state is complete. In non-interactive puzzle settings, the narrative is fixed and the underlying structure is hidden; once a model forms an early hypothesis under incomplete premises, it can […]
LaplacianFormer:Rethinking Linear Attention with Laplacian Kernel
arXiv:2604.20368v1 Announce Type: cross Abstract: The quadratic complexity of softmax attention presents a major obstacle for scaling Transformers to high-resolution vision tasks. Existing linear attention variants often replace the softmax with Gaussian kernels to reduce complexity, but such approximations lack theoretical grounding and tend to oversuppress mid-range token interactions. We propose LaplacianFormer, a Transformer variant […]
Response time of lateral predictive coding and benefits of modular structures
arXiv:2604.20524v1 Announce Type: new Abstract: Lateral predictive coding (LPC) is a simple theoretical framework to appreciate feature detection in biological neural circuits. Recent theoretical work [Huang et al., Phys.Rev.E 112, 034304 (2025)] has successfully constructed optimal LPC networks capable of extracting non-Gaussian hidden input features by imposing the tradeoff between energetic cost and information robustness, […]
BenGER: A Collaborative Web Platform for End-to-End Benchmarking of German Legal Tasks
arXiv:2604.13583v2 Announce Type: replace-cross Abstract: Evaluating large language models (LLMs) for legal reasoning requires workflows that span task design, expert annotation, model execution, and metric-based evaluation. In practice, these steps are split across platforms and scripts, limiting transparency, reproducibility, and participation by non-technical legal experts. We present the BenGER (Benchmark for German Law) framework, an […]
pAI/MSc: ML Theory Research with Humans on the Loop
arXiv:2604.20622v1 Announce Type: new Abstract: We present pAI/MSc, an open-source, customizable, modular multi-agent system for academic research workflows. Our goal is not autonomous scientific ideation, nor fully automated research. It is narrower and more practical: to reduce by orders of magnitude the human steering required to turn a specified hypothesis into a literature-grounded, mathematically established, […]
Benefits of Low-Cost Bio-Inspiration in the Age of Overparametrization
arXiv:2604.20365v1 Announce Type: cross Abstract: While Central Pattern Generators (CPGs) and Multi-Layer Perceptrons (MLP) are widely used paradigms in robot control, few systematic studies have been performed on the relative merits of large parameter spaces. In contexts where input and output spaces are small and performance is bounded, having more parameters to optimize may actively […]
Participatory provenance as representational auditing for AI-mediated public consultation
arXiv:2604.20711v1 Announce Type: new Abstract: Artificial intelligence is increasingly deployed to synthesize large-scale public input in policy consultations and participatory processes. Yet no formal framework exists for auditing whether these summaries faithfully represent the source population, an accountability gap that existing approaches to AI explainability, grounding and hallucination detection do not address because they focus […]
PromptEcho: Annotation-Free Reward from Vision-Language Models for Text-to-Image Reinforcement Learning
arXiv:2604.12652v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) can improve the prompt following capability of text-to-image (T2I) models, yet obtaining high-quality reward signals remains challenging: CLIP Score is too coarse-grained, while VLM-based reward models (e.g., RewardDance) require costly human-annotated preference data and additional fine-tuning. We propose PromptEcho, a reward construction method that requires emphno annotation […]
Where and What: Reasoning Dynamic and Implicit Preferences in Situated Conversational Recommendation
arXiv:2604.20749v1 Announce Type: new Abstract: Situated conversational recommendation (SCR), which utilizes visual scenes grounded in specific environments and natural language dialogue to deliver contextually appropriate recommendations, has emerged as a promising research direction due to its close alignment with real-world scenarios. Compared to traditional recommendations, SCR requires a deeper understanding of dynamic and implicit user […]
Bimanual Robot Manipulation via Multi-Agent In-Context Learning
arXiv:2604.20348v1 Announce Type: cross Abstract: Language Models (LLMs) have emerged as powerful reasoning engines for embodied control. In particular, In-Context Learning (ICL) enables off-the-shelf, text-only LLMs to predict robot actions without any task-specific training while preserving their generalization capabilities. Applying ICL to bimanual manipulation remains challenging, as the high-dimensional joint action space and tight inter-arm […]
Automatic Ontology Construction Using LLMs as an External Layer of Memory, Verification, and Planning for Hybrid Intelligent Systems
arXiv:2604.20795v1 Announce Type: new Abstract: This paper presents a hybrid architecture for intelligent systems in which large language models (LLMs) are extended with an external ontological memory layer. Instead of relying solely on parametric knowledge and vector-based retrieval (RAG), the proposed approach constructs and maintains a structured knowledge graph using RDF/OWL representations, enabling persistent, verifiable, […]