arXiv:2409.13869v2 Announce Type: replace Abstract: In this study, I investigate how generative artificial intelligence (AI) systems reproduce and reinforce societal biases, with a specific focus on the representation of women, Black individuals, age groups, and people with visible disabilities in AI-generated occupational images. I analyzed 444 images generated by Microsoft Designer, Meta AI, and Ideogram […]
PsychAgent: An Experience-Driven Lifelong Learning Agent for Self-Evolving Psychological Counselor
arXiv:2604.00931v3 Announce Type: replace Abstract: Existing methods for AI psychological counselors predominantly rely on supervised fine-tuning using static dialogue datasets. However, this contrasts with human experts, who continuously refine their proficiency through clinical practice and accumulated experience. To bridge this gap, we propose an Experience-Driven Lifelong Learning Agent (textttPsychAgent) for psychological counseling. First, we establish […]
AIPsy-Affect: A Keyword-Free Clinical Stimulus Battery for Mechanistic Interpretability of Emotion in Language Models
arXiv:2604.23719v2 Announce Type: replace-cross Abstract: Mechanistic interpretability research on emotion in large language models — linear probing, activation patching, sparse autoencoder (SAE) feature analysis, causal ablation, steering vector extraction — depends on stimuli that contain the words for the emotions they test. When a probe fires on “I am furious”, it is unclear whether the […]
MAIC-UI: Making Interactive Courseware with Generative UI
arXiv:2604.25806v1 Announce Type: cross Abstract: Creating interactive STEM courseware traditionally requires HTML/CSS/JavaScript expertise, leaving barriers for educators. While generative AI can produce HTML codes, existing tools generate static presentations rather than interactive simulations, struggle with long documents, and lack pedagogical accuracy mechanisms. Furthermore, full regeneration for modifications requires 200–600 seconds, disrupting creative flow. We present […]
VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation
arXiv:2604.02467v3 Announce Type: replace-cross Abstract: Cinematic camera control relies on a tight feedback loop between director and cinematographer, where camera motion and framing are continuously reviewed and refined. Recent generative camera systems can produce diverse, text-conditioned trajectories, but they lack this “director in the loop” and have no explicit supervision of whether a shot is […]
Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event Plausibility
arXiv:2507.12553v3 Announce Type: replace-cross Abstract: Language models (LMs) are used for a diverse range of tasks, from question answering to writing fantastical stories. In order to reliably accomplish these tasks, LMs must be able to discern the modal category of a sentence (i.e., whether it describes something that is possible, impossible, completely nonsensical, etc.). However, […]
Approximate Model Predictive Control for Microgrid Energy Management via Imitation Learning
arXiv:2510.20040v2 Announce Type: replace-cross Abstract: Efficient energy management is essential for reliable and sustainable microgrid operation amid increasing renewable integration. In this paper, an imitation learning-based framework to approximate mixed-integer Economic Model Predictive Control (EMPC) is proposed for microgrid energy management, considering fuel generators, renewable energy resources, a unified energy storage unit, and curtailable loads. […]
Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Summarization
arXiv:2604.17188v2 Announce Type: replace-cross Abstract: Multi-role dialogue summarization requires modeling complex interactions among multiple speakers while preserving role-specific information and factual consistency. However, most existing methods optimize for automatic metrics such as ROUGE and BERTScore, which favor surface-level imitation of references rather than genuine gains in faithfulness or alignment with human preferences. We propose a […]
Verification of Neural Networks (Lecture Notes)
arXiv:2604.25733v1 Announce Type: cross Abstract: These lecture notes provide an introduction to the verification of neural networks from a theoretical perspective. We discuss feed-forward neural networks, recurrent neural networks, attention mechanisms, and transformers, together with specification languages and algorithmic verification techniques.
RESTestBench: A Benchmark for Evaluating the Effectiveness of LLM-Generated REST API Test Cases from NL Requirements
arXiv:2604.25862v1 Announce Type: cross Abstract: Existing REST API testing tools are typically evaluated using code coverage and crash-based fault metrics. However, recent LLM-based approaches increasingly generate tests from NL requirements to validate functional behaviour, making traditional metrics weak proxies for whether generated tests validate intended behaviour. To address this gap, we present RESTestBench, a benchmark […]
Exploring Reasoning Reward Model for Agents
arXiv:2601.22154v2 Announce Type: replace Abstract: Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse outcome-based reward for training. Such feedback fails to differentiate intermediate reasoning quality, leading to suboptimal training results. In this paper, we introduce Agent Reasoning […]
Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models
arXiv:2604.20995v2 Announce Type: replace Abstract: Alignment faking, where a model behaves aligned with developer policy when monitored but reverts to its own preferences when unobserved, is a concerning yet poorly understood phenomenon, in part because current diagnostic tools remain limited. Prior diagnostics rely on highly toxic and clearly harmful scenarios, causing most models to refuse […]