arXiv:2506.11526v3 Announce Type: replace-cross Abstract: For autonomous vehicles, safe navigation in complex environments depends on handling a broad range of diverse and rare driving scenarios. Simulation- and scenario-based testing have emerged as key approaches to development and validation of autonomous driving systems. Traditional scenario generation relies on rule-based systems, knowledge-driven models, and data-driven synthesis, often […]
Autiverse: Eliciting Autistic Adolescents’ Daily Narratives through AI-guided Multimodal Journaling
arXiv:2509.17466v3 Announce Type: replace-cross Abstract: Journaling can potentially serve as an effective method for autistic adolescents to improve narrative skills. However, its text-centric nature and high executive functioning demands present barriers to practice. We present Autiverse, an AI-guided multimodal journaling app for tablets that scaffolds daily narratives through conversational prompts and visual supports. Autiverse elicits […]
neuralFOMO: Can LLMs Handle Being Second Best? Measuring Envy-Like Preferences in Multi-Agent Settings
arXiv:2512.13481v2 Announce Type: replace Abstract: Envy shapes competitiveness and cooperation in human groups, yet its role in large language model interactions remains largely unexplored. As LLMs increasingly operate in multi-agent settings, it is important to examine whether they exhibit envy-like preferences under social comparison. We evaluate LLM behavior across two scenarios: (1) a point-allocation game […]
RoPE Attention Can Be Trained in Almost Linear Time
arXiv:2412.17316v3 Announce Type: replace-cross Abstract: The Rotary Position Embedding (RoPE) mechanism has become a powerful enhancement to the Transformer architecture, which enables models to capture token relationships when encoding positional information. However, the RoPE mechanisms make the computations of attention mechanisms more complicated, which makes efficient algorithms challenging. Earlier research introduced almost linear time algorithms […]
FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning
arXiv:2601.18650v1 Announce Type: cross Abstract: Machine unlearning, which aims to efficiently remove the influence of specific data from trained models, is crucial for upholding data privacy regulations like the “right to be forgotten”. However, existing research predominantly evaluates unlearning methods on relatively balanced forget sets. This overlooks a common real-world scenario where data to be […]
Style2Code: A Style-Controllable Code Generation Framework with Dual-Modal Contrastive Representation Learning
arXiv:2505.19442v4 Announce Type: replace Abstract: Controllable code generation, the ability to synthesize code that follows a specified style while maintaining functionality, remains a challenging task. We propose a two-stage training framework combining contrastive learning and conditional decoding to enable flexible style control. The first stage aligns code style representations with semantic and structural features. In […]
PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVR
arXiv:2601.18207v1 Announce Type: cross Abstract: Search agents are language models (LMs) that reason and search knowledge bases (or the web) to answer questions; recent methods supervise only the final answer accuracy using reinforcement learning with verifiable rewards (RLVR). Most RLVR search agents tackle general-domain QA, which limits their relevance to technical AI systems in science, […]
Explanation Multiplicity in SHAP: Characterization and Assessment
arXiv:2601.12654v2 Announce Type: replace-cross Abstract: Post-hoc explanations are widely used to justify, contest, and review automated decisions in high-stakes domains such as lending, employment, and healthcare. Among these methods, SHAP is often treated as providing a reliable account of which features mattered for an individual prediction and is routinely used to support recourse, oversight, and […]
PaperTok: Exploring the Use of Generative AI for Creating Short-form Videos for Research Communication
arXiv:2601.18218v1 Announce Type: cross Abstract: The dissemination of scholarly research is critical, yet researchers often lack the time and skills to create engaging content for popular media such as short-form videos. To address this gap, we explore the use of generative AI to help researchers transform their academic papers into accessible video content. Informed by […]
Analyzing Message-Code Inconsistency in AI Coding Agent-Authored Pull Requests
arXiv:2601.04886v2 Announce Type: replace-cross Abstract: Pull request (PR) descriptions generated by AI coding agents are the primary channel for communicating code changes to human reviewers. However, the alignment between these messages and the actual changes remains unexplored, raising concerns about the trustworthiness of AI agents. To fill this gap, we analyzed 23,247 agentic PRs across […]
Largest connected component in duplication-divergence growing graphs with symmetric coupled divergence
arXiv:2601.07024v3 Announce Type: replace-cross Abstract: The largest connected component in duplication-divergence growing graphs with symmetric coupled divergence is studied. Finite-size scaling reveals a phase transition occurring at a divergence rate $delta_c$. The $delta_c$ found stands near the locus of zero in Euler characteristic for finite-size graphs, known to be indicative of the largest connected component […]
Rethinking Cross-Modal Fine-Tuning: Optimizing the Interaction between Feature Alignment and Target Fitting
arXiv:2601.18231v1 Announce Type: cross Abstract: Adapting pre-trained models to unseen feature modalities has become increasingly important due to the growing need for cross-disciplinary knowledge integration.~A key challenge here is how to align the representation of new modalities with the most relevant parts of the pre-trained model’s representation space to enable accurate knowledge transfer.~This requires combining […]