arXiv:2604.08504v1 Announce Type: cross Abstract: We initiate the study of language generation in the limit, a model recently introduced by Kleinberg and Mullainathan [KM24], under the constraint of differential privacy. We consider the continual release model, where a generator must eventually output a stream of valid strings while protecting the privacy of the entire input […]
Causal Discovery in Linear Models with Unobserved Variables and Measurement Error
arXiv:2407.19426v2 Announce Type: replace-cross Abstract: The presence of unobserved common causes and measurement error poses two major obstacles to causal structure learning, since ignoring either source of complexity can induce spurious causal relations among variables of interest. We study causal structure learning in linear systems where both challenges may occur simultaneously. We introduce a causal […]
Bias Detection in Emergency Psychiatry: Linking Negative Language to Diagnostic Disparities
arXiv:2509.02651v2 Announce Type: replace Abstract: The emergency department (ED) is a high stress environment with increased risk of clinician bias exposure. In the United States, Black patients are more likely than other racial/ethnic groups to obtain their first schizophrenia (SCZ) diagnosis in the ED, a highly stigmatizing disorder. Therefore, understanding the link between clinician bias […]
Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understanding
arXiv:2603.18472v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) perform strongly on natural images, yet their ability to understand discrete visual symbols remains unclear. We present a multi-domain benchmark spanning language, culture, mathematics, physics and chemistry, organized into three cognitive levels: perception and recognition, combination and reasoning, and association and critical thinking. Across leading […]
Are Sparse Autoencoders Useful for Java Function Bug Detection?
arXiv:2505.10375v4 Announce Type: replace-cross Abstract: Software vulnerabilities such as buffer overflows and SQL injections are a major source of security breaches. Traditional methods for vulnerability detection remain essential but are limited by high false positive rates, scalability issues, and reliance on manual effort. These constraints have driven interest in AI-based approaches to automated vulnerability detection […]
HST-HGN: Heterogeneous Spatial-Temporal Hypergraph Networks with Bidirectional State Space Models for Global Fatigue Assessment
arXiv:2604.08435v1 Announce Type: cross Abstract: It remains challenging to assess driver fatigue from untrimmed videos under constrained computational budgets, due to the difficulty of modeling long-range temporal dependencies in subtle facial expressions. Some existing approaches rely on computationally heavy architectures, whereas others employ traditional lightweight pairwise graph networks, despite their limited capacity to model high-order […]
AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation
arXiv:2604.08540v1 Announce Type: cross Abstract: Text-to-Audio-Video (T2AV) generation is rapidly becoming a core interface for media creation, yet its evaluation remains fragmented. Existing benchmarks largely assess audio and video in isolation or rely on coarse embedding similarity, failing to capture the fine-grained joint correctness required by realistic prompts. We introduce AVGen-Bench, a task-driven benchmark for […]
Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning
arXiv:2601.04666v2 Announce Type: replace Abstract: Large language model (LLM)-integrated applications have become increasingly prevalent, yet face critical security vulnerabilities from prompt injection (PI) attacks. Defending against PI attacks faces two major issues: malicious instructions can be injected through diverse vectors, and injected instructions often lack clear semantic boundaries from the surrounding context, making them difficult […]
Why we need an AI-resilient society
arXiv:1912.08786v2 Announce Type: replace-cross Abstract: Three generations of software have transformed the role of artificial intelligence in society. In the first, programmers wrote explicit logic; in the second, neural networks learned programs from data; in the third, large language models turn natural language itself into a programming interface. These shifts have consequences that reach far […]
RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification
arXiv:2503.02537v4 Announce Type: replace-cross Abstract: Diffusion models have achieved remarkable progress across various visual generation tasks. However, their performance significantly declines when generating content at resolutions higher than those used during training. Although numerous methods have been proposed to enable high-resolution generation, they all suffer from inefficiency. In this paper, we propose RectifiedHR, a straightforward […]
Self-Calibrating LLM-Based Analog Circuit Sizing with Interpretable Design Equations
arXiv:2604.07387v1 Announce Type: cross Abstract: We present a self-calibrating framework for analog circuit sizing in which a large language model (LLM) derives topology-specific analytical design equations directly from a raw circuit netlist. Unlike existing AI-driven sizing methods where the model proposes parameter adjustments or reduces a search space, the LLM produces a complete Python sizing […]
Beyond Stochastic Exploration: What Makes Training Data Valuable for Agentic Search
arXiv:2604.08124v1 Announce Type: new Abstract: Reinforcement learning (RL) has become an effective approach for advancing the reasoning capabilities of large language models (LLMs) through the strategic integration of external search engines. However, current RL-based search agents often rely on a process of stochastic exploration guided by carefully crafted outcome rewards, leading to inefficient reasoning trajectories […]