arXiv:2603.20275v1 Announce Type: cross Abstract: Transformer-based vision-language models (VLMs) contain substantial depth redundancy, yet the effect of removing specific decoder layers remains poorly understood, especially for domains that require tight coupling between perception and multi-step reasoning. We study structured decoder layer pruning through the lens of domain-aware activation similarity, measuring how strongly each layer transforms […]
Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives
arXiv:2511.06626v5 Announce Type: replace Abstract: As AI systems become more capable of complex agentic tasks, they also become more capable of pursuing undesirable objectives and causing harm. Previous work has attempted to catch these unsafe instances by interrogating models directly about their objectives and behaviors. However, the main weakness of trusting interrogations is that models […]
Hybrid Quantum Generative Adversarial Networks for Molecular Simulation and Drug Discovery
arXiv:2212.07826v2 Announce Type: replace-cross Abstract: In molecular research, the modelling and analysis of molecules through simulation is an important part that has a direct influence on medical development, material science and drug discovery. The processing power required to design protein chains with hundreds of peptides is huge. Classical computing techniques, including state-of-the-art machine learning models […]
On the Number of Conditional Independence Tests in Constraint-based Causal Discovery
arXiv:2603.21844v1 Announce Type: cross Abstract: Learning causal relations from observational data is a fundamental problem with wide-ranging applications across many fields. Constraint-based methods infer the underlying causal structure by performing conditional independence tests. However, existing algorithms such as the prominent PC algorithm need to perform a large number of independence tests, which in the worst […]
SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injection
arXiv:2603.22213v1 Announce Type: cross Abstract: While large language models (LLMs) are pretrained on massive amounts of data, their knowledge coverage remains incomplete in specialized, data-scarce domains, motivating extensive efforts to study synthetic data generation for knowledge injection. We propose SPA (Scaling Prompt-engineered Augmentation), a simple but tough-to-beat baseline that uses a small set of carefully […]
Rethinking Soft Compression in Retrieval-Augmented Generation: A Query-Conditioned Selector Perspective
arXiv:2602.15856v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) effectively grounds Large Language Models (LLMs) with external knowledge and is widely applied to Web-related tasks. However, its scalability is hindered by excessive context length and redundant retrievals. Recent research on soft context compression aims to address this by encoding long documents into compact embeddings, yet they […]
What Do World Models Learn in RL? Probing Latent Representations in Learned Environment Simulators
arXiv:2603.21546v1 Announce Type: cross Abstract: World models learn to simulate environment dynamics from experience, enabling sample-efficient reinforcement learning. But what do these models actually represent internally? We apply interpretability techniques–including linear and nonlinear probing, causal interventions, and attention analysis–to two architecturally distinct world models: IRIS (discrete token transformer) and DIAMOND (continuous diffusion UNet), trained on […]
Do LLMs Understand Collaborative Signals? Diagnosis and Repair
arXiv:2505.20730v4 Announce Type: replace-cross Abstract: Collaborative information from user-item interactions is a fundamental source of signal in successful recommender systems. Recently, researchers have attempted to incorporate this knowledge into large language model-based recommender approaches (LLMRec) to enhance their performance. However, there has been little fundamental analysis of whether LLMs can effectively reason over collaborative information. […]
Your VAR Model is Secretly an Efficient and Explainable Generative Classifier
arXiv:2510.12060v2 Announce Type: replace-cross Abstract: Generative classifiers, which leverage conditional generative models for classification, have recently demonstrated desirable properties such as robustness to distribution shifts. However, recent progress in this area has been largely driven by diffusion-based models, whose substantial computational cost severely limits scalability. This exclusive focus on diffusion-based methods has also constrained our […]
The Impact of Corporate AI Washing on Farmers’ Digital Financial Behavior Response — An Analysis from the Perspective of Digital Financial Exclusion
arXiv:2603.18421v2 Announce Type: replace-cross Abstract: In the context of the rapid development of digital finance, some financial technology companies exhibit the phenomenon of “AI washing,” where they overstate their AI capabilities while underinvesting in actual AI resources. This paper constructs a corporate-level AI washing index based on CHFS2019 data and AI investment data from 15-20 […]
Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models
arXiv:2603.21697v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) extend text-only LLMs with visual reasoning, but also introduce new safety failure modes under visually grounded instructions. We study comic-template jailbreaks that embed harmful goals inside simple three-panel visual narratives and prompt the model to role-play and “complete the comic.” Building on JailbreakBench and JailbreakV, […]
LRC-WeatherNet: LiDAR, RADAR, and Camera Fusion Network for Real-time Weather-type Classification in Autonomous Driving
arXiv:2603.21987v1 Announce Type: cross Abstract: Autonomous vehicles face major perception and navigation challenges in adverse weather such as rain, fog, and snow, which degrade the performance of LiDAR, RADAR, and RGB camera sensors. While each sensor type offers unique strengths, such as RADAR robustness in poor visibility and LiDAR precision in clear conditions, they also […]