arXiv AI
Aug 12
Situation Graph Prediction for User Perspective Modeling
arXiv:2602. 13319v2 Announce Type: replace Abstract: Perspective-aware AI requires modeling evolving internal states---goals, emotions, contexts---not merely preferences.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Aug 12
InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis
arXiv:2604. 13201v2 Announce Type: replace-cross Abstract: Large language models are emerging as scientific assistants, but evaluating their ability to reason from empirical data remains challenging.
arXiv AI
Aug 12
TransitReID: Transit OD Data Collection with Occlusion-Resistant Dynamic Passenger Re-Identification
arXiv:2504. 11500v3 Announce Type: replace-cross Abstract: Transit Origin-Destination (OD) data are fundamental for optimizing public transit services, yet current collection methods, such as manual surveys, Bluetooth/WiFi tracking, and Automated Passenger Counters, are often costly, device-dependent, or unable to support individual-level matching.
arXiv AI
Aug 12
Edge Phoneme Recognition for Children's Speech through Age-Aware Training
arXiv:2608. 10206v1 Announce Type: new Abstract: Detecting phonemes from children's speech has historically been difficult due to the scarcity of training data, and unique characteristics of children's speech.
arXiv AI
Aug 12
Exploration-Driven Personalized Federated Reinforcement Learning via Intrinsic Motivation
arXiv:2608. 10499v1 Announce Type: cross Abstract: Personalized Federated Reinforcement Learning (PFRL) takes a decentralized approach to storing and accessing information based on past experiences while keeping each client's data private during the learning of each client's policy.
arXiv AI
Aug 12
Selective Prediction Reduces the Negative Effects of Automation Bias Overall but Increases False Negatives
arXiv:2508. 07617v2 Announce Type: replace-cross Abstract: AI has the potential to augment human decision making.
arXiv AI
Aug 12
Demystifying Adversarial Robustness in Diffusion Models: Compression, Randomness, and Geometry
arXiv:2505. 22839v2 Announce Type: replace-cross Abstract: Recent studies suggest that diffusion models significantly improve the empirical adversarial robustness of deep neural network models.
arXiv AI
Aug 12
Why Do Safety Guardrails Degrade Across Languages?
arXiv:2605. 17173v2 Announce Type: replace-cross Abstract: Large language models exhibit safety degradation in non-English languages.
arXiv Machine Learning
Aug 12
Generator-Guided Inverse Sampling for L\'evy-Driven Generative Models
arXiv:2608. 10384v1 Announce Type: new Abstract: This paper studies inverse sampling for L\'evy-driven generative models from the perspective of Markov generators.
arXiv Machine Learning
Aug 12
Do Time-Series Forecasters Use the Right History: Recoverability, Recovery, and Functional Use of Temporal Delays
arXiv:2608. 10433v1 Announce Type: new Abstract: Forecast accuracy does not tell us which past inputs produced a prediction.
arXiv AI
Aug 12
Knowledge-Guided 3D CT Generation: A Conditioning-Centric Taxonomy
arXiv:2608. 09992v1 Announce Type: cross Abstract: Controllable generation guided by external knowledge is a key requirement in modern generative deep learning applications, enabling the synthesis of samples with explicit constraints on semantic content, structural properties, and variability.
arXiv Machine Learning
Aug 12
MultiModal Code-Switching: Interleaving Visual Objects into Language for Explicit Object-Level Alignment
arXiv:2608. 11167v1 Announce Type: cross Abstract: Existing Multimodal Large Language Models (MLLMs) predominantly rely on image-text pairs for modality alignment pretraining, mapping global image representations to long textual descriptions.
arXiv AI
Aug 12
Where Flow Matching Leaks: Characterising Membership Signals Along the Interpolation Path
arXiv:2606. 07271v3 Announce Type: replace-cross Abstract: Understanding memorization in generative models remains challenging, with implications for copyright and privacy.
arXiv Machine Learning
Aug 12
Deciding When to Switch: E-Processes for Adaptive Minimax Training for Generative Adversarial Nets
arXiv:2608. 10096v1 Announce Type: cross Abstract: Modern data science increasingly gives rise to hypothesis-testing problems that are not naturally formulated in terms of parameters within prespecified statistical models.
arXiv Machine Learning
Aug 12
InSight-doc: Agentic Visual Perception for Long-Document Understanding
arXiv:2608. 10628v1 Announce Type: cross Abstract: Long-document understanding often requires reasoning over many visually rich pages, making inference costly and prone to context rot.
arXiv AI
Aug 12
How to Verify Consistency of Probabilistic Claims
arXiv:2608. 11181v1 Announce Type: cross Abstract: When a probabilistic predictor answers many conditional-probability queries, are its answers self-consistent, and can this be verified in polynomial time?
arXiv Machine Learning
Aug 12
More Accurate, Less Human: Gestalt Grouping in Vision Models
arXiv:2608. 10195v1 Announce Type: cross Abstract: Human vision organizes what it sees into wholes: same-colored points group into series, similar marks cohere into categories, and shapes complete into recognizable objects.
arXiv AI
Aug 12
Generating Attacks for LLMs with GFlowNets
arXiv:2608. 10171v1 Announce Type: new Abstract: The rapid advancement of Large Language Models (LLMs) has facilitated their ubiquitous integration into various domains, leading to widespread adoption.
arXiv AI
Aug 12
Your LLM, Your Style: Behavioral Mode Axes for LLM Behavioral Control
arXiv:2608. 10703v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly act in interactive settings where their behavioral styles affect user experience, safety, and downstream decision making.
arXiv Machine Learning
Aug 12
Dreamer-SAC: Off-Policy Learning in Latent World Models for Sample-Efficient Autonomous Driving
arXiv:2608. 10386v1 Announce Type: new Abstract: Sample-efficient reinforcement learning for autonomous driving is often limited by the trade-off between data efficiency and model bias.