arXiv AI
Jul 15
Egocentric Bias in Vision-Language Models
arXiv:2602. 15892v2 Announce Type: replace-cross Abstract: Visual perspective taking--inferring how the world appears from another's viewpoint--is foundational to social cognition.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jul 15
Dynamic Resource Allocation for Ensemble Determinization MCTS
arXiv:2607. 13007v1 Announce Type: new Abstract: Simulation-based algorithms are especially suited for high-uncertainty environments such as adversarial board games with significant elements of randomness and hidden information.
arXiv AI
Jul 15
So Many Opinions, So Many LLMs: Comparing Large Language Models to Traditional Machine Learning for Open- Ended Survey Analysis
arXiv:2607. 11890v1 Announce Type: cross Abstract: Open-ended surveys offer valuable insights, but they are notoriously difficult to analyze at scale.
arXiv AI
Jul 15
Sparse Inter-Layer Dependencies of Transformer FFN Neurons
arXiv:2607. 11990v1 Announce Type: cross Abstract: Feedforward network (FFN) blocks account for a large fraction of the parameters and computation in Transformer architectures, yet their internal structure remains difficult to interpret due to the additive superposition induced by the residual stream.
arXiv AI
Jul 15
Knowledge- and Gradient-Guided Reinforcement Learning for Parametrized Action Markov Decision Processes
arXiv:2607. 12924v1 Announce Type: new Abstract: In this paper, we study Reinforcement Learning in Parametrized Action Markov Decision Processes (PAMDP), where each decision consists of a symbolic action and numerical parameters.
arXiv Machine Learning
Jul 15
SlimPer: Make Personalization Model Slim and Smart
arXiv:2607. 12281v1 Announce Type: cross Abstract: Transformer-style architectures are increasingly adopted for industrial recommendation systems, yet they inherit a design premise misaligned with the task: generative models rely on per-token autoregressive prediction, which justifies maintaining large intermediate tensors that scale with sequence length.
arXiv Machine Learning
Jul 15
Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning
arXiv:2512. 17788v2 Announce Type: replace Abstract: Multi-instance partial-label learning (MIPL) is a weakly supervised framework that extends the principles of multi-instance learning (MIL) and partial-label learning (PLL) to address the challenges of inexact supervision in both instance and label spaces.
arXiv Machine Learning
Jul 15
Reducing information dependency does not cause training data privacy. Adversarially non-robust features do
arXiv:2607. 12354v1 Announce Type: new Abstract: In this paper, we challenge the prevailing view that information dependency (including rote memorization) drives training data exposure to image reconstruction attacks.
arXiv Machine Learning
Jul 15
Understanding Structured Health Data through Interaction-Aware Mixture-of-Experts
arXiv:2607. 12255v1 Announce Type: new Abstract: We study interaction-aware mixture-of-experts for post-stroke rigidity prediction using multi-level views of structured health records.
arXiv AI
Jul 15
Inclusive Federated Learning Through Compliance-Weighted Noise Allocation in Healthcare AI
arXiv:2505. 22108v4 Announce Type: replace-cross Abstract: Background: Federated learning (FL) enables collaborative training of clinical AI models without centralizing patient data, but adoption is limited by privacy concerns, heterogeneous institutional compliance, and resource disparities; standard differential privacy (DP) applies uniform noise to all clients, penalizing well-compliant or under-resourced institutions.
arXiv AI
Jul 15
Real-time fall detection based on vision for low-power edge platforms
arXiv:2607. 12909v1 Announce Type: cross Abstract: Falling detection is vital for elderly care and intelligent surveillance; however, prevailing vision-based approaches predominantly frame it as static pose classification or discrete temporal pattern matching, fundamentally overlooking the instability dynamics of the human support system.
arXiv AI
Jul 15
Unveiling Complex Collective Behaviors from Simple Rewards
arXiv:2607. 12861v1 Announce Type: cross Abstract: Multi-agent Reinforcement Learning (MARL) holds great potential for robot swarms, but the black-box nature of neural policies complicates strategic analysis, limiting multi-robot applications.
arXiv AI
Jul 15
Explainable-by-Design Audio Deepfake Detection via Wiener-Hopf Linear Prediction
arXiv:2607. 12584v1 Announce Type: cross Abstract: The rapid advancement of synthetic speech generation methods has made audio deepfake detection a critical challenge in multimedia forensics.
arXiv Machine Learning
Jul 15
Did We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detection
arXiv:2607. 11969v1 Announce Type: cross Abstract: Point-adjustment (PA), long the default scoring protocol in time-series anomaly detection (TSAD), was shown by Kim et al.
arXiv AI
Jul 15
The Sound of Absence: Audio-Language Embedding Models Struggle with Negation
arXiv:2607. 12290v1 Announce Type: cross Abstract: Audio-language embedding models such as CLAP are widely evaluated on matching present sound events, but rarely on negation.
arXiv Machine Learning
Jul 15
What Makes a Representational Prior Work? Feature Families, Label-Free Invariances, and Critical Windows in Grokking
arXiv:2607. 12735v1 Announce Type: new Abstract: Companion work showed the grokking delay is causally the time to form task-structured representations, injectable via a contrastive prior.
arXiv Machine Learning
Jul 15
Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making
arXiv:2602. 07008v3 Announce Type: replace-cross Abstract: Reliable models should not only predict correctly, but also justify decisions with acceptable evidence.
arXiv Machine Learning
Jul 15
Adversarial Attacks on Online Handwriting using Salience-based Temporal Editing
arXiv:2607. 12500v1 Announce Type: new Abstract: Deep learning models for online handwriting recognition have been shown effective and are increasingly deployed in practical applications.
arXiv Machine Learning
Jul 15
Learning Mechanistic Reasoning for Chemical Reactions with Large Language Models
arXiv:2607. 12771v1 Announce Type: new Abstract: Reaction mechanisms consist of the step-by-step sequences of elementary reactions that explain chemical transformations.
arXiv AI
Jul 15
TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale
arXiv:2607. 13028v1 Announce Type: cross Abstract: Training robust autonomous driving agents requires a simulator that is fast enough for reinforcement learning at scale, realistic enough to ground behavior in real-world map structure, and diverse enough to cover the safety-critical long tail that logged data rarely contains.