arXiv AI
Jun 6
Residual Modeling for High-Fidelity Learned Compression of Scientific Data
arXiv:2606. 05389v1 Announce Type: new Abstract: Lossy compression is essential for massive spatiotemporal data from scientific simulations.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jun 6
Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization
arXiv:2605. 11632v2 Announce Type: replace-cross Abstract: Self-generated counterfactual explanations (SCEs) are minimally modified inputs (minimality) generated by large language models (LLMs) that flip their own predictions (validity), offering a causally grounded approach to unraveling black-box LLM behavior.
arXiv AI
Jun 6
UNIVID: Unified Vision-Language Model for Video Moderation
arXiv:2606. 05748v1 Announce Type: cross Abstract: Global-scale video moderation faces a dual challenge: the need for fine-grained multi-modal reasoning and the demand for interpretable outputs to support downstream enforcement.
arXiv AI
Jun 6
EasyLens: A Training-Free Plug-and-Play Subtle-Lesion Representation Amplifier for Medical Vision-Language Models
arXiv:2606. 06379v1 Announce Type: cross Abstract: Medical vision-language models (VLMs) have shown increasing potential for clinical image interpretation, including lesion detection and report generation.
arXiv AI
Jun 6
Class-Specific Branch Attention for Mitigating Gradient Interference under Class Imbalance
arXiv:2606. 05740v1 Announce Type: new Abstract: Deep neural networks trained under severe class imbalance often exhibit degraded performance, typically attributed to statistical bias.
arXiv AI
Jun 6
CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives
arXiv:2504. 10823v4 Announce Type: replace-cross Abstract: Navigating dilemmas involving conflicting values is challenging even for humans in high-stakes domains, let alone for AI, yet prior work has been limited to everyday scenarios.
arXiv AI
Jun 6
Geographic Bias and Diversity in AI Evaluation
arXiv:2606. 05187v1 Announce Type: cross Abstract: Among the many challenges hindering the responsible development and deployment of AI, arguably none has faced more intense scrutiny than bias in its various forms.
arXiv AI
Jun 6
VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents
arXiv:2606. 05395v1 Announce Type: cross Abstract: Reusable robot skills are becoming the basic units through which embodied agents turn open-ended instructions into long-horizon physical behavior.
arXiv AI
Jun 6
Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation
arXiv:2606. 05660v1 Announce Type: cross Abstract: Embodied AI systems are increasingly expected to reason and act over extended horizons in physical environments.
arXiv AI
Jun 6
Compositional Boundaries for Density Fusion
arXiv:2606. 05871v1 Announce Type: cross Abstract: Distributed uncertainty-management systems often combine local probabilistic models along aggregation trees chosen by communication, privacy, or scheduling constraints.
arXiv AI
Jun 6
Evaluating the Utility of Personal Health Records in Personalized Health AI
arXiv:2605. 18937v2 Announce Type: replace Abstract: Patient-managed Personal Health Records (PHRs) promises to empower patients to better understand their health; but information in the record is complex, potentially hindering insights.
arXiv AI
Jun 6
Assessing the Geographic Diversity of AI's Platial Representations in Image Generation
arXiv:2606. 05188v1 Announce Type: cross Abstract: (Gen)AI diversity is not merely an ethical issue.
arXiv AI
Jun 6
Correcting Prompt Dependence in LLM Benchmarks: A Bayesian Hierarchical Model with Embedding-Space Clustering
arXiv:2510. 05709v2 Announce Type: replace-cross Abstract: LLM benchmarking metrics often misstate performance and uncertainty as they rely on two assumptions that frequently do not hold in practice: (i) a sufficient number of evaluations are available for classical inference, and (ii) test prompts are independent.
arXiv AI
Jun 6
Towards Healthy Evolution: Exploring the Role and Mechanisms of Human-Agent Interaction in Self-Evolving Systems
arXiv:2606. 06114v1 Announce Type: new Abstract: Self-evolving agents improve through continual self-play and self-generated learning signals, but autonomous evolution can also cause capability degradation and safety drift.
arXiv AI
Jun 6
ECI: Effective Contrastive Information to Evaluate Hard-Negatives
arXiv:2603. 20990v2 Announce Type: replace-cross Abstract: Hard-negative source selection for dense retrieval is usually decided only after fine-tuning and downstream evaluation.
arXiv AI
Jun 6
HypRAG: Hyperbolic Dense Retrieval for Retrieval Augmented Generation
arXiv:2602. 07739v2 Announce Type: replace-cross Abstract: Embedding geometry plays a fundamental role in retrieval quality, yet dense retrievers for retrieval-augmented generation (RAG) remain largely confined to Euclidean space.
arXiv AI
Jun 6
Data Flow Control: Data Safety Policies for AI Agents
arXiv:2606. 05679v1 Announce Type: cross Abstract: Agents increasingly generate SQL, orchestrate pipelines, and automate data analysis on behalf of users.
arXiv AI
Jun 6
Whose Alignment? Comparing LLM Process Alignment Across Diverse Organizational Decision Contexts
arXiv:2605. 25256v2 Announce Type: replace Abstract: Steerable pluralism requires a model to faithfully represent one specified perspective.
arXiv AI
Jun 6
Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning
arXiv:2601. 21700v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) increasingly support culturally sensitive decision making, yet often exhibit misalignment due to skewed pretraining data and the absence of structured value representations.
arXiv AI
Jun 6
Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack
arXiv:2606. 05614v1 Announce Type: new Abstract: Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content.