arXiv Machine Learning
Jun 24
RE4: Transformation-aware Imitation of Object Interactions Using Manipulation Modes
arXiv:2606. 24403v1 Announce Type: cross Abstract: Object interaction tasks have been a focus of advances in imitation learning.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jun 24
Societal Alignment Frameworks Can Improve LLM Alignment
arXiv:2503. 00069v2 Announce Type: replace-cross Abstract: Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values - a process coined alignment.
arXiv AI
Jun 24
Breaking the Filter Bubble: A Semantic Pareto-DQN Framework for Multi-Objective Recommendation
arXiv:2606. 24042v1 Announce Type: new Abstract: Recommender systems often induce filter bubbles and semantic homogenization by monolithically optimizing for immediate user engagement.
arXiv AI
Jun 24
On the Position Bias of On-Policy Distillation
arXiv:2606. 22600v2 Announce Type: replace-cross Abstract: On-Policy Distillation (OPD) improves the learning efficiency of standard reinforcement learning through dense, token-level supervision from teachers.
arXiv AI
Jun 24
LLMs Prompted for Legal Context Object More: Overrefusal from Small On-Premises LLMs in Criminal Legal Context
arXiv:2606. 24585v1 Announce Type: new Abstract: While the validity of LLMs' use in the legal context remains subject to ethical and legal debate, legal professionals are already experimenting with personal LLMs, if only for translation and reformulation.
arXiv Machine Learning
Jun 24
Natural Identifiers for Privacy and Data Audits in Large Language Models
arXiv:2606. 24408v1 Announce Type: new Abstract: Assessing the privacy of large language models (LLMs) presents significant challenges.
arXiv Machine Learning
Jun 24
Federated Survival Analysis in Healthcare: A Multi-Model Evaluation on Cross-Institutional Heterogeneous Breast Cancer Data
arXiv:2606. 23871v1 Announce Type: new Abstract: Survival analysis is central to clinical decision-making, yet reliable time-to-event models require large, diverse cohorts that are rarely available at a single institution, while privacy regulations restrict the centralization of patient data.
arXiv AI
Jun 24
Quantifying Prior Dominance in RAG Systems
arXiv:2606. 23695v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) grounds Large Language Models in external knowledge, yet current evaluations rely on discrete heuristics that suffer from ''epistemic blindness'' - failing to distinguish genuine contextual information extraction from parametric memory recall.
arXiv AI
Jun 24
Selective Capability Unlearning in End-to-End Spoken Language Understanding
arXiv:2606. 24063v1 Announce Type: cross Abstract: Modern spoken language understanding (SLU) systems are increasingly deployed in real-world settings, where specific functionalities may need to be removed due to policy or safety constraints.
arXiv AI
Jun 24
Towards Federated Long-Tailed Graph Learning: An Energy-Guided Dual Decoupling Approach
arXiv:2606. 24237v1 Announce Type: new Abstract: Federated Graph Learning facilitates collaborative graph modeling across distributed clients while preserving data privacy.
arXiv AI
Jun 24
Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations
arXiv:2601. 22548v4 Announce Type: replace-cross Abstract: Recent research has shown that large language models (LLMs) favor their own outputs when acting as judges, undermining the integrity of automated post-training and evaluation workflows.
arXiv AI
Jun 24
Quant Convergence: Bridging Classical Value Investing and Modern Factor Models for Systematic Equity Selection
arXiv:2606. 24575v1 Announce Type: new Abstract: Modern finance relies heavily on complex machine learning models to find patterns in the stock market.
arXiv AI
Jun 24
FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning
arXiv:2606. 24231v1 Announce Type: new Abstract: Multimodal driving planning faces a long-standing tension between two paradigms: scoring-based methods benefit from dense reward supervision but are confined to a fixed action vocabulary, while anchor-based methods generate proposals dynamically yet suffer from sparse supervision constrained to a single ground-truth trajectory.
arXiv Machine Learning
Jun 24
An LLM-based Two-Stage Transformer Framework for Cross-Domain Bearing Fault Diagnosis with Limited Data
arXiv:2606. 24459v1 Announce Type: new Abstract: Bearing fault diagnosis faces critical challenges when dataset heterogeneity, operating condition variations, and limited labeled data occur simultaneously in industrial environments.
arXiv AI
Jun 24
A Simplex Witness Certificate and Escape Force for Constant Collapse in Variational Autoencoders
arXiv:2605. 18224v4 Announce Type: replace-cross Abstract: We study exact constant collapse in variational autoencoders: the deterministic encoder mean becomes independent of the input.
arXiv Machine Learning
Jun 24
A Differentially Private Weighted Empirical Risk Minimization Procedure and its Application to Outcome Weighted Learning
arXiv:2307. 13127v3 Announce Type: replace-cross Abstract: Data used to train predictive models via empirical risk minimization (ERM) often contain sensitive personal information.
arXiv Machine Learning
Jun 24
Experiments with Optimal Model Trees
arXiv:2503. 12902v4 Announce Type: replace Abstract: Model trees provide an appealing way to perform interpretable machine learning for both classification and regression problems.
arXiv AI
Jun 24
E-MRL: Cross-view Aligned Evidence-driven Multimodal Reinforcement Learning for Reliable 3D Tumor Analysis
arXiv:2606. 23888v1 Announce Type: cross Abstract: While Vision-Language Models (VLMs) show great promise in volumetric medical report generation, they frequently suffer from visual hallucinations and a lack of grounding in 3D CT data.
arXiv AI
Jun 24
HiPath: Hierarchical Vision-Language Alignment for Structured Pathology Report Prediction
arXiv:2603. 19957v2 Announce Type: replace-cross Abstract: Pathology reports are structured, multi-granular documents encoding diagnostic conclusions, histological grades, and ancillary test results across one or more anatomical sites; yet existing pathology vision-language models (VLMs) reduce this output to a flat label or free-form text.
arXiv Machine Learning
Jun 24
Generating adversarial inputs for a graph neural network model of AC power flow
arXiv:2602. 17975v2 Announce Type: replace Abstract: This work formulates and solves optimization problems to generate input points that yield high errors between a neural network's predicted AC power flow solution and solutions to the AC power flow equations.