arXiv AI
Jun 2
The Refusal--Compliance Tradeoff: A Large-Scale Safety Behavior Audit of Large Language Models
arXiv:2605. 05427v2 Announce Type: replace Abstract: Refusal rates are a poor proxy for LLM safety, i.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jun 2
Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction
arXiv:2606. 01850v1 Announce Type: new Abstract: Model compression techniques such as quantization and pruning are widely used to reduce the deployment cost of large language models (LLMs), with existing evaluations focusing almost exclusively on accuracy preservation.
arXiv AI
Jun 2
MViewRouter: Internalizing Geometric Equivariance via Multi-view Alternating Attention for Combinatorial Routing
arXiv:2606. 01084v1 Announce Type: cross Abstract: Combinatorial routing problems such as the Traveling Salesman Problem (TSP) and the Capacitated Vehicle Routing Problem (CVRP) are fundamental NP-hard problems with broad real-world applications.
arXiv AI
Jun 2
Bridging the Last Mile of Time Series Forecasting with LLM Agents
arXiv:2606. 02497v1 Announce Type: new Abstract: Time series forecasting has advanced rapidly, especially with the emergence of foundation models that show strong zero-shot performance on numerical extrapolation.
arXiv AI
Jun 2
Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition
arXiv:2606. 00959v1 Announce Type: new Abstract: Understanding modality interaction in multimodal large language models (MLLMs) is central to reliable deployment.
arXiv AI
Jun 2
Co-Fusion4D: Spatio-temporal Collaborative Fusion for Robust 3D Object Detection
arXiv:2605. 20301v2 Announce Type: replace-cross Abstract: In autonomous driving, 3D object detection is essential for accurate perception and reliable decision-making.
arXiv AI
Jun 2
Paradoxical noise preference in RNNs
arXiv:2601. 04539v2 Announce Type: replace-cross Abstract: In recurrent neural networks (RNNs) used to model biological neural networks, noise is typically introduced during training to emulate biological variability and regularize learning.
arXiv AI
Jun 2
SilentDrift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models
arXiv:2601. 14323v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models are increasingly deployed in safety-critical robotic applications, yet their security vulnerabilities remain underexplored.
arXiv AI
Jun 2
InFerActive: Interactive Tree-Based Exploration of LLM Sampling for Safety Evaluation
arXiv:2512. 10234v2 Announce Type: replace-cross Abstract: Even LLMs that appear safe during evaluation can still produce harmful responses in deployment.
arXiv AI
Jun 2
The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer
arXiv:2602. 02557v2 Announce Type: replace-cross Abstract: Recent advances in end-to-end trained omni-models have substantially improved audio capabilities by strengthening text-audio modality alignment.
arXiv AI
Jun 2
Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
arXiv:2604. 17415v3 Announce Type: replace-cross Abstract: Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model.
arXiv AI
Jun 2
When Does Predictive Inverse Dynamics Outperform Behavior Cloning?
arXiv:2601. 21718v2 Announce Type: replace-cross Abstract: Behavior cloning (BC) is a practical offline imitation learning method, but it often fails when expert demonstrations are limited.
arXiv Machine Learning
Jun 2
Profiling Privacy Preservation Against Gradient Inversion Attacks in Tabular Federated Learning
arXiv:2606. 00986v1 Announce Type: new Abstract: Federated learning (FL) enables multiple data holders to train machine learning models collaboratively without centralizing raw data, making it useful in privacy sensitive domains such as healthcare and institutional data sharing.
arXiv AI
Jun 2
Failure of contextual invariance in large language models
arXiv:2603. 23485v2 Announce Type: replace-cross Abstract: Standard evaluation practices assume that large language model (LLM) outputs are stable when prompts are embedded in contextually equivalent discourses.
arXiv AI
Jun 2
Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching
arXiv:2602. 05951v2 Announce Type: replace-cross Abstract: Flow matching has recently emerged as a promising alternative to diffusion-based generative models, particularly for text-to-image generation.
arXiv Machine Learning
Jun 2
Closing the Alignment-Maturity Gap in Federated Prototype Learning
arXiv:2606. 02172v1 Announce Type: new Abstract: Learning discriminative visual representations from distributed, heterogeneous data is a fundamental challenge in Federated Learning (FL).
arXiv AI
Jun 2
REAL: Resolving Knowledge Conflicts in Knowledge-Intensive Visual Question Answering via Reasoning-Pivot Alignment
arXiv:2602. 14065v2 Announce Type: replace Abstract: Knowledge-intensive Visual Question Answering (KI-VQA) frequently suffers from severe knowledge conflicts caused by the inherent limitations of open-domain retrieval.
arXiv AI
Jun 2
Repurposing Adversarial Perturbations for Continual Learning: From Defense to Active Alignment
arXiv:2606. 02322v1 Announce Type: cross Abstract: In dynamic environments, large language models need to keep adapting to new tasks, but continual learning often suffers from forgetting, limited transfer, and vulnerability to adversarial perturbations.
arXiv AI
Jun 2
A Monosemantic Attribution Framework for Stable Interpretability in Clinical Neuroscience Transformer-Based Language Models
arXiv:2601. 17952v2 Announce Type: replace-cross Abstract: Interpretability remains a key challenge for deploying language models (LM) in clinical settings such as progression diagnosis of Alzheimer disease, where early and trustworthy predictions are essential.
arXiv AI
Jun 2
Agent Operating Systems (AOS): Integrating Agentic Control Planes into, and Beyond, Traditional Operating Systems
arXiv:2606. 01508v1 Announce Type: cross Abstract: Traditional operating systems were designed around deterministic programs, explicit control flow, and human initiated workflows.