arXiv AI
Jun 9
Emergent alignment and the projectability of ethical personas
arXiv:2606. 09475v1 Announce Type: new Abstract: Work on `emergent misalignment' shows that finetuning LLMs on narrow tasks can induce broadly misaligned behavior.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jun 9
TAO: Tolerance-Aware Optimistic Verification for Floating-Point Neural Networks
arXiv:2510. 16028v4 Announce Type: replace-cross Abstract: Neural networks increasingly run on hardware outside the user's control (cloud GPUs, inference marketplaces).
arXiv Machine Learning
Jun 9
How Reliable are Fairness Audits with Unreliable Data?
arXiv:2506. 23033v2 Announce Type: replace Abstract: Fairness audits are a key component of responsible machine-learning deployment.
arXiv Machine Learning
Jun 9
Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search
arXiv:2512. 08724v3 Announce Type: replace Abstract: Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across sensitive attributes such as gender, race and age.
arXiv AI
Jun 9
Developing Distance-Aware Physics-Constrained Probabilistic Frameworks for Industrial Prognostics
arXiv:2512. 08499v3 Announce Type: replace-cross Abstract: Development of reliable and physically interpretable probabilistic frameworks for industrial prognostics remain nascent, and existing literature is often insensitive as inputs move away from the training manifold.
arXiv Machine Learning
Jun 9
Benchmark Datasets for Lead-Lag Forecasting on Social Platforms
arXiv:2511. 03877v2 Announce Type: replace Abstract: Social and collaborative platforms emit multivariate time-series traces in which early interactions -- such as views, likes, or downloads -- are followed, sometimes months or years later, by higher impact like citations, sales, or reviews.
arXiv Machine Learning
Jun 9
SAD-Flower: Flow Matching for Safe, Admissible, and Dynamically Consistent Planning
arXiv:2511. 05355v3 Announce Type: replace Abstract: Flow matching (FM) has shown promising results in data-driven planning.
arXiv AI
Jun 9
Self-Evolving Scientific Agent Discovers Generalizable Physically-Reasoned Fluid Control
arXiv:2606. 08405v1 Announce Type: new Abstract: While data-intensive deep reinforcement learning can optimize complex control policies, scientific discovery in physical systems fundamentally requires an interpretable chain of reasoning that connects physical evidence to structured control architectures.
arXiv Machine Learning
Jun 9
Few-step Cofolding with All-Atom Flow Maps
arXiv:2606. 08375v1 Announce Type: new Abstract: All-atom generative modeling of 3D biomolecular complexes has emerged as the dominant paradigm for predicting the structure of proteins and protein-ligand systems.
arXiv Machine Learning
Jun 9
Physically Consistent Null Space Alignment for Detection of Low-Magnitude False Data Injection Attacks
arXiv:2606. 08473v1 Announce Type: new Abstract: False data injection attacks (FDIAs) introducing small measurement perturbations can still cause large deviations in power system state estimation when the injected signals align with the pseudo-null space of the system model.
arXiv AI
Jun 9
Reliable to Expressive: A Curriculum for Rubric-Following Safety Judges
arXiv:2606. 09165v1 Announce Type: new Abstract: Safety judges are increasingly deployed to evaluate model outputs against evolving criteria, yet recent meta-evaluation work shows they remain brittle under prompt and rubric variation, with false negative-rate swings of up to 0.
arXiv Machine Learning
Jun 9
Physics-Guided Dual Decoding and Spectral Supervision for Global 3D Hydrometeor Prediction
arXiv:2606. 08563v1 Announce Type: new Abstract: While global data-driven models excel at predicting continuous atmospheric variables, three-dimensional hydrometeor forecasting remains challenging due to the zero-inflated, long-tailed distributions of these variables.
arXiv AI
Jun 9
Strained Coherence: A Pre-Failure Signal in Coding Agent Execution Trajectories
arXiv:2606. 07889v1 Announce Type: cross Abstract: LLM-based coding agents sometimes acknowledge a problem in their own reasoning and then proceed anyway.
arXiv Machine Learning
Jun 9
The Hidden Bias of Process Reward Models:PRISM for Rewarding the Right Reasoning
arXiv:2606. 09078v1 Announce Type: new Abstract: Process Reward Models (PRMs) improve credit assignment for reasoning by providing step-level feedback.
arXiv AI
Jun 9
SLMJury: Can Small Language Models Judge as Well as Large Ones?
arXiv:2606. 07810v1 Announce Type: cross Abstract: Large language models (LLMs) are widely used as judges for evaluating model outputs, but their high cost, latency, and opacity limit scalability.
arXiv Machine Learning
Jun 9
State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space
arXiv:2601. 04266v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models are widely deployed in safety-critical embodied AI applications such as robotics.
arXiv Machine Learning
Jun 9
Constrained user-item allocation for e-commerce marketing campaigns
arXiv:2606. 09623v1 Announce Type: new Abstract: When running marketing campaigns, retailers must decide which products to promote and which users to target.
arXiv AI
Jun 9
BRAIN: Bayesian Reasoning via Active Inference for Agentic and Embodied Intelligence in Mobile Networks
arXiv:2602. 14033v1 Announce Type: cross Abstract: Future sixth-generation (6G) mobile networks will demand artificial intelligence (AI) agents that are not only autonomous and efficient, but also capable of real-time adaptation in dynamic environments and transparent in their decisionmaking.
arXiv AI
Jun 9
CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents
arXiv:2605. 25624v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven breakthroughs in domains such as math, tool-use, and software engineering, yet its extension to computer-use agents (CUAs) has been bottlenecked by the scarcity of scalable training data with deterministic rewards.
arXiv AI
Jun 9
SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?
arXiv:2606. 07682v1 Announce Type: cross Abstract: AI agents are increasingly expected to complete long-horizon workflows that require sustained progress over hours, millions of tokens, and complex environments.