arXiv AI
Jul 22
Now You See the Hate: Adaptive View Retrieval for Hidden Hateful Illusions
arXiv:2607. 19061v1 Announce Type: cross Abstract: Hateful optical illusions expose a serious gap in current multimodal safety systems.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jul 22
On the Effectiveness of Pretraining for Graph Combinatorial Optimization
arXiv:2607. 19072v1 Announce Type: new Abstract: This paper introduces a self-supervised pretraining framework for graph combinatorial optimization specifically designed to address the nature of routing problems like the Traveling Salesman Problem.
arXiv Machine Learning
Jul 22
CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability
arXiv:2607. 19317v1 Announce Type: new Abstract: Circuit analysis can support not only model explanation but also downstream interventions such as pruning, editing, steering, and selective fine-tuning.
arXiv AI
Jul 22
Engineering Trustworthy Agentic AI for Critical Systems
arXiv:2607. 18548v1 Announce Type: new Abstract: Agentic artificial intelligence systems, capable of autonomous perception, planning, tool use, and multi-step action, are increasingly proposed for critical engineering domains where decisions carry physical, operational, or economic consequences.
arXiv AI
Jul 22
RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts
arXiv:2607. 18470v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has shown strong effectiveness in reinforcement learning from verifiable feedback, where sampled rollouts can be compared within a group using task-provided correctness signals.
arXiv AI
Jul 22
S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF
arXiv:2607. 18258v1 Announce Type: new Abstract: Reinforcement learning from human feedback (RLHF) with preference-based reward models often exhibits unstable training dynamics.
arXiv AI
Jul 22
Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model
arXiv:2607. 18958v1 Announce Type: cross Abstract: While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks.
arXiv AI
Jul 22
Falsifiable Release Gates for Self-Improving Systems: Standing Invariants at Scale
arXiv:2607. 13070v2 Announce Type: replace-cross Abstract: Safety claims for self-improving agent runtimes are almost always self-graded: a policy file, a guardrail, a promise in a README.
arXiv AI
Jul 22
Multi-layer MIMO Relay as Deep Physical Neural Networks: Power Amplifiers as Activation Functions
arXiv:2607. 18354v1 Announce Type: cross Abstract: Wireless physical neural networks (WPNNs) embed neural computation directly into analog hardware, offering lower energy consumption and latency than conventional digital implementations.
arXiv AI
Jul 22
The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems
arXiv:2607. 19292v1 Announce Type: cross Abstract: Current AI safety discourse still focuses disproportionately on visible failures, including obvious harms, dramatic misuse, and hypothetical catastrophic scenarios.
arXiv AI
Jul 22
Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data
arXiv:2606. 16952v2 Announce Type: replace-cross Abstract: The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a privacy-preserving alternative to sensitive real-world datasets.
arXiv AI
Jul 22
Operational Hallucination and Safety Drift in AI Agents
arXiv:2607. 18366v1 Announce Type: new Abstract: Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution.
arXiv AI
Jul 22
PRISP: Privacy-Safe Few-Shot Personalization via Lightweight Adaptation
arXiv:2601. 06471v2 Announce Type: replace-cross Abstract: Large language model (LLM) personalization aims to adapt general-purpose models to individual users.
arXiv AI
Jul 22
Reframing AI Loss of Control: What Control Is, How to Have It, How to Lose It
arXiv:2606. 12442v2 Announce Type: replace-cross Abstract: At present, loss of control risks have gained much prominence in public discussion, particularly in relation to AI, with extensive discourse present among academics, frontier labs, and even governments.
arXiv Machine Learning
Jul 22
NSMA: Neuro-Symbolic Manifold Alignment for Generalizable Adaptive Bitrate Streaming under Texture Shift
arXiv:2607. 18845v1 Announce Type: cross Abstract: For decades, ABR has kept two kinds of intelligence apart.
arXiv AI
Jul 22
Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges
arXiv:2607. 19011v1 Announce Type: cross Abstract: Multimodal humor in memes, cartoons, and comics remains difficult for AI systems because intended meaning depends on non-literal mechanisms, shared cultural knowledge, and communicative intent rather than literal scene description.
arXiv Machine Learning
Jul 22
Hybrid Latent-Structural Fusion (HLSF) for Cyber Anomaly Detection
arXiv:2607. 18479v1 Announce Type: new Abstract: Malicious anomalous activity detection is a fundamental challenge for cyber security systems.
arXiv AI
Jul 22
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment
arXiv:2607. 05462v2 Announce Type: replace-cross Abstract: As AI agents are incorporated into life science workflows, the capabilities that speed discovery might also enable misuse.
arXiv AI
Jul 22
Assistant or Actor? Student Trust, Control, and Delegation Regret When Using a General-Purpose AI Agent
arXiv:2607. 18257v1 Announce Type: cross Abstract: When AI agents shift from answering questions to taking actions, users face a new problem: deciding what to delegate, to a system whose action space they cannot fully anticipate.
arXiv AI
Jul 22
PlotTwist: A Creative Plot Generation Framework with Small Language Models
arXiv:2603. 16410v2 Announce Type: replace-cross Abstract: Creative plot generation presents a fundamental challenge for language models: transforming a concise premise into a coherent narrative that sustains global coherence, character development, pacing, tone consistency, and emotional progression.