PhyDrawGen: Physically Grounded Diagram Generation from Natural Language
arXiv:2605.30512v1 Announce Type: new Abstract: Generating physics diagrams from text requires strict adherence to physical laws. While current generative models…
Investigating Detection and Obfuscation of Prompt Injection Attacks Against Software Reverse Engineering AI Agents
arXiv:2605.30677v1 Announce Type: cross Abstract: Agentic software reverse engineering systems are vulnerable to prompt injection attacks placed into the source…
PInVerify: An Offline Embodied Benchmark for Active Instance Verification
arXiv:2605.30639v1 Announce Type: cross Abstract: Embodied agents have made strong progress in navigating to target objects, but reaching the goal…
An Organization-Scoped LLM Agent Runtime Architecture for Regulated Cybersecurity Operations
arXiv:2605.30604v1 Announce Type: cross Abstract: Regulated cybersecurity workflows lack a runtime substrate that enforces organization-level scope across retrieval, tool calls,…
Mental Damage: Caption Poisoning Attacks on Retrieval-Augmented Text-to-Music Generation
arXiv:2605.30365v1 Announce Type: cross Abstract: Retrieval-augmented text-to-music (TTM) systems augment underspecified user prompts using captions retrieved from a music caption…
Seeing Isn’t Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
arXiv:2605.30557v1 Announce Type: cross Abstract: Spatial reasoning is a fundamental capability for vision-language models (VLMs) deployed in real-world environments. However,…
Neural Network Verification using Partial Multi-Neuron Relaxation
arXiv:2605.30155v2 Announce Type: replace-cross Abstract: The increasing integration of deep neural networks in critical systems has spawned a theoretical and…
Preference-Shaped Expected Hypervolume and R2 Improvement: Exact Computation and Monotonicity
arXiv:2605.28746v2 Announce Type: replace-cross Abstract: This paper studies preference-shaped expected improvement criteria for Bayesian multiobjective optimization. We consider two indicator…
HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization
arXiv:2605.29843v1 Announce Type: cross Abstract: Post-training quantization (PTQ) is essential for deploying LLMs under memory and bandwidth constraints. However, extreme…