SafeRelBench: A Spatial-Relation-Aware Benchmark for Process-Level Safety in VLM-Driven Embodied Agents
arXiv:2607.14543v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used as the reasoning backbone of embodied agents, enabling robots…
What Models Express, Suppress, and Resist: Auditing Open-Weight LLMs with Persona Vectors
arXiv:2607.13162v2 Announce Type: replace-cross Abstract: What a language model will and will not do is largely set during post-training, but…
OriginBlame: Record- and Token-Level Data Provenance for AI Training Datasets
arXiv:2607.13037v1 Announce Type: new Abstract: When a data contributor requests removal, model trainers face a practical gap: unlearning algorithms require…
Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation
arXiv:2607.12752v2 Announce Type: replace-cross Abstract: While recent advances in 3D generation have enabled impressive visual synthesis, existing methods often rely…
From Prediction to Collaboration: Interactive Symbolic Music Analysis
arXiv:2607.13587v1 Announce Type: cross Abstract: Automatic symbolic music analysis has made substantial progress, yet existing systems are typically designed for…
Agile perceptive multi-skill locomotion for quadrupedal robots in the wild
arXiv:2607.13579v1 Announce Type: cross Abstract: Enabling quadrupedal robots to traverse complex terrains-from rugged outdoor environments to urban landscapes-requires seamless integration…
Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs
arXiv:2607.11997v2 Announce Type: replace-cross Abstract: Multi-task model merging combines separately trained expert models into a single model that handles all…