论文 Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching
论文 Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification
论文 ARCHead: Activation-Metric Residual Correction for Large Language Model Output Heads
论文 ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment in Vision-Language Models
论文 Knowing What Not to Answer: Selective Non-Compliance in Vision-Language Models
论文 WM-VLM: Probing Internal World Models for Interleaved Visual-Textual Reasoning