1 citations · 1 across the 4 of their papers we have counts for
7 papers
Human Demonstrations as Post-Training Data for Any Robot Body: Retargeting the Object, Not the Hand
Nagasrikanth Kallakuri
Human demonstrations are today used largely for pretraining vision-language-action models, with little ability to use the same data for target-embodiment or task-oriented training,…
Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate
Haocheng Ye, Aoting Hu, Xinwei Zhang +3
Text watermarking helps identify AI-generated content, but its effect on factual reliability remains underexplored. In this paper, we study watermarking hallucination: factual erro…
SteerProbe: Learning to Bypass Safety Steering in Vision-Language Models
Xinwei Zhang, Aoting Hu, Hangcheng Liu +3
Activation steering offers an inference-time defense for vision--language models (VLMs) by modifying intermediate representations without updating backbone parameters. However, pro…
HeadWiseKV: Budgeted Per-Head Cache Residency for Hybrid Long-Context Language Models
Renjie Xie, Juncheng Yang, Aoting Hu +4
Long-context inference retains a growing key--value (KV) cache during decoding, which consumes substantial GPU memory and can reduce generation throughput. This bottleneck remains…
Revisiting Black-Box Model Ownership Verification through Information Theory
Aoting Hu, Yanzhi Chen, Renjie Xie +2
Modern machine learning models require substantial computational resources and data to train, making them valuable intellectual property. Model watermarking has emerged as a practi…
VeriDIP: Verifying Ownership of Deep Neural Networks through Privacy Leakage Fingerprints
Aoting Hu, Zhigang Lu, Renjie Xie +1
Deploying Machine Learning as a Service gives rise to model plagiarism, leading to copyright infringement. Ownership testing techniques are designed to identify model fingerprints…
TableGAN-MCA: Evaluating Membership Collisions of GAN-Synthesized Tabular Data Releasing
Aoting Hu, Renjie Xie, Zhigang Lu +2
Generative Adversarial Networks (GAN)-synthesized table publishing lets people privately learn insights without access to the private table. However, existing studies on Membership…