Related papers: Asking Back: Interaction-Layer Antidistillation Wa…
How can we protect the intellectual property of trained NLP models? Modern NLP models are prone to stealing by querying and distilling from their publicly exposed APIs. However, existing protection methods such as watermarking only work for…
Large language models (LLMs) can be misused to reveal sensitive information, such as weapon-making instructions or writing malware. LLM providers rely on $\emph{monitoring}$ to detect and flag unsafe behavior during inference. An open…
Knowledge distillation transfers large teacher models to compact student models, enabling deployment on resource-limited platforms while suffering minimal performance degradation. However, this paradigm could lead to various security risks,…
Learning from demonstrations in embodied control is often cast as behavioral cloning, and recent diffusion or flow-matching policies improve this paradigm by modeling multi-modal expert actions. Yet these methods remain offline supervised…
Unsupervised anomaly detection encompasses diverse applications in industrial settings where a high-throughput and precision is imperative. Early works were centered around one-class-one-model paradigm, which poses significant challenges in…
Standard Knowledge Distillation (KD) compresses Large Language Models (LLMs) by optimizing final outputs, yet it typically treats the teacher's intermediate layer's thought process as a black box. While feature-based distillation attempts…
Recent advancements in large language models (LLMs) have highlighted the risk of misusing them, raising the need for accurate detection of LLM-generated content. In response, a viable solution is to inject imperceptible identifiers into…
Model distillation is frequently proposed as a technique to reduce the privacy leakage of machine learning. These empirical privacy defenses rely on the intuition that distilled ``student'' models protect the privacy of training data, as…
Self-distillation has emerged as a powerful framework for post-training LLMs, where a teacher conditioned on extra information guides a student without it, both from the same model. While this guidance is useful when the student has failed,…
The deployment and application of Large Language Models (LLMs) is hindered by their memory inefficiency, computational demands, and the high costs of API inferences. Traditional distillation methods, which transfer the capabilities of LLMs…
Knowledge distillation is widely applied in various fundamental vision models to enhance the performance of compact models. Existing knowledge distillation methods focus on designing different distillation targets to acquire knowledge from…
Recently, multi-modal content generation has attracted lots of attention from researchers by investigating the utilization of visual instruction tuning based on large language models (LLMs). To enhance the performance and generalization…
Deep learning algorithms have been shown to perform extremely well on many classical machine learning problems. However, recent studies have shown that deep learning, like other machine learning techniques, is vulnerable to adversarial…
Large Language Models (LLMs) have showcased their remarkable capabilities in diverse domains, encompassing natural language understanding, translation, and even code generation. The potential for LLMs to generate harmful content is a…
Leading open-source large language models (LLMs) such as Llama-3.1-Instruct-405B are extremely capable at generating text, answering questions, and solving a variety of natural language understanding tasks. However, they incur higher…
Large language models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing (NLP) tasks. However, these models are often difficult to deploy due to significant computational requirements and…
As deep learning (DL) models are widely and effectively used in Machine Learning as a Service (MLaaS) platforms, there is a rapidly growing interest in DL watermarking techniques that can be used to confirm the ownership of a particular…
Diffusion large language models (dLLMs) offer faster generation than autoregressive models while maintaining comparable quality, but existing watermarking methods fail on them due to their non-sequential decoding. Unlike autoregressive…
Billion-parameter Vision-Language-Action (VLA) policies have recently shown impressive performance in robotic manipulation, yet their size and inference cost remain major obstacles for real-time closed-loop control. We introduce…
On-policy distillation is a promising approach for transferring knowledge between language models, where a student learns from dense token-level signals along its own trajectories. This framework typically uses reverse KL divergence,…