6 papers
Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space
Yiwei Chen, Bingqi Shang, Sijia Liu
Open-weight large language models (LLMs) are increasingly developed through complex, multi-stage pipelines, leading to intricate lineage relationships that reflect model origin, ow…
Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered
Sijia Liu, Yicheng Lang, Soumyadeep Pal +6
Zeroth-order (ZO) optimization, learning from finite differences of function evaluations without backpropagation, has recently regained attention in deep learning due to its memory…
Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning
Bingqi Shang, Yiwei Chen, Yihua Zhang +2
Large language model (LLM) unlearning has become a critical mechanism for removing undesired data, knowledge, or behaviors from pre-trained models while retaining their general uti…
One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
Mohan Zhang, Yihua Zhang, Jinghan Jia +3
Modern large reasoning models (LRMs) exhibit impressive multi-step problem-solving via chain-of-thought (CoT) reasoning. However, this iterative thinking mechanism introduces a new…
When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
Hongkang Li, Yihua Zhang, Shuai Zhang +3
Task arithmetic refers to editing the pre-trained model by adding a weighted sum of task vectors, each of which is the weight update from the pre-trained model to fine-tuned models…
Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing
Hanhui Wang, Yihua Zhang, Ruizheng Bai +3
Recent advancements in diffusion models have made generative image editing more accessible, enabling creative edits but raising ethical concerns, particularly regarding malicious e…