216 citations · 319 across the 46 of their papers we have counts for
9 papers · 1 filter
DOW-KE: Anchor-Free Multi-Layer Knowledge Editing via Direct End-to-End Weight Optimization
Ran Chen, Junbo Zhang, Qianli Zhou +2
Multi-layer locate-then-edit methods for knowledge editing first optimize target residual-stream activations (anchors) at selected layers, then realize them layer by layer as weigh…
DataRx: Missingness-Aware Sampling for Safer Large Language Model Task-Specific Fine-Tuning
Junbo Zhang, Qianli Zhou, Xinyang Deng +1
Task-specific fine-tuning can improve the performance of large language models (LLMs) on downstream tasks. However, our study reveals that task-specific fine-tuning can also weaken…
DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning
Junbo Zhang, Qianli Zhou, Xinyang Deng +3
Large language models (LLMs) suffer from degraded safety capabilities even when fine-tuned with benign datasets. However, existing methods for identifying safety-degrading samples…
Dasheng AudioGen: A Unified Model for Generating Coherent Audio Scenes from Text
Jiahao Mei, Heinrich Dinkel, Yadong Niu +7
Audio generation has long been fragmented, with speech, music, and sound effects produced by domain-specific models that fail to jointly generate coherent audio scenes from a singl…
ActivityEditor: Learning to Synthesize Physically Valid Human Mobility
Chenjie Yang, Yutian Jiang, Anqi Liang +3
Human mobility modeling is indispensable for diverse urban applications. However, existing data-driven methods often suffer from data scarcity, limiting their applicability in regi…
DashengTokenizer: One layer is enough for unified audio understanding and generation
Heinrich Dinkel, Xingwei Sun, Gang Li +8
This paper introduces DashengTokenizer, a continuous audio tokenizer engineered for joint use in both understanding and generation tasks. Unlike conventional approaches, which trai…