10 papers
Neuron-Guided Fine-Tuning: Unlocking Efficient Alignment Mechanisms for Large Language Models
Zeyu Wu, Junchao Wu, Shudong Liu +8
Existing Supervised Fine-Tuning paradigms, particularly Full Parameter Fine-Tuning are often plagued by parameter redundancy, inconsistent data quality, and catastrophic forgetting…
ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models
Yujie Lin, Chengyi Yang, Zhishang Xiang +2
Large language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web corpora, raising concerns for p…
On the Robustness of Machine Unlearning for Vision-Language Models
Yujie Lin, Kaidi Jia, Jiayao Ma +2
Vision-language models (VLMs) may memorize undesirable information from training data, motivating growing interest in machine unlearning. In this work, we present the first systema…
m3BERT: A Modern, Multi-lingual, Matryoshka Bidirectional Encoder
Yaoxiang Wang, Simiao Zuo, Qingguo Hu +4
Embedding models are pivotal in industrial information retrieval systems like search and advertising. However, existing pretrained models often exhibit fixed architectures and embe…
Object Hallucination-Free Reinforcement Unlearning for Vision-Language Models
Kaidi Jia, Yujie Lin, Chengyi Yang +2
Vision-language models (VLMs) raise growing concerns about privacy, copyright, and bias, motivating machine unlearning to remove sensitive knowledge. However, existing methods prim…
GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models
Zhiwen Ruan, Yichao Du, Jianjie Zheng +6
A promising paradigm for adapting instruction-tuned language models is to learn task-specific updates on a pretrained base model and subsequently merge them into the instruction-tu…
Selective Contrastive Learning For Gloss Free Sign Language Translation
Changhao Lai, Rui Zhao, Xuewen Zhong +2
Sign language translation (SLT) converts continuous sign videos into spoken-language text, yet it remains challenging due to the intrinsic modality mismatch between visual signs an…
CNSL-bench: Benchmarking the Sign Language Understanding Capabilities of MLLMs on Chinese National Sign Language
Rui Zhao, Xuewen Zhong, Xiaoyun Zheng +2
Sign language research has achieved significant progress due to the advances in large language models (LLMs). However, the intrinsic ability of LLMs to understand sign language, es…
ExPosST: Explicit Positioning with Adaptive Masking for LLM-Based Simultaneous Machine Translation
Yuzhe Shang, Pengzhi Gao, Yazheng Yang +4
Large language models (LLMs) have recently demonstrated promising performance in simultaneous machine translation (SimulMT). However, applying decoder-only LLMs to SimulMT introduc…
Scaling Model and Data for Multilingual Machine Translation with Open Large Language Models
Yuzhe Shang, Pengzhi Gao, Wei Liu +2
Open large language models (LLMs) have demonstrated improving multilingual capabilities in recent years. In this paper, we present a study of open LLMs for multilingual machine tra…