4 citations · 6 across the 17 of their papers we have counts for
18 papers
RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation
Leyi Pan, Shuchang Tao, Yunpeng Zhai +5
On-policy self-distillation (OPSD) provides dense, token-level supervision for reasoning models by aligning a model's own distribution with that under privileged context, typically…
mAVE: A Watermark for Joint Audio-Visual Generation Models
Luyang Si, Leyi Pan, Lijie Wen +1
Watermarking joint audio-visual generation supports vendor copyright protection and content provenance. However, independently valid audio and video watermarks do not establish a s…
FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving
Chia-chi Hsieh, Zan Zong, Xinyang Chen +3
The growing demand for large language models (LLMs) requires serving systems to handle many concurrent requests with diverse service level objectives (SLOs). This exacerbates head-…
d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models
Leyi Pan, Shuchang Tao, Yunpeng Zhai +8
Reinforcement learning (RL) is pivotal for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, existing dLLM policy optimization methods suffe…
MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Models
Leyi Pan, Sheng Guan, Zheyu Fu +9
We introduce MarkDiffusion, an open-source Python toolkit for generative watermarking of latent diffusion models. It comprises three key components: a unified implementation framew…
GenCNER: A Generative Framework for Continual Named Entity Recognition
Yawen Yang, Fukun Ma, Shiao Meng +2
Traditional named entity recognition (NER) aims to identify text mentions into pre-defined entity types. Continual Named Entity Recognition (CNER) is introduced since entity catego…
GapDNER: A Gap-Aware Grid Tagging Model for Discontinuous Named Entity Recognition
Yawen Yang, Fukun Ma, Shiao Meng +2
In biomedical fields, one named entity may consist of a series of non-adjacent tokens and overlap with other entities. Previous methods recognize discontinuous entities by connecti…
Toward Robust Multilingual Adaptation of LLMs for Low-Resource Languages
Haolin Li, Haipeng Zhang, Mang Li +4
Large language models (LLMs) continue to struggle with low-resource languages, primarily due to limited training data, translation noise, and unstable cross-lingual alignment. To a…
Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models
Leyi Pan, Zheyu Fu, Yunpeng Zhai +9
Omni-modal Large Language Models (OLLMs) that integrate visual, auditory, and textual processing face severe safety risks. They exhibit fragile defenses against audio-visual joint…
Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking
Yijie Xu, Aiwei Liu, Xuming Hu +2
As open-source large language models (LLMs) like Llama3 become more capable, it is crucial to develop watermarking techniques to detect their potential misuse. Existing watermarkin…
Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?
Leyi Pan, Aiwei Liu, Shiyu Huang +5
The radioactive nature of Large Language Model (LLM) watermarking enables the detection of watermarks inherited by student models when trained on the outputs of watermarked teacher…
TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights
Aiwei Liu, Haoping Bai, Zhiyun Lu +9
Direct Preference Optimization (DPO) has been widely adopted for preference alignment of Large Language Models (LLMs) due to its simplicity and effectiveness. However, DPO is deriv…
Can Watermarked LLMs be Identified by Users via Crafted Prompts?
Aiwei Liu, Sheng Guan, Yiming Liu +6
Text watermarking for Large Language Models (LLMs) has made significant progress in detecting LLM outputs and preventing misuse. Current watermarking techniques offer high detectab…
Interpretable Contrastive Monte Carlo Tree Search Reasoning
Zitian Gao, Boye Niu, Xuzheng He +5
We propose SC-MCTS*: a novel Monte Carlo Tree Search (MCTS) reasoning algorithm for Large Language Models (LLMs), significantly improves both reasoning accuracy and speed. Our moti…
WaterSeeker: Pioneering Efficient Detection of Watermarked Segments in Large Documents
Leyi Pan, Aiwei Liu, Yijian Lu +6
Watermarking algorithms for large language models (LLMs) have attained high accuracy in detecting LLM-generated text. However, existing methods primarily focus on distinguishing fu…
ChatCite: LLM Agent with Human Workflow Guidance for Comparative Literature Summary
Yutong Li, Lu Chen, Aiwei Liu +2
The literature review is an indispensable step in the research process. It provides the benefit of comprehending the research problem and understanding the current research situati…
Lost in Overlap: Exploring Logit-based Watermark Collision in LLMs
Yiyang Luo, Ke Lin, Chao Gu +3
The proliferation of large language models (LLMs) in generating content raises concerns about text copyright. Watermarking methods, particularly logit-based approaches, embed imper…
Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation
Aiwei Liu, Haoping Bai, Zhiyun Lu +5
Aligning large language models (LLMs) with human expectations without human-annotated preference data is an important problem. In this paper, we propose a method to evaluate the re…