BPM Team of Tsinghua University
Pinned Loading
Repositories
- MarkLLM Public
MarkLLM: An Open-Source Toolkit for LLM Watermarking.（EMNLP 2024 System Demonstration)
THU-BPM/MarkLLM’s past year of commit activity - MarkDiffusion Public
MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Models
THU-BPM/MarkDiffusion’s past year of commit activity - Omni-SafetyBench Public
Code for paper "Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models".
THU-BPM/Omni-SafetyBench’s past year of commit activity - Watermark-Radioactivity-Attack Public
Code and data for paper "Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?". (ACL 2025 Main)
THU-BPM/Watermark-Radioactivity-Attack’s past year of commit activity - WaterSeeker Public
Code and data for paper "WaterSeeker: Pioneering Efficient Detection of Watermarked Segments in Large Language Models." accepted by NAACL 2025.
THU-BPM/WaterSeeker’s past year of commit activity - ICT Public
Official repo for ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models
THU-BPM/ICT’s past year of commit activity - Watermarked_LLM_Identification Public
Code and data for paper "Can Watermarked LLMs be Identified by Users via Crafted Prompts?" Accepted by ICLR 2025 (Spotlight)
THU-BPM/Watermarked_LLM_Identification’s past year of commit activity - Robust_Watermark Public
Code and data for paper "A Semantic Invariant Robust Watermark for Large Language Models" accepted by ICLR 2024.
THU-BPM/Robust_Watermark’s past year of commit activity - Env-DocRE Public
Code and data for ACL 2024 Findings paper "On the Robustness of Document-Level Relation Extraction Models to Entity Name Variations"
THU-BPM/Env-DocRE’s past year of commit activity - MRE Public
THU-BPM/MRE’s past year of commit activity
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…