Jingbiao's Blog

「Hinc lucem et pocula sacra」

The Bitter Lesson of Personal Memory: Why OpenClaw Still Can't Remember You

Introducing ATM-Bench: The First Benchmark for Long-Term Personalized Memory QA

Paper: arxiv.org/abs/2603.01990 Code: github.com/JingbiaoMei/ATM-Bench Dataset: huggingface.co/datasets/Jingbiao/ATM-Bench Project Page: atmbench.github.io Ask your AI assistant or OpenC...

3-minute Pitch: ExPO-HM — Learning to Explain-then-Detect for Hateful Meme Detection

Published in ICLR 2026

Project page here Paper on arXiv / OpenReview Code available here Hateful meme detection has largely been framed as binary classification: a model outputs hateful or benign and, at best, a...

3-minute Pitch: Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection

Published in EMNLP 2025 Main Conference (Oral)

Project page here Paper on arXiv / ACL Anthology Code available here In our earlier work RGCL (ACL 2024), we showed that retrieval guidance over a CLIP-style encoder could sharpen hateful ...

3-minute Pitch: Retrieval Guided Contrastive Learning for Hateful Memes Detection

Published in ACL2024 Main Conference

Project Page here Code available here Hateful memes are captioned images promoting hostility towards specific social groups. Most hateful memes detection systems are logistic classifiers bui...

Sunset in Cambridge at Parkers Pieces

Parkers Pieces, Cambridge

Deploy Outline on Synology NAS

Docker images to use To deploy Outline, we need to use docker-compose to run and configure several docker images. The images we need to use are the main Outline image outlinewiki/outline:latest and...

Faiss-GPU

Faiss-GPU library import To use Faiss-GPU, you need to import torch before faiss. Otherwise, you will get an error like this when you are trying to use faiss gpu_index = faiss.index_cpu_to_gpu(res,...

Deploy Opensource Multimodal Large Language Models

LLaVA, MiniGPT4,...

LLaVA Project Page Paper Demo Data Model running the server python -m llava.serve.model_worker –host 0.0.0.0 –controller http://localhost:10000 –port 40000 –worker http://localhost:40000 –model-pa...

Deploy LLM on any device

Running LLaMA and LLaMA based models on your workstation, or your laptop, or even on your Synology NAS

Ubuntu Docker setup for Synology NAS Install Docker on Synology NAS as add-on package Tutorial here Open Package Center Search Docker Install Docker D...

The morning after the snow in Cambridge

Jesus Green, Cambridge St John’s College, Cambridge King’s College, Cambridge ————- Parker’s Piece, Cambridge