I am happy to announce that I have joined Hunan University (#119 in the U.S. News Best Global Universities Ranking 2025) as an Assistant Professor. I look forward to collaborating with more of you in the future with the topic of Multimodal learning.😀.

RT @ZixuanYI_: Happy to share that our paper entitled “Enhancing Recommender Systems: Deep Modality Alignment with Large Multi-Modal Encode….

RT @ir_glasgow: A large contingent of our staff and students at @GlasgowCS are currently heading to #sigir2024! Do check out the papers and….

#ICASSP2024 Happy to attend IEEE International Conference on Acoustics, Speech, and Signal Processing! Really good welcome ceremony and nice K-pop welcome reception!

Also Special thanks to Jheng-Hong Yang et al. @mattjustram for the AToMiC dataset! Can't achieve this paper without their efforts!.

Glad to share that our paper "CFIR: Fast and Effective Long-Text to Image Retrieval for Large Corpora" has been accepted at #SIGIR2024 as a full paper, a joint work with @Solis_xurige, @richardm_, and @joemonj.

RT @ir_glasgow: Excellent summary by @claclarke of how IR evaluation has changed in the era of LLMs #ecir2024

RT @ecir2024: Here are your volunteers for #ecir2024 Look out for people in blue t-shirts! 👕 They will be around all week to help you out,….

RT @ecir2024: Hope you heard the bell!. Time for the second session of the day!! #ecir2024.

RT @ir_glasgow: In addition to hosting the #ecir2024 conference next week, many of our staff and students @GlasgowCS will be actively engag….

RT @TheBMVA: Passionate about #ComputerVision, #MachineLearning, and #AI? Be part of something extraordinary by sponsoring #BMVC and #MIUA….

RT @ecir2024: #ecir2024 will feature a great #IndustryDay programme, organised by @olivierjeunen and @imoulinier 1/6.

You can view the full paper at: In this paper, we leverage pre-training capabilities Multimodal Large Language Models (MLLMs) to enable the creation of a simplified framework, thus mitigating the need for task-specific encoders.

Happy to announce that our full paper is accepted by CORE A* IEEE International Conference on Robotics and Automation (ICRA 2024): ZIJUN LONG, George Killick, Richard McCreadie, Gerardo Aragon Camarasa. 'RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language Models'.

RT @ecir2024: Just over one week to go until the workshop proposals submission deadline: Sep 06, 2023. Looking forward to seeing all the gr….

Proud to present our paper: ”A robust Vision Transformer for Crisis Image Classifications” at ISCRAM 2023. @iscram2023 @mimran15

Built the new work station: 13900K + 4090 with water cooling system. Hope it does not overheat🙃

RT @craig_macdonald: .@IDAglasgow and .@ir_glasgow photo today. Reckon the professional photographer will take a few better ones… https://t….

RTX 4090 is really impressive!

RT @ir_glasgow: For the first time since the start of the pandemic, we have been able to have an in person dinner to celebrate the successf….