News

3 Papers Accepted at IJCAI-ECAI 2026

 

Held from 15 – 21 August 2026, the 35th International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2026) will be held in Bremen, Germany, featuring AI research across multiple domains.

Congratulations to the following researchers from A*STAR Centre for Frontier AI Research (A*STAR CFAR) on having their papers accepted at IJCAI-ECAI 2026:

  • Prof Ong Yew Soon, Chief Artificial Intelligence (AI) Scientist and Advisor
  • Dr Joey Zhou, Deputy Director, A*STAR CFAR and Principal Scientist
  • Dr Ooi Chin Chun, Investigator
  • Dr Pan Yuangang, Early Career Investigator
  • Dr Lin Jiaqi, Scientist
  • Dr Yao Yinghua, Scientist

List of accepted papers:

1.Learning Well-Structured Logits: Leveraging Vision–Language Complementarity for Open-World Test-Time Adaptation
Jia-Qi Lin, Yinghua Yao, Chang-Dong Wang, Yuangang Pan

We introduce VLCO, a complementary logit framework that leverages discriminative and vision-language models for robust open-world test-time adaptation.
2.Amortised Multi-Objective Optimisation Across Tasks with Generative Solution Modelling
Tingyang Wei***, Jiao Liu, Abhishek Gupta, Chin Chun Ooi, Puay Siew Tan, Yew-Soon Ong

We introduce a parametric multi-objective Bayesian optimiser that alternates between generative solution modelling and acquisition-driven search for optimising multiple tasks and solution generation for unseen parametrised tasks.
3.Unrestricted Targeted Deep Hashing Attack via Contrastive Latent Diffusion
Fan Yang , Chuan Ma, Yuhui Zheng , Xiaobo Shen and Joey Tianyi Zhou

This paper proposes UTDHA, the first unrestricted targeted attack for deep hashing using contrastive-guided latent diffusion, which generates adversarial examples by optimising in latent space to preserve naturalness while ensuring effectiveness. Through contrastive guidance and consistency constraints, UTDHA outperforms existing ℓp-norm based attacks in both attack success rate and imperceptibility on three benchmarks.

* denotes former CFAR student
** denotes former CFAR researcher
*** denotes current CFAR student
(accurate at time of posting)

> >More on IJCAI-ECAI 2026.