← Search

Chengfeng Wu

2 accepted papers

2026

CORE-MTL: Rethinking Gradient Balancing via Causal Orthogonal Representations

ICML 2026poster

Multi-task learning (MTL) aims to construct a joint model for multiple tasks by sharing a common representation across domains. To achieve this goal, existing optimization-centric methods either balance task gradients or modify the shared architecture. However, as these approaches remain agnostic to…

Cited by 0SourceScholar
2026

Global-Lens Transformers: Adaptive Token Mixing for Dynamic Link Prediction

AAAI 2026technical

Dynamic graph learning plays a pivotal role in modeling evolving relationships over time, especially for temporal link prediction tasks in domains such as traffic systems, social networks, and recommendation platforms. While Transformer-based models have demonstrated strong performance by capturing

Cited by 0SourcePDFScholar