🏢 College of Intelligence and Computing, Tianjin University

GSIP framework mitigates catastrophic forgetting in graph class incremental learning by preserving crucial graph information, achieving a 10% improvement in forgetting metrics.

Deep RL policy learning is improved by identifying and boosting key parameter update directions using a novel temporal SVD analysis, leading to more efficient and effective learning.

Dual-Stream Interactive Transformers (DSIT) revolutionizes single image reflection separation by using a novel dual-attention mechanism that captures inter- and intra-layer correlations, significantly…

PERIA: Holistic language & vision planning for complex robotic manipulation!

Boost OOD detection accuracy with diverseMix: a novel method enhancing auxiliary outlier diversity, provably improving generalization and achieving state-of-the-art results.

IRCAN tackles LLM knowledge conflicts by identifying and reweighting context-aware neurons, significantly improving context-sensitive outputs.

Deep Correlated Prompting enhances large multimodal models’ robustness against missing data by leveraging inter-layer and cross-modality correlations in prompts, achieving superior performance with mi…

Conditional Controllable Fusion (CCF) achieves training-free, adaptable image fusion by dynamically injecting fusion conditions into a pre-trained denoising diffusion model.