Zhixuan Lin

5 papers · 2019–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13) 🐣 Hot Topic Early Bird

Venues

ICLR (3) ICML (1) NeurIPS (1)

Top co-authors

Jindong Jiang (2) Yi-Fu Wu (2) Sungjin Ahn (2) Aaron Courville (2) Evgenii Nikishin (2) Gautam Singh (1) Xiaowei Zhou (1) Hujun Bao (1) weihao sun (1) Pierluca D'Oro (1)

Research topics

Deep Learning (3) Machine Learning (3) Architectures (3) Artificial Intelligence (2) Computer Vision (2) Core AI · Artificial Intelligence (2) Core Methods (2) Models (2) Core AI · Computer Vision (1) Generation (1) Learning Types (1) Processing (1) Techniques (1)

Keywords

generative model (2) reinforcement learning (1) feature learning (1) scene understanding (1) image retrieval (1) language modeling (1) object discovery (1) transformation invariance (1) off-policy learning (1) latent variable model (1) length extrapolation (1) geometric transformation (1) long-context modeling (1) forget gate (1) group convolution (1) object-centric world model (1) spatial attention (1) multi-modal uncertainty (1) temporal imagination (1) structured world model (1)

Papers

Forgetting Transformer: Softmax Attention with a Forget Gate ICLR 2025 The Curse of Diversity in Ensemble-Based Exploration ICLR 2024 Improving Generative Imagination in Object-Centric World Models ICML 2020 SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition ICLR 2020 GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs NeurIPS 2019