/ Research /
Pioneering Causality-Empowered Models for the
Next Generation of Intelligence
Advancing the frontier of causal intelligence - by develop foundation models and agents that reason not only from patterns, but from cause-and-effect.
Unlike large language models (LLMs) that rely on next-token prediction without explicit causal structure, our systems are designed to be interpretable, generalizable, and intervention-ready.
These innovations strengthen the foundations
of intelligence systems across domains.
Research Directions
Research pioneers pillars of causality-empowered AI
Related Paper List
Research Topics
Why Causality Matters
While today’s LLMs excel at fluency and pattern recognition, they face critical limitations
linkedin →
X →
© 2025 Abel.AI, Inc. All rights reserved.
Limited
Interpretability
Coherent outputs without structured causal representations.
Weak Generalization
Fragile under out-of-distribution shifts.
No Interventions
or Counterfactuals
Incapable of systematic “what-if” reasoning for decision support.
"Towards generalizable reinforcement learning via causality-guided self-adaptive representations." Yang, Yupei, Biwei Huang, Fan Feng, Xinyue Wang, Shikui Tu, and Lei Xu. arXiv preprint arXiv:2407.20651 (2024).
"Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning." Wang, Xinyue, and Biwei Huang. arXiv preprint arXiv:2505.08361 (2025).
"Learning world models with identifiable factorization." Liu, Yuren, Biwei Huang, Zhengmao Zhu, Honglong Tian, Mingming Gong, Yang Yu, and Kun Zhang. Advances in Neural Information Processing Systems 36 (2023): 31831-31864.
03｜Causal Driven World Model
05｜Counterfactual Reasoning
"Natural counterfactuals with necessary backtracking." Hao, Guang-Yuan, Jiji Zhang, Biwei Huang, Hao Wang, and Kun Zhang. Advances in Neural Information Processing Systems 37 (2024): 14962-14995.
"Counterfactual generation with identifiability guarantees." Yan, Hanqi, Lingjing Kong, Lin Gui, Yuejie Chi, Eric Xing, Yulan He, and Kun Zhang. Advances in Neural Information Processing Systems 36 (2023): 56256-56277.