1 citations · 2 across the 10 of their papers we have counts for
11 papers
Remember Less, Adapt Longer: Bounded-State In-Context Reinforcement Learning with Recurrent Summary Memory
Jiawen Wang, Cheng Xue, Peng Zhang +1
In-context reinforcement learning (ICRL) enables agents to adapt to new tasks without parameter updates, relying on memory to retain what they learn from experience. For agents ope…
Can Reasoning Models Detect Changes to their Chains of Thought?
Sathvik Napa, Utkarsh Singh, Chengyuan Xue +2
There are many reasons one may want to edit a model's chain of thought (CoT) -- e.g., to prefill it with reasoning from a stronger model or to remove steps that may yield unsafe ou…
Rapid Open-World Adaptation by Adaptation Principles Learning
Cheng Xue, Ekaterina Nikonova, Peng Zhang +1
Novelty adaptation is the ability of an intelligent agent to adjust its behavior in response to changes in its environment. This is an important characteristic of intelligent agent…
Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discovery
Ekaterina Nikonova, Cheng Xue, Jochen Renz
Deep reinforcement learning suffers from catastrophic forgetting and sample inefficiency making it less applicable to the ever-changing real world. However, the ability to use prev…
Knowledge Boosting: Rethinking Medical Contrastive Vision-Language Pre-Training
Xiaofei Chen, Yuting He, Cheng Xue +3
The foundation models based on pre-training technology have significantly advanced artificial intelligence from theoretical to practical applications. These models have facilitated…
NovPhy: A Testbed for Physical Reasoning in Open-world Environments
Chathura Gamage, Vimukthini Pinto, Cheng Xue +4
Due to the emergence of AI systems that interact with the physical environment, there is an increased interest in incorporating physical reasoning capabilities into those AI system…
Don't do it: Safer Reinforcement Learning With Rule-based Guidance
Ekaterina Nikonova, Cheng Xue, Jochen Renz
During training, reinforcement learning systems interact with the world without considering the safety of their actions. When deployed into the real world, such systems can be dang…
Measuring Difficulty of Novelty Reaction
Ekaterina Nikonova, Cheng Xue, Vimukthini Pinto +3
Current AI systems are designed to solve close-world problems with the assumption that the underlying world is remaining more or less the same. However, when dealing with real-worl…
Phy-Q as a measure for physical reasoning intelligence
Cheng Xue, Vimukthini Pinto, Chathura Gamage +3
Humans are well-versed in reasoning about the behaviors of physical objects and choosing actions accordingly to accomplish tasks, while it remains a major challenge for AI. To faci…
Hi-Phy: A Benchmark for Hierarchical Physical Reasoning
Cheng Xue, Vimukthini Pinto, Chathura Gamage +2
Reasoning about the behaviour of physical objects is a key capability of agents operating in physical worlds. Humans are very experienced in physical reasoning while it remains a m…
The Difficulty of Novelty Detection in Open-World Physical Domains: An Application to Angry Birds
Vimukthini Pinto, Cheng Xue, Chathura Nagoda Gamage +2
Detecting and responding to novel situations in open-world environments is a key capability of human cognition and is a persistent problem for AI systems. In an open-world, novelti…