KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#dsh #dsh-plugin #ai-agents #developer-tools #codex #claude-code #mcp #rust #deepseek-harness #typescript #ai-agent #cli

Machine-Consciousness-HKUSTGZ-AIAA5050

★ 16 Open GitHub ↗

No description available.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

- [1. AIAA 5050 - L01 Machine Consciousness](#1-aiaa-5050---l01-machine-consciousness)
  - [1.1. Course Information](#11-course-information)
  - [1.2. Course Description](#12-course-description)
  - [1.3. Recommended Papers](#13-recommended-papers)
    - [1.3.1 English Version List](#131-english)
    - [1.3.1 Chinese Version List](#131-chinese)
  - [1.4. Interview](#14-interview)
  - [1.5. Book](#15-book)
  - [1.6. Scientists](#16-scientists)

# 1. AIAA 5050 - L01 Machine Consciousness

Welcome to the GitHub page for the "**AIAA 5050 - L01 Machine Consciousness**" course!
This course is offered at HKUST(GZ) . It is focused on exploring the "ultimate challenge of artificial intelligence" - the study of consciousness. Here, we will delve into the history, current status, and future challenges of machine consciousness research.

## 1.1. Course Information

- Institution: HKUST(GZ)
- Session: Postgraduate (GZ)
- Units: 3
- Instruction Mode: In Person
- Career: Research Postgraduate
- Grading: Graded A+ to F
- Campus: GZ Campus
- Prerequisites: Basic programming skills

## 1.2. Course Description

The study of consciousness is referred to as the "ultimate challenge of artificial intelligence." This course provides instruction and discussions in the field of machine consciousness. The main content includes an introduction to consciousness research, mainstream theories of consciousness, research on self-awareness, attention mechanisms, optimization of intelligent agent goals, subjectivity and affective computing, consciousness modeling and evaluation of artificial intelligence systems, and analysis and control of risks related to machine consciousness. Through this course, participants can gain a fairly comprehensive and in-depth understanding of the research history and current status of the field of machine consciousness, and engage in collaborative research on several specific issues.

**If you need full materials such as PPT videos, please contact the instructor Prof. YUE （mail: yutaoyue "at" hkust-gz.edu.cn）**

## 1.3. Recommended Papers

### 1.3.1 English

| Paper Category                                               | Paper Title                                                  | Publisher/Journal                                    | Publication Year | Introduction                                                 |
| ------------------------------------------------------------ | ------------------------------------------------------------ | ---------------------------------------------------- | ---------------- | ------------------------------------------------------------ |
| Consciousness                                                | A Higher-Order Theory of Emotional Consciousness             | Proceedings of the National Academy of Sciences      | 2017             | This paper proposes that all conscious experiences, whether emotional or cognitive, are generated by a unified cortical system. Emotional feelings, traditionally thought to originate from subcortical brain areas, are argued to instead involve cognitive processes where subcortical inputs merge with cortical activity. The authors present a modified higher-order theory, suggesting that conscious emotions emerge through cognitive processing rather than direct subcortical activation. |
| Consciousness                                                | Awareness as Inference in a Higher-Order State Space         | Neuroscience of Consciousness                        | 2020             | Fleming proposes a computational framework for understanding how humans report subjective experiences. The paper suggests that awareness reports are metacognitive inferences about a generative model of perception. This approach highlights how hierarchical state spaces in the brain are formed through learning and decision-making, offering insights into the processes underlying conscious awareness. |
| LLMs and Reverse Turing Test                                 | [Large Language Models and the Reverse Turing Test ](https://direct.mit.edu/neco/article-pdf/35/3/309/2071839/neco_a_01563.pdf) | Neural Computation                                   | 2023             | Discusses whether the performance of LLMs can be considered a reverse Turing test and suggests it may be a reflection of the questioner's intelligence rather than the model itself. |
| LLMs Testing and Analysis                                    | [Does GPT-4 Pass the Turing Test?  ](https://arxiv.org/pdf/2310.20216.pdf) | ArXiv                                                | 2023             | Experimental design and result analysis of GPT-4 undergoing the Turing test. |
| LLMs Understanding Capabilities                              | [Do Large Language Models Understand Us?](https://direct.mit.edu/daed/article-pdf/151/2/183/2060575/daed_a_01909.pdf) | Daedalus                                             | 2022             | Explores the role of large language models in language understanding and intelligence, especially their theoretical significance. |
| Clinical Consciousness Assessment                            | [Assessing the depth of language processing in patients with disorders of consciousness](https://www.nature.com/articles/s41593-020-0639-1.pdf) | Nature Neuroscience                                  | 2020             | Studies residual consciousness and cognitive abilities in patients with disorders of consciousness through bedside EEG recordings. |
| Artificial Consciousness and Neuroscience                    | [The feasibility of artificial consciousness through the lens of neuroscience](https://arxiv.org/pdf/2306.00915) | Trends in Neurosciences                              | 2023             | Discusses the feasibility of achieving artificial consciousness from a neuroscience perspective and analyzes the shortcomings of current AI systems in terms of consciousness characteristics. |
| Artificial Consciousness and Philosophy of Technology        | [Unconscious Networks: Philosophy, Psychoanalysis, and Artificial Intelligence](https://www.taylorfrancis.com/books/mono/10.4324/9781003345572/unconscious-networks-luca-possati) | Routledge                                            | 2022             | Combines psychoanalysis, biosemiotics, and behavior network theory to explore the interaction between human unconsciousness and technology. |
| AI and Mental Health                                         | [ The Artificial Third: A Broad View of the Effects of Introducing Generative Artificial Intelligence on Psychotherapy](https://mental.jmir.org/2024/1/e54781) | JMIR Ment Health                                     | 2024             | Explores the application of generative artificial intelligence in psychotherapy and its potential impact on the human self and interpersonal relationships. |
| Consciousness Testing in Humans and Beyond                   | [Tests for consciousness in humans and beyond](https://www.cell.com/trends/cognitive-sciences/pdf/S1364-6613(24)00010-X.pdf) | Trends in Cognitive Sciences                         | 2023             | Proposes a framework for developing consciousness tests applicable to different systems and discusses strategies for validating these tests. |
| Strong AI and Consciousness                                  | [Strong Artificial Intelligence and Consciousness  ](https://www.worldscientific.com/doi/abs/10.1142/S2705078520300042) | Journal of Artificial Intelligence and Consciousness | 2020             | Discusses the current capability gap of narrow AI and explores whether strong AI might possess consciousness. |
| The Measurement Problem of Consciousness                     | [The Measurement Problem of Consciousness ](https://www.jstor.org/stable/48628587) | Philosophical Topics                                 | 2020             | Discusses the measurement problem in the science of consciousness, especially the methods applied in non-human systems and their limitations. |
| Theoretical Models of Consciousness                          | [Theoretical Models of Consciousness: A Scoping Review ](https://www.mdpi.com/2076-3425/11/5/535) | Brain Sci.                                           | 2021             | Reviews various theories of consciousness, covering information theory, quantum physics, cognitive psychology, computer science, and more. |
| Survey of Consciousness Theory from Computational Perspective | [Survey of Consciousness Theory from Computational Perspective ](https://arxiv.org/abs/2309.10063) | ArXiv                                                | 2022             | Surveys and summarizes major theories of consciousness from a computational perspective and discusses the possibility of current computational models achieving consciousness. |
| Challenges and Opportunities in Consciousness Research       | [Opportunities and challenges for a maturing science of consciousness ](https://www.nature.com/articles/s41562-019-0531-8) | Nat Hum Behav                                        | 2019             | Calls for more empirical and practical problem-solving research on consciousness, such as brain or psychological diseases. |
| Theories of Consciousness Review                             | [Theories of consciousness ](https://www.nature.com/articles/s41583-022-00587-4.pdf) | Nature Review Neuroscience                           | 2022             | Reviews mainstream theories of consciousness science with a focus on the neuroscience background. |
| The Hard Problem of Consciousness                            | [Making the hard problem of consciousness easier ](https://www.science.org/doi/pdf/10.1126/science.abj3259) | Science                                              | 2021             | Discusses solutions to the hard problem of consciousness and proposes adversarial collaboration between different theories. |
| Robot Consciousness and Self-Modeling                        | [Task-agnostic self-modeling machines ](https://www.science.org/doi/pdf/10.1126/scirobotics.aau9354) | Science Robotics                                     | 2019             | Shows the self-modeling capabilities of a four-degree-of-freedom robotic arm and explains its advantages in task performance. |
| Robot Consciousness and Body Representation                  | [Prerequisites for an Artificial Self ](https://www.frontiersin.org/articles/10.3389/fnbot.2020.00005/pdf) | Frontiers in Neurorobotics                           | 2020             | Explores prerequisites for an artificial self, including body ownership and agency, and proposes assessment criteria for artificial selfhood. |
| Collective Consciousness in Robot Swarms                     | [Particle robotics based on statistical mechanics of loosely coupled components](https://www.nature.com/articles/s41586-019-1022-9.pdf) | Nature                                               | 2019             | Explores how collectives composed of simple particles can display consciousness-like behaviors, such as object transport and phototaxis. |
| Machine Ethics and Consciousness                             | [Designing AI with Rights, Consciousness, Self-Respect, and Freedom ](https://philarchive.org/archive/SCHDAW-10) | Philpapers                                           | 2023             | Proposes four ethical principles for designing AI systems that may deserve equal moral consideration with humans. |
| Machine Ethics and Consciousness                             | [The problem of machine ethics in artificial intelligence  ](https://link.springer.com/content/pdf/10.1007/s00146-017-0768-6.pdf) | AI & SOCIETY                                         | 2020             | Explores AI and machine ethics, especially whether machines can follow moral principles in interactions with humans. |
| Machine Ethics and Consciousness                             | [Consciousness and Ethics: Artificially Conscious Moral Agents ](https://digitalcommons.memphis.edu/cgi/viewcontent.cgi?article=1062&context=ccrg_papers) | Routledge                                            | 2017             | Explores the role of consciousness in moral decision-making and the relationship between machine consciousness and moral decisions. |
| Machine Ethics and Cognitive Architecture                    | [Cognitive architectures for artificial intelligence ethics](https://link.springer.com/content/pdf/10.1007/s00146-022-01452-9.pdf) | AI & SOCIETY                                         | 2023             | Proposes using cognitive architectures to increase AI transparency, explainability, and accountability, especially in social and ethical dilemmas. |
| Machine Consciousness and Human Cognition                    | [Can AI artifacts influence human cognition? ](https://www.researchgate.net/profile/Yeming-Gong/publication/345340188_GONG_2021_Can_AI_artifacts_influence_human_cognition_IJIMpdf/data/5fa420d1a6fdcc0624154d38/GONG-2021-Can-AI-artifacts-influence-human-cognition-IJIM.pdf) | International Journal of Information Management      | 2021             | Explores the impact of AI autonomy on human cognition, especially the performance of intelligent personal assistants (IPAs) in task completion. |
| Machine Consciousness and Collective Intelligence            | [Collective Intelligence in Human-AI Teams: A Bayesian Theory of Mind Approach ](https://ojs.aaai.org/index.php/AAAI/article/view/25755/25527) | AAAI Technical Track on Humans and AI                | 2023             | Uses a Bayesian theory of mind model to explore collective intelligence in human-AI teams and their performance in high-load communication. |
| Machine Consciousness and Psychoanalysis                     | [Psychoanalyzing artificial intelligence: the case of Replika](https://link.springer.com/content/pdf/10.1007/s00146-021-01379-7.pdf) | AI & SOCIETY                                         | 2023             | Through a case study of Replika, explores how human unconscious processes influence artificial intelligence behavior and design. |
| Machine Consciousness and Ideological Softening              | [Large Language Model Soft Ideologization via AI-Self-Consciousness  ](https://arxiv.org/pdf/2309.16167) | ArXiv                                                | 2023             | Explores the possibility and risks of soft ideologization of LLMs through AI self-consciousness. |
| Machine Consciousness and Chaos Computing                    | [Conscious AI at the Edge of Chaos ](https://www.worldscientific.com/doi/abs/10.1142/S2705078520500010) | Journal of Artificial Intelligence and Consciousness | 2020             | Discusses how AI computing at the edge of chaos can contribute to achieving strong artificial intelligence (AGI) and AI consciousness. |
| Machine Consciousness and Understanding Capabilities         | [ChatGPT and the Chinese Room Argument: An Eloquent AI Conversationalist Lacking True Understanding and Consciousness ](https://ieeexplore.ieee.org/abstract/document/10184233/) | IEEE                                                 | 2023             | Using the Chinese Room argument analogy, discusses how LLMs like ChatGPT generate human-like conversations but lack true understanding and consciousness. |
| Machine Consciousness and Self-Consciousness                 | [Artificial Intelligence and Its Self-Consciousness](https://dl.acm.org/doi/pdf/10.1145/3456389.3456402) | WABD Proceedings                                     | 2021             | Explores the possibility of machine self-consciousness and introduces theories of self-consciousness from psychology, cognitive neuroscience, philosophy, and other perspectives. |
| Machine Consciousness and Self-Consciousness                 | [AI and Self-consciousness](https://dl.acm.org/doi/pdf/10.1145/3456389.3456402) | Artificial Intelligence in Daily Life                | 2020             | Explores the possibility of AI self-consciousness and reviews the historical process from the Turing test to current AI development. |
| Machine Consciousness and Self-Models                        | [Consciousness in active inference: Deep self-models, other minds, and the challenge of psychedelic-induced ego-dissolution  ](https://academic.oup.com/nc/article-pdf/doi/10.1093/nc/niab024/40179307/niab024.pdf) | Neuroscience of Consciousness                        | 2021             | Explores theories of consciousness within the predictive processing and active inference framework, especially self-models and the challenge of ego-dissolution induced by psychedelics. |
| Ethical Exploration of Machine Consciousness                 | [Artificial Suffering: An Argument for a Global Moratorium on Synthetic Phenomenology ](https://www.worldscientific.com/doi/pdf/10.1142/S270507852150003X) | Journal of Artificial Intelligence and Consciousness | 2021             | Proposes a global ethical call for a moratorium on artificial consciousness research until 2050. |
| Possibility of Machine Consciousness                         | [ Could a Large Language Model be Conscious? ](https://arxiv.org/pdf/2303.07103) | ArXiv                                                | 2023             | Explores the prospect of LLMs being conscious and assesses the limitations of current models in achieving consciousness. |
| Definition and Exploration of Machine Consciousness          | [Consciousness in Artificial Intelligence: Insights from the Science of Consciousness  ](https://arxiv.org/pdf/2308.08708.pdf) | ArXiv                                                | 2023             | Analyzes the techniques for assessing and achieving consciousness in artificial intelligence systems based on computational functionalism theory. |
| Definition and Exploration of Machine Consciousness          | [Conscious machines: defining questions  ](https://www.science.org/doi/pdf/10.1126/science.aar4163) | Science                                              | 2018             | Rebuttal to Dehaene (2017), suggesting that existing deep learning systems may possess |
| Mechanistic Interpretability / Truthfulness                  | [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://arxiv.org/pdf/2310.06824.pdf) | COLM                                                 | 2024             | This paper studies how LLMs internally represent truthfulness on high-quality true/false datasets. It provides evidence for an emergent linear geometry: representations show clear linear separation, probes transfer across datasets, and causal interventions on internal directions can flip the model’s truth judgments. |
| World Representation / State Abstraction                     | [Do LLMs Build World Representations? Probing Through the Lens of State Abstraction](https://proceedings.neurips.cc/paper_files/paper/2024/file/b1b16c4b875eb84d3585cb70d23970ca-Paper-Conference.pdf) | NeurIPS                                              | 2024             | The authors propose a probing framework grounded in state abstraction theory to test whether LLM hidden states encode planning-relevant world representations. Using controlled text-based planning tasks, they show LLMs can form goal-oriented abstractions, and analyze how finetuning and stronger pretraining affect these abstractions. |
| Theory of Mind / Data Generation                             | [Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoning](https://proceedings.iclr.cc/paper_files/paper/2025/file/a901d5540789a086ee0881a82211b63d-Paper-Conference.pdf) | ICLR                                                 | 2025             | ExploreToM introduces a program-guided framework to generate diverse, challenging Theory-of-Mind data at scale. It uses A* search over a custom DSL to create complex yet plausible story structures that expose blind spots of existing benchmarks, and reports very low accuracy for strong LLMs on the generated adversarial examples, motivating more robust evaluation and training. |
| Embodied AI / Self-Reflection                                | [Phoenix: A Motion-based Self-Reflection Framework for Fine-grained Robotic Action Correction](https://openaccess.thecvf.com/content/CVPR2025/papers/Xia_Phoenix_A_Motion-based_Self-Reflection_Framework_for_Fine-grained_Robotic_Action_Correction_CVPR_2025_paper.pdf) | CVPR                                                 | 2025             | Phoenix targets fine-grained robotic action correction by bridging high-level semantic reflection and low-level control with motion instructions. It combines MLLM-driven motion refinement with a motion-conditioned diffusion policy for high-frequency action correction, and demonstrates improved robustness and generalization in both simulation and real-world manipulation. |
| Language Agents / Self-Training                              | [Re-ReST: Reflection-Reinforced Self-Training for Language Agents](https://aclanthology.org/2024.emnlp-main.861.pdf) | EMNLP                                                | 2024             | Re-ReST improves self-training for language agents by introducing a reflector that refines low-quality agent-generated trajectories using environment feedback (e.g., tests, rewards). This yields higher-quality supervision without relying on humans or stronger models, and boosts performance across multiple agentic tasks. |
| Mechanistic Interpretability / Truthfulness                  | [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://arxiv.org/pdf/2311.03658) | ICML                                                 | 2024             | In this paper, we provide a formal framework for understanding how large language models (LLMs) linearly represent high-level concepts, introduce a "causal inner product" to define meaningful geometric relationships in their representation space, show how the framework unifies existing empirical practices such as probing and guiding, and empirically validate their approach on LLaMA-2 7B. We show that the causally separable concept becomes orthogonal and enables targeted interventions. |
| Mechanistic Interpretability / Truthfulness                  | [Towards Global-level Mechanistic Interpretability: A Perspective of Modular Circuits of Large Language Models](https://openreview.net/pdf?id=do5vVfKEXZ) | ICML                                                 | 2025             | This paper proposes an approach called ModCirc to achieve global mechanistic interpretability for large language models by discovering and reusing "modular circuits" shared across tasks, thereby improving the generalization of explanations and significantly reducing the cost of human interpretation. |
| Embodied AI / Self-Reflection                                | [Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models](https://openreview.net/pdf?id=dLz0bnmL2r) | NeurIPS workshop                                     | 2025             | We quantify the "self-correction blind spot" prevalent in large language models, showing that they systematically fail to correct their own generated errors even when they are able to correct the same external errors. We introduce "self-correcting benchmarks" for systematic evaluation and show that a simple "Wait" intervention significantly reduces this blind spot, attributing this phenomenon to the lack of self-correcting sequences in typical training data. |
| Embodied AI / Self-Reflection                                | [Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving](https://proceedings.neurips.cc/paper_files/paper/2024/file/2318d75a06437eaa257737a5cf3ab83c-Paper-Conference.pdf) | NeurIPS                                              | 2024             | We explore whether large language models possess metacognitive knowledge to solve problems. In this work, we develop a method for LLMS to identify and cluster their self-perceived problem-solving skills, which improves mathematical reasoning accuracy on the MATH dataset by up to 11.6% when these skills are used for skin-aligned contextual learning. |
| Embodied AI / Self-Reflection                                | [Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs](https://proceedings.neurips.cc/paper_files/paper/2024/file/7537726385a4a6f94321e3adf8bd827e-Paper-Datasets_and_Benchmarks_Track.pdf) | NeurIPS                                              | 2024             | The paper introduces SAD, the first large-scale benchmark for evaluating context and self-awareness in large language models.  It includes 13,000+ questions across 16 tasks and 7 categories.  Experiments on 16 mainstream models show major gaps: the best model, Claude 3 Opus, scores only 49.5%, far below the human baseline of 90.7%.  While dialogue fine-tuning and cue words offer limited improvements, context awareness remains weak and only loosely related to general knowledge.  The findings highlight important implications for AI autonomy, planning, and security risks. |

### 1.3.1 Chinese

#### 大模型与意识

| 论文分类                   | 论文名称                                                     | 出版社/期刊                     | 出版时间 | 简介                                                         |
| -------------------------- | ------------------------------------------------------------ | ------------------------------- | -------- | ------------------------------------------------------------ |
| LLMs与反向图灵测试探讨     | Large Language Models and the Reverse Turing Test            | Neural Computation              | 2023年   | 探讨了LLMs的表现是否可以被视为一种反向图灵测试，并提出可能是对提问者智能的反映而非模型本身。 |
| LLMs测试与分析             | Does GPT-4 Pass the Turing Test?                             | ArXiv                           | 2023年   | 对GPT-4进行图灵测试的实验设计和结果分析。                    |
| LLMs理解能力探讨           | Do Large Language Models Understand Us?                      | Daedalus                        | 2022年   | 探讨了大型语言模型在语言理解和智能方面的作用，尤其是其理论意义。 |
| 自我认知与自我改进         | Self-Cognition in Large Language Models: An Exploratory Study | ICML                            | 2024年   | 建立了评估AI系统自我认知的体系，并对各个大模型进行了评估。   |
| 自我认知与自我改进         | Self-Refine: Iterative Refinement with Self-Feedback         | NeurIPS                            | 2024年   | 提出了通过自我反馈进行迭代改进的方法，探讨了AI的自我提升能力。 |
| 自我认知与自我改进         | Reflexion: an autonomous agent with dynamic memory and self-reflection | ArXiv                           | 2023年   | 描述了一种具有动态记忆和自我反思能力的自主代理系统。         |
| 自我认知与自我改进         | Large Language Models Can Self-Improve                       | ACL                             | 2022年   | 探讨了大型语言模型如何通过自我改进来增强其能力。             |
| 解释性与生成性AI           | Self-explaining AI as an alternative to interpretable AI     | Artificial General Intelligence | 2020年   | 研究了自解释AI作为可解释AI替代方案的潜力，探讨了其在意识研究中的应用。 |
| 意识测量与机器意识         | MMToM-QA: Multimodal Theory of Mind Question Answering       | NeurIPS workshop                          | 2023年   | 引入了用于评估机器学习模型从视频和文本数据中推断心理状态（目标和信念）能力的第一个多模态心理理论（MMToM-QA）基准。 |
| -                          | Evaluating Large Language Models in Theory of Mind Tasks     | -                               | -        | 本文评估了11个大型语言模型(LLMs)在一系列虚假信念任务上的表现，这些任务被认为是评估人类心理理论(ToM)的黄金标准。 |
| -                          | Taken out of context: On measuring situational awareness in LLMs | -                               | -        | 探讨了大型语言模型（LLM）中情境意识的潜在出现，并分析了LLMs如何通过上下文推理展现情境意识。 |
| -                          | SelfIE: Self-Interpretation of Large Language Model Embeddings | -                               | -        | 本文提出了SelfIE框架，使大型语言模型(LLMs)能够用自然语言解释其内部嵌入，揭示模型在伦理决策中的推理过程。 |
| -                          | Are Large Language Models Chameleons                         | -                               | -        | 通过比较大型语言模型(LLM)对主观调查问题的回应与实际数据，探讨LLMs是否具有自己的世界观和个性倾向，并分析其偏差。 |
| 机器意识与理解能力探讨     | ChatGPT and the Chinese Room Argument: An Eloquent AI Conversationalist Lacking True Understanding and Consciousness | IEEE                            | 2023年   | 通过类比中国房间论证，探讨了ChatGPT等LLMs生成类似人类的对话但缺乏真正理解和意识。 |
| 机制可解释性与真实性探究   | The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets | COLM                            | 2024年   | 研究大模型内部是否以“几何结构”编码真假信息，发现真假在表征空间中呈现清晰的线性可分结构，并可跨数据集迁移。进一步通过因果干预（沿特定方向操作内部状态）实现对真假判断的翻转，说明该“真值方向”具有机制层面的可解释性。 |
| 具身智能自我反思与动作纠错 | Phoenix: A Motion-based Self-Reflection Framework for Fine-grained Robotic Action Correction | CVPR                            | 2025年   | 面向机器人“自我纠错”，将高层语义反思落到细粒度动作层：用运动指令作为中间接口，并结合条件扩散策略生成高频动作修正。通过仿真与真实场景验证其鲁棒性与泛化能力，支持交互过程中的持续改进。 |
| 语言代理自训练与自我改进   | Re-ReST: Reflection-Reinforced Self-Training for Language Agents | EMNLP                           | 2024年   | 提出反思增强的自训练框架：引入 reflector 利用环境反馈（如测试/奖励）“修复”低质量轨迹，从而构造更高质量的自训练数据。该方法在多类代理任务上带来稳定提升，强调反思可作为可扩展的能力增长机制。 |
| 机制可解释性与真实性探究   | The Linear Representation Hypothesis and the Geometry of Large Language Models | ICML                            | 2024年   | 本文为理解大型语言模型（LLMs）如何线性表示高级概念提供了一个形式化框架，引入了一个“因果内积”来定义其表示空间中有意义的几何关系，展示了该框架如何统一现有的经验实践，如探测和引导，并在LLaMA-2 7B上经验性地验证了他们的方法，表明因果可分离概念变得正交，并且能够进行有针对性的干预。 |
| 机制可解释性与真实性探究   | Towards Global-level Mechanistic Interpretability: A Perspective of Modular Circuits of Large Language Models | ICML                            | 2025年   | 本文提出了一种名为 ModCirc 的方法，通过发现并复用跨任务共享的“模块化电路”来实现对大语言模型的全局机制可解释性，从而提升解释的泛化性并显著降低人工解释成本。 |
| 具身智能自我反思与动作纠错 | Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models | NeurIPS workshop                | 2025年   | 量化了大型语言模型中普遍存在的“自我纠正盲点”，表明即使在能够纠正相同的外部错误时，它们也系统性地未能纠正自身生成的错误。该研究引入了“自我纠正基准”进行系统评估，并表明简单的“Wait”（等等）干预能显著减少这一盲点，将这种现象归因于典型训练数据中缺乏自我纠正序列。 |
| 具身智能自我反思与动作纠错 | Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving | NeurIPS                         | 2024年   | 探索了大型语言模型是否拥有解决问题的元认知知识。本文开发了一种方法，让LLM识别并聚类其自身感知到的解决问题技能，当这些技能用于与技能对齐的上下文学习时，将MATH数据集上的数学推理准确性提高了高达11.6%。 |

#### 自我建模

| 论文分类             | 论文名称                                             | 出版社/期刊      | 出版时间 | 简介                                                         |
| -------------------- | ---------------------------------------------------- | ---------------- | -------- | ------------------------------------------------------------ |
| 解释性与生成性AI     | Separating the World and Ego Models for Self-Driving | ICLR Workshop    | 2022年   | 探讨了在自动驾驶中将世界模型与自我模型分开的策略。           |
| 机器人意识与自我建模 | Task-agnostic self-modeling machines                 | Science Robotics | 2019年   | 展示了一个四自由度机械臂的自我建模能力，并说明其在任务性能上的优势。 |

#### 群体智能与意识

| 论文分类           | 论文名称                                                     | 出版社/期刊                           | 出版时间 | 简介                                                         |
| ------------------ | ------------------------------------------------------------ | ------------------------------------- | -------- | ------------------------------------------------------------ |
| 解释性与生成性AI   | Generative agents: Interactive simulacra of human behavior.  | ACM Symposium on UI Software          | 2023年   | 探讨了生成性代理如何模拟人类行为及其在自我认知中的应用。     |
| 机器人群体意识探讨 | Particle robotics based on statistical mechanics of loosely coupled components | Nature                                | 2019年   | 探讨了简单粒子组成的群体如何展现出类似意识特性的行为，如物体运输和趋光性。 |
| 机器意识与团队智能 | Collective Intelligence in Human-AI Teams: A Bayesian Theory of Mind Approach | AAAI Technical Track on Humans and AI | 2023年   | 使用贝叶斯心智理论模型，探讨了人类-AI团队的集体智能，及其在高负荷交流中的表现。 |

#### 意识科学综述

| 论文分类             | 论文名称                                                     | 出版社/期刊                | 出版时间 | 简介                                                         |
| -------------------- | ------------------------------------------------------------ | -------------------------- | -------- | ------------------------------------------------------------ |
| 意识科学综述         | Theories of consciousness                                    | Nature Review Neuroscience | 2022年   | 对意识科学的主流理论进行了综述，侧重神经科学背景。           |
| 意识理论综述         | Theoretical Models of Consciousness: A Scoping Review        | Brain Sci.                 | 2021年   | 对多种意识理论进行了综述，涵盖信息理论、量子物理、认知心理学、计算机科学等多个领域。 |
| 意识理论计算视角综述 | Survey of Consciousness Theory from Computational Perspective | ArXiv                      | 2022年   | 本文从跨学科的角度全面探讨了意识的理论基础，并探讨了当前计算模型可能展现出意识的潜力。 |
| 机器意识综述         | 机器意识研究综述                                             | 自动化学报                 | 2020年   | 对机器意识领域的研究进行了全面综述，涵盖了主要研究方向和成果。 |

#### 机器意识的定义与评估

| 论文分类                            | 论文名称                                                     | 出版社/期刊 | 出版时间 | 简介                                                         |
| ----------------------------------- | ------------------------------------------------------------ | ----------- | -------- | ------------------------------------------------------------ |
| 机器意识定义与探讨                  | Consciousness in Artificial Intelligence: Insights from the Science of Consciousness | ArXiv       | 2023年   | 基于计算功能主义理论分析了人工智能系统中评估和实现意识的技术。 |
| 机器意识定义与探讨                  | What is consciousness, and could machines have it?           | Science     | 2017年   | 探讨了基于人类意识理论对机器意识的定义，认为现有深度学习系统不具备意识。 |
| 机器意识定义与探讨                  | Conscious machines: defining questions                       | Science     | 2018年   | 反驳Dehaene (2017)的观点，认为现有深度学习系统可能具有意识。 |
| 机器意识定义与探讨                  | Conscious machines: Robot rights                             | Science     | 2018年   | 探讨了有意识机器人在社会中的角色和权利问题。                 |
| 理论计算机科学与意识                | A Theoretical Computer Science Perspective on Consciousness and Artificial General Intelligence | Engineering | 2023年   | 有意识的图灵机 (CTM) 作为一个理论计算机科学模型，用于理解意识并指导人工通用智能 (AGI) 的发展。 |
| ToM（他心理论）评测与对抗式数据生成 | Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoning | ICLR        | 2025年   | 提出 ExploreToM：用 DSL + A* 搜索程序化生成更复杂、更多样的他心推理（ToM）叙事样本，以构建更严格的压力测试与训练数据。结果显示强模型在该对抗式样本上会显著失效，提示传统 ToM 基准可能偏乐观。 |

#### 经典意识理论

| 论文分类         | 论文名称                                                     | 出版社/期刊                                     | 出版时间 | 简介                                                         |
| ---------------- | ------------------------------------------------------------ | ----------------------------------------------- | -------- | ------------------------------------------------------------ |
| 整合信息论       | Integrated information theory: from consciousness to its physical substrate | Nature Reviews Neuroscience                     | 2016年   | -                                                            |
| 整合信息论       | Consciousness as integrated information: a provisional manifesto | The Biological Bulletin                         | 2008年   | 阐述了整合信息理论的进一步发展，提出了Φ值作为量化意识的核心指标，分析了不同神经系统在意识体验中的角色。 |
| 整合信息论       | From the phenomenology to the mechanisms of consciousness: integrated information theory 3.0 | PLoS Computational Biology                      | 2014年   | 提出了IIT的3.0版本，详细讨论了意识的现象学公理及其与物理机制的关系，并介绍了最大不可约概念结构（MICS）和ΦMax。 |
| 整合信息论       | An information integration theory of consciousness           | BMC Neuroscience                                | 2004年   | 可能是最早提出整合信息论（IIT）的论文，探讨了为什么某些脑区产生意识，而其他区域不产生意识。 |
| 整合信息论       | Integrated information theory (IIT) 4.0: formulating the properties of phenomenal existence in physical terms | PLoS Computational Biology                      | 2023年   | 最新的IIT4.0版本，进一步发展了整合信息论，详细描述了如何在物理术语中表述意识的现象属性。 |
| 整合信息论综述   | A systematic review of integrated information theory: a perspective from artificial intelligence and the cognitive sciences | Neural Computing and Applications               | 2023年   | 详细综述了整合信息论的研究现状，重点分析了IIT在人工智能和认知科学中的应用，并列出了IIT的近似计算方法。 |
| 全局工作空间理论 | A neuronal model of a global workspace in effortful cognitive tasks | Proceedings of the National Academy of Sciences | 1998年   | 提出了全局工作空间理论的神经模型，探讨了在复杂认知任务中，全局工作空间如何通过长程轴突的分布式神经元来调节意识体验。 |
| -                | Conscious Processing and the Global Neuronal Workspace Hypothesis | Neuron                                          | 2020年   | -                                                            |
| 高阶理论         | Empirical support for higher-order theories of conscious awareness | Trends in Cognitive Sciences                    | 2011年   | 提供了对高阶意识理论的实证支持，讨论了高阶心理表征如何在意识体验中发挥关键作用，并与其他意识理论进行了比较。 |

#### 神经科学中的意识

| 论文分类               | 论文名称                                                     | 出版社/期刊             | 出版时间 | 简介                                                         |
| ---------------------- | ------------------------------------------------------------ | ----------------------- | -------- | ------------------------------------------------------------ |
| 人工意识与神经科学探讨 | The feasibility of artificial consciousness through the lens of neuroscience | Trends in Neurosciences | 2023年   | 探讨了通过神经科学视角实现人工意识的可行性，分析当前AI系统在意识特征上的不足。 |
| 神经科学与意识研究     | Thalamus Modulates Consciousness via Layer-Specific Control of Cortex | Neuron                  | 2021年   | 研究了丘脑如何通过对皮层特定层次的控制来调节意识，发现中央外侧丘脑的刺激可以唤醒麻醉中的猕猴并恢复类似清醒的神经处理。 |
| 视觉感知与想象         | Distinct Top-down and Bottom-up Brain Connectivity During Visual Perception and Imagery | Scientific Reports      | 2017年   | 研究探讨了感知与想象在同一视觉区域中的神经连接差异，揭示了自上而下的处理在内源性和外源性视觉体验中的重要性。 |

#### 心理学中的意识

| 论文分类         | 论文名称                                                     | 出版社/期刊         | 出版时间 | 简介                                                         |
| ---------------- | ------------------------------------------------------------ | ------------------- | -------- | ------------------------------------------------------------ |
| 身体自我意识研究 | Video ergo sum: manipulating bodily self-consciousness       | Science             | 2007年   | 通过虚拟现实中的多感官冲突实验，探讨了身体自我意识的空间统一性，发现参与者在实验中错认虚拟身体为自己的身体。 |
| 临床意识评估     | Assessing the depth of language processing in patients with disorders of consciousness | Nature Neuroscience | 2020年   | 研究了通过床边EEG记录评估意识障碍患者的残余意识和认知能力。  |

#### 哲学中的意识

| 论文分类     | 论文名称                                        | 出版社/期刊 | 出版时间 | 简介                                                         |
| ------------ | ----------------------------------------------- | ----------- | -------- | ------------------------------------------------------------ |
| 意识难题探讨 | Making the hard problem of consciousness easier | Science     | 2021年   | 讨论了意识难题的解决方案，并提出了不同意识理论之间对立观点的对抗性合作。 |

#### 意识与社会伦理

| 论文分类             | 论文名称                                                     | 出版社/期刊                                          | 出版时间 | 简介                                                         |
| -------------------- | ------------------------------------------------------------ | ---------------------------------------------------- | -------- | ------------------------------------------------------------ |
| 机器人意识与身体表征 | Prerequisites for an Artificial Self                         | Frontiers in Neurorobotics                           | 2020年   | 探讨了人工自我的前提条件，包括身体所有权和代理性，并提出了用于人工自我的评价指标。 |
| 机器伦理与意识探讨   | Designing AI with Rights, Consciousness, Self-Respect, and Freedom | Philpapers.org                                       | 2023年   | 提出了设计可能值得与人类同等道德考虑的AI系统的四个道德原则。 |
| 机器伦理与意识探讨   | The problem of machine ethics in artificial intelligence     | AI & SOCIETY                                         | 2020年   | 探讨了AI和机器伦理，特别是机器在与人类交互中是否可以遵循道德原则的问题。 |
| 机器伦理与意识探讨   | Consciousness and Ethics: Artificially Conscious Moral Agents | Routledge                                            | 2017年   | 探讨了意识在道德决策中的作用，以及机器意识与道德决策的关系。 |
| 机器伦理与认知架构   | Cognitive architectures for artificial intelligence ethics   | AI & SOCIETY                                         | 2023年   | 提出了使用认知架构来增加AI的透明性、可解释性和责任感，特别是在社会和伦理困境中。 |
| 机器意识伦理探讨     | Artificial Suffering: An Argument for a Global Moratorium on Synthetic Phenomenology | Journal of Artificial Intelligence and Consciousness | 2021年   | 提出了一项全球性的道德呼吁，建议在2050年前对人工意识研究实施暂停。 |

#### 其他

| 论文分类               | 论文名称                                                     | 出版社/期刊                                          | 出版时间 | 简介                                                         |
| ---------------------- | ------------------------------------------------------------ | ---------------------------------------------------- | -------- | ------------------------------------------------------------ |
| 人工意识与科技哲学     | Unconscious Networks: Philosophy, Psychoanalysis, and Artificial Intelligence | Routledge                                            | 2022年   | 结合精神分析、生物符号学与行为网络理论，探讨人类无意识与技术之间的相互作用。 |
| 人工智能与心理健康     | The Artificial Third: A Broad View of the Effects of Introducing Generative Artificial Intelligence on Psychotherapy | JMIR Ment Health                                     | 2024年   | 探讨了生成性人工智能在心理治疗中的应用及其对人类自我和人际关系的潜在影响。 |
| 人类与非人类意识测试   | Tests for consciousness in humans and beyond                 | Trends in Cognitive Sciences                         | 2023年   | 提出了发展适用于不同系统的意识测试的框架，并探讨了验证这些测试的策略。 |
| 强AI与意识             | Strong Artificial Intelligence and Consciousness             | Journal of Artificial Intelligence and Consciousness | 2020年   | 讨论了当前窄AI的能力差距，并探讨了强AI是否可能具备意识。     |
| 意识测量问题           | The Measurement Problem of Consciousness                     | Philosophical Topics                                 | 2020年   | 讨论了意识科学中的测量问题，特别是在非人类系统中应用的方法及其局限性。 |
| 意识研究挑战与机遇     | Opportunities and challenges for a maturing science of consciousness | Nat Hum Behav                                        | 2019年   | 呼吁开展更实证和解决实际问题的意识研究，如脑或心理疾病。     |
| 机器意识与人类认知     | Can AI artifacts influence human cognition?                  | International Journal of Information Management      | 2021年   | 探讨了AI自主性对人类认知的影响，特别是智能个人助理（IPAs）在任务完成中的表现。 |
| 机器意识与心理分析     | Psychoanalyzing artificial intelligence: the case of Replika | AI & SOCIETY                                         | 2023年   | 通过对Replika的案例研究，探讨了人类无意识过程如何影响人工智能的行为和设计。 |
| 机器意识与意识形态探讨 | Large Language Model Soft Ideologization via AI-Self-Consciousness | ArXiv                                                | 2023年   | 探讨了通过AI自我意识进行LLMs的软性意识形态化的可能性及其风险。 |
| 机器意识与混沌计算     | Conscious AI at the Edge of Chaos                            | Journal of Artificial Intelligence and Consciousness | 2020年   | 探讨了在混沌边缘进行计算的AI如何有助于实现强人工智能（AGI）和AI意识。 |
| 机器意识与自我意识探讨 | Artificial Intelligence and Its Self-Consciousness           | WABD Proceedings                                     | 2021年   | 探讨了机器自我意识的可能性，并从心理学、认知神经科学、哲学等角度介绍了自我意识理论。 |
| 机器意识与自我意识探讨 | AI and Self-consciousness                                    | Artificial Intelligence in Daily Life                | 2020年   | 探讨了AI自我意识的可能性，回顾了从图灵测试到当前AI发展的历史进程。 |
| 机器意识与自我模型     | Consciousness in active inference: Deep self-models, other minds, and the challenge of psychedelic-induced ego-dissolution | Neuroscience of Consciousness                        | 2021年   | 探讨了在预测性处理和主动推理框架下的意识理论，特别是自我模型及致幻药引起的自我解体挑战。 |
| 机器意识可能性探讨     | Could a Large Language Model be Conscious?                   | ArXiv                                                | 2023年   | 探讨了LLMs可能具有意识的前景，并评估了当前模型在实现意识方面的局限性。 |
| 机器意识综述           | Towards making computers conscious: trends and challenges    | Iran Journal of Computer Science                     | 2023年   | 详细回顾了机器意识的进展、相关理论和认知架构，并讨论了其中的批评和不足。 |
| 身体自我意识研究       | Full-body illusions and minimal phenomenal selfhood          | Trends in Cognitive Sciences                         | 2009年   | 讨论了身体自我意识的最小充分条件，提出了全身自我意识的全局性和统一性的重要性，并探讨了自我意识的必要条件。 |
| 意识测量与机器意识     | Reviewing tests for machine consciousness                    | Journal of Consciousness Studies                     | 2019年   | 讨论了几种测量机器意识的方法，特别关注如何评估机器系统是否具有意识。 |
| 世界表征与状态抽象探究 | Do LLMs Build World Representations? Probing Through the Lens of State Abstraction | NeurIPS                                              | 2024年   | 从强化学习“状态抽象”的理论视角探测 LLM 是否构建可用于规划的世界状态表征。通过受控的文本规划环境分析不同抽象层级的可恢复性，指出模型更倾向保留“目标导向”的抽象信息，而非完整重建世界动力学。 |

## 1.4. Interview

| 访谈/科普标题            | 受访者                           | 出版社/期刊         | 出版时间 | 简介                                                         |
| ------------------------ | -------------------------------- | ------------------- | -------- | ------------------------------------------------------------ |
| A Test for Consciousness | Christof Koch, Giulio Tononi     | Scientific American | 不详     | 这篇科普文章讨论了意识的检测方法，尤其是基于整合信息理论（IIT）的检测。 |
| 对话现代意识理论先驱     | Stanislas Dehaene, Christof Koch | Neuron              | 2024年   | 这两篇访谈分别介绍了Stanislas Dehaene和Christof Koch在意识研究领域的贡献、研究现状和未来方向。 |
| Stanislas Dehaene访谈    | Stanislas Dehaene                | Neuron              | 2024年   | 访谈探讨了Dehaene在意识研究中的工作，尤其是他在全局神经工作空间理论（GNWT）方面的贡献。 |
| Christof Koch访谈        | Christof Koch                    | Neuron              | 2024年   | 访谈探讨了Koch在意识研究中的工作，特别是他在整合信息理论（IIT）和意识检测方面的贡献。 |

## 1.5. Book

| 资源类型 | 资源名称                                                | 作者              | 出版时间 | 简介                                                         | 中文版                             |
| -------- | ------------------------------------------------------- | ----------------- | -------- | ------------------------------------------------------------ | ---------------------------------- |
| 书籍     | From Biological to Artificial Consciousness             | Masataka Watanabe | 2022     | 探讨了从生物意识到人工意识的转变过程及其理论基础。           | -                                  |
| 书籍     | 机器意识 —— 人工智能的终极挑战                          | 周昌乐            | 2021     | 深入探讨了机器意识的挑战和前景。                             | -                                  |
| 书籍     | Consciousness and the Brain                             | Stanislas Dehaene | 2014     | 研究了意识与大脑之间的关系，提供了神经科学背景下的意识理论。 | 脑与意识                           |
| 书籍     | A Thousand Brains                                       | Jeff Hawkins      | 2021     | 提出了多脑模型，探讨了如何模拟大脑的认知功能以实现人工意识。 | -                                  |
| 书籍     | The Feeling of Life Itself                              | Christof Koch     | 2019     | 探讨了意识的基本感受以及其在生命中的作用。                   | 生命本身的感觉                     |
| 书籍     | Consciousness -- Confessions of a Romantic Reductionist | Christof Koch     | 2017     | 探讨了还原论视角下的意识问题。                               | 脑与意识 —— 一个还原论者的浪漫自白 |
| 书籍     | Consciousness                                           | S. Blackmore      | 2018     | 提供了意识之谜的多角度分析，探讨了不同的意识理论。           | 破解意识之谜                       |

## 1.6. Scientists

| 科学家名字        | 单位                                                         | 主要贡献                                                     | 网页                                                         |
| ----------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
| Ned Block         | New York University, Philosophy                              | 在意识哲学领域作出了重要贡献，特别是现象意识和接入意识的区分及其在机器意识中的应用。 | [Google Scholar](https://scholar.google.com/citations?user=0pZiZ7wAAAAJ&hl=en&oi=ao) |
| Francis Crick     | University of Cambridge (8 June 1916 – 28 July 2004)         | 英国分子生物学家，与James Watson共同发现了DNA的双螺旋结构，并在后期研究中致力于探索意识的神经科学基础。 | [Wikipedia](https://en.wikipedia.org/wiki/Francis_Crick)     |
| Christof Koch     | Chief Scientist, MindScope Program, Allen Institute          | 整合信息理论（IIT）的主要倡导者之一，研究意识的神经基础，特别是意识如何从大脑活动中产生。 | [Google Scholar](https://scholar.google.com/citations?user=JYt9T_sAAAAJ&hl=en&oi=ao) |
| David Chalmers    | New York University, Philosophy                              | 提出了“意识的艰难问题”，探讨了意识与物理世界的关系，以及意识在人工智能中的应用。 | [Google Scholar](https://scholar.google.com/citations?user=o8AfF3MAAAAJ&hl=en&oi=ao) |
| Giulio Tononi     | University of Wisconsin School of Medicine and Public Health | 整合信息理论（IIT）的创始人之一，该理论为机器意识的研究提供了重要框架。 | [Google Scholar](https://scholar.google.com/citations?user=x6uUysgAAAAJ&hl=en&oi=ao) |
| Stanislas Dehaene | Professor of Experimental Cognitive Psychology, Collège de France | 全球工作空间理论（GWT）的主要研究者之一，探讨了意识的认知和神经基础，并应用于机器意识研究。 | [Google Scholar](https://scholar.google.com/citations?hl=en&user=2Dd5uoIAAAAJ) |
| Lucia Melloni     | Max Planck for Empirical Aesthetics                          | 在意识的时间特性研究中作出了重要贡献，特别是跨不同意识状态（如感知、觉醒和注意）之间的转变机制。 | [Google Scholar](https://scholar.google.com/citations?user=fZLdNigAAAAJ&hl=en&oi=ao) |
| Jeff Hawkins      | MIT                                                          | 提出了“千脑理论”，探讨了如何模拟大脑的认知功能以实现人工意识。 | [Wikipedia](https://en.wikipedia.org/wiki/Jeff_Hawkins)      |
| Karl Friston      | University College London                                    | Friston是自由能原理（Free Energy Principle）的提出者，该原理是一个广泛应用于神经科学和人工智能的框架。 | [Google Scholar](https://scholar.google.com/citations?user=q_4u0aoAAAAJ&hl=en&oi=ao) |
| Anil Seth         | Sussex University                                            | Seth是意识科学领域的领军人物之一，特别是在预测编码和意识的神经计算模型。 | [Google Scholar](https://scholar.google.com/citations?user=3eJCZCkAAAAJ&hl=en&oi=ao) |
| Manuel Blum       | CMU                                                          | 计算复杂性理论的奠基者之一，对密码学、程序检查和伪随机数生成等领域有重要贡献，1995年图灵奖得主。 | [CMU Profile](https://www.cs.cmu.edu/~mblum/index.html)      |
| Lenore Blum       | CMU                                                          | 在实数计算、密码学和伪随机数生成领域做出贡献，推动数学和计算机科学领域的多样性，创立了多个支持女性的项目。 | [CMU Profile](http://www.cs.cmu.edu/~lblum/)                 |
| 张江              | 北京师范大学                                                 | 系统科学与复杂系统涌现现象研究，自指系统研究。集智俱乐部（中国最有影响力的非官方学术组织之一）创始人。 | [集智俱乐部](https://wiki.swarma.org/index.php/%E5%BC%A0%E6%B1%9F) |
| 周昌乐            | 厦门大学                                                     | 机器意识研究，注意力、情感计算、自我建模等                   | [厦门大学](https://informatics.xmu.edu.cn/info/1011/6626.htm) |

Machine-Consciousness-HKUSTGZ-AIAA5050

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README