Chain-of-Thought (CoT) reasoning has become a powerful framework for improving complex problem-solving capabilities in Multimodal Large Language Models (MLLMs). However, the verbose nature of textual reasoning introduces significant inefficiencies. In this work, we propose $\textbf{Heima}$ (as hidden llama), an efficient reasoning framework that leverages reasoning CoTs at hidden latent space. We design the Heima Encoder to condense each intermediate CoT into a compact, higher-level hidden representation using a single thinking token, effectively minimizing verbosity and reducing the overall number of tokens required during the reasoning process. Meanwhile, we design corresponding Heima Decoder with traditional Large Language Models (LLMs) to adaptively interpret the hidden representations into variable-length textual sequence, reconstructing reasoning processes that closely resemble the original CoTs. Experimental results across diverse reasoning MLLM benchmarks demonstrate that Heima model achieves higher generation efficiency while maintaining or even better zero-shot task accuracy. Moreover, the effective reconstruction of multimodal reasoning processes with Heima Decoder validates both the robustness and interpretability of our approach.
Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学北京校区人工智能学院);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);University College London, University of London(伦敦大学大学学院);Dalian University of Technology(大连理工大学)
Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China(中国人民大学人工智能学院);Beijing Key Laboratory of Research on Large Models(北京大型模型研究关键实验室);Engineering Research Center of Next-Generation Intelligent Search(下一代智能搜索工程研究中心);College of Artificial Intelligence, Tianjin University of Science(天津科技大学人工智能学院)
Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳));Huawei Noah’s Ark Lab(华为诺亚方舟实验室);Tsinghua University(清华大学);The Chinese University of Hong Kong(香港中文大学);Zhongguancun Academy(中关村学院);Shenzhen Loop Area Institute(深圳河套学院)
Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
University of California, Santa Barbara(加州大学圣芭芭拉分校);University of California, Santa Cruz(加州大学圣克ruz分校);University of California, Los Angeles(加州大学洛杉矶分校);Purdue University(普渡大学);LMSYS Org(LMSYS组织);Microsoft(微软)
Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学人工智能学院);Department of Computer Science, National University of Singapore(新加坡国立大学计算机科学系);Ant Group(蚂蚁集团)
CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models
Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China(电子科技大学智能协同计算实验室);Ubiquitous Intelligence and Trusted Services Key Laboratory of Sichuan Province(四川省泛在智能与可信服务重点实验室)
Rewarding How Models Think Pedagogically: Integrating Pedagogical Reasoning and Thinking Rewards for LLMs in Education
Chosun University(昌原大学);Korea University(韩国大学);Seoul National University(首尔国立大学);Korea Institute for Curriculum and Evaluation(韩国课程与评价研究院);Upstage;Indiana University Bloomington(印第安纳大学布卢明顿分校);Nanyang Technological University(南洋理工大学)
RAIN-Merging: A Gradient-Free Method to Enhance Instruction Following in Large Reasoning Models with Preserved Thinking Format
Institute of Image Processing and Pattern Recoginition, School of Automation and Intelligent Sensing, Shanghai Jiao Tong University(图像处理与模式识别研究所,自动化与智能感知学院,上海交通大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));MoE Key Laboratory of System Control and Information Processing (Shanghai)(系统控制与信息处理国家重点实验室(上海))