Selected work

Representative Papers

Mental Model Management: An Operator-Based Framework for LLM Memory

Aug 15, 2026

This study addresses the challenge of lacking compact and dynamically evolving conceptual representations in large language models (LLMs) by proposing the 3M framework. This approach models knowledge as compact mental models and introduces innovative operator mechanisms, including chunking, extractive retrieval, consistency verification, and evolution, to enable continuous knowledge integration and dynamic reorganization. The research effectively overcomes memory management bottlenecks in LLMs by achieving dynamic knowledge evolution while maintaining representational compactness. Consequently, this method significantly enhances the model's knowledge reasoning capabilities and establishes a novel paradigm for constructing intelligent systems equipped with adaptive memory.

0 citationsRead paper

Adaptive Search in Collatz Exponent-Code Space via 2-adic and 3-adic Constraints

Jul 10, 2026

This study investigates structural obstacles to orbit convergence in the Collatz conjecture, aiming to characterize essential features of potential counterexamples. It introduces the “2-3-∞ diagnostic framework,” which for the first time jointly incorporates 2-adic initial conditions and 3-adic terminal constraints within a finite-index symbolic space derived from accelerated mappings. By integrating real-valued drift metrics, asymptotic residue theory, and adaptive evolutionary search, the work demonstrates that any counterexample must exhibit near-critical drift and small residue. Moreover, it proves that the asymptotic residue rate of integer-generated codes is zero. Experimental results over orbit lengths from 100 to 400 significantly improve the performance trade-off at finite lengths, with all configurations maintaining a positive residue rate, thereby validating the framework’s effectiveness and novelty.

0 citationsRead paper

WOLF-VLA: Whole-Body Humanoid Optimal Locomotion Framework for Vision-Language-Action Learning

Jun 24, 2026

This work addresses key challenges in applying vision–language–action (VLA) models to whole-body, contact-rich humanoid robot control—namely, data scarcity, dynamically inconsistent demonstrations, and the difficulty of simultaneously ensuring optimality and safety. To overcome these limitations, we propose an end-to-end learning framework that integrates whole-body optimal control with large-scale multimodal data. We introduce, for the first time, a dynamically consistent multimodal dataset of whole-body humanoid motions, enabling direct generation of robust, safe, and high-performance motor policies from natural language instructions. Experimental results demonstrate that the learned policies exhibit strong generalization across diverse tasks and environmental conditions, robustness to variations in initial states, and state-of-the-art performance across multiple metrics, while establishing a reproducible benchmark for future research.

0 citationsRead paper

Advanced Calibration Analysis and Tools: Identifying Influential Observations in Stochastic Interest Rate Model Calibration

Jun 18, 2026

This study addresses the limitations of traditional multifactor interest rate model calibration, which often neglects the influence of market data and parameter uncertainty, thereby hindering reliable assessment of calibration quality. The authors formulate calibration within a nonlinear regression framework, demonstrating that minimizing the root mean squared relative error (RMSRE) is equivalent to weighted least squares. They introduce, for the first time, an influence diagnostic framework tailored to stochastic interest rate models, enabling local sensitivity analysis with boundary constraints and confidence interval estimation. Their approach integrates weighted hat matrices, influence functions, the functional delta method, and an efficient Jacobian decomposition leveraging analytical gradients from at-the-money (ATM) cap prices. Empirical analysis using euro ATM cap data from 2016–2025 reveals pronounced leverage effects near parameter boundaries, effective dimensionality reduction, and a marked shift in parameter stability after 2022, indicating that low RMSRE alone does not guarantee trustworthy calibration.

0 citationsRead paper

FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation

Jun 18, 2026

Existing vision-language-action (VLA) models exhibit limited generalization in few-shot imitation learning. This work proposes a future-conditioned framework that enables long-horizon reasoning without pixel-level reconstruction by explicitly predicting task-relevant future interaction embeddings and implicitly aligning goal observations in a latent space. The approach introduces, for the first time, a future-oriented mechanism into few-shot VLA adaptation, allowing joint training using only action-free videos and interpretable as learning a value-like future-conditioned representation. Experiments demonstrate that the method achieves a 95.7% success rate on the LIBERO benchmark with merely 20 demonstrations, yields 7–12% absolute improvements on RoboCasa, and attains up to a 26% absolute gain in real-world robotic tasks, substantially advancing the state of the art in few-shot VLA adaptation.

0 citationsRead paper

Recent publications

Latest Papers

Mental Model Management: An Operator-Based Framework for LLM Memory

Aug 15, 2026

This study addresses the challenge of lacking compact and dynamically evolving conceptual representations in large language models (LLMs) by proposing the 3M framework. This approach models knowledge as compact mental models and introduces innovative operator mechanisms, including chunking, extractive retrieval, consistency verification, and evolution, to enable continuous knowledge integration and dynamic reorganization. The research effectively overcomes memory management bottlenecks in LLMs by achieving dynamic knowledge evolution while maintaining representational compactness. Consequently, this method significantly enhances the model's knowledge reasoning capabilities and establishes a novel paradigm for constructing intelligent systems equipped with adaptive memory.

0 citationsRead paper

Adaptive Search in Collatz Exponent-Code Space via 2-adic and 3-adic Constraints

Jul 10, 2026

This study investigates structural obstacles to orbit convergence in the Collatz conjecture, aiming to characterize essential features of potential counterexamples. It introduces the “2-3-∞ diagnostic framework,” which for the first time jointly incorporates 2-adic initial conditions and 3-adic terminal constraints within a finite-index symbolic space derived from accelerated mappings. By integrating real-valued drift metrics, asymptotic residue theory, and adaptive evolutionary search, the work demonstrates that any counterexample must exhibit near-critical drift and small residue. Moreover, it proves that the asymptotic residue rate of integer-generated codes is zero. Experimental results over orbit lengths from 100 to 400 significantly improve the performance trade-off at finite lengths, with all configurations maintaining a positive residue rate, thereby validating the framework’s effectiveness and novelty.

0 citationsRead paper

WOLF-VLA: Whole-Body Humanoid Optimal Locomotion Framework for Vision-Language-Action Learning

Jun 24, 2026

This work addresses key challenges in applying vision–language–action (VLA) models to whole-body, contact-rich humanoid robot control—namely, data scarcity, dynamically inconsistent demonstrations, and the difficulty of simultaneously ensuring optimality and safety. To overcome these limitations, we propose an end-to-end learning framework that integrates whole-body optimal control with large-scale multimodal data. We introduce, for the first time, a dynamically consistent multimodal dataset of whole-body humanoid motions, enabling direct generation of robust, safe, and high-performance motor policies from natural language instructions. Experimental results demonstrate that the learned policies exhibit strong generalization across diverse tasks and environmental conditions, robustness to variations in initial states, and state-of-the-art performance across multiple metrics, while establishing a reproducible benchmark for future research.

0 citationsRead paper

Advanced Calibration Analysis and Tools: Identifying Influential Observations in Stochastic Interest Rate Model Calibration

Jun 18, 2026

This study addresses the limitations of traditional multifactor interest rate model calibration, which often neglects the influence of market data and parameter uncertainty, thereby hindering reliable assessment of calibration quality. The authors formulate calibration within a nonlinear regression framework, demonstrating that minimizing the root mean squared relative error (RMSRE) is equivalent to weighted least squares. They introduce, for the first time, an influence diagnostic framework tailored to stochastic interest rate models, enabling local sensitivity analysis with boundary constraints and confidence interval estimation. Their approach integrates weighted hat matrices, influence functions, the functional delta method, and an efficient Jacobian decomposition leveraging analytical gradients from at-the-money (ATM) cap prices. Empirical analysis using euro ATM cap data from 2016–2025 reveals pronounced leverage effects near parameter boundaries, effective dimensionality reduction, and a marked shift in parameter stability after 2022, indicating that low RMSRE alone does not guarantee trustworthy calibration.

0 citationsRead paper

FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation

Jun 18, 2026

Existing vision-language-action (VLA) models exhibit limited generalization in few-shot imitation learning. This work proposes a future-conditioned framework that enables long-horizon reasoning without pixel-level reconstruction by explicitly predicting task-relevant future interaction embeddings and implicitly aligning goal observations in a latent space. The approach introduces, for the first time, a future-oriented mechanism into few-shot VLA adaptation, allowing joint training using only action-free videos and interpretable as learning a value-like future-conditioned representation. Experiments demonstrate that the method achieves a 95.7% success rate on the LIBERO benchmark with merely 20 demonstrations, yields 7–12% absolute improvements on RoboCasa, and attains up to a 26% absolute gain in real-world robotic tasks, substantially advancing the state of the art in few-shot VLA adaptation.

0 citationsRead paper