Recent advances in Multimodal Large Language Models (MLLMs) have enabled joint reasoning over financial textual and visual inputs. However, they still struggle with financial terminology, logical consistency, and numerical computations. Moreover, while commercial large models perform well on reasoning tasks, their high inference costs limit their scalable usage in real world financial applications. We thus propose a cost-effective framework, CLER, that combines contrastive retrieval with step-wise reflection to improve reasoning performance. Also, the reasoning cost is only generated in the test stage when using commercial large models. CLER leverages FinErrorSet, a dataset of 8,000+ mistake correction pairs from diverse open-source MLLMs. A fine grained retriever is trained to identify structurally relevant errors for self-correction through individual reflection. Experiments on three benchmarks show that CLER consistently outperforms other baselines. To our knowledge, CLER is the first framework to use cross-model errors for financial reasoning.

Ensuring character identity consistency across varying prompts remains a fundamental limitation in diffusion-based text-to-image generation. We propose CharCom, a modular and parameter-efficient framework that achieves character-consistent story illustration through composable LoRA adapters, enabling efficient per-character customization without retraining the base model. Built on a frozen diffusion backbone, CharCom dynamically composes adapters at inference using prompt-aware control. Experiments on multi-scene narratives demonstrate that CharCom significantly enhances character fidelity, semantic alignment, and temporal coherence. It remains robust in crowded scenes and enables scalable multi-character generation with minimal overhead, making it well-suited for real-world applications such as story illustration and animation.

In an era where the capabilities of large language models (LLM) like ChatGPT are transforming digital communication, the challenge of directing these tools to create extensive, coherent narratives on an epic-scale has emerged as a critical frontier. This study introduces a novel methodology that fuses the spontaneous story generation of LLMs with the precision of auto-prompted reinforcement learning for crafting epic-scale, coherent narratives. Our approach starts with generating a skeletal outline, followed by iterative expansion, and blending operations for maintaining structural coherence in long-form content. To train the reinforcement learning model efficiently, we introduce an environment simulator that leverages a database of historical LLM interactions, circumventing the limitations of direct LLM interactions. This method enhances the decision-making process of the RL agent, enabling more effective prompt selection and narrative flow in extended texts. We validate its effectiveness through experiments, demonstrating the model’s ability to generate structured, narrative-driven text, thereby setting a new pathway towards AI-driven, large-scale storytelling.

Large language models (LLMs) such as ChatGPT and GPT-4 have demonstrated impressive capabilities in various generative tasks. However, their performance is often hampered by limitations in accessing and leveraging long-term memory, leading to specific vulnerabilities and biases, especially during long interactions. This paper introduces ChatLogic, an innovative framework specifically targeted at LLM reasoning tasks that can enhance the performance of LLMs in multi-step deductive reasoning tasks by integrating logic programming. In Chat-Logic, the language model plays a central role, acting as a controller and participating in every system operation stage. We propose a novel method of converting logic problems into symbolic integration with an inference engine. This approach leverages large language models’ situational understanding and imitation skills and uses symbolic memory to enhance multi-step deductive reasoning capabilities. Our results show that the ChatLogic framework significantly improves the multi-step reasoning capabilities of LLMs. The source code and data are available at https://github.com/Strong-AI-Lab/ChatLogic.

In the Internet of Vehicles, low service delay and fast response are two essential factors to ensure the safety and smooth operation of vehicle networking. As core technologies, the 5G and edge computing networks play a fundamental role in reducing the pressure on the backbone network of vehicle networking and decreasing the service exchange delay. The previous edge server placement strategy can not be directly applied to deploying vehicle networking services, resulting in the degradation of system performance and user quality of experience. To solve the above problem, we propose a reliable edge server deployment algorithm called CFD based on Deep Deterministic Policy Gradient (DDPG). Firstly, the Canopy algorithm is used to cluster the location information of roadside units, and the initial cluster number is obtained. Then, the fuzzy C clustering algorithm (FCM) is leveraged to remove the "noise" and acquire the roadside units’ initial division and priority matrix. Finally, based on the DDPG algorithm, the optimal division of roadside units is obtained, and the cluster center is utilized as the deployment location of the edge server. Many experiments have been conducted, and the results show that, compared with the benchmark algorithm, the CFD algorithm improves the load balancing degree by 25%.

In this paper, we have discussed the full-order robust observer design problem for a class of nonlinear uncertain systems with time-varying delay. The goal of this problem is to design a nonlinear robust observer such that, for time-varying delay and unstructured parameter, the observer can guarantee the observing process robustly stable. A robust nonlinear observer is obtained, the observer gain matrix is included in a Hamiltonian matrix. A numerical example is given to demonstrate the validity of the proposed approach.

This paper presents the design of a mixed-sensitivity H/sub /spl infin// controller, the aim is to obtain good reference tracking properties as well as to properly reject sinusoidal disturbance for suppressing vibrations. The proposed approach is based on the frequency weighting functions which give an extended model to design a stabilizing H/sub /spl infin// controller. The method is applied to a 3-motor web winding system to compensate the web tension disturbance caused by the sinusoidal vibration on winder.