Minimum Entropy Coupling with Bottleneck

This paper investigates a novel lossy compression framework operating under logarithmic loss, designed to handle situations where the reconstruction distribution diverges from the source distribution. This framework is especially relevant for applications that require joint compression and retrieval, and in scenarios involving distributional shifts due to processing. We show that the proposed formulation extends the classical minimum entropy coupling framework by integrating a bottleneck, allowing for a controlled degree of stochasticity in the coupling. We explore the decomposition of the Minimum Entropy Coupling with Bottleneck (MEC-B) into two distinct optimization problems: Entropy-Bounded Information Maximization (EBIM) for the encoder, and Minimum Entropy Coupling (MEC) for the decoder. Through extensive analysis, we provide a greedy algorithm for EBIM with guaranteed performance, and characterize the optimal solution near functional mappings, yielding significant theoretical insights into the structural complexity of this problem. Furthermore, we illustrate the practical application of MEC-B through experiments in Markov Coding Games (MCGs) under rate limits. These games simulate a communication scenario within a Markov Decision Process, where an agent must transmit a compressed message from a sender to a receiver through its actions. Our experiments highlight the trade-offs between MDP rewards and receiver accuracy across various compression rates, showcasing the efficacy of our method compared to conventional compression baseline.

ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction

Exposure Correction (EC) aims to recover proper exposure conditions for images captured under over-exposure or under-exposure scenarios. While existing deep learning models have shown promising results, few have fully embedded Retinex theory into their architecture, highlighting a gap in current methodologies. Additionally, the balance between high performance and efficiency remains an under-explored problem for exposure correction task. Inspired by Mamba which demonstrates powerful and highly efficient sequence modeling, we introduce a novel framework based on Mamba for Exposure Correction (ECMamba) with dual pathways, each dedicated to the restoration of reflectance and illumination map, respectively. Specifically, we firstly derive the Retinex theory and we train a Retinex estimator capable of mapping inputs into two intermediary spaces, each approximating the target reflectance and illumination map, respectively. This setup facilitates the refined restoration process of the subsequent Exposure Correction Mamba Module (ECMM). Moreover, we develop a novel 2D Selective State-space layer guided by Retinex information (Retinex-SS2D) as the core operator of ECMM. This architecture incorporates an innovative 2D scanning strategy based on deformable feature aggregation, thereby enhancing both efficiency and effectiveness. Extensive experiment results and comprehensive ablation studies demonstrate the outstanding performance and the importance of each component of our proposed ECMamba. Code is available at https://github.com/LowlevelAI/ECMamba.

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

Multimodal Large Language Models (MLLMs) have shown promising progress in understanding and analyzing video content. However, processing long videos remains a significant challenge constrained by LLM's context size. To address this limitation, we propose LongVU, a spatiotemporal adaptive compression mechanism thats reduces the number of video tokens while preserving visual details of long videos. Our idea is based on leveraging cross-modal query and inter-frame dependencies to adaptively reduce temporal and spatial redundancy in videos. Specifically, we leverage DINOv2 features to remove redundant frames that exhibit high similarity. Then we utilize text-guided cross-modal query for selective frame feature reduction. Further, we perform spatial token reduction across frames based on their temporal dependencies. Our adaptive compression strategy effectively processes a large number of frames with little visual information loss within given context length. Our LongVU consistently surpass existing methods across a variety of video understanding benchmarks, especially on hour-long video understanding tasks such as VideoMME and MLVU. Given a light-weight LLM, our LongVU also scales effectively into a smaller size with state-of-the-art video understanding performance.

Data-driven Probabilistic Trajectory Learning with High Temporal Resolution in Terminal Airspace

Predicting flight trajectories is a research area that holds significant merit. In this paper, we propose a data-driven learning framework, that leverages the predictive and feature extraction capabilities of the mixture models and seq2seq-based neural networks while addressing prevalent challenges caused by error propagation and dimensionality reduction. After training with this framework, the learned model can improve long-step prediction accuracy significantly given the past trajectories and the context information. The accuracy and effectiveness of the approach are evaluated by comparing the predicted trajectories with the ground truth. The results indicate that the proposed method has outperformed the state-of-the-art predicting methods on a terminal airspace flight trajectory dataset. The trajectories generated by the proposed method have a higher temporal resolution(1 timestep per second vs 0.1 timestep per second) and are closer to the ground truth.

Learning-accelerated A* Search for Risk-aware Path Planning

Safety is a critical concern for urban flights of autonomous Unmanned Aerial Vehicles. In populated environments, risk should be accounted for to produce an effective and safe path, known as risk-aware path planning. Risk-aware path planning can be modeled as a Constrained Shortest Path (CSP) problem, aiming to identify the shortest possible route that adheres to specified safety thresholds. CSP is NP-hard and poses significant computational challenges. Although many traditional methods can solve it accurately, all of them are very slow. Our method introduces an additional safety dimension to the traditional A* (called ASD A*), enabling A* to handle CSP. Furthermore, we develop a custom learning-based heuristic using transformer-based neural networks, which significantly reduces the computational load and improves the performance of the ASD A* algorithm. The proposed method is well-validated with both random and realistic simulation scenarios.

RobustSVC: HuBERT-based Melody Extractor and Adversarial Learning for Robust Singing Voice Conversion

Singing voice conversion (SVC) is hindered by noise sensitivity due to the use of non-robust methods for extracting pitch and energy during the inference. As clean signals are key for the source audio in SVC, music source separation preprocessing offers a viable solution for handling noisy audio, like singing with background music (BGM). However, current separating methods struggle to fully remove noise or excessively suppress signal components, affecting the naturalness and similarity of the processed audio. To tackle this, our study introduces RobustSVC, a novel any-to-one SVC framework that converts noisy vocals into clean vocals sung by the target singer. We replace the non-robust feature with a HuBERT-based melody extractor and use adversarial training mechanisms with three discriminators to reduce information leakage in self-supervised representations. Experimental results show that RobustSVC is noise-robust and achieves higher similarity and naturalness than baseline methods in both noisy and clean vocal conditions.

On the Convergence of Sigmoid and tanh Fuzzy General Grey Cognitive Maps

Fuzzy General Grey Cognitive Map (FGGCM) and Fuzzy Grey Cognitive Map (FGCM) are extensions of Fuzzy Cognitive Map (FCM) in terms of uncertainty. FGGCM allows for the processing of general grey number with multiple intervals, enabling FCM to better address uncertain situations. Although the convergence of FCM and FGCM has been discussed in many literature, the convergence of FGGCM has not been thoroughly explored. This paper aims to fill this research gap. First, metrics for the general grey number space and its vector space is given and proved using the Minkowski inequality. By utilizing the characteristic that Cauchy sequences are convergent sequences, the completeness of these two space is demonstrated. On this premise, utilizing Banach fixed point theorem and Browder-Gohde-Kirk fixed point theorem, combined with Lagrange's mean value theorem and Cauchy's inequality, deduces the sufficient conditions for FGGCM to converge to a unique fixed point when using tanh and sigmoid functions as activation functions. The sufficient conditions for the kernels and greyness of FGGCM to converge to a unique fixed point are also provided separately. Finally, based on Web Experience and Civil engineering FCM, designed corresponding FGGCM with sigmoid and tanh as activation functions by modifying the weights to general grey numbers. By comparing with the convergence theorems of FCM and FGCM, the effectiveness of the theorems proposed in this paper was verified. It was also demonstrated that the convergence theorems of FCM are special cases of the theorems proposed in this paper. The study for convergence of FGGCM is of great significance for guiding the learning algorithm of FGGCM, which is needed for designing FGGCM with specific fixed points, lays a solid theoretical foundation for the application of FGGCM in fields such as control, prediction, and decision support systems.

Gaussian Rate-Distortion-Perception Coding and Entropy-Constrained Scalar Quantization

This paper investigates the best known bounds on the quadratic Gaussian distortion-rate-perception function with limited common randomness for the Kullback-Leibler divergence-based perception measure, as well as their counterparts for the squared Wasserstein-2 distance-based perception measure, recently established by Xie et al. These bounds are shown to be nondegenerate in the sense that they cannot be deduced from each other via a refined version of Talagrand's transportation inequality. On the other hand, an improved lower bound is established when the perception measure is given by the squared Wasserstein-2 distance. In addition, it is revealed by exploiting the connection between rate-distortion-perception coding and entropy-constrained scalar quantization that all the aforementioned bounds are generally not tight in the weak perception constraint regime.

Cross-subject Brain Functional Connectivity Analysis for Multi-task Cognitive State Evaluation

Cognition refers to the function of information perception and processing, which is the fundamental psychological essence of human beings. It is responsible for reasoning and decision-making, while its evaluation is significant for the aviation domain in mitigating potential safety risks. Existing studies tend to use varied methods for cognitive state evaluation yet have limitations in timeliness, generalisation, and interpretability. Accordingly, this study adopts brain functional connectivity with electroencephalography signals to capture associations in brain regions across multiple subjects for evaluating real-time cognitive states. Specifically, a virtual reality-based flight platform is constructed with multi-screen embedded. Three distinctive cognitive tasks are designed and each has three degrees of difficulty. Thirty subjects are acquired for analysis and evaluation. The results are interpreted through different perspectives, including inner-subject and cross-subject for task-wise and gender-wise underlying brain functional connectivity. Additionally, this study incorporates questionnaire-based, task performance-based, and physiological measure-based approaches to fairly label the trials. A multi-class cognitive state evaluation is further conducted with the active brain connections. Benchmarking results demonstrate that the identified brain regions have considerable influences in cognition, with a multi-class accuracy rate of 95.83% surpassing existing studies. The derived findings bring significance to understanding the dynamic relationships among human brain functional regions, cross-subject cognitive behaviours, and decision-making, which have promising practical application values.

Improving Retrieval Augmented Language Model with Self-Reasoning

The Retrieval-Augmented Language Model (RALM) has shown remarkable performance on knowledge-intensive tasks by incorporating external knowledge during inference, which mitigates the factual hallucinations inherited in large language models (LLMs). Despite these advancements, challenges persist in the implementation of RALMs, particularly concerning their reliability and traceability. To be specific, the irrelevant document retrieval may result in unhelpful response generation or even deteriorate the performance of LLMs, while the lack of proper citations in generated outputs complicates efforts to verify the trustworthiness of the models. To this end, we propose a novel self-reasoning framework aimed at improving the reliability and traceability of RALMs, whose core idea is to leverage reasoning trajectories generated by the LLM itself. The framework involves constructing self-reason trajectories with three processes: a relevance-aware process, an evidence-aware selective process, and a trajectory analysis process. We have evaluated our framework across four public datasets (two short-form QA datasets, one long-form QA dataset, and one fact verification dataset) to demonstrate the superiority of our method, which can outperform existing state-of-art models and can achieve comparable performance with GPT-4, while only using 2,000 training samples.