Continuous Policy and Value Iteration for Stochastic Control Problems and Its Convergence

We introduce a continuous policy-value iteration algorithm where the approximations of the value function of a stochastic control problem and the optimal control are simultaneously updated through Langevin-type dynamics. This framework applies to both the entropy-regularized relaxed control problems and the classical control problems, with infinite horizon. We establish policy improvement and demonstrate convergence to the optimal control under the monotonicity condition of the Hamiltonian. By utilizing Langevin-type stochastic differential equations for continuous updates along the policy iteration direction, our approach enables the use of distribution sampling and non-convex learning techniques in machine learning to optimize the value function and identify the optimal control simultaneously.

Towards Visuospatial Cognition via Hierarchical Fusion of Visual Experts

While Multimodal Large Language Models (MLLMs) excel at general vision-language tasks, visuospatial cognition - reasoning about spatial layouts, relations, and dynamics - remains a significant challenge. Existing models often lack the necessary architectural components and specialized training data for fine-grained spatial understanding. We introduce ViCA2 (Visuospatial Cognitive Assistant 2), a novel MLLM designed to enhance spatial reasoning. ViCA2 features a dual vision encoder architecture integrating SigLIP for semantics and Hiera for spatial structure, coupled with a token ratio control mechanism for efficiency. We also developed ViCA-322K, a new large-scale dataset with over 322,000 spatially grounded question-answer pairs for targeted instruction tuning. On the challenging VSI-Bench benchmark, our ViCA2-7B model achieves a state-of-the-art average score of 56.8, significantly surpassing larger open-source models (e.g., LLaVA-NeXT-Video-72B, 40.9) and leading proprietary models (Gemini-1.5 Pro, 45.4). This demonstrates the effectiveness of our approach in achieving strong visuospatial intelligence with a compact model. We release ViCA2, its codebase, and the ViCA-322K dataset to facilitate further research.

Visuospatial Cognitive Assistant

Video-based spatial cognition is vital for robotics and embodied AI but challenges current Vision-Language Models (VLMs). This paper makes two key contributions. First, we introduce ViCA (Visuospatial Cognitive Assistant)-322K, a diverse dataset of 322,003 QA pairs from real-world indoor videos (ARKitScenes, ScanNet, ScanNet++), offering supervision for 3D metadata-grounded queries and video-based complex reasoning. Second, we develop ViCA-7B, fine-tuned on ViCA-322K, which achieves new state-of-the-art on all eight VSI-Bench tasks, outperforming existing models, including larger ones (e.g., +26.1 on Absolute Distance). For interpretability, we present ViCA-Thinking-2.68K, a dataset with explicit reasoning chains, and fine-tune ViCA-7B to create ViCA-7B-Thinking, a model that articulates its spatial reasoning. Our work highlights the importance of targeted data and suggests paths for improved temporal-spatial modeling. We release all resources to foster research in robust visuospatial intelligence.

Non-Reversible Langevin Algorithms for Constrained Sampling

We consider the constrained sampling problem where the goal is to sample from a target distribution on a constrained domain. We propose skew-reflected non-reversible Langevin dynamics (SRNLD), a continuous-time stochastic differential equation with skew-reflected boundary. We obtain non-asymptotic convergence rate of SRNLD to the target distribution in both total variation and 1-Wasserstein distances. By breaking reversibility, we show that the convergence is faster than the special case of the reversible dynamics. Based on the discretization of SRNLD, we propose skew-reflected non-reversible Langevin Monte Carlo (SRNLMC), and obtain non-asymptotic discretization error from SRNLD, and convergence guarantees to the target distribution in 1-Wasserstein distance. We show better performance guarantees than the projected Langevin Monte Carlo in the literature that is based on the reversible dynamics. Numerical experiments are provided for both synthetic and real datasets to show efficiency of the proposed algorithms.

SyncViolinist: Music-Oriented Violin Motion Generation Based on Bowing and Fingering

Automatically generating realistic musical performance motion can greatly enhance digital media production, often involving collaboration between professionals and musicians. However, capturing the intricate body, hand, and finger movements required for accurate musical performances is challenging. Existing methods often fall short due to the complex mapping between audio and motion, typically requiring additional inputs like scores or MIDI data. In this work, we present SyncViolinist, a multi-stage end-to-end framework that generates synchronized violin performance motion solely from audio input. Our method overcomes the challenge of capturing both global and fine-grained performance features through two key modules: a bowing/fingering module and a motion generation module. The bowing/fingering module extracts detailed playing information from the audio, which the motion generation module uses to create precise, coordinated body motions reflecting the temporal granularity and nature of the violin performance. We demonstrate the effectiveness of SyncViolinist with significantly improved qualitative and quantitative results from unseen violin performance audio, outperforming state-of-the-art methods. Extensive subjective evaluations involving professional violinists further validate our approach. The code and dataset are available at https://github.com/Kakanat/SyncViolinist.

Constrained Exploration via Reflected Replica Exchange Stochastic Gradient Langevin Dynamics

Replica exchange stochastic gradient Langevin dynamics (reSGLD) is an effective sampler for non-convex learning in large-scale datasets. However, the simulation may encounter stagnation issues when the high-temperature chain delves too deeply into the distribution tails. To tackle this issue, we propose reflected reSGLD (r2SGLD): an algorithm tailored for constrained non-convex exploration by utilizing reflection steps within a bounded domain. Theoretically, we observe that reducing the diameter of the domain enhances mixing rates, exhibiting a \emph{quadratic} behavior. Empirically, we test its performance through extensive experiments, including identifying dynamical systems with physical constraints, simulations of constrained multi-modal distributions, and image classification tasks. The theoretical and empirical findings highlight the crucial role of constrained exploration in improving the simulation efficiency.

Fisher information dissipation for time inhomogeneous stochastic differential equations

We provide a Lyapunov convergence analysis for time-inhomogeneous variable coefficient stochastic differential equations (SDEs). Three typical examples include overdamped, irreversible drift, and underdamped Langevin dynamics. We first formula the probability transition equation of Langevin dynamics as a modified gradient flow of the Kullback-Leibler divergence in the probability space with respect to time-dependent optimal transport metrics. This formulation contains both gradient and non-gradient directions depending on a class of time-dependent target distribution. We then select a time-dependent relative Fisher information functional as a Lyapunov functional. We develop a time-dependent Hessian matrix condition, which guarantees the convergence of the probability density function of the SDE. We verify the proposed conditions for several time-inhomogeneous Langevin dynamics. For the overdamped Langevin dynamics, we prove the $O(t^{-1/2})$ convergence in $L^1$ distance for the simulated annealing dynamics with a strongly convex potential function. For the irreversible drift Langevin dynamics, we prove an improved convergence towards the target distribution in an asymptotic regime. We also verify the convergence condition for the underdamped Langevin dynamics. Numerical examples demonstrate the convergence results for the time-dependent Langevin dynamics.

Reconfigurable Intelligent Surface-Enabled Array Radar for Interference Mitigation

Conventional active array radars often jointly design the transmit and receive beamforming for effectively suppressing interferences. To further promote the interference suppression performance, this paper introduces a reconfigurable intelligent surface (RIS) to assist the radar receiver because the RIS has the ability to bring plentiful additional degrees-of-freedom. To maximize the output signal-to-interference-plus-noise ratio (SINR) of receive array, we formulate the codesign of transmit beamforming and RIS-assisted receive beamforming into a nonconvex constrained fractional programming problem, and then propose an alternating minimization-based algorithm to jointly optimize the transmitor beamfmer, receive beamformer and RIS reflection coefficients. Concretely, we translate the RIS reflection coefficients design into a series of unimodular quadratic programming (UQP) subproblems by employing the Dinkelbach transform, and offer the closed-form optimal solutions of transmit and receive beamformers according to the minimum variance distortionless response principle. To tackle the UQP subproblems efficiently, we propose a second-order Riemannian Newton method (RNM) with improved Riemannian Newton direction, which avoids the line search and has better convergence speed than typical first-order Riemannian manifold optimization methods. Moreover, we derive the convergence of the proposed codesign algorithm by deducing the explicit convergence condition of RNM. We also analyze the computational complexity. Numerical results demonstrate that the proposed RIS-assisted array radar has superior performance of interference suppression to the RIS-free one, and the SINR improvement is proportional to the number of RIS elements.

Reflected Schrödinger Bridge for Constrained Generative Modeling

Diffusion models have become the go-to method for large-scale generative models in real-world applications. These applications often involve data distributions confined within bounded domains, typically requiring ad-hoc thresholding techniques for boundary enforcement. Reflected diffusion models (Lou23) aim to enhance generalizability by generating the data distribution through a backward process governed by reflected Brownian motion. However, reflected diffusion models may not easily adapt to diverse domains without the derivation of proper diffeomorphic mappings and do not guarantee optimal transport properties. To overcome these limitations, we introduce the Reflected Schrodinger Bridge algorithm: an entropy-regularized optimal transport approach tailored for generating data within diverse bounded domains. We derive elegant reflected forward-backward stochastic differential equations with Neumann and Robin boundary conditions, extend divergence-based likelihood training to bounded domains, and explore natural connections to entropic optimal transport for the study of approximate linear convergence - a valuable insight for practical training. Our algorithm yields robust generative modeling in diverse domains, and its scalability is demonstrated in real-world constrained generative modeling through standard image benchmarks.

Gaze-Driven Sentence Simplification for Language Learners: Enhancing Comprehension and Readability

Language learners should regularly engage in reading challenging materials as part of their study routine. Nevertheless, constantly referring to dictionaries is time-consuming and distracting. This paper presents a novel gaze-driven sentence simplification system designed to enhance reading comprehension while maintaining their focus on the content. Our system incorporates machine learning models tailored to individual learners, combining eye gaze features and linguistic features to assess sentence comprehension. When the system identifies comprehension difficulties, it provides simplified versions by replacing complex vocabulary and grammar with simpler alternatives via GPT-3.5. We conducted an experiment with 19 English learners, collecting data on their eye movements while reading English text. The results demonstrated that our system is capable of accurately estimating sentence-level comprehension. Additionally, we found that GPT-3.5 simplification improved readability in terms of traditional readability metrics and individual word difficulty, paraphrasing across different linguistic levels.