Search

LLMs exhibit advanced reasoning capabilities, offering the potential to transform natural language questions into mathematical models. However, existing open-source datasets in operations research domain lack detailed annotations of the modeling process, such as variable definitions, focusing solely on objective values, which hinders reinforcement learning applications. To address this, we release the StructuredOR dataset, annotated with comprehensive labels that capture the complete mathematical modeling process. We further propose BPP-Search, a algorithm that integrates reinforcement learning into a tree-of-thought structure using Beam search, a Process reward model, and a pairwise Preference algorithm. This approach enables efficient exploration of tree structures, avoiding exhaustive search while improving accuracy. Extensive experiments on StructuredOR, NL4OPT, and MAMO-ComplexLP datasets show that BPP-Search significantly outperforms state-of-the-art methods. In tree-based reasoning, BPP-Search excels in accuracy and efficiency, enabling faster retrieval of correct solutions.

In this paper, we consider the conditional generation problem by guiding off-the-shelf unconditional diffusion models with differentiable loss functions in a plug-and-play fashion. While previous research has primarily focused on balancing the unconditional diffusion model and the guided loss through a tuned weight hyperparameter, we propose a novel framework that distinctly decouples these two components. Specifically, we introduce two variables ${x}$ and ${z}$, to represent the generated samples governed by the unconditional generation model and the guidance function, respectively. This decoupling reformulates conditional generation into two manageable subproblems, unified by the constraint ${x} = {z}$. Leveraging this setup, we develop a new algorithm based on the Alternating Direction Method of Multipliers (ADMM) to adaptively balance these components. Additionally, we establish the equivalence between the diffusion reverse step and the proximal operator of ADMM and provide a detailed convergence analysis of our algorithm under certain mild assumptions. Our experiments demonstrate that our proposed method ADMMDiff consistently generates high-quality samples while ensuring strong adherence to the conditioning criteria. It outperforms existing methods across a range of conditional generation tasks, including image generation with various guidance and controllable motion synthesis.

Visual Speech Recognition (VSR) aims to recognize corresponding text by analyzing visual information from lip movements. Due to the high variability and weak information of lip movements, VSR tasks require effectively utilizing any information from any source and at any level. In this paper, we propose a VSR method based on audio-visual cross-modal alignment, named AlignVSR. The method leverages the audio modality as an auxiliary information source and utilizes the global and local correspondence between the audio and visual modalities to improve visual-to-text inference. Specifically, the method first captures global alignment between video and audio through a cross-modal attention mechanism from video frames to a bank of audio units. Then, based on the temporal correspondence between audio and video, a frame-level local alignment loss is introduced to refine the global alignment, improving the utility of the audio information. Experimental results on the LRS2 and CNVSRC.Single datasets consistently show that AlignVSR outperforms several mainstream VSR methods, demonstrating its superior and robust performance.

In the field of spoken language processing, audio-visual speech processing is receiving increasing research attention. Key components of this research include tasks such as lip reading, audio-visual speech recognition, and visual-to-speech synthesis. Although significant success has been achieved, theoretical analysis is still insufficient for audio-visual tasks. This paper presents a quantitative analysis based on information theory, focusing on information intersection between different modalities. Our results show that this analysis is valuable for understanding the difficulties of audio-visual processing tasks as well as the benefits that could be obtained by modality integration., Comment: Accepted by ISCSLP2024

The first Chinese Continuous Visual Speech Recognition Challenge aimed to probe the performance of Large Vocabulary Continuous Visual Speech Recognition (LVC-VSR) on two tasks: (1) Single-speaker VSR for a particular speaker and (2) Multi-speaker VSR for a set of registered speakers. The challenge yielded highly successful results, with the best submission significantly outperforming the baseline, particularly in the single-speaker task. This paper comprehensively reviews the challenge, encompassing the data profile, task specifications, and baseline system construction. It also summarises the representative techniques employed by the submitted systems, highlighting the most effective approaches. Additional information and resources about this challenge can be accessed through the official website at http://cnceleb.org/competition., Comment: Accepted by INTERSPEECH 2024

Recent studies have advocated the detection of fake videos as a one-class detection task, predicated on the hypothesis that the consistency between audio and visual modalities of genuine data is more significant than that of fake data. This methodology, which solely relies on genuine audio-visual data while negating the need for forged counterparts, is thus delineated as a `zero-shot' detection paradigm. This paper introduces a novel zero-shot detection approach anchored in content consistency across audio and video. By employing pre-trained ASR and VSR models, we recognize the audio and video content sequences, respectively. Then, the edit distance between the two sequences is computed to assess whether the claimed video is genuine. Experimental results indicate that, compared to two mainstream approaches based on semantic consistency and temporal consistency, our approach achieves superior generalizability across various deepfake techniques and demonstrates strong robustness against audio-visual perturbations. Finally, state-of-the-art performance gains can be achieved by simply integrating the decision scores of these three systems., Comment: to be published in INTERSPEECH 2024

Recent studies in neuro-symbolic learning have explored the integration of logical knowledge into deep learning via encoding logical constraints as an additional loss function. However, existing approaches tend to vacuously satisfy logical constraints through shortcuts, failing to fully exploit the knowledge. In this paper, we present a new framework for learning with logical constraints. Specifically, we address the shortcut satisfaction issue by introducing dual variables for logical connectives, encoding how the constraint is satisfied. We further propose a variational framework where the encoded logical constraint is expressed as a distributional loss that is compatible with the model's original training loss. The theoretical analysis shows that the proposed approach bears salient properties, and the experimental evaluations demonstrate its superior performance in both model generalizability and constraint satisfaction., Comment: Published as a conference paper at ICLR 2023, and code is available at https://github.com/SoftWiser-group/NeSy-without-Shortcuts

Significance testing aims to determine whether a proposition about the population distribution is the truth or not given observations. However, traditional significance testing often needs to derive the distribution of the testing statistic, failing to deal with complex nonlinear relationships. In this paper, we propose to conduct Full Bayesian Significance Testing for neural networks, called \textit{n}FBST, to overcome the limitation in relationship characterization of traditional approaches. A Bayesian neural network is utilized to fit the nonlinear and multi-dimensional relationships with small errors and avoid hard theoretical derivation by computing the evidence value. Besides, \textit{n}FBST can test not only global significance but also local and instance-wise significance, which previous testing methods don't focus on. Moreover, \textit{n}FBST is a general framework that can be extended based on the measures selected, such as Grad-\textit{n}FBST, LRP-\textit{n}FBST, DeepLIFT-\textit{n}FBST, LIME-\textit{n}FBST. A range of experiments on both simulated and real data are conducted to show the advantages of our method., Comment: Published as a conference paper at AAAI 2024

We introduce a new analytic framework to analyze the convergence of the Randomized Stochastic Gradient Descent Ascent (RSGDA) algorithm for stochastic minimax optimization problems. Under the so-called NC-PL condition on one of the variables, our analysis improves the state-of-the-art convergence results in the current literature and hence broadens the applicable range of the RSGDA. We also introduce a simple yet effective strategy to accelerate RSGDA , and empirically validate its efficiency on both synthetic data and real data.

The curve skeleton is an important shape descriptor that has been utilized in various applications in computer graphics, machine vision, and artificial intelligence. In this study, the endpoint-based part-aware curve skeleton (EPCS) extraction method for low-quality point clouds is proposed. The novel random center shift (RCS) method is first proposed for detecting the endpoints on point clouds. The endpoints are used as the initial seed points for dividing each part into layers, and then the skeletal points are obtained by computing the center points of the oriented bounding box (OBB) of the layers. Subsequently, the skeletal points are connected, thus forming the branches. Furthermore, the multi-vector momentum-driven (MVMD) method is also proposed for locating the junction points that connect the branches. Due to the shape differences between different parts on point clouds, the global topology of the skeleton is finally optimized by removing the redundant junction points, re-connecting some branches using the proposed MVMD method, and applying an interpolation method based on the splitting operator. Consequently, a complete and smooth curve skeleton is achieved. The proposed EPCS method is compared with several state-of-the-art methods, and the experimental results verify its robustness, effectiveness, and efficiency. Furthermore, the skeleton extraction and model segmentation results on the point clouds of broken Terracotta also highlight the utility of the proposed method., Comment: Need to modify

We study the dynamics of gyrotactic swimmers in turbulence, whose orientation is governed by gravitational torque and local fluid velocity gradient. The gyrotaxis strength is measured by the ratio of the Kolmogorov time scale to the reorientation time scale due to gravity, and a large value of this ratio means the gyrotaxis is strong. By means of direct numerical simulations, we investigate the effects of swimming velocity and gyrotactic stability on spatial accumulation and alignment. Three-dimensional Vorono{\"\i} analysis is used to study the spatial distribution and time evolution of the particle concentration. We study spatial distribution by examing the overall preferential sampling and where clusters and voids (subsets of particles that have small and large Vorono{\"\i} volumes respectively) form. Compared with the ensemble particles, the preferential sampling of clusters and voids is found to be more pronounced. The clustering of fast swimmers lasts much longer than slower swimmers when the gyrotaxis is strong and intermediate, but an opposite trend emerges when the gyrotaxis is weak. In addition, we study the preferential alignment with the Lagrangian stretching direction, with which passive slender rods have been known to align. We show that the Lagrangian alignment is reduced by the swimming velocity when the gyrotaxis is weak, while the Lagrangian alignment is enhanced for the regime in which gyrotaxis is strong.