Federated learning (FL) as one of the novel branches of distributed machine learning (ML), develops global models through a private procedure without direct access to local datasets. However, access to model updates (e.g. gradient updates in deep neural networks) transferred between clients and servers can reveal sensitive information to adversaries. Differential privacy (DP) offers a framework that gives a privacy guarantee by adding certain amounts of noise to parameters. This approach, although being effective in terms of privacy, adversely affects model performance due to noise involvement. Hence, it is always needed to find a balance between noise injection and the sacrificed accuracy. To address this challenge, we propose adaptive noise addition in FL which decides the value of injected noise based on features' relative importance. Here, we first propose two effective methods for prioritizing features in deep neural network models and then perturb models' weights based on this information. Specifically, we try to figure out whether the idea of adding more noise to less important parameters and less noise to more important parameters can effectively save the model accuracy while preserving privacy. Our experiments confirm this statement under some conditions. The amount of noise injected, the proportion of parameters involved, and the number of global iterations can significantly change the output. While a careful choice of parameters by considering the properties of datasets can improve privacy without intense loss of accuracy, a bad choice can make the model performance worse.
Advancements in large language models (LLMs) have demonstrated their potential in facilitating high-level reasoning, logical reasoning and robotics planning. Recently, LLMs have also been able to generate reward functions for low-level robot actions, effectively bridging the interface between high-level planning and low-level robot control. However, the challenge remains that even with syntactically correct plans, robots can still fail to achieve their intended goals. This failure can be attributed to imperfect plans proposed by LLMs or to unforeseeable environmental circumstances that hinder the execution of planned subtasks due to erroneous assumptions about the state of objects. One way to prevent these challenges is to rely on human-provided step-by-step instructions, limiting the autonomy of robotic systems. Vision Language Models (VLMs) have shown remarkable success in tasks such as visual question answering and image captioning. Leveraging the capabilities of VLMs, we present a novel framework called Robotic Replanning with Perception and Language Models (RePLan) that enables real-time replanning capabilities for long-horizon tasks. This framework utilizes the physical grounding provided by a VLM's understanding of the world's state to adapt robot actions when the initial plan fails to achieve the desired goal. We test our approach within four environments containing seven long-horizion tasks. We find that RePLan enables a robot to successfully adapt to unforeseen obstacles while accomplishing open-ended, long-horizon goals, where baseline models cannot. Find more information at https://replan-lm.github.io/replan.github.io/
The explosion of data has resulted in more and more associated text being transmitted along with images. Inspired by from distributed source coding, many works utilize image side information to enhance image compression. However, existing methods generally do not consider using text as side information to enhance perceptual compression of images, even though the benefits of multimodal synergy have been widely demonstrated in research. This begs the following question: How can we effectively transfer text-level semantic dependencies to help image compression, which is only available to the decoder? In this work, we propose a novel deep image compression method with text-guided side information to achieve a better rate-perception-distortion tradeoff. Specifically, we employ the CLIP text encoder and an effective Semantic-Spatial Aware block to fuse the text and image features. This is done by predicting a semantic mask to guide the learned text-adaptive affine transformation at the pixel level. Furthermore, we design a text-conditional generative adversarial networks to improve the perceptual quality of reconstructed images. Extensive experiments involving four datasets and ten image quality assessment metrics demonstrate that the proposed approach achieves superior results in terms of rate-perception trade-off and semantic distortion.
Existing music-driven 3D dance generation methods mainly concentrate on high-quality dance generation, but lack sufficient control during the generation process. To address these issues, we propose a unified framework capable of generating high-quality dance movements and supporting multi-modal control, including genre control, semantic control, and spatial control. First, we decouple the dance generation network from the dance control network, thereby avoiding the degradation in dance quality when adding additional control information. Second, we design specific control strategies for different control information and integrate them into a unified framework. Experimental results show that the proposed dance generation framework outperforms state-of-the-art methods in terms of motion quality and controllability.
Categorization is an important topic both for biological and artificial neural networks. Here, we take an information theoretic approach to assess the efficiency of the representations induced by category learning. We show that one can decompose the relevant Bayesian cost into two components, one for the coding part and one for the decoding part. Minimizing the coding cost implies maximizing the mutual information between the set of categories and the neural activities. We analytically show that this mutual information can be written as the sum of two terms that can be interpreted as (i) finding an appropriate representation space, and, (ii) building a representation with the appropriate metrics, based on the neural Fisher information on this space. One main consequence is that category learning induces an expansion of neural space near decision boundaries. Finally, we provide numerical illustrations that show how Fisher information of the coding neural population aligns with the boundaries between categories.
Astronomical observations typically provide three-dimensional maps, encoding the distribution of the observed flux in (1) the two angles of the celestial sphere and (2) energy/frequency. An important task regarding such maps is to statistically characterize populations of point sources too dim to be individually detected. As the properties of a single dim source will be poorly constrained, instead one commonly studies the population as a whole, inferring a source-count distribution (SCD) that describes the number density of sources as a function of their brightness. Statistical and machine learning methods for recovering SCDs exist; however, they typically entirely neglect spectral information associated with the energy distribution of the flux. We present a deep learning framework able to jointly reconstruct the spectra of different emission components and the SCD of point-source populations. In a proof-of-concept example, we show that our method accurately extracts even complex-shaped spectra and SCDs from simulated maps.
Hyperdimensional computing (HDC) is an emerging computing paradigm that exploits the distributed representation of input data in a hyperdimensional space, the dimensions of which are typically between 1,000--10,000. The hyperdimensional distributed representation enables energy-efficient, low-latency, and noise-robust computations with low-precision and basic arithmetic operations. In this study, we propose optical hyperdimensional distributed representations based on laser speckles for adaptive, efficient, and low-latency optical sensor processing. In the proposed approach, sensory information is optically mapped into a hyperdimensional space with >250,000 dimensions, enabling HDC-based cognitive processing. We use this approach for the processing of a soft-touch interface and a tactile sensor and demonstrate to achieve high accuracy of touch or tactile recognition while significantly reducing training data amount and computational burdens, compared with previous machine-learning-based sensing approaches. Furthermore, we show that this approach enables adaptive recalibration to keep high accuracy even under different conditions.
Large language models are known for encoding a vast amount of factual knowledge, but they often becomes outdated due to the ever-changing nature of external information. A promising solution to this challenge is the utilization of model editing methods to update the knowledge in an efficient manner. However, the majority of existing model editing techniques are limited to monolingual frameworks, thus failing to address the crucial issue of cross-lingual knowledge synchronization for multilingual models. To tackle this problem, we propose a simple yet effective method that trains multilingual patch neuron to store cross-lingual knowledge. It can be easily adapted to existing approaches to enhance their cross-lingual editing capabilities. To evaluate our method, we conduct experiments using both the XNLI dataset and a self-constructed XFEVER dataset. Experimental results demonstrate that our proposed method achieves improved performance in cross-lingual editing tasks without requiring excessive modifications to the original methodology, thereby showcasing its user-friendly characteristics. Codes will be released soon.
In this work, we introduce Context-Aware MultiModal Learner (CaMML), for tuning large multimodal models (LMMs). CaMML, a lightweight module, is crafted to seamlessly integrate multimodal contextual samples into large models, thereby empowering the model to derive knowledge from analogous, domain-specific, up-to-date information and make grounded inferences. Importantly, CaMML is highly scalable and can efficiently handle lengthy multimodal context examples owing to its hierarchical design. Based on CaMML, we have developed two multimodal models, CaMML-7B and CaMML-13B, that have shown exceptional performance across an array of benchmark datasets for multimodal tasks. Remarkably, CaMML-13B achieves the state-of-the-art performance on over ten widely recognized multimodal benchmark datasets, surpassing LLaVA-1.5 (13B) with a noticeable margin, without integration of any external resources. Moreover, we have conducted extensive ablative studies to inspect the inner workings of CaMML and performed qualitative analyses to showcase its effectiveness in handling real-world challenging cases.
In recent years, there has been growing interest in the video-based action quality assessment (AQA). Most existing methods typically solve AQA problem by considering the entire video yet overlooking the inherent stage-level characteristics of actions. To address this issue, we design a novel Multi-stage Contrastive Regression (MCoRe) framework for the AQA task. This approach allows us to efficiently extract spatial-temporal information, while simultaneously reducing computational costs by segmenting the input video into multiple stages or procedures. Inspired by the graph contrastive learning, we propose a new stage-wise contrastive learning loss function to enhance performance. As a result, MCoRe demonstrates the state-of-the-art result so far on the widely-adopted fine-grained AQA dataset.