The high computational costs of large language models (LLMs) have led to a flurry of research on LLM compression, via methods such as quantization, sparsification, or structured pruning. A new frontier in this area is given by \emph{dynamic, non-uniform} compression methods, which adjust the compression levels (e.g., sparsity) per-block or even per-layer in order to minimize accuracy loss, while guaranteeing a global compression threshold. Yet, current methods rely on heuristics for identifying the "importance" of a given layer towards the loss, based on assumptions such as \emph{error monotonicity}, i.e. that the end-to-end model compression error is proportional to the sum of layer-wise errors. In this paper, we revisit this area, and propose a new and general approach for dynamic compression that is provably optimal in a given input range. We begin from the motivating observation that, in general, \emph{error monotonicity does not hold for LLMs}: compressed models with lower sum of per-layer errors can perform \emph{worse} than models with higher error sums. To address this, we propose a new general evolutionary framework for dynamic LLM compression called EvoPress, which has provable convergence, and low sample and evaluation complexity. We show that these theoretical guarantees lead to highly competitive practical performance for dynamic compression of Llama, Mistral and Phi models. Via EvoPress, we set new state-of-the-art results across all compression approaches: structural pruning (block/layer dropping), unstructured sparsity, as well as quantization with dynamic bitwidths. Our code is available at https://github.com/IST-DASLab/EvoPress.

Electricity forecasting has been a recurring research topic, as it is key to finding the right balance between production and consumption. While most papers are focused on the national or regional scale, few are interested in the household level. Desegregated forecast is a common topic in Machine Learning (ML) literature but lacks explainability that household energy forecasts require. This paper specifically targets the challenges of forecasting electricity use at the household level. This paper confronts common Machine Learning algorithms to electricity household forecasts, weighing the pros and cons, including accuracy and explainability with well-known key metrics. Furthermore, we also confront them in this paper with the business challenges specific to this sector such as explainability or outliers resistance. We introduce a custom decision tree, aiming at providing a fair estimate of the energy consumption, while being explainable and consistent with human intuition. We show that this novel method allows greater explainability without sacrificing much accuracy. The custom tree methodology can be used in various business use cases but is subject to limitations, such as a lack of resilience with outliers.

Road Extraction is a sub-domain of Remote Sensing applications; it is a subject of extensive and ongoing research. The procedure of automatically extracting roads from satellite imagery encounters significant challenges due to the multi-scale and diverse structures of roads; improvement in this field is needed. The DeepLab series, known for its proficiency in semantic segmentation due to its efficiency in interpreting multi-scale objects' features, addresses some of these challenges caused by the varying nature of roads. The present work proposes the utilization of DeepLabV3+, the latest version of the DeepLab series, by introducing an innovative Dense Depthwise Dilated Separable Spatial Pyramid Pooling (DenseDDSSPP) module and integrating it in place of the conventional Atrous Spatial Pyramid Pooling (ASPP) module. This modification enhances the extraction of complex road structures from satellite images. This study hypothesizes that the integration of DenseDDSSPP, combined with an appropriately selected backbone network and a Squeeze-and-Excitation block, will generate an efficient dense feature map by focusing on relevant features, leading to more precise and accurate road extraction from Remote Sensing images. The results section presents a comparison of our model's performance against state-of-the-art models, demonstrating better results that highlight the effectiveness and success of the proposed approach.

Latent diffusion models have enabled continuous-state diffusion models to handle a variety of datasets, including categorical data. However, most methods rely on fixed pretrained embeddings, limiting the benefits of joint training with the diffusion model. While jointly learning the embedding (via reconstruction loss) and the latent diffusion model (via score matching loss) could enhance performance, our analysis shows that end-to-end training risks embedding collapse, degrading generation quality. To address this issue, we introduce CATDM, a continuous diffusion framework within the embedding space that stabilizes training. We propose a novel objective combining the joint embedding-diffusion variational lower bound with a Consistency-Matching (CM) regularizer, alongside a shifted cosine noise schedule and random dropping strategy. The CM regularizer ensures the recovery of the true data distribution. Experiments on benchmarks show that CATDM mitigates embedding collapse, yielding superior results on FFHQ, LSUN Churches, and LSUN Bedrooms. In particular, CATDM achieves an FID of 6.81 on ImageNet 256 256 with 50 steps. It outperforms non-autoregressive models in machine translation and is on a par with previous methods in text generation. These probabilistic models learn the inverse of a Markov chain that gradually converts data into pure Gaussian noise, using noise-conditioned score functions (i.e., gradients of log density), which are defined only for continuous data. The core concept is to progressively recover the original data distribution using a learned transition kernel. They offer stable and relatively efficient training procedures that contribute to their success. Recent advances, such as consistency models (Song et al., 2023; Kim et al., 2023; Luo et al., 2023), have further enhanced diffusion models by reducing the number of sampling steps, making them more practical for real-world applications.

In processing multiple time series, accounting for the individual features of each sequence can be challenging. To address this, modern deep learning methods for time series analysis combine a shared (global) model with local layers, specific to each time series, often implemented as learnable embeddings. Ideally, these local embeddings should encode meaningful representations of the unique dynamics of each sequence. However, when these are learned end-to-end as parameters of a forecasting model, they may end up acting as mere sequence identifiers. Shared processing blocks may then become reliant on such identifiers, limiting their transferability to new contexts. In this paper, we address this issue by investigating methods to regularize the learning of local learnable embeddings for time series processing. Specifically, we perform the first extensive empirical study on the subject and show how such regularizations consistently improve performance in widely adopted architectures. Furthermore, we show that methods preventing the co-adaptation of local and global parameters are particularly effective in this context. This hypothesis is validated by comparing several methods preventing the downstream models from relying on sequence identifiers, going as far as completely resetting the embeddings during training. The obtained results provide an important contribution to understanding the interplay between learnable local parameters and shared processing layers: a key challenge in modern time series processing models and a step toward developing effective foundation models for time series.

Advances in diffusion models for generative artificial intelligence have recently propagated to the time series (TS) domain, demonstrating state-of-the-art performance on various tasks. However, prior works on TS diffusion models often borrow the framework of existing works proposed in other domains without considering the characteristics of TS data, leading to suboptimal performance. In this work, we propose Adaptive Noise schedule for Time series diffusion models (ANT), which automatically predetermines proper noise schedules for given TS datasets based on their statistics representing non-stationarity. Our intuition is that an optimal noise schedule should satisfy the following desiderata: 1) It linearly reduces the non-stationarity of TS data so that all diffusion steps are equally meaningful, 2) the data is corrupted to the random noise at the final step, and 3) the number of steps is sufficiently large. The proposed method is practical for use in that it eliminates the necessity of finding the optimal noise schedule with a small additional cost to compute the statistics for given datasets, which can be done offline before training. We validate the effectiveness of our method across various tasks, including TS forecasting, refinement, and generation, on datasets from diverse domains. Code is available at this repository: https://github.com/seunghan96/ANT.

Over the past few months, some of the most prominent people in AI have fashioned themselves as modern messiahs and their products as deities. Top executives and respected researchers at the world's biggest tech companies, including a recent Nobel laureate, are all at once insisting that superintelligent software is just around the corner, going so far as to provide timelines: They will build it within six years, or four years, or maybe just two. Although AI executives commonly speak of the coming AGI revolution--referring to artificial "general" intelligence that rivals or exceeds human capability--they notably have all at this moment coalesced around real, albeit loose, deadlines. Many of their prophecies also have an undeniable utopian slant. First, Demis Hassabis, the head of Google DeepMind, repeated in August his suggestion from earlier this year that AGI could arrive by 2030, adding that "we could cure most diseases within the next decade or two."

Ultrasound (US) has the unique potential to offer access to medical imaging to anyone, everywhere. Devices have become ultra-portable and cost-effective, akin to the stethoscope. Nevertheless US image quality and diagnostic efficacy are still highly operator- and patient-dependent. In difficult-to-image patients, image quality is often insufficient for reliable diagnosis. In this paper, we put forth that US imaging systems can be recast as information-seeking agents that engage in reciprocal interactions with their anatomical environment. Such agents autonomously adapt their transmit-receive sequences to fully personalize imaging and actively maximize information gain in-situ. To that end, we will show that the sequence of pulse-echo experiments that a US system performs can be interpreted as a perception-action loop: the action is the data acquisition, probing tissue with acoustic waves and recording reflections at the detection array, and perception is the inference of the anatomical and or functional state, potentially including associated diagnostic quantities. We then equip systems with a mechanism to actively reduce uncertainty and maximize diagnostic value across a sequence of experiments, treating action and perception jointly using Bayesian inference given generative models of the environment and action-conditional pulse-echo observations. Since the representation capacity of the generative models dictates both the quality of inferred anatomical states and the effectiveness of inferred sequences of future imaging actions, we will be greatly leveraging the enormous advances in deep generative modelling that are currently disrupting many fields and society at large. Finally, we show some examples of cognitive, closed-loop, US systems that perform active beamsteering and adaptive scanline selection, based on deep generative models that track anatomical belief states.

In practical applications, the unpredictable movement of obstacles and the imprecise state observation of robots introduce significant uncertainties for the swarm of robots, especially in cluster environments. However, existing methods are difficult to realize safe navigation, considering uncertainties, complex environmental structures, and robot swarms. This paper introduces an extended state model predictive control planner with a safe probability field to address the multi-robot navigation problem in complex, dynamic, and uncertain environments. Initially, the safe probability field offers an innovative approach to model the uncertainty of external dynamic obstacles, combining it with an unconstrained optimization method to generate safe trajectories for multi-robot online. Subsequently, the extended state model predictive controller can accurately track these generated trajectories while considering the robots' inherent model constraints and state uncertainty, thus ensuring the practical feasibility of the planned trajectories. Simulation experiments show a success rate four times higher than that of state-of-the-art algorithms. Physical experiments demonstrate the method's ability to operate in real-time, enabling safe navigation for multi-robot in uncertain environments.

Mobile robots have shown immense potential and are expected to be widely used in the service industry. The importance of automatic navigation and voice cloning cannot be overstated as they enable functional robots to provide high-quality services. The objective of this work is to develop a control algorithm for the automatic navigation of a humanoid mobile robot called Cruzr, which is a service robot manufactured by Ubtech. Initially, a virtual environment is constructed in the simulation software Gazebo using Simultaneous Localization And Mapping (SLAM), and global path planning is carried out by means of local path tracking. The two-wheel differential chassis kinematics model is employed to ensure autonomous dynamic obstacle avoidance for the robot chassis. Furthermore, the mapping and trajectory generation algorithms developed in the simulation environment are successfully implemented on the real robot Cruzr. The performance of automatic navigation is compared between the Dynamic Window Approach (DWA) and Model Predictive Control (MPC) algorithms. Additionally, a mobile application for voice cloning is created based on a Hidden Markov Model, and the proposed Chatbot is also tested and deployed on Cruzr.