Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment

Visuomotor robot policies, increasingly pre-trained on large-scale datasets, promise significant advancements across robotics domains. However, aligning these policies with end-user preferences remains a challenge, particularly when the preferences are hard to specify. While reinforcement learning from human feedback (RLHF) has become the predominant mechanism for alignment in non-embodied domains like large language models, it has not seen the same success in aligning visuomotor policies due to the prohibitive amount of human feedback required to learn visual reward functions. To address this limitation, we propose Representation-Aligned Preference-based Learning (RAPL), an observation-only method for learning visual rewards from significantly less human preference feedback. Unlike traditional RLHF, RAPL focuses human feedback on fine-tuning pre-trained vision encoders to align with the end-user's visual representation and then constructs a dense visual reward via feature matching in this aligned representation space. We first validate RAPL through simulation experiments in the X-Magical benchmark and Franka Panda robotic manipulation, demonstrating that it can learn rewards aligned with human preferences, more efficiently uses preference data, and generalizes across robot embodiments. Finally, our hardware experiments align pre-trained Diffusion Policies for three object manipulation tasks. We find that RAPL can fine-tune these policies with 5x less real human preference data, taking the first step towards minimizing human feedback while maximizing visuomotor robot policy alignment.

MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAM

Simultaneous localization and mapping (SLAM) systems with novel view synthesis capabilities are widely used in computer vision, with applications in augmented reality, robotics, and autonomous driving. However, existing approaches are limited to single-agent operation. Recent work has addressed this problem using a distributed neural scene representation. Unfortunately, existing methods are slow, cannot accurately render real-world data, are restricted to two agents, and have limited tracking accuracy. In contrast, we propose a rigidly deformable 3D Gaussian-based scene representation that dramatically speeds up the system. However, improving tracking accuracy and reconstructing a globally consistent map from multiple agents remains challenging due to trajectory drift and discrepancies across agents' observations. Therefore, we propose new tracking and map-merging mechanisms and integrate loop closure in the Gaussian-based SLAM pipeline. We evaluate MAGiC-SLAM on synthetic and real-world datasets and find it more accurate and faster than the state of the art.

REDUCIO! Generating 1024$\times$1024 Video within 16 Seconds using Extremely Compressed Motion Latents

Commercial video generation models have exhibited realistic, high-fidelity results but are still restricted to limited access. One crucial obstacle for large-scale applications is the expensive training and inference cost. In this paper, we argue that videos contain much more redundant information than images, thus can be encoded by very few motion latents based on a content image. Towards this goal, we design an image-conditioned VAE to encode a video to an extremely compressed motion latent space. This magic Reducio charm enables 64x reduction of latents compared to a common 2D VAE, without sacrificing the quality. Training diffusion models on such a compact representation easily allows for generating 1K resolution videos. We then adopt a two-stage video generation paradigm, which performs text-to-image and text-image-to-video sequentially. Extensive experiments show that our Reducio-DiT achieves strong performance in evaluation, though trained with limited GPU resources. More importantly, our method significantly boost the efficiency of video LDMs both in training and inference. We train Reducio-DiT in around 3.2K training hours in total and generate a 16-frame 1024*1024 video clip within 15.5 seconds on a single A100 GPU. Code released at https://github.com/microsoft/Reducio-VAE .

A Multimodal Adaptive Graph-based Intelligent Classification Model for Fake News

Numerous studies have been proposed to detect fake news focusing on multi-modalities based on machine and/or deep learning. However, studies focusing on graph-based structures using geometric deep learning are lacking. To address this challenge, we introduce the Multimodal Adaptive Graph-based Intelligent Classification (aptly referred to as MAGIC) for fake news detection. Specifically, the Encoder Representations from Transformers was used for text vectorization whilst ResNet50 was used for images. A comprehensive information interaction graph was built using the adaptive Graph Attention Network before classifying the multimodal input through the Softmax function. MAGIC was trained and tested on two fake news datasets, that is, Fakeddit (English) and Multimodal Fake News Detection (Chinese), with the model achieving an accuracy of 98.8\% and 86.3\%, respectively. Ablation experiments also revealed MAGIC to yield superior performance across both the datasets. Findings show that a graph-based deep learning adaptive model is effective in detecting multimodal fake news, surpassing state-of-the-art methods.

FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations

Sketch animations offer a powerful medium for visual storytelling, from simple flip-book doodles to professional studio productions. While traditional animation requires teams of skilled artists to draw key frames and in-between frames, existing automation attempts still demand significant artistic effort through precise motion paths or keyframe specification. We present FlipSketch, a system that brings back the magic of flip-book animation -- just draw your idea and describe how you want it to move! Our approach harnesses motion priors from text-to-video diffusion models, adapting them to generate sketch animations through three key innovations: (i) fine-tuning for sketch-style frame generation, (ii) a reference frame mechanism that preserves visual integrity of input sketch through noise refinement, and (iii) a dual-attention composition that enables fluid motion without losing visual consistency. Unlike constrained vector animations, our raster frames support dynamic sketch transformations, capturing the expressive freedom of traditional animation. The result is an intuitive system that makes sketch animation as simple as doodling and describing, while maintaining the artistic essence of hand-drawn animation.

One-Shot Manipulation Strategy Learning by Making Contact Analogies

We present a novel approach, MAGIC (manipulation analogies for generalizable intelligent contacts), for one-shot learning of manipulation strategies with fast and extensive generalization to novel objects. By leveraging a reference action trajectory, MAGIC effectively identifies similar contact points and sequences of actions on novel objects to replicate a demonstrated strategy, such as using different hooks to retrieve distant objects of different shapes and sizes. Our method is based on a two-stage contact-point matching process that combines global shape matching using pretrained neural features with local curvature analysis to ensure precise and physically plausible contact points. We experiment with three tasks including scooping, hanging, and hooking objects. MAGIC demonstrates superior performance over existing methods, achieving significant improvements in runtime speed and generalization to different object categories. Website: https://magic-2024.github.io/ .

1st-Order Magic: Analysis of Sharpness-Aware Minimization

Sharpness-Aware Minimization (SAM) is an optimization technique designed to improve generalization by favoring flatter loss minima. To achieve this, SAM optimizes a modified objective that penalizes sharpness, using computationally efficient approximations. Interestingly, we find that more precise approximations of the proposed SAM objective degrade generalization performance, suggesting that the generalization benefits of SAM are rooted in these approximations rather than in the original intended mechanism. This highlights a gap in our understanding of SAM's effectiveness and calls for further investigation into the role of approximations in optimization.

Power Plays: Unleashing Machine Learning Magic in Smart Grids

The integration of machine learning into smart grid systems represents a transformative step in enhancing the efficiency, reliability, and sustainability of modern energy networks. By adding advanced data analytics, these systems can better manage the complexities of renewable energy integration, demand response, and predictive maintenance. Machine learning algorithms analyze vast amounts of data from smart meters, sensors, and other grid components to optimize energy distribution, forecast demand, and detect irregularities that could indicate potential failures. This enables more precise load balancing, reduces operational costs, and enhances the resilience of the grid against disturbances. Furthermore, the use of predictive models helps in anticipating equipment failures, thereby improving the reliability of the energy supply. As smart grids continue to evolve, the role of machine learning in managing decentralized energy sources and enabling real-time decision-making will become increasingly critical. However, the deployment of these technologies also raises challenges related to data privacy, security, and the need for robust infrastructure. Addressing these issues in this research authors will focus on realizing the full potential of smart grids, ensuring they meet the growing energy demands while maintaining a focus on sustainability and efficiency using Machine Learning techniques. Furthermore, this research will help determine the smart grid's essentiality with the aid of Machine Learning. Multiple ML algorithms have been integrated along with their pros and cons. The future scope of these algorithms are also integrated.

Efficient Deep Learning Board: Training Feedback Is Not All You Need

Current automatic deep learning (i.e., AutoDL) frameworks rely on training feedback from actual runs, which often hinder their ability to provide quick and clear performance predictions for selecting suitable DL systems. To address this issue, we propose EfficientDL, an innovative deep learning board designed for automatic performance prediction and component recommendation. EfficientDL can quickly and precisely recommend twenty-seven system components and predict the performance of DL models without requiring any training feedback. The magic of no training feedback comes from our proposed comprehensive, multi-dimensional, fine-grained system component dataset, which enables us to develop a static performance prediction model and comprehensive optimized component recommendation algorithm (i.e., {\alpha}\b{eta}-BO search), removing the dependency on actually running parameterized models during the traditional optimization search process. The simplicity and power of EfficientDL stem from its compatibility with most DL models. For example, EfficientDL operates seamlessly with mainstream models such as ResNet50, MobileNetV3, EfficientNet-B0, MaxViT-T, Swin-B, and DaViT-T, bringing competitive performance improvements. Besides, experimental results on the CIFAR-10 dataset reveal that EfficientDL outperforms existing AutoML tools in both accuracy and efficiency (approximately 20 times faster along with 1.31% Top-1 accuracy improvement than the cutting-edge methods). Source code, pretrained models, and datasets are available at https://github.com/OpenSELab/EfficientDL.

Learnable Optimization-Based Algorithms for Low-Dose CT Reconstruction

Low-dose computed tomography (LDCT) aims to minimize the radiation exposure to patients while maintaining diagnostic image quality. However, traditional CT reconstruction algorithms often struggle with the ill-posed nature of the problem, resulting in severe image artifacts. Recent advances in optimization-based deep learning algorithms offer promising solutions to improve LDCT reconstruction. In this paper, we explore learnable optimization algorithms (LOA) for CT reconstruction, which integrate deep learning within variational models to enhance the regularization process. These methods, including LEARN++ and MAGIC, leverage dual-domain networks that optimize both image and sinogram data, significantly improving reconstruction quality. We also present proximal gradient descent and ADMM-inspired networks, which are efficient and theoretically grounded approaches. Our results demonstrate that these learnable methods outperform traditional techniques, offering enhanced artifact reduction, better detail preservation, and robust performance in clinical scenarios.