Consistency models (CMs) offer faster sampling than traditional diffusion models, but their training is resource-intensive. For example, as of 2024, training a state-of-the-art CM on CIFAR-10 takes one week on 8 GPUs. In this work, we propose an effective scheme for training CMs that largely improves the efficiency of building such models. Specifically, by expressing CM trajectories via a particular differential equation, we argue that diffusion models can be viewed as a special case of CMs. We can thus fine-tune a consistency model starting from a pretrained diffusion model and progressively approximate the full consistency condition to stronger degrees over the training process. Our resulting method, which we term Easy Consistency Tuning (ECT), achieves vastly reduced training times while improving upon the quality of previous methods: for example, ECT achieves a 2-step FID of 2.73 on CIFAR10 within 1 hour on a single A100 GPU, matching Consistency Distillation trained for hundreds of GPU hours. Owing to this computational efficiency, we investigate the scaling laws of CMs under ECT, showing that they obey the classic power law scaling, hinting at their ability to improve efficiency and performance at larger scales. Our [code](https://github.com/locuslab/ect) is available.

Videos are often used to learn or extract the necessary information to complete tasks in ways different than what text or static imagery can provide. However, many existing agent benchmarks neglect long-context video understanding, instead focus- ing on text or static image inputs. To bridge this gap, we introduce VideoWebArena (VideoWA), a benchmark for evaluating the capabilities of long-context multimodal agents for video understanding. VideoWA consists of 2,021 web agent tasks based on manually crafted video tutorials, which total almost four hours of content. For our benchmark, we define a taxonomy of long-context video-based agent tasks with two main areas of focus: skill retention and factual retention. While skill retention tasks evaluate whether an agent can use a given human demonstration to complete a task efficiently, the factual retention task evaluates whether an agent can retrieve instruction-relevant information from a video to complete a task. We find that the best model achieves a 13.3% success rate on factual retention tasks and 45.8% on factual retention QA pairs—far below human success rates of 73.9% and 79.3%, respectively. On skill retention tasks, long-context models perform worse with tutorials than without, exhibiting a 5% performance decrease in WebArena tasks and a 10.3% decrease in VisualWebArena tasks. Our work highlights performance gaps in the agentic abilities of long-context multimodal models and provides as a testbed for the future development of long-context video agents.

Digital payment systems have revolutionized financial transactions, offering unparalleled convenience and accessibility to users worldwide. However, the increasing popularity of these platforms has also attracted malicious actors seeking to exploit their vulnerabilities for financial gain. To address this challenge, robust and adaptable scam detection mechanisms are crucial for maintaining the trust and safety of digital payment ecosystems. This paper presents a comprehensive approach to scam detection, focusing on the Unified Payments Interface (UPI) in India, Google Pay (GPay) as a specific use case. The approach leverages Large Language Models (LLMs) to enhance scam classification accuracy and designs a digital assistant to aid human reviewers in identifying and mitigating fraudulent activities. The results demonstrate the potential of LLMs in augmenting existing machine learning models and improving the efficiency, accuracy, quality, and consistency of scam reviews, ultimately contributing to a safer and more secure digital payment landscape. Our evaluation of the Gemini Ultra model on curated transaction data showed a 93.33% accuracy in scam classification. Furthermore, the model demonstrated 89% accuracy in generating reasoning for these classifications. A promising fact, the model identified 32% new accurate reasons for suspected scams that human reviewers had not included in the review notes.

The goal of dimension reduction tools is to construct a low-dimensional representation of high-dimensional data. These tools are employed for a variety of reasons such as noise reduction, visualization, and to lower computational costs. However, there is a fundamental issue that is discussed in other modeling problems that is often overlooked in dimension reduction-overfitting. In the context of other modeling problems, techniques such as feature-selection, cross-validation, and regularization are employed to combat overfitting, but rarely are such precautions taken when applying dimension reduction. Prior applications of the two most popular non-linear dimension reduction methods, t-SNE and UMAP, fail to acknowledge data as a combination of signal and noise when assessing performance. These methods are typically calibrated to capture the entirety of the data, not just the signal. In this paper, we demonstrate the importance of acknowledging noise when calibrating hyperparameters and present a framework that enables users to do so. We use this framework to explore the role hyperparameter calibration plays in overfitting the data when applying t-SNE and UMAP. More specifically, we show previously recommended values for perplexity and n_neighbors are too small and overfit the noise. We also provide a workflow others may use to calibrate hyperparameters in the presence of noise.

Much of the literature on robotic perception focuses on the visual modality. Vision provides a global observation of a scene, making it broadly useful. However, in the domain of robotic manipulation, vision alone can sometimes prove inadequate: in the presence of occlusions or poor lighting, visual object identification might be difficult. The sense of touch can provide robots with an alternative mechanism for recognizing objects. In this paper, we study the problem of touch-based instance recognition. We propose a novel framing of the problem as multi-modal recognition: the goal of our system is to recognize, given a visual and tactile observation, whether or not these observations correspond to the same object. To our knowledge, our work is the first to address this type of multi-modal instance recognition problem on such a large-scale with our analysis spanning 98 different objects. We employ a robot equipped with two GelSight touch sensors, one on each finger, and a self-supervised, autonomous data collection procedure to collect a dataset of tactile observations and images. Our experimental results show that it is possible to accurately recognize object instances by touch alone, including instances of novel objects that were never seen during training. Our learned model outperforms other methods on this complex task, including that of human volunteers.

Abstract Traditionally, location systems have been built bottom-up beginning with low-level sensors and adding layers up to high-level context. Consequently, they have focused on a single location–detection technology. With sharing of user location in mind, we created Personal Location Agent for Communicating Entities (PLACE), an infrastructure that incorporates multiple location technologies for the purpose of establishing user location with better coverage, at varying granularities, and with better accuracy. PLACE supports sensor fusion and access control using a common versatile language to describe user locations in a common universe. It's design provides an alternative approach to location systems and insight into the general problem of sharing user location information.