Losing Visual Needles in Image Haystacks: Vision Language Models are Easily Distracted in Short and Long Contexts

We present LoCoVQA, a dynamic benchmark generator for evaluating long-context extractive reasoning in vision language models (VLMs). LoCoVQA augments test examples for mathematical reasoning, VQA, and character recognition tasks with increasingly long visual contexts composed of both in-distribution and out-of-distribution distractor images. Across these tasks, a diverse set of VLMs rapidly lose performance as the visual context length grows, often exhibiting a striking exponential decay trend. This test assesses how well VLMs can ignore irrelevant information when answering queries -- a task that is quite easy for language models (LMs) in the text domain -- demonstrating that current state-of-the-art VLMs lack this essential capability for many long-context applications.

Bi-level Trajectory Optimization on Uneven Terrains with Differentiable Wheel-Terrain Interaction Model

Navigation of wheeled vehicles on uneven terrain necessitates going beyond the 2D approaches for trajectory planning. Specifically, it is essential to incorporate the full 6dof variation of vehicle pose and its associated stability cost in the planning process. To this end, most recent works aim to learn a neural network model to predict the vehicle evolution. However, such approaches are data-intensive and fraught with generalization issues. In this paper, we present a purely model-based approach that just requires the digital elevation information of the terrain. Specifically, we express the wheel-terrain interaction and 6dof pose prediction as a non-linear least squares (NLS) problem. As a result, trajectory planning can be viewed as a bi-level optimization. The inner optimization layer predicts the pose on the terrain along a given trajectory, while the outer layer deforms the trajectory itself to reduce the stability and kinematic costs of the pose. We improve the state-of-the-art in the following respects. First, we show that our NLS based pose prediction closely matches the output from a high-fidelity physics engine. This result coupled with the fact that we can query gradients of the NLS solver, makes our pose predictor, a differentiable wheel-terrain interaction model. We further leverage this differentiability to efficiently solve the proposed bi-level trajectory optimization problem. Finally, we perform extensive experiments, and comparison with a baseline to showcase the effectiveness of our approach in obtaining smooth, stable trajectories.

Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2)

With advances in the quality of text-to-image (T2I) models has come interest in benchmarking their prompt faithfulness-the semantic coherence of generated images to the prompts they were conditioned on. A variety of T2I faithfulness metrics have been proposed, leveraging advances in cross-modal embeddings and vision-language models (VLMs). However, these metrics are not rigorously compared and benchmarked, instead presented against few weak baselines by correlation to human Likert scores over a set of easy-to-discriminate images. We introduce T2IScoreScore (TS2), a curated set of semantic error graphs containing a prompt and a set increasingly erroneous images. These allow us to rigorously judge whether a given prompt faithfulness metric can correctly order images with respect to their objective error count and significantly discriminate between different error nodes, using meta-metric scores derived from established statistical tests. Surprisingly, we find that the state-of-the-art VLM-based metrics (e.g., TIFA, DSG, LLMScore, VIEScore) we tested fail to significantly outperform simple feature-based metrics like CLIPScore, particularly on a hard subset of naturally-occurring T2I model errors. TS2 will enable the development of better T2I prompt faithfulness metrics through more rigorous comparison of their conformity to expected orderings and separations under objective criteria.

Standing on FURM ground -- A framework for evaluating Fair, Useful, and Reliable AI Models in healthcare systems

The impact of using artificial intelligence (AI) to guide patient care or operational processes is an interplay of the AI model's output, the decision-making protocol based on that output, and the capacity of the stakeholders involved to take the necessary subsequent action. Estimating the effects of this interplay before deployment, and studying it in real time afterwards, are essential to bridge the chasm between AI model development and achievable benefit. To accomplish this, the Data Science team at Stanford Health Care has developed a Testing and Evaluation (T&E) mechanism to identify fair, useful and reliable AI models (FURM) by conducting an ethical review to identify potential value mismatches, simulations to estimate usefulness, financial projections to assess sustainability, as well as analyses to determine IT feasibility, design a deployment strategy, and recommend a prospective monitoring and evaluation plan. We report on FURM assessments done to evaluate six AI guided solutions for potential adoption, spanning clinical and operational settings, each with the potential to impact from several dozen to tens of thousands of patients each year. We describe the assessment process, summarize the six assessments, and share our framework to enable others to conduct similar assessments. Of the six solutions we assessed, two have moved into a planning and implementation phase. Our novel contributions - usefulness estimates by simulation, financial projections to quantify sustainability, and a process to do ethical assessments - as well as their underlying methods and open source tools, are available for other healthcare systems to conduct actionable evaluations of candidate AI solutions.

ATPPNet: Attention based Temporal Point cloud Prediction Network

Point cloud prediction is an important yet challenging task in the field of autonomous driving. The goal is to predict future point cloud sequences that maintain object structures while accurately representing their temporal motion. These predicted point clouds help in other subsequent tasks like object trajectory estimation for collision avoidance or estimating locations with the least odometry drift. In this work, we present ATPPNet, a novel architecture that predicts future point cloud sequences given a sequence of previous time step point clouds obtained with LiDAR sensor. ATPPNet leverages Conv-LSTM along with channel-wise and spatial attention dually complemented by a 3D-CNN branch for extracting an enhanced spatio-temporal context to recover high quality fidel predictions of future point clouds. We conduct extensive experiments on publicly available datasets and report impressive performance outperforming the existing methods. We also conduct a thorough ablative study of the proposed architecture and provide an application study that highlights the potential of our model for tasks like odometry estimation.

OCTO+: A Suite for Automatic Open-Vocabulary Object Placement in Mixed Reality

One key challenge in Augmented Reality is the placement of virtual content in natural locations. Most existing automated techniques can only work with a closed-vocabulary, fixed set of objects. In this paper, we introduce and evaluate several methods for automatic object placement using recent advances in open-vocabulary vision-language models. Through a multifaceted evaluation, we identify a new state-of-the-art method, OCTO+. We also introduce a benchmark for automatically evaluating the placement of virtual objects in augmented reality, alleviating the need for costly user studies. Through this, in addition to human evaluations, we find that OCTO+ places objects in a valid region over 70% of the time, outperforming other methods on a range of metrics.

OCTOPUS: Open-vocabulary Content Tracking and Object Placement Using Semantic Understanding in Mixed Reality

One key challenge in augmented reality is the placement of virtual content in natural locations. Existing automated techniques are only able to work with a closed-vocabulary, fixed set of objects. In this paper, we introduce a new open-vocabulary method for object placement. Our eight-stage pipeline leverages recent advances in segmentation models, vision-language models, and LLMs to place any virtual object in any AR camera frame or scene. In a preliminary user study, we show that our method performs at least as well as human experts 57% of the time.

NeuroSMPC: A Neural Network guided Sampling Based MPC for On-Road Autonomous Driving

In this paper we show an effective means of integrating data driven frameworks to sampling based optimal control to vastly reduce the compute time for easy adoption and adaptation to real time applications such as on-road autonomous driving in the presence of dynamic actors. Presented with training examples, a spatio-temporal CNN learns to predict the optimal mean control over a finite horizon that precludes further resampling, an iterative process that makes sampling based optimal control formulations difficult to adopt in real time settings. Generating control samples around the network-predicted optimal mean retains the advantage of sample diversity while enabling real time rollout of trajectories that avoids multiple dynamic obstacles in an on-road navigation setting. Further the 3D CNN architecture implicitly learns the future trajectories of the dynamic agents in the scene resulting in successful collision free navigation despite no explicit future trajectory prediction. We show performance gain over multiple baselines in a number of on-road scenes through closed loop simulations in CARLA. We also showcase the real world applicability of our system by running it on our custom Autonomous Driving Platform (AutoDP).

Hilbert Space Embedding-based Trajectory Optimization for Multi-Modal Uncertain Obstacle Trajectory Prediction

Safe autonomous driving critically depends on how well the ego-vehicle can predict the trajectories of neighboring vehicles. To this end, several trajectory prediction algorithms have been presented in the existing literature. Many of these approaches output a multi-modal distribution of obstacle trajectories instead of a single deterministic prediction to account for the underlying uncertainty. However, existing planners cannot handle the multi-modality based on just sample-level information of the predictions. With this motivation, this paper proposes a trajectory optimizer that can leverage the distributional aspects of the prediction in a computationally tractable and sample-efficient manner. Our optimizer can work with arbitrarily complex distributions and thus can be used with output distribution represented as a deep neural network. The core of our approach is built on embedding distribution in Reproducing Kernel Hilbert Space (RKHS), which we leverage in two ways. First, we propose an RKHS embedding approach to select probable samples from the obstacle trajectory distribution. Second, we rephrase chance-constrained optimization as distribution matching in RKHS and propose a novel sampling-based optimizer for its solution. We validate our approach with hand-crafted and neural network-based predictors trained on real-world datasets and show improvement over the existing stochastic optimization approaches in safety metrics.

SAppKG: Mobile App Recommendation Using Knowledge Graph and Side Information-A Secure Framework

Due to the rapid development of technology and the widespread usage of smartphones, the number of mobile applications is exponentially growing. Finding a suitable collection of apps that aligns with users needs and preferences can be challenging. However, mobile app recommender systems have emerged as a helpful tool in simplifying this process. But there is a drawback to employing app recommender systems. These systems need access to user data, which is a serious security violation. While users seek accurate opinions, they do not want to compromise their privacy in the process. We address this issue by developing SAppKG, an end-to-end user privacy-preserving knowledge graph architecture for mobile app recommendation based on knowledge graph models such as SAppKG-S and SAppKG-D, that utilized the interaction data and side information of app attributes. We tested the proposed model on real-world data from the Google Play app store, using precision, recall, mean absolute precision, and mean reciprocal rank. We found that the proposed model improved results on all four metrics. We also compared the proposed model to baseline models and found that it outperformed them on all four metrics.