Xin Huang

Wenwen Zhuang, Xin Huang, Xiantao Zhang et al.

Multimodal Large Language Models (MLLMs) excel in solving text-based mathematical problems, but they struggle with mathematical diagrams since they are primarily trained on natural scene images. For humans, visual aids generally enhance problem-solving, but MLLMs perform worse as information shifts from textual to visual modality. This decline is mainly due to their shortcomings in aligning images and text. To tackle aforementioned challenges, we propose Math-PUMA, a methodology focused on Progressive Upward Multimodal Alignment. This approach is designed to improve the mathematical reasoning skills of MLLMs through a three-stage training process, with the second stage being the critical alignment stage. We first enhance the language model's mathematical reasoning capabilities with extensive set of textual mathematical problems. We then construct a multimodal dataset with varying degrees of textual and visual information, creating data pairs by presenting each problem in at least two forms. By leveraging the Kullback-Leibler (KL) divergence of next-token prediction distributions to align visual and textual modalities, consistent problem-solving abilities are ensured. Finally, we utilize multimodal instruction tuning for MLLMs with high-quality multimodal data. Experimental results on multiple mathematical reasoning benchmarks demonstrate that the MLLMs trained with Math-PUMA surpass most open-source MLLMs. Our approach effectively narrows the performance gap for problems presented in different modalities. The code and data are available at: \url{https://github.com/wwzhuang01/Math-PUMA}.

Zhuohao Yin, Xin Huang

Visual Word Sense Disambiguation (VWSD) is a multi-modal task that aims to select, among a batch of candidate images, the one that best entails the target word's meaning within a limited context. In this paper, we propose a multi-modal retrieval framework that maximally leverages pretrained Vision-Language models, as well as open knowledge bases and datasets. Our system consists of the following key components: (1) Gloss matching: a pretrained bi-encoder model is used to match contexts with proper senses of the target words; (2) Prompting: matched glosses and other textual information, such as synonyms, are incorporated using a prompting template; (3) Image retrieval: semantically matching images are retrieved from large open datasets using prompts as queries; (4) Modality fusion: contextual information from different modalities are fused and used for prediction. Although our system does not produce the most competitive results at SemEval-2023 Task 1, we are still able to beat nearly half of the teams. More importantly, our experiments reveal acute insights for the field of Word Sense Disambiguation (WSD) and multi-modal learning. Our code is available on GitHub.

Xin Huang, Guy Rosman, Ashkan Jasour et al.

When predicting trajectories of road agents, motion predictors usually approximate the future distribution by a limited number of samples. This constraint requires the predictors to generate samples that best support the task given task specifications. However, existing predictors are often optimized and evaluated via task-agnostic measures without accounting for the use of predictions in downstream tasks, and thus could result in sub-optimal task performance. In this paper, we propose a task-informed motion prediction model that better supports the tasks through its predictions, by jointly reasoning about prediction accuracy and the utility of the downstream tasks, which is commonly used to evaluate the task performance. The task utility function does not require the full task information, but rather a specification of the utility of the task, resulting in predictors that serve a wide range of downstream tasks. We demonstrate our approach on two use cases of common decision making tasks and their utility functions, in the context of autonomous driving and parallel autonomy. Experiment results show that our predictor produces accurate predictions that improve the task performance by a large margin in both tasks when compared to task-agnostic baselines on the Waymo Open Motion dataset.

Xin Huang, Meng Feng, Ashkan Jasour et al.

Risk-bounded motion planning is an important yet difficult problem for safety-critical tasks. While existing mathematical programming methods offer theoretical guarantees in the context of constrained Markov decision processes, they either lack scalability in solving larger problems or produce conservative plans. Recent advances in deep reinforcement learning improve scalability by learning policy networks as function approximators. In this paper, we propose an extension of soft actor critic model to estimate the execution risk of a plan through a risk critic and produce risk-bounded policies efficiently by adding an extra risk term in the loss function of the policy network. We define the execution risk in an accurate form, as opposed to approximating it through a summation of immediate risks at each time step that leads to conservative plans. Our proposed model is conditioned on a continuous spectrum of risk bounds, allowing the user to adjust the risk-averse level of the agent on the fly. Through a set of experiments, we show the advantage of our model in terms of both computational time and plan quality, compared to a state-of-the-art mathematical programming baseline, and validate its performance in more complicated scenarios, including nonlinear dynamics and larger state space.

Allen Wang, Xin Huang, Ashkan Jasour et al.

This paper presents fast non-sampling based methods to assess the risk of trajectories for autonomous vehicles when probabilistic predictions of other agents' futures are generated by deep neural networks (DNNs). The presented methods address a wide range of representations for uncertain predictions including both Gaussian and non-Gaussian mixture models for predictions of both agent positions and controls. We show that the problem of risk assessment when Gaussian mixture models (GMMs) of agent positions are learned can be solved rapidly to arbitrary levels of accuracy with existing numerical methods. To address the problem of risk assessment for non-Gaussian mixture models of agent position, we propose finding upper bounds on risk using Chebyshev's Inequality and sums-of-squares (SOS) programming; they are both of interest as the former is much faster while the latter can be arbitrarily tight. These approaches only require statistical moments of agent positions to determine upper bounds on risk. To perform risk assessment when models are learned for agent controls as opposed to positions, we develop TreeRing, an algorithm analogous to tree search over the ring of polynomials that can be used to exactly propagate moments of control distributions into position distributions through nonlinear dynamics. The presented methods are demonstrated on realistic predictions from DNNs trained on the Argoverse and CARLA datasets and are shown to be effective for rapidly assessing the probability of low probability events.

Xin Huang, Stephen G. McGill, Jonathan A. DeCastro et al.

Predicting driver intentions is a difficult and crucial task for advanced driver assistance systems. Traditional confidence measures on predictions often ignore the way predicted trajectories affect downstream decisions for safe driving. In this paper, we propose a novel multi-task intent recognition neural network that predicts not only probabilistic driver trajectories, but also utility statistics associated with the predictions for a given downstream task. We establish a decision criterion for parallel autonomy that takes into account the role of driver trajectory prediction in real-time decision making by reasoning about estimated task-specific utility statistics. We further improve the robustness of our system by considering uncertainties in downstream planning tasks that may lead to unsafe decisions. We test our online system on a realistic urban driving dataset, and demonstrate its advantage in terms of recall and fall-out metrics compared to baseline methods, and demonstrate its effectiveness in intervention and warning use cases.

Xin Huang, Stephen G. McGill, Jonathan A. DeCastro et al.

Vehicle trajectory prediction is crucial for autonomous driving and advanced driver assistant systems. While existing approaches may sample from a predicted distribution of vehicle trajectories, they lack the ability to explore it -- a key ability for evaluating safety from a planning and verification perspective. In this work, we devise a novel approach for generating realistic and diverse vehicle trajectories. We extend the generative adversarial network (GAN) framework with a low-dimensional approximate semantic space, and shape that space to capture semantics such as merging and turning. We sample from this space in a way that mimics the predicted distribution, but allows us to control coverage of semantically distinct outcomes. We validate our approach on a publicly available dataset and show results that achieve state-of-the-art prediction performance, while providing improved coverage of the space of predicted trajectory semantics.

Boli Chen, Xin Huang, Lin Xiao et al.

Different from the traditional classification tasks which assume mutual exclusion of labels, hierarchical multi-label classification (HMLC) aims to assign multiple labels to every instance with the labels organized under hierarchical relations. Besides the labels, since linguistic ontologies are intrinsic hierarchies, the conceptual relations between words can also form hierarchical structures. Thus it can be a challenge to learn mappings from word hierarchies to label hierarchies. We propose to model the word and label hierarchies by embedding them jointly in the hyperbolic space. The main reason is that the tree-likeness of the hyperbolic space matches the complexity of symbolic data with hierarchical structures. A new Hyperbolic Interaction Model (HyperIM) is designed to learn the label-aware document representations and make predictions for HMLC. Extensive experiments are conducted on three benchmark datasets. The results have demonstrated that the new model can realistically capture the complex data structures and further improve the performance for HMLC comparing with the state-of-the-art methods. To facilitate future research, our code is publicly available.

Xin Huang, Boli Chen, Lin Xiao et al.

Extreme multi-label text classification (XMTC) aims at tagging a document with most relevant labels from an extremely large-scale label set. It is a challenging problem especially for the tail labels because there are only few training documents to build classifier. This paper is motivated to better explore the semantic relationship between each document and extreme labels by taking advantage of both document content and label correlation. Our objective is to establish an explicit label-aware representation for each document with a hybrid attention deep neural network model(LAHA). LAHA consists of three parts. The first part adopts a multi-label self-attention mechanism to detect the contribution of each word to labels. The second part exploits the label structure and document content to determine the semantic connection between words and labels in a same latent space. An adaptive fusion strategy is designed in the third part to obtain the final label-aware document representation so that the essence of previous two parts can be sufficiently integrated. Extensive experiments have been conducted on six benchmark datasets by comparing with the state-of-the-art methods. The results show the superiority of our proposed LAHA method, especially on the tail labels.

Xin Huang, Sungkweon Hong, Andreas Hofmann et al.

A crucial challenge to efficient and robust motion planning for autonomous vehicles is understanding the intentions of the surrounding agents. Ignoring the intentions of the other agents in dynamic environments can lead to risky or over-conservative plans. In this work, we model the motion planning problem as a partially observable Markov decision process (POMDP) and propose an online system that combines an intent recognition algorithm and a POMDP solver to generate risk-bounded plans for the ego vehicle navigating with a number of dynamic agent vehicles. The intent recognition algorithm predicts the probabilistic hybrid motion states of each agent vehicle over a finite horizon using Bayesian filtering and a library of pre-learned maneuver motion models. We update the POMDP model with the intent recognition results in real time and solve it using a heuristic search algorithm which produces policies with upper-bound guarantees on the probability of near colliding with other dynamic agents. We demonstrate that our system is able to generate better motion plans in terms of efficiency and safety in a number of challenging environments including unprotected intersection left turns and lane changes as compared to the baseline methods.

Xin Huang, Stephen McGill, Brian C. Williams et al.

Predicting the motion of a driver's vehicle is crucial for advanced driving systems, enabling detection of potential risks towards shared control between the driver and automation systems. In this paper, we propose a variational neural network approach that predicts future driver trajectory distributions for the vehicle based on multiple sensors. Our predictor generates both a conditional variational distribution of future trajectories, as well as a confidence estimate for different time horizons. Our approach allows us to handle inherently uncertain situations, and reason about information gain from each input, as well as combine our model with additional predictors, creating a mixture of experts. We show how to augment the variational predictor with a physics-based predictor, and based on their confidence estimations, improve overall system performance. The resulting combined model is aware of the uncertainty associated with its predictions, which can help the vehicle autonomy to make decisions with more confidence. The model is validated on real-world urban driving data collected in multiple locations. This validation demonstrates that our approach improves the prediction error of a physics-based model by 25% while successfully identifying the uncertain cases with 82% accuracy.