Jing Bi

Nguyen Nguyen, Jing Bi, Ali Vosoughi et al.

The capability of intelligent models to extrapolate and comprehend changes in object states is a crucial yet demanding aspect of AI research, particularly through the lens of human interaction in real-world settings. This task involves describing complex visual environments, identifying active objects, and interpreting their changes as conveyed through language. Traditional methods, which isolate object captioning and state change detection, offer a limited view of dynamic environments. Moreover, relying on a small set of symbolic words to represent changes has restricted the expressiveness of the language. To address these challenges, in this paper, we introduce the Object State Captioning and State Change Representation (OSCaR) dataset and benchmark. OSCaR consists of 14,084 annotated video segments with nearly 1,000 unique objects from various egocentric video collections. It sets a new testbed for evaluating multimodal large language models (MLLMs). Our experiments demonstrate that while MLLMs show some skill, they lack a full understanding of object state changes. The benchmark includes a fine-tuned model that, despite initial capabilities, requires significant improvements in accuracy and generalization ability for effective understanding of these changes. Our code and dataset are available at https://github.com/nguyennm1024/OSCaR.

Yolo Yunlong Tang, Daiki Shimada, Jing Bi et al.

Large language models (LLMs) have demonstrated remarkable capabilities in natural language and multimodal domains. By fine-tuning multimodal LLMs with temporal annotations from well-annotated datasets, e.g., dense video captioning datasets, their temporal understanding capacity in video-language tasks can be obtained. However, there is a notable lack of untrimmed audio-visual video datasets with precise temporal annotations for events. This deficiency hinders LLMs from learning the alignment between time, audio-visual events, and text tokens, thus impairing their ability to temporally localize audio-visual events in videos. To address this gap, we introduce PU-VALOR, a comprehensive audio-visual dataset comprising over 114,000 pseudo-untrimmed videos with detailed temporal annotations. PU-VALOR is derived from the large-scale but coarse-annotated audio-visual dataset VALOR, through a subtle method involving event-based video clustering, random temporal scaling, and permutation. By fine-tuning a multimodal LLM on PU-VALOR, we developed AVicuna, a model capable of aligning audio-visual events with temporal intervals and corresponding text tokens. AVicuna excels in temporal localization and time-aware dialogue capabilities. Our experiments demonstrate that AVicuna effectively handles temporal understanding in audio-visual videos and achieves state-of-the-art performance on open-ended video QA, audio-visual QA, and audio-visual event dense localization tasks.

Jing Bi, Junjia Guo, Susan Liang et al.

Visual reasoning is central to human cognition, enabling individuals to interpret and abstractly understand their environment. Although recent Multimodal Large Language Models (MLLMs) have demonstrated impressive performance across language and vision-language tasks, existing benchmarks primarily measure recognition-based skills and inadequately assess true visual reasoning capabilities. To bridge this critical gap, we introduce VERIFY, a benchmark explicitly designed to isolate and rigorously evaluate the visual reasoning capabilities of state-of-the-art MLLMs. VERIFY compels models to reason primarily from visual information, providing minimal textual context to reduce reliance on domain-specific knowledge and linguistic biases. Each problem is accompanied by a human-annotated reasoning path, making it the first to provide in-depth evaluation of model decision-making processes. Additionally, we propose novel metrics that assess visual reasoning fidelity beyond mere accuracy, highlighting critical imbalances in current model reasoning patterns. Our comprehensive benchmarking of leading MLLMs uncovers significant limitations, underscoring the need for a balanced and holistic approach to both perception and reasoning. For more teaser and testing, visit our project page (https://verify-eqh.pages.dev/).

Jing Bi, Junjia Guo, Yunlong Tang et al.

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable progress in visual understanding. This impressive leap raises a compelling question: how can language models, initially trained solely on linguistic data, effectively interpret and process visual content? This paper aims to address this question with systematic investigation across 4 model families and 4 model scales, uncovering a unique class of attention heads that focus specifically on visual content. Our analysis reveals a strong correlation between the behavior of these attention heads, the distribution of attention weights, and their concentration on visual tokens within the input. These findings enhance our understanding of how LLMs adapt to multimodal tasks, demonstrating their potential to bridge the gap between textual and visual understanding. This work paves the way for the development of AI systems capable of engaging with diverse modalities.

Sam Lerman, Jing Bi

rQdia regularizes Q-value distributions with augmented images in pixel-based deep reinforcement learning. With a simple auxiliary loss, that equalizes these distributions via MSE, rQdia boosts DrQ and SAC on 9/12 and 10/12 tasks respectively in the MuJoCo Continuous Control Suite from pixels, and Data-Efficient Rainbow on 18/26 Atari Arcade environments. Gains are measured in both sample efficiency and longer-term training. Moreover, the addition of rQdia finally propels model-free continuous control from pixels over the state encoding baseline.

Jing Bi, Chenliang Xu

Learning to perform activities through demonstration requires extracting meaningful information about the environment from observations. In this research, we investigate the challenge of planning high-level goal-oriented actions in a simulation setting from an egocentric perspective. We present a novel task, interactive action planning, and propose an approach that combines topological affordance memory with transformer architecture. The process of memorizing the environment's structure through extracting affordances facilitates selecting appropriate actions based on the context. Moreover, the memory model allows us to detect action deviations while accomplishing specific objectives. To assess the method's versatility, we evaluate it in a realistic interactive simulation environment. Our experimental results demonstrate that the proposed approach learns meaningful representations, resulting in improved performance and robust when action deviations occur.

Yu-hsuan Chen, Jing Bi, Cyril Ngo Ngoc et al.

AI-driven surrogate modeling has become an increasingly effective alternative to physics-based simulations for 3D design, analysis, and manufacturing. These models leverage data-driven methods to predict physical quantities traditionally requiring computationally expensive simulations. However, the scarcity of labeled CAD-to-simulation datasets has driven recent advancements in self-supervised and foundation models, where geometric representation learning is performed offline and later fine-tuned for specific downstream tasks. While these approaches have shown promise, their effectiveness is limited in applications requiring fine-scale geometric detail preservation. This work introduces a self-supervised geometric representation learning method designed to capture fine-scale geometric features from non-parametric 3D models. Unlike traditional end-to-end surrogate models, this approach decouples geometric feature extraction from downstream physics tasks, learning a latent space embedding guided by geometric reconstruction losses. Key elements include the essential use of near-zero level sampling and the innovative batch-adaptive attention-weighted loss function, which enhance the encoding of intricate design features. The proposed method is validated through case studies in structural mechanics, demonstrating strong performance in capturing design features and enabling accurate few-shot physics predictions. Comparisons with traditional parametric surrogate modeling highlight its potential to bridge the gap between geometric and physics-based representations, providing an effective solution for surrogate modeling in data-scarce scenarios.

Jing Bi, Jiebo Luo, Chenliang Xu

Learning new skills by observing humans' behaviors is an essential capability of AI. In this work, we leverage instructional videos to study humans' decision-making processes, focusing on learning a model to plan goal-directed actions in real-life videos. In contrast to conventional action recognition, goal-directed actions are based on expectations of their outcomes requiring causal knowledge of potential consequences of actions. Thus, integrating the environment structure with goals is critical for solving this task. Previous works learn a single world model will fail to distinguish various tasks, resulting in an ambiguous latent space; planning through it will gradually neglect the desired outcomes since the global information of the future goal degrades quickly as the procedure evolves. We address these limitations with a new formulation of procedure planning and propose novel algorithms to model human behaviors through Bayesian Inference and model-based Imitation Learning. Experiments conducted on real-world instructional videos show that our method can achieve state-of-the-art performance in reaching the indicated goals. Furthermore, the learned contextual information presents interesting features for planning in a latent space.

Jing Shi, Jing Bi, Yingru Liu et al.

The marriage of recurrent neural networks and neural ordinary differential networks (ODE-RNN) is effective in modeling irregularly-observed sequences. While ODE produces the smooth hidden states between observation intervals, the RNN will trigger a hidden state jump when a new observation arrives, thus cause the interpolation discontinuity problem. To address this issue, we propose the cubic spline smoothing compensation, which is a stand-alone module upon either the output or the hidden state of ODE-RNN and can be trained end-to-end. We derive its analytical solution and provide its theoretical interpolation error bound. Extensive experiments indicate its merits over both ODE-RNN and cubic spline interpolation.

Jing Bi, Vikas Dhiman, Tianyou Xiao et al.

Learning from Demonstrations (LfD) via Behavior Cloning (BC) works well on multiple complex tasks. However, a limitation of the typical LfD approach is that it requires expert demonstrations for all scenarios, including those in which the algorithm is already well-trained. The recently proposed Learning from Interventions (LfI) overcomes this limitation by using an expert overseer. The expert overseer only intervenes when it suspects that an unsafe action is about to be taken. Although LfI significantly improves over LfD, the state-of-the-art LfI fails to account for delay caused by the expert's reaction time and only learns short-term behavior. We address these limitations by 1) interpolating the expert's interventions back in time, and 2) by splitting the policy into two hierarchical levels, one that generates sub-goals for the future and another that generates actions to reach those desired sub-goals. This sub-goal prediction forces the algorithm to learn long-term behavior while also being robust to the expert's reaction time. Our experiments show that LfI using sub-goals in a hierarchical policy framework trains faster and achieves better asymptotic performance than typical LfD.

Jing Bi, Tianyou Xiao, Qiuyue Sun et al.

Deep neural networks trained on demonstrations of human actions give robot the ability to perform self-driving on the road. However, navigation in a pedestrian-rich environment, such as a campus setup, is still challenging---one needs to take frequent interventions to the robot and take control over the robot from early steps leading to a mistake. An arduous burden is, hence, placed on the learning framework design and data acquisition. In this paper, we propose a new learning-from-intervention Dataset Aggregation (DAgger) algorithm to overcome the limitations brought by applying imitation learning to navigation in the pedestrian-rich environment. Our new learning algorithm implements an error backtrack function that is able to effectively learn from expert interventions. Combining our new learning algorithm with deep convolutional neural networks and a hierarchically-nested policy-selection mechanism, we show that our robot is able to map pixels direct to control commands and navigate successfully in real world without explicitly modeling the pedestrian behaviors or the world model.