AVicuna: Audio-Visual LLM with Interleaver and Context-Boundary Alignment for Temporal Referential Dialogue

In everyday communication, humans frequently use speech and gestures to refer to specific areas or objects, a process known as Referential Dialogue (RD). While prior studies have investigated RD through Large Language Models (LLMs) or Large Multimodal Models (LMMs) in static contexts, the exploration of Temporal Referential Dialogue (TRD) within audio-visual media remains limited. Two primary challenges hinder progress in this field: (1) the absence of comprehensive, untrimmed audio-visual video datasets with precise temporal annotations, and (2) the need for methods to integrate complex temporal auditory and visual cues effectively. To address these challenges, we introduce a novel framework to generate PU-VALOR, an extensive audio-visual dataset comprising over 114,000 untrimmed videos with accurate temporal demarcations. We also present AVicuna, featuring an Audio-Visual Tokens Interleaver (AVTI) that ensures the temporal alignment of audio-visual information. Additionally, we develop the A5-222K dataset, encompassing more than 200,000 audio-text pairings, to facilitate the audio and text alignments. Our experiments demonstrate that AVicuna can effectively handle TRD in audio-visual videos and achieve state-of-the-art performance on various audio-visual video understanding tasks, particularly in untrimmed videos. We further investigate the optimal audio-interleaving rate for interleaved audio-visual inputs, which maximizes performance on the Audio-Visual Event Dense Localization task.

OSCaR: Object State Captioning and State Change Representation

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 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.

Video Understanding with Large Language Models: A Survey

With the burgeoning growth of online video platforms and the escalating volume of video content, the demand for proficient video understanding tools has intensified markedly. Given the remarkable capabilities of Large Language Models (LLMs) in language and multimodal tasks, this survey provides a detailed overview of the recent advancements in video understanding harnessing the power of LLMs (Vid-LLMs). The emergent capabilities of Vid-LLMs are surprisingly advanced, particularly their ability for open-ended spatial-temporal reasoning combined with commonsense knowledge, suggesting a promising path for future video understanding. We examine the unique characteristics and capabilities of Vid-LLMs, categorizing the approaches into four main types: LLM-based Video Agents, Vid-LLMs Pretraining, Vid-LLMs Instruction Tuning, and Hybrid Methods. Furthermore, this survey presents a comprehensive study of the tasks, datasets, and evaluation methodologies for Vid-LLMs. Additionally, it explores the expansive applications of Vid-LLMs across various domains, highlighting their remarkable scalability and versatility in real-world video understanding challenges. Finally, it summarizes the limitations of existing Vid-LLMs and outlines directions for future research. For more information, readers are recommended to visit the repository at https://github.com/yunlong10/Awesome-LLMs-for-Video-Understanding.

MISAR: A Multimodal Instructional System with Augmented Reality

Augmented reality (AR) requires the seamless integration of visual, auditory, and linguistic channels for optimized human-computer interaction. While auditory and visual inputs facilitate real-time and contextual user guidance, the potential of large language models (LLMs) in this landscape remains largely untapped. Our study introduces an innovative method harnessing LLMs to assimilate information from visual, auditory, and contextual modalities. Focusing on the unique challenge of task performance quantification in AR, we utilize egocentric video, speech, and context analysis. The integration of LLMs facilitates enhanced state estimation, marking a step towards more adaptive AR systems. Code, dataset, and demo will be available at https://github.com/nguyennm1024/misar.

Multi-omics Prediction from High-content Cellular Imaging with Deep Learning

High-content cellular imaging, transcriptomics, and proteomics data provide rich and complementary views on the molecular layers of biology that influence cellular states and function. However, the biological determinants through which changes in multi-omics measurements influence cellular morphology have not yet been systematically explored, and the degree to which cell imaging could potentially enable the prediction of multi-omics directly from cell imaging data is therefore currently unclear. Here, we address the question of whether it is possible to predict bulk multi-omics measurements directly from cell images using Image2Omics -- a deep learning approach that predicts multi-omics in a cell population directly from high-content images stained with multiplexed fluorescent dyes. We perform an experimental evaluation in gene-edited macrophages derived from human induced pluripotent stem cell (hiPSC) under multiple stimulation conditions and demonstrate that Image2Omics achieves significantly better performance in predicting transcriptomics and proteomics measurements directly from cell images than predictors based on the mean observed training set abundance. We observed significant predictability of abundances for 5903 (22.43%; 95% CI: 8.77%, 38.88%) and 5819 (22.11%; 95% CI: 10.40%, 38.08%) transcripts out of 26137 in M1 and M2-stimulated macrophages respectively and for 1933 (38.77%; 95% CI: 36.94%, 39.85%) and 2055 (41.22%; 95% CI: 39.31%, 42.42%) proteins out of 4986 in M1 and M2-stimulated macrophages respectively. Our results show that some transcript and protein abundances are predictable from cell imaging and that cell imaging may potentially, in some settings and depending on the mechanisms of interest and desired performance threshold, even be a scalable and resource-efficient substitute for multi-omics measurements.

Performances of Symmetric Loss for Private Data from Exponential Mechanism

This study explores the robustness of learning by symmetric loss on private data. Specifically, we leverage exponential mechanism (EM) on private labels. First, we theoretically re-discussed properties of EM when it is used for private learning with symmetric loss. Then, we propose numerical guidance of privacy budgets corresponding to different data scales and utility guarantees. Further, we conducted experiments on the CIFAR-10 dataset to present the traits of symmetric loss. Since EM is a more generic differential privacy (DP) technique, it being robust has the potential for it to be generalized, and to make other DP techniques more robust.

Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning

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.

Cubic Spline Smoothing Compensation for Irregularly Sampled Sequences

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.

Learning from Interventions using Hierarchical Policies for Safe Learning

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.