Alkesh Patel

Alkesh Patel, Melis Ozyildirim, Ying-Chang Cheng et al.

Long video summarization presents significant challenges for current multimodal large language models (MLLMs), particularly in maintaining temporal fidelity over extended durations and producing summaries that are both semantically and temporally grounded. In this work, we present LVSum, a human-annotated benchmark designed specifically for evaluating long video summarization with fine-grained temporal alignment. LVSum comprises diverse long-form videos across 13 domains, each paired with human-generated summaries containing precise temporal references. We conduct a comprehensive evaluation of both proprietary and open-source MLLMs on LVSum, assessing performance using newly introduced LLM-based metrics for content relevance and modality coherence, alongside standard evaluation metrics. Our experiments reveal systematic gaps in temporal understanding among existing MLLMs and offer insights that establish a new foundation for advancing temporal reasoning in long video summarization.

Shruti Bhargava, Anand Dhoot, Ing-Marie Jonsson et al.

Voice assistants help users make phone calls, send messages, create events, navigate, and do a lot more. However, assistants have limited capacity to understand their users' context. In this work, we aim to take a step in this direction. Our work dives into a new experience for users to refer to phone numbers, addresses, email addresses, URLs, and dates on their phone screens. Our focus lies in reference understanding, which becomes particularly interesting when multiple similar texts are present on screen, similar to visual grounding. We collect a dataset and propose a lightweight general-purpose model for this novel experience. Due to the high cost of consuming pixels directly, our system is designed to rely on the extracted text from the UI. Our model is modular, thus offering flexibility, improved interpretability, and efficient runtime memory utilization.

Zhen Zhang, Changyi Yang, Zijie Xia et al.

Token serves as the fundamental unit of computation in modern autoregressive models, and generation length directly influences both inference cost and reasoning performance. Despite its importance, existing approaches lack fine-grained length modeling, operating primarily at the coarse-grained sequence level. We introduce the Length Value Model (LenVM), a token-level framework that models the remaining generation length. By formulating length modeling as a value estimation problem and assigning a constant negative reward to each generated token, LenVM predicts a bounded, discounted return that serves as a monotone proxy for the remaining generation horizon. This formulation yields supervision that is annotation-free, dense, unbiased, and scalable. Experiments on LLMs and VLMs demonstrate LenVM provides a highly effective signal at inference time. On the LIFEBench exact length matching task, applying LenVM to a 7B model improves the length score from 30.9 to 64.8, significantly outperforming frontier closed-source models. Furthermore, LenVM enables continuous control over the trade off between performance and efficiency. On GSM8K at a budget of 200 tokens, LenVM maintains 63% accuracy compared to 6 percent for token budget baseline. It also accurately predicts total generation length from the prompt boundary. Finally, LenVM's token-level values offer an interpretable view of generation dynamics, revealing how specific tokens shift reasoning toward shorter or longer regimes. Results demonstrate that LenVM supports a broad range of applications and token length can be effectively modeled as a token-level value signal, highlighting the potential of LenVM as a general framework for length modeling and as a length-specific value signal that could support future RL training. Code is available at https://github.com/eric-ai-lab/Length-Value-Model.

Alkesh Patel, Vibhav Chitalia, Yinfei Yang

Egocentric Video Question Answering (QA) requires models to handle long-horizon temporal reasoning, first-person perspectives, and specialized challenges like frequent camera movement. This paper systematically evaluates both proprietary and open-source Multimodal Large Language Models (MLLMs) on QaEgo4Dv2 - a refined dataset of egocentric videos derived from QaEgo4D. Four popular MLLMs (GPT-4o, Gemini-1.5-Pro, Video-LLaVa-7B and Qwen2-VL-7B-Instruct) are assessed using zero-shot and fine-tuned approaches for both OpenQA and CloseQA settings. We introduce QaEgo4Dv2 to mitigate annotation noise in QaEgo4D, enabling more reliable comparison. Our results show that fine-tuned Video-LLaVa-7B and Qwen2-VL-7B-Instruct achieve new state-of-the-art performance, surpassing previous benchmarks by up to +2.6% ROUGE/METEOR (for OpenQA) and +13% accuracy (for CloseQA). We also present a thorough error analysis, indicating the model's difficulty in spatial reasoning and fine-grained object recognition - key areas for future improvement.

Halim Cagri Ates, Shruti Bhargava, Site Li et al.

Successfully handling context is essential for any dialog understanding task. This context maybe be conversational (relying on previous user queries or system responses), visual (relying on what the user sees, for example, on their screen), or background (based on signals such as a ringing alarm or playing music). In this work, we present an overview of MARRS, or Multimodal Reference Resolution System, an on-device framework within a Natural Language Understanding system, responsible for handling conversational, visual and background context. In particular, we present different machine learning models to enable handing contextual queries; specifically, one to enable reference resolution, and one to handle context via query rewriting. We also describe how these models complement each other to form a unified, coherent, lightweight system that can understand context while preserving user privacy.

Deepak Nathani, Cheng Zhang, Chang Huan et al.

Proactive agents that anticipate user needs and autonomously execute tasks hold great promise as digital assistants, yet the lack of realistic user simulation frameworks hinders their development. Existing approaches model apps as flat tool-calling APIs, failing to capture the stateful and sequential nature of user interaction in digital environments and making realistic user simulation infeasible. We introduce Proactive Agent Research Environment (Pare), a framework for building and evaluating proactive agents in digital environments. Pare models applications as finite state machines with stateful navigation and state-dependent action space for the user simulator, enabling active user simulation. Building on this foundation, we present Pare-Bench, a benchmark of 143 diverse tasks spanning communication, productivity, scheduling, and lifestyle apps, designed to test context observation, goal inference, intervention timing, and multi-app orchestration.

Alkesh Patel, Joel Ruben Antony Moniz, Roman Nguyen et al.

In multimodal assistant, where vision is also one of the input modalities, the identification of user intent becomes a challenging task as visual input can influence the outcome. Current digital assistants take spoken input and try to determine the user intent from conversational or device context. So, a dataset, which includes visual input (i.e. images or videos for the corresponding questions targeted for multimodal assistant use cases, is not readily available. The research in visual question answering (VQA) and visual question generation (VQG) is a great step forward. However, they do not capture questions that a visually-abled person would ask multimodal assistants. Moreover, many times questions do not seek information from external knowledge. In this paper, we provide a new dataset, MMIU (MultiModal Intent Understanding), that contains questions and corresponding intents provided by human annotators while looking at images. We, then, use this dataset for intent classification task in multimodal digital assistant. We also experiment with various approaches for combining vision and language features including the use of multimodal transformer for classification of image-question pairs into 14 intents. We provide the benchmark results and discuss the role of visual and text features for the intent classification task on our dataset.

Alkesh Patel, Akanksha Bindal, Hadas Kotek et al.

Generating natural, diverse, and meaningful questions from images is an essential task for multimodal assistants as it confirms whether they have understood the object and scene in the images properly. The research in visual question answering (VQA) and visual question generation (VQG) is a great step. However, this research does not capture questions that a visually-abled person would ask multimodal assistants. Recently published datasets such as KB-VQA, FVQA, and OK-VQA try to collect questions that look for external knowledge which makes them appropriate for multimodal assistants. However, they still contain many obvious and common-sense questions that humans would not usually ask a digital assistant. In this paper, we provide a new benchmark dataset that contains questions generated by human annotators keeping in mind what they would ask multimodal digital assistants. Large scale annotations for several hundred thousand images are expensive and time-consuming, so we also present an effective way of automatically generating questions from unseen images. In this paper, we present an approach for generating diverse and meaningful questions that consider image content and metadata of image (e.g., location, associated keyword). We evaluate our approach using standard evaluation metrics such as BLEU, METEOR, ROUGE, and CIDEr to show the relevance of generated questions with human-provided questions. We also measure the diversity of generated questions using generative strength and inventiveness metrics. We report new state-of-the-art results on the public and our datasets.

Deepak Muralidharan, Joel Ruben Antony Moniz, Sida Gao et al.

Named Entity Recognition (NER) and Entity Linking (EL) play an essential role in voice assistant interaction, but are challenging due to the special difficulties associated with spoken user queries. In this paper, we propose a novel architecture that jointly solves the NER and EL tasks by combining them in a joint reranking module. We show that our proposed framework improves NER accuracy by up to 3.13% and EL accuracy by up to 3.6% in F1 score. The features used also lead to better accuracies in other natural language understanding tasks, such as domain classification and semantic parsing.