Quantitative 3D spatial reasoning from egocentric RGB-D video is a critical capability for next-generation wearable assistants. Yet existing benchmarks do not reflect the challenges of handling (1) natural egocentric video, (2) posed RGB-D video inputs, and (3) challenging quantitative 3D spatial reasoning Q A. To fill this gap, we introduce R3D-Bench (Reasoning in 3D), a benchmark of 3,033 quantitative spatial reasoning questions across 15 types – spanning multiple-choice, distance-based, and volumetric reasoning questions – built on top of 57 egocentric video sequences from Aria Digital Twin. To set a strong baseline on this dataset, we introduce R3D, a model-agnostic spatial tool-calling framework. In contrast to existing approaches that directly embed 3D information into the model's input representation, R3D constructs a 3D scene from video using segmentation and depth-lifted object representations. It provides this information to an LLM through eight composable spatial tools. On R3D-Bench, R3D with Qwen3-VL 235B achieves 73.5

Vision encoders are a critical component of vision-language models, and scaling their capacity effectively improves performance. However, dense scaling increases compute cost and inference latency. Mixture-of-Experts (MoE) architectures offer a compelling alternative, having enabled efficient scaling in LLMs, yet the MoE design space for CLIP-style vision encoders remains underexplored at State-of-the-Art (SOTA) levels. In this work, we systematically study MoE designs for vision encoder scaling and find that fine-grained MoE topologies yield substantial gains over both dense and standard MoE counterparts. We further propose an auxiliary-loss-free balancing variant for better expert utilization, and design a specialized MoE kernel to mitigate inference latency overhead. To enhance video capabilities while preserving image knowledge, we introduce frame-level distillation paired with a novel freezing mechanism. We pretrain a series of Mixture-of-Experts Vision Encoders (MoE-ViE) across a range of sizes, all consistently outperforming their dense counterparts. Our largest model matches the zero-shot performance of a SOTA encoder 1.7x its size at 76

We envision a proactive multi-modal assistant system which gives users real-time step-by-step guidance on a procedural task, autonomously deciding when to interrupt, and how to coach. However, progress is limited by the absence of large-scale, cross-domain benchmarks that reflect realistic conditions, particularly the common case in which users deviate from the expected step sequence. We address this gap with four contributions: (1) we release EgoProactive, a large-scale wearable-egocentric dataset for proactive procedural assistance with explicit Out-of-Plan (OOP) annotations and recovery steps; (2) we augment five established benchmarks (Ego4D, EPIC-KITCHENS, EgoExo4D, HoloAssist, HowTo100M) into Pro2Bench under a unified proactive-guidance schema; (3) we propose a decoupled planner–interaction architecture specialized for procedural state, visual cues, and recovery injection; (4) we introduce a post-training recipe that transfers across model families, validated by cross-backbone replication on Llama 4 and Qwen-3.6-VL. In extensive experiments, our trained Llama-4 system substantially improves objective intervention quality over strong proprietary baselines (Claude Opus 4.6, Gemini 3.1 Pro, GPT 5.2) and open-weight baselines (Qwen3 VL 235B) baselines across all six datasets. Oracle-plan experiments further show that, when plan quality is controlled, the trained duplex model produces high-quality guidance and large gains on Out-of-Plan recovery.

Vision-language models are integral to computer vision research, yet many high-performing models remain closed-source, obscuring their data, design and training recipe. The research community has responded by using distillation from black-box models to label training data, achieving strong benchmark results, at the cost of measurable scientific progress. However, without knowing the details of the teacher model and its data sources, scientific progress remains difficult to measure. In this paper, we study building a Perception Language Model (PLM) in a fully open and reproducible framework for transparent research in image and video understanding. We analyze standard training pipelines without distillation from proprietary models and explore large-scale synthetic data to identify critical data gaps, particularly in detailed video understanding. To bridge these gaps, we release 2.8M human-labeled instances of fine-grained video question-answer pairs and spatio-temporally grounded video captions. Additionally, we introduce PLM–VideoBench, a suite for evaluating challenging video understanding tasks focusing on the ability to reason about ''what'', ''where'', ''when'', and ''how'' of a video. We make our work fully reproducible by providing data, training recipes, code & models.

We introduce WearVQA, the first benchmark specifically designed to evaluate the Visual Question Answering (VQA) capabilities of multi-model AI assistant on wearable devices like smart glasses. Unlike prior benchmarks that focus on high-quality, third-person imagery, WearVQA reflects the unique challenges of ego-centric interaction-where visual inputs may be occluded, poorly lit, unzoomed, or blurry, and questions are grounded in realistic wearable use cases. The benchmark comprises 2,520 carefully curated image-question-answer triplets, spanning 7 diverse image domains including both text-centric and general scenes, 10 cognitive task types ranging from basic recognition to various forms of reasoning, and 6 common wearables-specific image quality issues. All questions are designed to be answerable using only the visual input and common senses. WearVQA is paired with a rigorous LLM-as-a-judge evaluation framework with 96

Recent advances in conversational AI have been substantial, but developing real-time systems for perceptual task guidance remains challenging. These systems must provide interactive, proactive assistance based on streaming visual inputs, yet their development is constrained by the costly and labor-intensive process of data collection and system evaluation. To address these limitations, we present a comprehensive framework with three key contributions. First, we introduce a novel data curation pipeline that synthesizes dialogues from annotated egocentric videos, resulting in ProAssist, a large-scale synthetic dialogue dataset spanning multiple domains. Second, we develop a suite of automatic evaluation metrics, validated through extensive human studies. Third, we propose an end-to-end model that processes streaming video inputs to generate contextually appropriate responses, incorporating novel techniques for handling data imbalance and long-duration videos. This work lays the foundation for developing real-time, proactive AI assistants capable of guiding users through diverse tasks.

In this paper, we investigate the problem of "generation supervision" in large language models, and present a novel bicameral architecture to separate supervision signals from their core capability, helpfulness. Doppelgänger, a new module parallel to the underlying language model, supervises the generation of each token, and learns to concurrently predict the supervision score(s) of the sequences up to and including each token. In this work, we present the theoretical findings, and leave the report on experimental results to a forthcoming publication.

We present Any-Modality Augmented Language Model (AnyMAL), a unified model that reasons over diverse input modality signals (i.e. text, image, video, audio, IMU motion sensor), and generates textual responses. AnyMAL inherits the powerful text-based reasoning abilities of the state-of-the-art LLMs including LLaMA-2 (70B), and converts modality-specific signals to the joint textual space through a pre-trained aligner module. To further strengthen the multimodal LLM's capabilities, we fine-tune the model with a multimodal instruction set manually collected to cover diverse topics and tasks beyond simple QAs. We conduct comprehensive empirical analysis comprising both human and automatic evaluations, and demonstrate state-of-the-art performance on various multimodal tasks.

This article introduces the Tenth Dialog System Technology Challenge (DSTC-10). This edition of the DSTC focuses on applying end-to-end dialog technologies for five distinct tasks in dialog systems, namely 1. Incorporation of Meme images into open domain dialogs, 2. Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations, 3. Situated Interactive Multimodal dialogs, 4. Reasoning for Audio Visual Scene-Aware Dialog, and 5. Automatic Evaluation and Moderation of Open-domainDialogue Systems. This article describes the task definition, provided datasets, baselines, and evaluation setup for each track. We also summarize the results of the submitted systems to highlight the general trends of the state-of-the-art technologies for the tasks.

Vision-extended LLMs have made significant strides in Visual Question Answering (VQA). Despite these advancements, VLLMs still encounter substantial difficulties in handling queries involving long-tail entities, with a tendency to produce erroneous or hallucinated responses. In this work, we introduce a novel evaluative benchmark named SnapNTell , specifically tailored for entity-centric VQA. This task aims to test the models’ capabilities in identifying entities and providing detailed, entity-specific knowledge. We have developed the SnapNTell Dataset , distinct from traditional VQA datasets: (1) It encompasses a wide range of categorized entities, each represented by images and explicitly named in the answers; (2) It features QA pairs that require extensive knowledge for accurate responses. The dataset is organized into 22 major categories, containing 7,568 unique entities in total. For each entity, we curated 10 illustrative images and crafted 10 knowledge-intensive QA pairs. To address this novel task, we devised a scalable, efficient, and transparent retrieval-augmented multimodal LLM. Our approach markedly outperforms existing methods on the SnapNTell dataset, achieving a 66.5% improvement in the BELURT score.

We present IMU2CLIP, a novel pre-training approach to align Inertial Measurement Unit (IMU) motion sensor recordings with text and video, by projecting them into the joint representation space of Contrastive Language-Image Pre-training (CLIP). The proposed approach allows IMU2CLIP to translate human motions (as measured by IMU sensors) into their corresponding textual descriptions and videos – while preserving the transitivity across these modalities. We introduce several new IMU-based Wearable AI applications such as motion-based media search, or an LM-based multimodal reasoning with motion sensor data – all using text as the grounding platform. In addition, we show that IMU2CLIP significantly improves downstream performances when fine-tuned for each application, demonstrating its universal usage as a new pre-trained resource. Our code and models will be released publicly.

Building an AI assistant that can seamlessly converse and instruct humans, in a user-centric situated scenario, requires several essential abilities: (1) spatial and temporal understanding of the situated and real-time user scenes, (2) capability of grounding the actively perceived visuals of users to conversation contexts, and (3) conversational reasoning over past utterances to perform just-in-time assistance. However, we currently lack a large-scale benchmark that captures user.assistant interactions with all of the aforementioned features. To this end, we propose SIMMC-VR, an extension of the SIMMC 2.0 dataset to a video-grounded taskoriented dialog dataset that captures real-world AI-assisted user scenarios in VR. We propose a novel data collection paradigm that involves (1) generating object-centric multimodal dialog flows with egocentric visual streams and visually-grounded templates, and (2) manually paraphrasing the simulated dialogs for naturalness and diversity while preserving multimodal dependencies. To measure meaningful progress in the field, we propose four tasks to address the new challenges in SIMMC-VR, which require complex spatial-temporal dialog reasoning in active egocentric scenes. We benchmark the proposed tasks with strong multimodal models, and highlight the key capabilities that current models lack for future research directions.

People capture photos and videos to relive and share memories of personal significance. Recently, media montages (stories) have become a popular mode of sharing these memories due to their intuitive and powerful storytelling capabilities. However, creating such montages usually involves a lot of manual searches, clicks, and selections that are time-consuming and cumbersome, adversely affecting user experiences. To alleviate this, we propose task-oriented dialogs for montage creation as a novel interactive tool to seamlessly search, compile, and edit montages from a media collection. To the best of our knowledge, our work is the first to leverage multi-turn conversations for such a challenging application, extending the previous literature studying simple media retrieval tasks. We collect a new dataset C3 (Conversational Content Creation), comprising 10k dialogs conditioned on media montages simulated from a large media collection. We take a simulate-and-paraphrase approach to collect these dialogs to be both cost and time efficient, while drawing from natural language distribution. Our analysis and benchmarking of state-of-the-art language models showcase the multimodal challenges present in the dataset. Lastly, we present a real-world mobile demo application that shows the feasibility of the proposed work in real-world applications. Our code and data will be made publicly available.

Recent years have seen an increasing trend in the volume of personal media captured by users, thanks to the advent of smartphones and smart glasses, resulting in large media collections. Despite conversation being an intuitive human-computer interface, current efforts focus mostly on single-shot natural language based media retrieval to aid users query their media and re-live their memories. This severely limits the search functionality as users can neither ask follow-up queries nor obtain information without first formulating a single-turn query. In this work, we propose dialogs for connected memories as a powerful tool to empower users to search their media collection through a multi-turn, interactive conversation. Towards this, we collect a new task-oriented dialog dataset COMET, which contains 11.5k user<->assistant dialogs (totaling 103k utterances), grounded in simulated personal memory graphs. We employ a resource-efficient, two-phase data collection pipeline that uses: (1) a novel multimodal dialog simulator that generates synthetic dialog flows grounded in memory graphs, and, (2) manual paraphrasing to obtain natural language utterances. We analyze COMET, formulate four main tasks to benchmark meaningful progress, and adopt state-of-the-art language models as strong baselines, in order to highlight the multimodal challenges captured by our dataset.

We present IMU2CLIP, a novel pre-training approach to align Inertial Measurement Unit (IMU) motion sensor recordings with video and text, by projecting them into the joint representation space of Contrastive Language-Image Pre-training (CLIP). The proposed approach allows IMU2CLIP to translate human motions (as measured by IMU sensors) into their corresponding textual descriptions and videos -- while preserving the transitivity across these modalities. We explore several new IMU-based applications that IMU2CLIP enables, such as motion-based media retrieval and natural language reasoning tasks with motion data. In addition, we show that IMU2CLIP can significantly improve the downstream performance when fine-tuned for each application (e.g. activity recognition), demonstrating the universal usage of IMU2CLIP as a new pre-trained resource. Our code will be made publicly available.

We introduce a unified framework to jointly model images, text, and human attention traces. Our work is built on top of the recent Localized Narratives annotation frame-work [31], where each word of a given caption is paired with a mouse trace segment. We propose two novel tasks: (1) predict a trace given an image and caption (i.e., visual grounding), and (2) predict a caption and a trace given only an image. Learning the grounding of each word is challenging, due to noise in the human-provided traces and the presence of words that cannot be meaningfully visually grounded. We present a novel model architecture that is jointly trained on dual tasks (controlled trace generation and controlled caption generation). To evaluate the quality of the generated traces, we propose a local bipartite matching (LBM) distance metric which allows the comparison of two traces of different lengths. Extensive experiments show our model is robust to the imperfect training data and outperforms the baselines by a clear margin. More-over, we demonstrate that our model pre-trained on the pro-posed tasks can be also beneficial to the downstream task of COCO’s guided image captioning. Our code 1 and project page 2 are publicly available.

Next generation task-oriented dialog systems need to understand conversational contexts with their perceived surroundings, to effectively help users in the real-world multimodal environment. Existing task-oriented dialog datasets aimed towards virtual assistance fall short and do not situate the dialog in the user’s multimodal context. To overcome, we present a new dataset for Situated and Interactive Multimodal Conversations, SIMMC 2.0, which includes 11K task-oriented user<->assistant dialogs (117K utterances) in the shopping domain, grounded in immersive and photo-realistic scenes. The dialogs are collection using a two-phase pipeline: (1) A novel multimodal dialog simulator generates simulated dialog flows, with an emphasis on diversity and richness of interactions, (2) Manual paraphrasing of generating utterances to draw from natural language distribution. We provide an in-depth analysis of the collected dataset, and describe in detail the four main benchmark tasks we propose for SIMMC 2.0. Our baseline model, powered by the state-of-the-art language model, shows promising results, and highlights new challenges and directions for the community to study.

We present NN-grams, a novel, hybrid language model integrating n-grams and neural networks (NN) for speech recognition. The model takes as input both word histories as well as n-gram counts. Thus, it combines the memorization capacity and scalability of an n-gram model with the generalization ability of neural networks. We report experiments where the model is trained on 26B words. NN-grams are efficient at run-time since they do not include an output soft-max layer. The model is trained using noise contrastive estimation (NCE), an approach that transforms the estimation problem of neural networks into one of binary classification between data samples and noise samples. We present results with noise samples derived from either an n-gram distribution or from speech recognition lattices. NN-grams outperforms an n-gram model on an Italian speech recognition dictation task.

BACKGROUND:This paper introduces and applies a genome wide predictive study to learn a model that predicts whether a new subject will develop breast cancer or not, based on her SNP profile.RESULTS:We first genotyped 696 female subjects (348 breast cancer cases and 348 apparently healthy controls), predominantly of Caucasian origin from Alberta, Canada using Affymetrix Human SNP 6.0 arrays. Then, we applied EIGENSTRAT population stratification correction method to remove 73 subjects not belonging to the Caucasian population. Then, we filtered any SNP that had any missing calls, whose genotype frequency was deviated from Hardy-Weinberg equilibrium, or whose minor allele frequency was less than 5%. Finally, we applied a combination of MeanDiff feature selection method and KNN learning method to this filtered dataset to produce a breast cancer prediction model. LOOCV accuracy of this classifier is 59.55%. Random permutation tests show that this result is significantly better than the baseline accuracy of 51.52%. Sensitivity analysis shows that the classifier is fairly robust to the number of MeanDiff-selected SNPs. External validation on the CGEMS breast cancer dataset, the only other publicly available breast cancer dataset, shows that this combination of MeanDiff and KNN leads to a LOOCV accuracy of 60.25%, which is significantly better than its baseline of 50.06%. We then considered a dozen different combinations of feature selection and learning method, but found that none of these combinations produces a better predictive model than our model. We also considered various biological feature selection methods like selecting SNPs reported in recent genome wide association studies to be associated with breast cancer, selecting SNPs in genes associated with KEGG cancer pathways, or selecting SNPs associated with breast cancer in the F-SNP database to produce predictive models, but again found that none of these models achieved accuracy better than baseline.CONCLUSIONS:We anticipate producing more accurate breast cancer prediction models by recruiting more study subjects, providing more accurate labelling of phenotypes (to accommodate the heterogeneity of breast cancer), measuring other genomic alterations such as point mutations and copy number variations, and incorporating non-genetic information about subjects such as environmental and lifestyle factors.