Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness

Evaluating the factuality of long-form generations has focused predominantly on precision, measuring whether the claims a model makes are correct. The dominant decompose-search-verify pipeline catches incorrect claims well but says little about whether a response contains all the information it should. Measuring factual completeness, the missing half of factuality, is harder: it requires enumerating the full set of facts a complete answer should contain, and these facts rarely form a flat list. They often involve open-ended sets where coverage is what matters, ordered processes, and relationships among facts that a list of independent boolean checks fails to capture. We introduce a two-level meta-rubric framework for evaluating open-ended generation, and instantiate it as Gamut (Grounded Assessment of Multimodal Factuality), a benchmark for factual completeness in long-form generation. The framework rests on a two-level rubric representation: a structured meta-rubric captures the organization and importance of the required content, which is then mechanically compiled into a flat checklist of binary, machine-gradable rubrics that an LLM judge scores reliably. We construct 1,813 questions grounded in real wearable imagery across 10 diverse domains, each paired with an evidence-backed rubric verified by expert human annotators. Because the framework is modality-agnostic, we also release a text-only variant. Evaluating 14 frontier and open-weight models, we find the benchmark genuinely challenging (best score 58.7% from Gemini 3.1 Pro), highly discriminative, and robust to the choice of judge.

R3D: Quantitative 3D Spatial Reasoning for Egocentric Wearables

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% mean relative accuracy, substantially outperforming the best depth-enabled baseline (CuTR+Tools, 61.9%) and the best RGB-only baseline (Gemini 3 Flash, 46.5%).

S-EMBER: A Large-Scale Benchmark for Streaming Egocentric Memory Retrieval

As wearable devices enable continuous first-person recording, AI assistants must reason across long time horizons to recall past experiences-a capability known as episodic memory. Current benchmarks often rely on offline evaluation with access to entire video files, failing to simulate the streaming reality of wearable intelligence. We introduce S-EMBER (Streaming Egocentric Memory Benchmark for Episodic Retrieval), a large-scale benchmark comprising 3,141 videos totaling 388 hours of organic activity captured via Ray-Ban Meta smart glasses. S-EMBER formalizes grounded streaming episodic retrieval, a paradigm shift from global offline search to causal, active recall triggered by visual events in a continuous stream. We provide 9,448 QA pairs requiring manual visual proof through precise temporal localization and supporting flexible response lengths to simulate natural human-AI interaction. Our extensive benchmarking of frontier models uncovers a localization paradox: while semantic reasoning improves with parameter scale, temporal grounding precision remains a stagnant architectural bottleneck that does not benefit from brute-force increases in model size, resolution, or frame density. S-EMBER establishes a hardware-authentic foundation for developing grounded, reliable episodic memory in the next generation of wearable AI agents.

Plan, Watch, Recover: A Benchmark and Architectures for Proactive Procedural Assistance

We envision a proactive multi-modal assistant system which gives users real-time step-by-step guidance on a procedural task, autonomously deciding \textit{when} to interrupt, and \textit{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: \textbf{(1)}~we release \textbf{EgoProactive}, a large-scale wearable-egocentric dataset for proactive procedural assistance with explicit Out-of-Plan (OOP) annotations and recovery steps; \textbf{(2)}~we augment five established benchmarks (Ego4D, EPIC-KITCHENS, EgoExo4D, HoloAssist, HowTo100M) into \textbf{Pro\textsuperscript{2}Bench} under a unified proactive-guidance schema; \textbf{(3)}~we propose a \textbf{decoupled planner--interaction architecture} specialized for procedural state, visual cues, and recovery injection; \textbf{(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.

Pixel-Grounded Retrieval for Knowledgeable Large Multimodal Models

Visual Question Answering (VQA) often requires coupling fine-grained perception with factual knowledge beyond the input image. Prior multimodal Retrieval-Augmented Generation (MM-RAG) systems improve factual grounding but lack an internal policy for when and how to retrieve. We propose PixSearch, the first end-to-end Segmenting Large Multimodal Model (LMM) that unifies region-level perception and retrieval-augmented reasoning. During encoding, PixSearch emits <search> tokens to trigger retrieval, selects query modalities (text, image, or region), and generates pixel-level masks that directly serve as visual queries, eliminating the reliance on modular pipelines (detectors, segmenters, captioners, etc.). A two-stage supervised fine-tuning regimen with search-interleaved supervision teaches retrieval timing and query selection while preserving segmentation ability. On egocentric and entity-centric VQA benchmarks, PixSearch substantially improves factual consistency and generalization, yielding a 19.7% relative gain in accuracy on CRAG-MM compared to whole image retrieval, while retaining competitive reasoning performance on various VQA and text-only QA tasks.

Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage

End-to-end speech-in speech-out dialogue systems are emerging as a powerful alternative to traditional ASR-LLM-TTS pipelines, generating more natural, expressive responses with significantly lower latency. However, these systems remain prone to hallucinations due to limited factual grounding. While text-based dialogue systems address this challenge by integrating tools such as web search and knowledge graph APIs, we introduce the first approach to extend tool use directly into speech-in speech-out systems. A key challenge is that tool integration substantially increases response latency, disrupting conversational flow. To mitigate this, we propose Streaming Retrieval-Augmented Generation (Streaming RAG), a novel framework that reduces user-perceived latency by predicting tool queries in parallel with user speech, even before the user finishes speaking. Specifically, we develop a post-training pipeline that teaches the model when to issue tool calls during ongoing speech and how to generate spoken summaries that fuse audio queries with retrieved text results, thereby improving both accuracy and responsiveness. To evaluate our approach, we construct AudioCRAG, a benchmark created by converting queries from the publicly available CRAG dataset into speech form. Experimental results demonstrate that our streaming RAG approach increases QA accuracy by up to 200% relative (from 11.1% to 34.2% absolute) and further enhances user experience by reducing tool use latency by 20%. Importantly, our streaming RAG approach is modality-agnostic and can be applied equally to typed input, paving the way for more agentic, real-time AI assistants.

Proactive Assistant Dialogue Generation from Streaming Egocentric Videos

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 \dataset, 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. Project page: https://pro-assist.github.io/

VisualLens: Personalization through Visual History

We hypothesize that a user's visual history with images reflecting their daily life, offers valuable insights into their interests and preferences, and can be leveraged for personalization. Among the many challenges to achieve this goal, the foremost is the diversity and noises in the visual history, containing images not necessarily related to a recommendation task, not necessarily reflecting the user's interest, or even not necessarily preference-relevant. Existing recommendation systems either rely on task-specific user interaction logs, such as online shopping history for shopping recommendations, or focus on text signals. We propose a novel approach, VisualLens, that extracts, filters, and refines image representations, and leverages these signals for personalization. We created two new benchmarks with task-agnostic visual histories, and show that our method improves over state-of-the-art recommendations by 5-10% on Hit@3, and improves over GPT-4o by 2-5%. Our approach paves the way for personalized recommendations in scenarios where traditional methods fail.

Doppelgänger's Watch: A Split Objective Approach to Large Language Models

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. Doppelg\"anger, 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.

SnapNTell: Enhancing Entity-Centric Visual Question Answering with Retrieval Augmented Multimodal LLM

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 \textbf{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 \textbf{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 will soon make the dataset and the source code publicly accessible.