Quanwei Tang, Dong Zhang, Shoushan Li +1cs.SD cs.AI
While long-form audio meeting understanding (LAMU) is garnering growing attention, task-specific question answering (QA) datasets remain scarce. Existing speech QA paradigms and state-of-the-art Speech LLMs suffer from acoustic information loss and poor long-term context memory. To address these issues, we construct the LongAudioQA dataset and propose the GRGA model, which models heterogeneous audio features into a multi-dimensional graph and leverages agent planning for retrieval and answer generation.
Retrieval-Augmented Generation (RAG) systems have attracted significant interest for their ability to mitigate hallucinations in Large Language Models (LLMs). Although knowledge databases for RAG are increasingly diversifying to include various modalities such as speech and text, research on handling such multi-modal database scenarios remains limited. In this paper, we propose STeReO (Speech and Text Reranking Orchestrator), a reranker based on speech and text retrievers that aggregates disparate modality databases. To address the lack of specialized training data, we first curate a dataset comprising queries, mixed-modality evidence, and their corresponding relevance ranks. We then train the reranker and evaluate its effectiveness in both single-modality and mixed-modality scenarios. Our results demonstrate that the proposed algorithm excels at selecting the most relevant evidence, thereby significantly improving downstream question-answering performance.
Video understanding benchmarks have long centered on single-camera settings, where modern multi-modal language models achieve strong performance across image and video tasks. Yet, the real world runs on multi-camera networks: autonomous vehicles, security systems, and robots all gather data across many simultaneous views. We argue that this is not simply "more" of the single-camera problem; it is fundamentally different. Multi-camera reasoning requires handling context that scales with the number of views, resolving occlusions visible from only a subset of cameras, judging which views matter, and integrating evidence across perspectives that may overlap or diverge. Current models struggle with exactly these challenges, yet no benchmark systematically targets them. We introduce CrossView, a multi-camera video question-answering benchmark spanning autonomous driving, security surveillance, egocentric/exocentric video, and robotics. Evaluation of proprietary models, such as GPT-5.2, and open-source models, like Qwen3-VL, reveals consistently low accuracy, with open-source models trailing by a wide margin. Performance scales strongly with a model's ability to jointly process multiple viewpoints, positioning CrossView as a rigorous benchmark for multi-camera video. We open-source our code and dataset at https://utaustin-swarmlab.github.io/CrossView.
Large language models (LLMs) have shown remarkable reasoning and generative capabilities, motivating their use as universal reasoning engines for perception. While modern approaches such as vision-language models (VLMs) have attempted to incorporate reasoning capabilities into visual sensing, the integration of LLMs with the millimeter-wave (mmWave) modality-despite its unique advantages under low light and occlusion-remains largely unexplored. The principal bottlenecks stem from the scarcity of radar language pairs, severe cross-dataset heterogeneity, and the absence of a foundational mmWave encoder. We address this gap through a minimal textualization interface that serializes each mmWave point cloud into concise natural language, allowing off-the-shelf LLMs to operate in a question answering (QA) setting. Building on this, we present mmWave-QA, the first benchmark for language-conditioned mmWave human perception. mmWave-QA aggregates heterogeneous public mmWave datasets and harmonizes them via calibration-aware preprocessing and global taxonomy alignment, while providing natural language QA. Spanning six scenarios and five QA tasks, the benchmark enables standardized evaluation across diverse mmWave hardware and experimental conditions, establishing a foundation for scalable research on mmWave-LLM integration. We further evaluate and analyze LLMs on our mmWave-QA, highlighting their zero-shot reasoning potential for radar perception, as well as their robustness under visual degradation.
Counterfactual video understanding evaluates whether models grasp physical and commonsense regularities. However, existing multiple-choice question (MCQ) benchmarks inadvertently leak target events through their questions and candidate options. This reduces the core challenge from active discovery to text-guided verification. In this paper, we present FADE, an effective training framework for counterfactual discovery and explanation. Our method is built on an evidence-first, two-stage training paradigm. First, evidence-internalized supervised fine-tuning grounds the model's predictions in decisive visual anomalies. Second, we apply a fading-anchor reinforcement learning strategy that progressively removes textual guidance, compelling the model to independently discover and explain evidence. To rigorously evaluate this capability, we also introduce an effective pipeline that converts existing MCQ datasets into aligned MCQ, open-ended question answering (OQA), and captioning tasks without requiring additional data curation. Our simple approach yields strong results. Using Qwen3-VL-8B as the baseline, FADE achieves state-of-the-art strict paired scores across all three tasks on DualityVidQA-test and IPV-Bench, outperforming GPT-5.6. In specific, when transitioning from constrained MCQs to unconstrained OQA and captioning, our model demonstrates remarkable robustness. Its performance retention is 90.4% and 67.4% on DualityVidQA-test-substantially higher than the 48.1% and 30.7% retained by GPT-5.6. We hope this simple framework can serve as a solid baseline for future research in unconstrained counterfactual video understanding.
Omnimodal language models (OLMs) enable unified audio-visual understanding, but processing long joint token sequences makes inference computationally prohibitive. While recent token compression methods attempt to alleviate this burden, compressing modalities in isolation often destroys the temporal cross-modal anchors necessary for coherent reasoning. We introduce Omni2LoRA, a two-stage framework for efficient parametric memory compression via coherence-preserving context distillation that bypasses the token bottleneck entirely. First, a Perceiver hypernetwork processes intermediate representations from a frozen OLM to encode the multimodal context into a full-rank Low-Rank Adaptation (LoRA) adapter in a single forward pass. To prevent the resulting parameter footprint from scaling linearly with recording length, we optimize a discrete rank allocation policy via Group Relative Policy Optimization (GRPO) that uses a modality-ablated counterfactual reward to explicitly penalize the loss of audio-visual coherence, forcing the model to allocate its fixed sub-linear rank budget to synergistic cross-modal anchors rather than isolated visual features. Across three omnimodal backbones, Omni2LoRA operating at a 30% rank budget outperforms direct full-context inference and strong token-compression baselines (OmniZip, OMAC, O-MARC) on four audio-visual question answering benchmarks, improving average accuracy by 8-12% over the strongest baseline and remaining stable under compression ratios as tight as 75%, where token-pruning methods degrade sharply. By converting multimodal memory into a fixed-budget, reusable parameter state, our method drives answer-time multimodal-token load to zero, cutting per-query Time to First Token (TTFT) by up to 12x relative to full-context inference and amortizing to under 0.5s after a handful of queries.
Sitong Gong, Caixin Kang, Tianyu Yan +7cs.CV cs.AI
A wearable assistant should both answer questions about its visual history and recognize when that history is useful to the present situation. Existing video-memory systems primarily support question-conditioned recall, whereas proactive assistants typically use separate memory and control mechanisms. We introduce GROVE, a training-free framework that supports both behaviors with one memory grown causally from a continuous video stream. GROVE retains fine-grained perceptual evidence and incrementally consolidates it into time-stamped moments, coherent episodes, and recurring cross-day patterns. Each stratum is paired with a scale-native retrieval skill for locating an observation, replaying an activity, or traversing long-range regularities. Reactive QA and proactive assistance share this memory and access interface, differing in whether retrieval is initiated by a user query or the current situation. Across multiple benchmarks including the challenging MM-lifelong and EgoServe, GROVE achieves the best results among the compared methods. Controlled ablations show that the temporal strata and their access skills are complementary, with patterns providing the largest benefit when evidence spans multiple days. Code will be available at https://github.com/SitongGong/GROVE.
Recent 3D vision-language models (3D VLMs) construct geometry aware tokens by projecting 2D visual features into world coordinates, enabling spatial reasoning for tasks such as 3D question answering. However, this design generates thousands of tokens per scene, resulting in substantial computational and memory overhead. While token compression has been extensively studied in 2D VLMs, existing approaches rely on semantic relevance or attention-based selection that overlook the structured spatial nature of 3D tokens. Moreover, redundancy in 3D representations cannot be resolved by spatial proximity alone, as object-level token imbalance persists even after spatial aggregation. To address this, we propose 3DZip, a three-stage token compression framework that first applies coarse voxelization to remove point-level redundancy, then selects anchor tokens based on feature-space diversity via a Determinantal Point Process, and finally merges remaining tokens under spatial constraints to preserve geometric coherence. Experiments on three 3D question answering benchmarks demonstrate that 3DZip consistently outperforms existing compression methods, retaining 94.7% of the original performance with only 128 tokens, achieving a $1.92\times$ faster inference speed.
Retrieval-Augmented Generation (RAG) has become essential for knowledge-intensive question answering, yet scaling RAG pipelines remains challenging due to the prohibitive computational cost of processing lengthy retrieved contexts. Existing compression approaches face a fundamental trade-off: hard compression methods operate online in a query-aware fashion but achieve only modest compression rates and typically require fine-tuning the generative model, while soft compression methods attain higher ratios but rely on costly offline encoding that is entirely agnostic to the input query. To bridge this gap, we introduce RAGOCR, a novel framework that compresses retrieved documents into compact visual representations conditioned on the input query. To further balance compression rate and information fidelity, we introduce a query-aware dynamic resolution mechanism that adaptively allocates visual granularity based on each document's estimated relevance and complexity: highly relevant passages are rendered at higher resolution to preserve fine-grained details, while peripheral documents are aggressively compressed at lower resolution. Experiments on five QA benchmarks using the MedOmniKB retrieval corpus demonstrate that RAGOCR surpasses naive RAG by over 15\% in accuracy while requiring only one-eighth the number of input tokens, and consistently outperforms both hard and soft compression baselines across varying retrieval depths.
Recent advances in sign language (SL) understanding (SLU) have led to remarkable progress in tasks such as continuous SL recognition and SL translation. However, these tasks are designed with predefined objectives, requiring models to learn a fixed mapping from sign videos to glosses or spoken-language sentences. As a result, they provide only a limited assessment of whether a model truly understands the semantic content of SL videos. To address this limitation, \textbf{we first propose a new task, Sign Language Question Answering (SLQA)}, which evaluates SL understanding by requiring models to answer arbitrary natural language questions about SL videos. Unlike previous SLU tasks, SLQA provides a more flexible and comprehensive evaluation framework that assesses multiple reasoning capabilities beyond recognition and translation. To facilitate this task, \textbf{we further construct two SignQA benchmarks} based on PHOENIX14T and CSL-Daily by automatically generating question-answer pairs from existing gloss and sentence annotations using carefully designed templates. The resulting datasets cover five complementary question categories, including position reasoning, structural reasoning, visual search, gloss recognition, and translation understanding. \textbf{Finally, we propose a simple yet effective baseline model} equipped with a Question-Conditioned Modulated Temporal Downsampling module and an in-domain knowledge transfer strategy, enabling effective knowledge transfer from existing SLU tasks while enhancing question-aware temporal feature modeling. Extensive experiments demonstrate that our baseline consistently outperforms representative vision-language models across all question categories, establishing a strong benchmark for future research on SLQA. Datasets are available at:{https://huggingface.co/datasets/hulala/SignQA-2026}.
Question answering (QA) over complex documents requires models to retrieve and integrate evidence distributed across distant document regions and modalities. Multimodal GraphRAG provides a promising direction by organizing document evidence with graph structures. However, existing methods often suffer from unreliable cross-modal evidence indexing and expensive graph traversal. To address these issues, we propose HVM-GraphRAG, a holistic-view multimodal GraphRAG framework on complex document. HVM-GraphRAG uses a holistic view to guide graph construction, thereby reducing noisy and conflicting graph updates and building reliable indices between concept-level graph nodes and supporting multimodal chunks. During retrieval, HVM-GraphRAG searches over a compact concept-level graph and directly accesses supporting evidence through the constructed index, avoiding costly traversal over dense entity-level graphs. After obtaining the retrieved evidence, HVM-GraphRAG further reorganizes chunks into modality-specific groups, enabling the answering model to better integrate heterogeneous evidence. Experiments on three datasets show that HVM-GraphRAG achieves the best answer performance in most evaluated settings while substantially improving online retrieval efficiency over representative graph-based baselines.
Omni-modal evidence-seeking QA requires agents to answer questions whose evidence is sparsely distributed across videos, audio, images, web pages, and computation results. Existing agentic multimodal systems often leave evidence in scratchpads, tool trajectories, or free-form histories, making it difficult to track what has been grounded, what remains missing, and when the evidence is sufficient to answer. We propose Omni-Decision, a training-free evidence-state system that turns omni-modal QA into a query-scoped evidence-closure process. For each query, Omni-Decision maintains a structured evidence state containing confirmed evidence, unresolved conflicts, fact and computation dependencies, and open evidence needs. A shared state view conditions planning, evidence acquisition, validation, repair, and finalization. Heterogeneous observations from media, web, computation, and verification modules are normalized, judged, and committed through deterministic state updates. This design enables targeted evidence acquisition, preserves sparse cross-modal cues, and provides inspectable control over repair and stopping. Omni-Decision achieves 45.6% accuracy on OmniGAIA and 58.3% on WorldSense, improving over the baselines by +27.3 and +30.2 percentage points, respectively. No-state ablations and trajectory audits further support the role of explicit evidence-state control in multi-step omni-modal evidence seeking.
Automated understanding of complex soccer scenarios from video remains a significant challenge for contemporary vision-language models (VLMs), which suffer from shallow cross-modal alignment and exhibit fundamental limitations in multi-step reasoning and coordinated tool integration. We present TreeSoc, a structured reasoning framework that reformulates soccer video question answering as a hierarchical search problem rather than a single-pass prediction. Specifically, TreeSoc employs a dynamic depth-first search (DFS) mechanism that decomposes complex queries into sequentially ordered sub-tasks, enabling iterative reasoning refinement through explicit intermediate states. This tree-structured decomposition naturally supports adaptive tool routing, wherein domain-specific modules are selectively activated and their outputs incorporated at each reasoning node to produce contextually grounded predictions. On SoccerBench, TreeSoc achieves state-of-the-art performance, with accuracies of 85.2%, 87.4%, and 82.2% on TextQA, ImageQA, and VideoQA, respectively. Additionally, TreeSoc further demonstrates strong cross-domain generalization, attaining 74.16% accuracy on NExT-QA. These results establish structured, tool-augmented tree reasoning as an effective paradigm for robust video understanding. Code is available at: https://github.com/thanhnhan29/TreeSoc.
We present our submission to the QANTA 2026 shared challenge at the ICML 2026 Workshop on Efficient Multimodal Question Answering (EMM-QA). Quanta evaluates multimodal quizbowl systems that answer pyramid-style questions from incrementally revealed text and accompanying images while operating under realistic efficiency constraints. The challenge consists of two distinct tasks: Tossup questions, which require deciding when to answer under uncertainty, and Bonus questions, which emphasize accurate answer selection and human adoption. To address these differing objectives, we develop a task-specific two-agent architecture. Our Tossup agent utilizes a GPT-4o-mini-class model (referred to as GPT-4.1-mini in the competition logs) with confidence-calibrated answering and a domain-specific numeric reasoning policy that reduces overconfident predictions from isolated quantitative clues. Our Bonus agent uses GPT-4o-class model (referred to as GPT-4.1) with leadin-aware reasoning, structured relational reasoning, and multimodal evidence integration to improve exact answer selection. Rather than relying on a retrieval pipeline or model ensembles, our approach emphasizes efficient reasoning policies and confidence calibration within a hosted-only environment. Our system achieved the highest overall leaderboard score of 0.402, including a Tossup score of 0.238 and a Bonus Effect score of 0.164. The results demonstrate that lightweight, task-specific reasoning strategies can provide strong performance on resource-constrained multimodal question answering benchmarks.
Yixuan Li, Guangzhi Sun, Yudong Yang +3cs.CV cs.AI cs.SD
Video large language models (LLMs) are often constrained by computation and memory budgets, leading them to use reduced frame rates and spatial resolutions, which may cause them to miss critical information for question answering (QA). A practical and efficient solution is a two-stage paradigm: first perform coarse video understanding to localize relevant segments, and then re-watch these segments at higher temporal or spatial fidelity. In this paper, we present video-SALMONN-R$^3$, the first end-to-end video-LLM that enables re-watch through reinforcement learning without relying on chain-of-thought (CoT) cold-start. This design removes the need for costly CoT data annotations and avoids CoT-based supervised fine-tuning (SFT), which can otherwise degrade the pretrained video understanding abilities. To address the mismatch between the reasoning-first behavior induced by re-watch and the answer-first tendency of pretrained video-LLMs, we propose a re-answer strategy, in which the model first produces a direct answer in the first watch and then refines it after re-watching. Finally, to improve question adherence during re-watching, we propose a re-ask mechanism that re-injects the query when revisiting localized segments. Experimental results show that video-SALMONN-R$^3$ consistently outperforms both the base model and the QA-SFT baseline, while surpassing prior re-watch-based approaches with significantly lower computational cost. Code, models, and data will be publicly released upon acceptance.
External memory effectively grounds large language models (LLMs) and vision-language models (VLMs)-based question answering (QA) in relevant multimodal evidence. However, existing memory paradigms represent each memory item in raw text and image forms, so retrieval-based systems must pass the retrieved text or images to the generation LLMs/VLMs, resulting in high token consumption and storage pressure, making it unaffordable for resource-constrained applications. We propose Latent Memory, a latent-space memory paradigm that replaces each raw text or image evidence item with a single high-dimensional latent token produced by a small compressor LLM/VLM. Rather than retrieving raw evidence for generation, Latent Memory operates in a unified latent representation space: the query is embedded into this space to retrieve relevant latent tokens, and the retrieved latent tokens are directly prompted to a pretrained LLM or VLM for answer generation. To make each latent token simultaneously informative for reconstruction, retrieval, and generation, we train the compressor with reconstruction, contrastive, and distillation objectives in a unified end-to-end manner. Latent Memory is evaluated on seven text-only QA benchmarks (e.g., HotpotQA) and multimodal QA benchmarks, where it achieves competitive QA performance compared to advanced RAG baselines while consuming 3x to 10x fewer generator tokens. It can also deliver the strongest image-grounded QA performance on WebQA. Code is available at https://github.com/zz1358m/Latent-Memory-Master.
Muhammad Umer Sheikh, Hassan Abid, Khawar Shehzad +2cs.LG cs.AI
Climate change research increasingly requires AI systems that reason across text, dynamic visual content, and scientific figures, yet existing climate QA benchmarks are small, mostly textual, and cover a narrow range of models. We introduce MMClima, a large-scale multimodal climate question answering framework with 104k+ expert-validated question-answer pairs spanning articles, video transcriptions, and figures across five core climate science domains. MMClima is constructed via automated claim extraction and QA synthesis with human-in-the-loop validation to ensure both scale and reliability. Using MMClima, we benchmark state-of-the-art multimodal language models on tasks requiring factual recall, visual interpretation, and cross-modal synthesis. We additionally fine-tune on the textual split to produce mmclima-70b-txt, a domain-adapted baseline that outperforms strong open- and closed-source models on textual QA. We release the dataset, evaluation pipeline, fine-tuned model weights, and data creation framework to support standardized multimodal evaluation for climate science.
Jingyuan Chen, Sheng Jin, Haopeng Sun +2cs.CV cs.AI
Computer-Aided Design (CAD) underpins modern engineering and manufacturing by enabling the creation of precise, editable 3D models. However, CAD research typically studies tasks in isolation, and multi-modal, multi-task learning for CAD is hindered by the absence of a unified benchmark. To address this gap, we introduce UniCAD, a comprehensive benchmark for multi-modal CAD learning that covers point-to-CAD reconstruction, text/image-to-CAD generation, and CAD question answering across diverse input modalities. Alongside the benchmark, we present UniCAD-MLLM, a universal multi-modal large language model that ingests text, images, sketches, and point clouds and performs these heterogeneous tasks in an end-to-end fashion within a single framework. Extensive experiments on the UniCAD and Fusion360 benchmarks demonstrate that UniCAD-MLLM achieves state-of-the-art performance across all tasks, outperforming existing task-specific and multi-task baselines. We will release the dataset, code, and pretrained models to accelerate future research.
Recent advances in self-evolution video understanding frameworks have demonstrated the potential of autonomous learning without human annotations. However, existing methods often suffer from weakly controlled optimization and uncontrolled difficulty progression, as they lack structured guidance throughout the iterative learning process. To address these limitations, we propose CurEvo, a curriculum-guided self-evolution framework that introduces curriculum learning into self-evolution to achieve more structured and progressive model improvement. CurEvo dynamically regulates task difficulty, refines evaluation criteria, and balances data diversity according to model competence, forming a curriculum-guided feedback loop that aligns learning complexity with model capability. Built upon this principle, we develop a multi-dimensional adaptive QA framework that jointly evolves question generation and answer evaluation across perception, recognition, and understanding dimensions, ensuring coherent and measurable curriculum progression. Through this integration, CurEvo transforms weakly controlled self-evolution into a more structured learning process for autonomous video understanding. Across seven backbones, CurEvo consistently improves both benchmark accuracy and evaluator-based semantic score on four VideoQA benchmarks, validating the effectiveness of curriculum-guided self-evolution for video understanding.