Multimodal Large Language Models (MLLMs) have recently achieved remarkable progress in vision-language understanding. Yet, human perception is inherently multisensory, integrating sight, sound, and motion to reason about the world. Among these modalities, sound provides indispensable cues about spatial layout, off-screen events, and causal interactions, particularly in egocentric settings where auditory and visual signals are tightly coupled. To this end, we introduce EgoSound, the first benchmark designed to systematically evaluate egocentric sound understanding in MLLMs. EgoSound unifies data from Ego4D and EgoBlind, encompassing both sighted and sound-dependent experiences. It defines a seven-task taxonomy spanning intrinsic sound perception, spatial localization, causal inference, and cross-modal reasoning. Constructed through a multi-stage auto-generative pipeline, EgoSound contains 7315 validated QA pairs across 900 videos. Comprehensive experiments on nine state-of-the-art MLLMs reveal that current models exhibit emerging auditory reasoning abilities but remain limited in fine-grained spatial and causal understanding. EgoSound establishes a challenging foundation for advancing multisensory egocentric intelligence, bridging the gap between seeing and truly hearing the world. Project page: https://groolegend.github.io/EgoSound/.
论文检索
输入标题、作者或关键词，从 2,006 篇学术成果中精准定位
In real-world multimodal applications, systems usually need to comprehend arbitrarily combined and interleaved multimodal inputs from users, while also generating outputs in any interleaved multimedia form. This capability defines the goal of any-to-any interleaved multimodal learning under a unified paradigm of understanding and generation, posing new challenges and opportunities for advancing Multimodal Large Language Models (MLLMs). To foster and benchmark this capability, this paper introduces the UniM benchmark, the first Unified Any-to-Any Interleaved Multimodal dataset. UniM contains 31K high-quality instances across 30 domains and 7 representative modalities: text, image, audio, video, document, code, and 3D, each requiring multiple intertwined reasoning and generation capabilities. We further introduce the UniM Evaluation Suite, which assesses models along three dimensions: Semantic Correctness & Generation Quality, Response Structure Integrity, and Interleaved Coherence. In addition, we propose UniMA, an agentic baseline model equipped with traceable reasoning for structured interleaved generation. Comprehensive experiments demonstrate the difficulty of UniM and highlight key challenges and directions for advancing unified any-to-any multimodal intelligence.
Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction
PDF ↗Reconstructing dynamic visual experiences as videos from functional magnetic resonance imaging (fMRI) is pivotal for advancing the understanding of neural processes. However, current fMRI-to-video reconstruction methods are hindered by a semantic gap between noisy fMRI signals and the rich content of videos, stemming from a reliance on incomplete semantic embeddings that neither capture video-specific cues (e.g., actions) nor integrate prior knowledge. To this end, we draw inspiration from the dual-pathway processing mechanism in human brain and introduce CineNeuron, a novel hierarchical framework for semantically enhanced video reconstruction from fMRI signals with two synergistic stages. First, a bottom-up semantic enrichment stage maps fMRI signals to a rich embedding space that comprehensively captures textual semantics, image contents, action concepts, and object categories. Second, a top-down memory integration stage utilizes the proposed Mixture-of-Memories method to dynamically select relevant "memories" from previously seen data and fuse them with the fMRI embedding to refine the video reconstruction. Extensive experimental results on two fMRI-to-video benchmarks demonstrate that CineNeuron surpasses state-of-the-art methods across various metrics.
Recent multimodal large language models (MLLMs) such as GPT-4o and Qwen3-Omni show strong perception but struggle in multi-speaker, dialogue-centric settings that demand agentic reasoning, tracking who speaks, maintaining roles, and grounding events across time. These scenarios are central to multimodal audio-video understanding, where models must jointly reason over audio and visual streams in applications such as conversational video assistants and meeting analytics. We introduce AMusE, a benchmark designed around tasks that are inherently agentic, requiring models to decompose complex audio-visual interactions into planning, grounding, and reflection steps. It evaluates MLLMs across three modes: zero-shot, guided, and agentic, and six task families, including spatio-temporal speaker grounding and multimodal dialogue summarization. Across all modes, current models exhibit weak multi-speaker reasoning and inconsistent behavior under both non-agentic and agentic evaluation. Motivated by the inherently agentic nature of these tasks and recent advances in LLM agents, we propose RAFT, a data-efficient agentic alignment framework that integrates reward optimization with intrinsic multimodal self-evaluation as reward and selective parameter adaptation for data and parameter-efficient updates. Using RAFT, we achieve up to 39.52% relative improvement in accuracy on our benchmark. Together, AMusE and RAFT provide a practical platform for examining agentic reasoning in multimodal models and improving their capabilities.
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models
PDF ↗Video Large Language Models (VLLMs) demonstrate strong video understanding but suffer from inefficiency due to redundant visual tokens. Existing pruning primary targets intra-frame spatial redundancy or prunes inside the LLM with shallow-layer overhead, yielding suboptimal spatiotemporal reduction and underutilizing long-context compressibility. All of them often discard subtle yet informative context from merged or pruned tokens. In this paper, we propose a new perspective that elaborates token Anchors within intra-frame and inter-frame to comprehensively aggregate the informative contexts via local-global Optimal Transport (AOT). Specifically, we first establish local- and global-aware token anchors within each frame under the attention guidance, which then optimal transport aggregates the informative contexts from pruned tokens, constructing intra-frame token anchors. Then, building on the temporal frame clips, the first frame within each clip will be considered as the keyframe anchors to ensemble similar information from consecutive frames through optimal transport, while keeping distinct tokens to represent temporal dynamics, leading to efficient token reduction in a training-free manner. Extensive evaluations show that our proposed AOT obtains competitive performances across various short- and long-video benchmarks on leading video LLMs, obtaining substantial computational efficiency while preserving temporal and visual fidelity.
CineSRD: Leveraging Visual, Acoustic, and Linguistic Cues for Open-World Visual Media Speaker Diarization
PDF ↗Traditional speaker diarization systems have primarily focused on constrained scenarios such as meetings and interviews, where the number of speakers is limited and acoustic conditions are relatively clean. To explore open-world speaker diarization, we extend this task to the visual media domain, encompassing complex audiovisual programs such as films and TV series. This new setting introduces several challenges, including long-form video understanding, a large number of speakers, cross-modal asynchrony between audio and visual cues, and uncontrolled in-the-wild variability. To address these challenges, we propose Cinematic Speaker Registration & Diarization (CineSRD), a unified multimodal framework that leverages visual, acoustic, and linguistic cues from video, speech, and subtitles for speaker annotation. CineSRD first performs visual anchor clustering to register initial speakers and then integrates an audio language model for speaker turn detection, refining annotations and supplementing unregistered off-screen speakers. Furthermore, we construct and release a dedicated speaker diarization benchmark for visual media that includes Chinese and English programs. Experimental results demonstrate that CineSRD achieves superior performance on the proposed benchmark and competitive results on conventional datasets, validating its robustness and generalizability in open-world visual media settings.
TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding
PDF ↗We introduce TimeViper, a hybrid vision-language model designed to tackle challenges of long video understanding. Processing long videos demands both an efficient model architecture and an effective mechanism for handling extended temporal contexts. To this end, TimeViper adopts a hybrid Mamba-Transformer backbone that combines the efficiency of state-space models with the expressivity of attention mechanisms. Through this hybrid design, we reveal the vision-to-text information aggregation phenomenon, where information progressively flows from vision tokens to text tokens across increasing LLM depth, resulting in severe vision token redundancy. Motivated by this observation, we propose TransV, a token information transfer module that transfers and compresses vision tokens into instruction tokens while maintaining multimodal understanding capabilities. This design enables TimeViper to process hour-long videos exceeding thousands of frames. Extensive experiments across multiple benchmarks demonstrate that TimeViper competes with state-of-the-art models while reducing inference cost. We further analyze attention behaviors of both Mamba and Transformer layers, offering new insights into hybrid model interpretability. This work represents an initial step towards developing, interpreting, and compressing hybrid Mamba-Transformer architectures.
Video data provides a rich source beyond expensive action-labeled data for advancing robot learning. Recent approaches have demonstrated promising potential in leveraging video data by learning latent actions for policy training. The latent action tokenizer encodes latent actions between successive video frames, and the tokenizer is trained to reconstruct future frames using current frames and the encoded latent actions. However, the unique pairing of successive frames permits future frame reconstruction with little understanding of transition dynamics, hindering the learning of semantically consistent latent actions. Moreover, the tokenizer typically allocates distinct latent action subsets to individual embodiments to accommodate heterogeneous morphologies, constraining knowledge transfer. To overcome such limitations, we propose the action-centric cycle consistency, aiming to establish a unified latent action space. Our method samples latent actions from the latent action space and decodes them with video frames to generate diverse subsequent frames, then enforces cycle consistency by predicting the sampled actions from both original and generated frames. Our concise method creates a challenging task that learns corresponding latent actions from current frames and diverse generated future frames, compelling the tokenizer to develop semantically consistent action representations. Additionally, sampled latent actions can be applied to video frames from distinct embodiments, facilitating the alignment of latent actions across embodiments. Experiments demonstrate that our approach achieves a 20.1% improvement over OpenVLA on the LIBERO benchmark and increases the average length from 3.27 to 3.93 on the CALVIN benchmark. In real-world experiments, our method maintains strong performance with a 44% improvement.
Forecasting gaze behavior is an important task for understanding user intent and creating AR/VR systems that can anticipate where users will look and interact next. While prior works have addressed predicting scanpaths in static images, forecasting gaze in egocentric videos presents new challenges due to the dynamic nature of the scene and the camera wearer's continuous movement through the 3D environment. To address these challenges, we formulate the novel task of egocentric scanpath prediction as forecasting a sequence of future fixations in 3D Cartesian coordinates relative to the last observed camera pose, producing a 3D scanpath that is grounded in the environment. We propose a transformer architecture that leverages egocentric video frames, head pose, and past 3D gaze observations to predict future 3D fixation sequences. We evaluate our method on the Aria Digital Twin dataset. Our findings establish a baseline for the novel task of 3D scanpath prediction and highlight important architectural elements for our task.
Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding
PDF ↗The application of Large Multimodal Models (LMMs) to long-form video understanding is constrained by limited context lengths and the computationally prohibitive cost of processing dense video tokens. Consequently, recent research has focused on query-aware frame selection, methods that often incur significant computational overhead. This paper challenges the assumption that such complex search mechanisms are universally necessary. We first identify and validate a query typology distinguishing between global query and localized query. We demonstrate that while uniform sampling is both effective and efficient for global queries, localized queries indeed necessitate query-aware selection for optimal performance. Building on this insight, we propose DIG, a training-free frame selection framework that adapts its strategy based on the query type. Specifically, DIG employs efficient uniform sampling for global queries while activating a specialized pipeline to extract query-relevant frames for localized queries. Experiments on three long-form video understanding benchmarks demonstrate that DIG consistently outperforms existing baselines and robustly improves LMM performance, even when scaling the input frame count to 256.
DeRVOS: Decoupling Consistent Trajectory Generation and Multimodal Understanding for Referring Video Object Segmentation
PDF ↗Referring video object segmentation (RVOS) aims to segment objects within a video according to natural language expressions. Unlike earlier works focusing on static single-object scenarios, recent studies address more complex motion scenes. Previous methods typically adopt a query-based, logically multi-stage pipeline to handle these scenarios. However, this paradigm learns trajectory consistency modeling and multimodal fusion from scratch, which often leads to trajectory inconsistencies and insufficient multimodal understanding. To address these limitations, we propose DeRVOS, a framework that decouples RVOS into two key branches: consistent trajectory generation and multimodal understanding. We extract temporally consistent object representations using a powerful pretrained instance trajectory generation model and perform cross-modal alignment via a unified multimodal encoder, enabling upstream modeling of trajectory consistency and vision-language understanding. This design reduces RVOS to the task of modeling the relationship between referring expressions and instance trajectories. To connect the two branches and enable efficient motion-aware semantic understanding, we introduce the Trajectory Alignment and Implicit Selection (TAIS) module, which progressively performs cross-frame multimodal alignment and motion-guided implicit trajectory selection. Extensive experiments demonstrate that DeRVOS achieves state-of-the-art results on both traditional RVOS benchmarks and the challenging MeViS dataset, surpassing LVLM-based methods by 4.7%.
UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models
PDF ↗With the advancement of multi-modal Large Language Models (LLMs), Video LLMs have been further developed to perform on holistic and specialized video understanding. However, existing works are limited to specialized video understanding tasks, failing to achieve a comprehensive and multi-grained video perception. To bridge this gap, we introduce UFVideo, the first Video LLM with unified multi-grained cooperative understanding capabilities. Specifically, we design unified visual-language guided alignment to flexibly handle video understanding across global, pixel and temporal scales within a single model. UFVideo dynamically encodes the visual and text inputs of different tasks and generates the textual response, temporal localization, or grounded mask. Additionally, to evaluate challenging multi-grained video understanding tasks, we construct the UFVideo-Bench consisting of three distinct collaborative tasks within the scales, which demonstrates UFVideo's flexibility and advantages over GPT-4o. Furthermore, we validate the effectiveness of our model across 9 public benchmarks covering various common video understanding tasks, providing valuable insights for future Video LLMs.
Video Question Answering (VideoQA) has made significant strides by leveraging multimodal learning to align visual and textual modalities. However, current benchmarks overwhelmingly focus on questions answerable through explicit visual content - actions, objects, and events - directly observable within individual frames or short clips. To truly understand videos as humans do, models must go beyond what is directly shown, inferring hidden relationships and contextual cues that are only implied across frames. Current benchmarks fail to capture this essential aspect of video understanding. To address this gap, we introduce VRR-QA, a benchmark for Visual Relational Reasoning Beyond Explicit Cues. We curate our benchmark from creative and cinematic videos such as movies, that deliberately employ storytelling techniques which omit direct depictions of certain events or relations, requiring viewers to infer them. VRR-QA comprises 1K meticulously expert-annotated QA pairs drawn from 1K creative video clips covering 15 genres across 7 decades of content, from both live-action and animated titles. Our extensive evaluations on 14 leading VideoQA models reveals consistent and significant performance degradation, underscoring their reliance on surface-level visual cues and highlighting the difficulty of implicit reasoning. Even the best model substantially underperforms human baselines with only 64% accuracy. Performance variations across models further illustrate the complexity and diversity of the challenges presented by VRR-QA. By releasing both dataset and data collection framework, VRR-QA establishes a rigorous, diverse, and reproducible testbed for advancing VideoQA.
Learning to See Through a Baby's Eyes: Early Visual Diets Enable Robust Visual Intelligence in Humans and Machines
PDF ↗Newborns perceive the world with low-acuity, color-degraded, and temporally continuous vision, which gradually sharpens as infants develop. To explore the ecological advantages of such staged "visual diets", we train self-supervised learning (SSL) models on object-centric videos under constraints that simulate infant vision: grayscale-to-color (C), blur-to-sharp (A), and preserved temporal continuity (T)--collectively termed CATDiet. For evaluation, we establish a comprehensive benchmark across ten datasets, covering clean and corrupted image recognition, texture-shape cue conflict tests, silhouette recognition, depth-order classification, and the visual cliff paradigm.All CATDiet variants demonstrate enhanced robustness in object recognition, despite being trained solely on object-centric videos. Remarkably, models also exhibit biologically aligned developmental patterns, including neural plasticity changes mirroring synaptic density in macaque V1 and behaviors resembling infants' visual cliff responses. Building on these insights, CombDiet initializes SSL with CATDiet before standard training while preserving temporal continuity. Trained on object-centric or head-mounted infant videos, CombDiet outperforms standard SSL on both in-domain and out-of-domain object recognition and depth perception. Together, these results suggest that the developmental progression of early infant visual experience offers a powerful reverse-engineering framework for understanding the emergence of robust visual intelligence in machines. All code, data, and models are available at Github.
Accurate capture of human-object interaction from ubiquitous sensors like RGB cameras is important for applications in human understanding, gaming, and robot learning. However, inferring 4D interactions from a single RGB view is highly challenging due to the unknown object and human information, depth ambiguity, occlusion, and complex motion, which hinder consistent 3D and temporal reconstruction. Previous methods simplify the setup by assuming ground truth object template or constraining to a limited set of object categories. We present CARI4D, the first category-agnostic method that reconstructs spatially and temporarily consistent 4D human-object interaction at metric scale from monocular RGB videos. To this end, we propose a pose hypothesis selection algorithm that robustly integrates the individual predictions from foundation models, jointly refine them through a learned render-and-compare paradigm to ensure spatial, temporal and pixel alignment, and finally reasoning about intricate contacts for further refinement satisfying physical constraints. Experiments show that our method outperforms prior art by 35% on in-distribution dataset and 36% on unseen dataset in terms of reconstruction error. Our model generalizes beyond the training categories and thus can be applied zero-shot to in-the-wild internet videos. Our code and pretrained models will be publicly released.
Large vision-language models struggle with medical video understanding, where spatial precision, temporal reasoning, and clinical semantics are critical. To address this, we first introduce MedVidBench, a large-scale benchmark of 531,850 video-instruction pairs across 8 medical sources spanning video, segment, and frame-level tasks, curated through a rigorous quality assurance pipeline with expert-guided prompting and dual-model validation. While supervised fine-tuning on MedVidBench yields noticeable gains, standard Reinforcement Learning (RL) fails due to imbalanced reward scales across datasets, which destabilizes optimization and leads to training collapse. To overcome this, we introduce MedGRPO, a novel RL framework for balanced multi-dataset training with two key innovations: (1) cross-dataset reward normalization that maps each dataset's median performance to a common reward value, ensuring fair optimization regardless of difficulty, and (2) a medical LLM judge that evaluates caption quality on five clinical dimensions through comparative similarity scoring. Supervised fine-tuning Qwen2.5-VL-7B on MedVidBench substantially outperforms GPT-4.1 and Gemini-2.5-Flash across all tasks, demonstrating MedVidBench's efficacy, while our MedGRPO framework further improves upon the SFT baseline across grounding and captioning tasks. Our work establishes a foundational benchmark and robust training methodology for advancing vision-language models in medical domains.
Long-form video understanding remains challenging due to the extended temporal structure and dense multimodal cues. Despite recent progress, many existing approaches still rely on hand-crafted reasoning pipelines or employ token-consuming video preprocessing to guide MLLMs in autonomous reasoning. To overcome these limitations, we introduce VideoARM, an agentic reasoning-over-hierarchical-memory paradigm for long-form video understanding. Instead of static, exhaustive preprocessing, VideoARM performs adaptive, on-the-fly agentic reasoning and memory construction. Specifically, VideoARM performs an adaptive and continuous loop of observing, thinking, acting, and memorizing, where a controller autonomously invokes tools to interpret the video in a coarse-to-fine manner, thereby substantially reducing token consumption. In parallel, a hierarchical multimodal memory continuously captures and updates multi-level clues throughout the operation of the agent, providing precise contextual information to support the controller in decision-making. Experiments on prevalent benchmarks demonstrate that VideoARM outperforms the state-of-the-art method, DVD, while significantly reducing token consumption for long-form videos.
Recent advances in large vision models (LVMs) have shifted from modality-specific designs toward unified architectures that jointly process images, videos, and 3D data. However, existing unified LVMs primarily pursue functional integration, while overlooking the deeper goal of cross-vision synergy: the ability to reason over complementary priors across visual modalities. To address this, we present PolyV, a unified LVM that achieves cross-vision synergy at both the architectural and training levels. Architecturally, PolyV adopts a sparse Mixture-of-Experts LVM coordinated by a dynamic modality router, allowing each expert to specialize in modality-specific priors while enabling bidirectional interaction and mutual refinement across modalities. Training-wise, a synergy-aware paradigm combines modality-specific pretraining with coarse-to-fine synergy tuning via knowledge distillation and object-/relation-level alignment. Extensive experiments on 10 benchmarks spanning image, video, and 3D understanding, including synergy-focused datasets requiring spatial or temporal priors, demonstrate that PolyV consistently outperforms existing models, achieving over 10% average improvement over its backbone. Overall, PolyV establishes a unified framework for synesthetic visual reasoning, advancing toward truly synergistic LVMs.
The rapid progress of Multimodal Large Language Models (MLLMs) marks a significant step toward artificial general intelligence, offering great potential for augmenting human capabilities. However, their ability to provide effective assistance in dynamic, real-world environments remains largely underexplored. Existing video benchmarks predominantly assess passive understanding through retrospective analysis or isolated perception tasks, failing to capture the interactive and adaptive nature of real-time user assistance. To bridge this gap, we introduce LifeEval, a multimodal benchmark designed to evaluate real-time, task-oriented human-AI collaboration in daily life from an egocentric perspective. LifeEval emphasizes three key aspects: task-oriented holistic evaluation, egocentric real-time perception from continuous first-person streams, and human-assistant collaborative interaction through natural dialogues. Constructed via a rigorous annotation pipeline, the benchmark comprises 4,075 high-quality question-answer pairs across 6 core capability dimensions. Extensive evaluations of 26 state-of-the-art MLLMs on LifeEval reveal substantial challenges in achieving timely, effective and adaptive interaction, highlighting essential directions for advancing human-centered interactive intelligence.
We introduce a novel method for video Scene Text Segmentation (STS), a task critical for understanding dynamic visual content. Despite the success of foundation models like Segment Anything Model 2 (SAM2) in generic segmentation, their application to video STS is hindered by the reliance on external prompts, limited output resolution, and instability in video sequences. To address these, we present a comprehensive framework based on SAM2. First, we fine-tune the image encoder using LoRA and integrate a self-prompting module, enabling the model to autonomously generate text-specific prompts. Second, we augment the decoder with additional upsampling branches at 512x512 and 1024x1024 resolutions, complementing the original 256x256 output to produce high-fidelity, multi-resolution masks. Third, we enhance the memory mechanism by combining short-term memory with a top-k selection strategy, ensuring temporally consistent and stable segmentation across video frames. A significant obstacle in video STS is data scarcity. To this end, we contribute two datasets: STS-SynthV, containing 1,410 synthetic video clips generated via FlowText, and STS-RealV, comprising 660 meticulously annotated real-world video sequences. Extensive experiments demonstrate that our method achieves state-of-the-art performance on multiple video and image scene text benchmarks. The data and code:https://github.com/insuper-zhang/SAM2Text/.