Understanding how (multimodal) large language models perform on physics problems requires benchmarks that reflect the difficulty and breadth of expert-level physical reasoning. Existing physics benchmarks remain limited in the following two important ways: (1) short of high-difficulty datasets, and (2) lack of comprehensive coverage of visual forms, knowledge points, and step-by-step solution processes. As a result, model performance on current datasets may not be fully representative of their ability to solve complex physics problems. To address these issues, we present PhysElite, a large-scale bilingual multimodal benchmark for Olympiad-level physics reasoning. PhysElite contains 11,586 Olympiad-tier problems. For each problem, we provide corresponding visual diagrams, step-by-step bilingual Chinese-English solution derivations, and the final answer. We benchmark 18 open-source and closed-source MLLMs, and find that even the strongest model reaches only 33.7% answer accuracy. We additionally conduct step-level process evaluation to diagnose where models fail in the reasoning chain. Our datasets are released at https://github.com/PremiLab-Math/PhysElite.
Subject-driven image generation aims to synthesize new images that preserve the identity of the given subject while following textual instructions. Existing approaches often encode text and reference images separately. This limits cross-modal reasoning abilities and causes copy-paste artifacts. Recent frameworks that connect multimodal models and diffusion models improve instruction following, but largely overlook identity preservation. To address these limitations, we condition diffusion models on Multimodal Large Language Models (MLLMs) that jointly encode text and reference images, and augment it with VAE-based identity conditioning. A novel Dual Layer Aggregation (DLA) module is designed to aggregate multi-level MLLM features for optimal conditioning, and a multi-stage denoising strategy is applied to progressively balance the semantic information from MLLM and fine-detail identity from VAE during inference. Extensive experiments demonstrate that our approach harmonizes multimodal understanding with identity preservation, mitigates copy-paste issues, and achieves superior performance regarding human preference on subject-driven image generation. Our project website is available at https://zsh2000.github.io/squeeze-mllm-subject-gen/.
Joint audio-video generation models are rapidly approaching professional production quality, raising a central question: do they understand audio-visual physics, or merely generate plausible sounds and frames that violate real-world consistency? We introduce AV-Phys Bench, a benchmark for evaluating physical commonsense in joint audio-video generation. AV-Phys Bench tests models across three scene categories: Steady State, Event Transition, and Environment Transition. It covers physics-grounded subcategories drawn from real-world scenes, plus Anti-AV-Physics prompts that deliberately request physically inconsistent audio-video behavior. Each generation is evaluated along five dimensions: visual semantic adherence, audio semantic adherence, visual physical commonsense, audio physical commonsense, and cross-modal physical commonsense. Across three proprietary and four open-source models, we find that Seedance 2.0 performs best overall, but all models remain far from robust physical understanding. Performance drops sharply on event-driven and environment-driven transitions, and even strong proprietary systems collapse on Anti-AV-Physics prompts. We further introduce AV-Phys Agent, a ReAct-style evaluator that combines a multimodal language model with deterministic acoustic measurement tools, producing rankings that closely align with human ratings. Our results identify cross-modal physical consistency and transition-driven scene dynamics as key open challenges for joint audio-video generation.
Embodied Question Answering (EQA) couples active visual perception, vision-language reasoning, and sequential decision making, and has traditionally been evaluated in temporally stable environments where visual evidence can be accumulated reliably. In realistic multimedia settings such as dynamic human-populated scenes, however, moving people and transient occlusions introduce human-induced perceptual variations: task-relevant multimodal cues become transient, viewpoint-dependent, and incompletely captured in individual views. Conventional store-then-retrieve strategies generate redundant visual evidence and incur high inference cost, making them ill-suited to such variations. This exposes two core problems for embodied agents: resolving viewpoint-dependent ambiguity, and maintaining compact evidence for efficient inference. To address these challenges, we present DIVRR (Dynamic-Informed View Refinement with Relevance-guided Rotation and adaptive memory selection), a training-free active evidence-acquisition framework for EQA. DIVRR combines question-conditioned room guidance with relevance-triggered view augmentation to guide exploration and additional observation. Selective memory admission uses the same relevance signal as view augmentation to retain high-scoring evidence, reducing stored entries while keeping the retrieved visual context compact. To evaluate EQA under human-induced perceptual variations, we introduce DynHuman-EQA, a dynamic human-populated EQA dataset constructed in Habitat, comprising dynamic and static subsets under shared scene layouts. Experiments on DynHuman-EQA and HM-EQA show that DIVRR outperforms existing baselines in both accuracy and memory efficiency. The gains are most pronounced in dynamic human-populated scenes.
Just Noticeable Distortion (JND)-guided pre-filter is a promising technique for improving the perceptual compression efficiency of image coding. However, existing methods are often computationally expensive, and the field lacks standardized benchmarks for fair comparison. To address these challenges, this paper introduces a twofold contribution. First, we develop and open-source FJNDF-Pytorch, a unified benchmark for frequency-domain JND-Guided pre-filters. Second, leveraging this platform, we propose a complete learning framework for a novel, lightweight Convolutional Neural Network (CNN). Experimental results demonstrate that our proposed method achieves state-of-the-art compression efficiency, consistently outperforming competitors across multiple datasets and encoders. In terms of computational cost, our model is exceptionally lightweight, requiring only 7.15 GFLOPs to process a 1080p image, which is merely 14.1% of the cost of recent lightweight network. Our work presents a robust, state-of-the-art solution that excels in both performance and efficiency, supported by a reproducible research platform. The open-source implementation is available at https://github.com/viplab-fudan/FJNDF-Pytorch.
Large public datasets have driven recent progress in machine learning, from text and vision to speech and general audio. Music remains an outlier, as copyright blocks redistribution of training audio, while many modern tasks need individual stems rather than mixtures. Existing multitrack resources trade off realism, scale, and licensing, while synthetic alternatives rely on proprietary VSTs or naive open rendering that yields weak stems. We introduce SPDMX, a listening-guided rendering of public-domain PDMX scores into an openly-licensed stem corpus with aligned scores and an open render pipeline: $253{,}982$ songs, $490{,}159$ mono stems, and $5{,}469$ song-hours at $44.1$ kHz under CC BY 4.0, with paired MIDI and identifiers linking to PDMX metadata. $88{,}403$ songs ($34.8\%$; $2{,}734$ song-hours) provide multitrack supervision. To our knowledge, this is the largest openly-licensed synthetic multitrack subset by song-hours, enabling source separation, stem-conditioned synthesis, MIDI-to-audio, transcription, and joint symbolic-audio modeling. We release the corpus, metadata, and open pipeline for reuse on other symbolic collections. Demos and experimental notes are on the project page.
Unified multimodal models combine image understanding and generation within one system, creating an opportunity to improve both capabilities through paired image--text supervision. We examine the outputs of a pretrained unified model in both directions and observe a loss of specificity: generated images can contain the requested objects with incorrect attributes, while captions identify a scene without expressing its distinguishing details. These failures call for supervision that specifies both the visual content to realize and the descriptive differences to distinguish. We propose UniMore, a post-training method that derives these complementary learning tasks from the fine-grained content of image--text pairs. The generation route predicts grounded crops from their corresponding phrases, matching the scope of the condition and visual target while using the native visual objective. The understanding route combines positive-caption fitting with ranking against captions that omit or alter details, conditioned on the full image. The two routes are optimized independently, and their learned updates are combined into a single unified model without changing its inference procedure. Experiments show gains across multiple understanding and generation benchmarks.
Referring multi-object tracking enables users to specify targets through natural language, but existing Refer-MOT benchmarks primarily focus on single-camera settings. We formalize Referring Multi-Target Multi-Camera Tracking (Refer-MTMCT), where free-form queries specify identity-consistent trajectories to be recovered across a network of sequential, sparse-overlap cameras. We introduce Refer-CityFlow, a benchmark built on CityFlow's global cross-camera identity annotations and augmented with language queries requiring joint language grounding, cross-camera association, and spatio-temporal reasoning. Refer-CityFlow covers 96 videos from 40 roadside cameras with 660+ identity-consistent cross-camera trajectories, 4,362 trajectory-level descriptions, and 7,699 queries, including 1,699 real-user queries collected from 50 participants. Reference experiments on the four-camera Scenario 02 show that single-camera referring trackers reach 14.95-18.28 HOTA on real-user queries, while the evaluated cross-view method achieves about 0.05 HOTA in direct transfer. To establish reference performance, we provide M3Track, a modular multimodal reference framework in which a large language model (LLM)-based agent orchestrates interchangeable detection, tracking, and cross-camera association modules. M3Track reaches 44.10 HOTA and 65.40 IDF1 on the same real-user query set. The project repository is available at https://github.com/phuongnguyen194/Refer-CityFlow-and--M3Track.
Recent advances in Gaussian splatting have enabled efficient and photorealistic head avatar reconstruction, yet monocular video-based or image-based methods still suffer from under-constrained geometry and texture, leading to artifacts such as blurring, stretching, and temporal instability. We present EDGAR (Efficient Diffusion-Driven Gaussian Avatar Refinement), a conditional diffusion framework designed to enhance the quality of Gaussian avatars by correcting artifacts while preserving identity fidelity. To train EDGAR, we construct EDGAR-SET, a hybrid triplet dataset composed of real-captured and synthetic-rendered samples, which simulates realistic Gaussian avatar failure cases by pairing degraded renderings with ground-truth and reference images. EDGAR refines degraded frames through a fusion block that injects identity features extracted by the self-supervised Sapiens model into a one-step diffusion backbone, enabling effective artifact removal without sacrificing efficiency. Our EDGAR model incorporates a Mixture-of-Experts (MoE) architecture to address diverse degradation types and severity levels. The refined multi-view renderings are subsequently used as pseudo-targets to optimize a single underlying Gaussian avatar, so that the final avatar can be rendered without applying EDGAR to every output frame. Experiments on three different Gaussian avatar reconstruction methods, each evaluated under three different settings, show improvements in both perceptual and reconstruction measures over the raw outputs and an SDEdit-style refinement baseline. In addition, cross-view evaluation demonstrates improved calibrated consistency, while tests under large yaw and open-mouth expressions verify robustness under extreme settings. These results collectively indicate a useful operating regime for recoverable appearance artifacts. The code is available at https://kwanyun.github.io/edgar/
Speaker-recognition benchmarks test how accurately a model recovers the speaker label of a recording, treating voice identity as a property of the person who produced it. However, these benchmarks do not evaluate how humans perceive voice identity. Whether a listener hears two voices as the same person has consequences for intellectual property rights, cybersecurity, and everyday life. We introduce the Voice Identity Perception benchmark (VIPBench), which contains 124,876 same-or-different judgments from 1,290 listeners on 9,800 recording pairs from 100 public figures. The pairs include real recordings, voice clones generated by a text-to-speech system, and morphs between two speakers' voices. We also define four tasks that evaluate the alignment between speaker-representation models and human identity perception. The first two tasks measure how well a model's similarity score predicts the proportion of listeners who respond "same" and the majority response. The other two measure whether a model and listeners find the same speaker pairs similar, and whether a model's relationship to listener judgments holds equally for real and synthetic recordings. We evaluate eleven publicly available speech models. Listener judgments diverge from speaker labels most often for voice clones: in 41% of responses, listeners judged a clone and a real recording of the same speaker to be different people. No model reaches the noise ceiling; the best model explains 61% of the explainable variance. Models trained with speaker labels align with listeners better than self-supervised models do, yet a model with a 12% error rate on speaker labels aligns with listeners as well as models with error rates below 2%. VIPBench enables the evaluation of speaker models against human perception on real, cloned, and morphed speech, and our results motivate training speaker models directly on listener judgments.
Generative creative interfaces routinely report the user's position within a space of possibilities. Such displays imply that the quantities shown were measured from the artefact; in a growing class of systems they are instead predicted by a language model describing its own output, and the two are indistinguishable on screen. Most creative domains lack an agreed measurement against which such a self-report can be checked; audio admits one. In a measurement study of a working LLM-driven timbre interface, what a user can cause proves separable from what the interface reports. The first is exactly characterisable: the reachable set is a zonotope in parameter space whose dimension increases by one per sound placed, so the space the model may act within is demonstrably the user's own. The second is inaccurate. The displayed position differs from measurement by approximately three times the width of that region, and the error has two independent sources: model-predicted coordinates, whose accuracy varies twofold between the two models evaluated, and the interpolation step, which arises from combining synthesiser parameters and is unaffected by model quality. End to end, 27 of 36 refinement instructions produced no perceptible change, and under the weaker model the facility performed no action while reporting convergence. Effective agency (what a user can cause) and epistemic agency (whether they can know it) are therefore separable and independently engineered: structurally enforced constraints survive model failure, whereas guarantees resting on the model's own report do not. The failure mode that remains is silence presented as success. We close with a short protocol for building and auditing such displays.
Visual object removal can eliminate a target from video frames, yet its acoustic trace persists in the soundtrack, causing obvious audio-visual inconsistency. Existing video inpainting models operate solely on pixels, while audio editing models, especially for the sound removal task, are typically driven by text and therefore rely on limited single-modal control, which is less effective than multimodal guidance that provides stronger semantic grounding and temporal synchronization cues. In this paper, we present Text-Visual Guided Sound Removal (TV-AudioRemover), a target sound removal framework that leverages the visually edited video together with a natural-language instruction to suppress the sound associated with the removed visual object from the original audio mixture. To acquire high-quality training data, we devise a pipeline to construct a million-scale dataset of single-object audio-visual aligned samples, from which we synthesize mixture-target pairs customized for model training. To effectively leverage visual context and follow instruction intent, we augment the model architecture with task tokens, generalizable instruction modeling, and modality-specific global guidance. We further adopt multi-task training to strengthen task-role comprehension, and employ a hard-mixture curriculum that leverages semantically similar acoustic mixtures during fine-tuning to enhance fine-grained source discrimination. To support evaluation, we present AV-Remove-Bench, a comprehensive audio-visual object removal benchmark, along with dedicated objective metrics and an MLLM-based evaluation protocol. Experiments demonstrate that our method achieves state-of-the-art performance on both subjective and objective metrics. Project page: https://yjx-research.github.io/TV-AudioRemover/.
Accurately assessing the risk of cesarean section (CS) delivery is critical, especially in settings with limited medical resources, where access to healthcare is often restricted. Early and reliable risk prediction allows better-informed prenatal care decisions and can improve maternal and neonatal outcomes. However, most existing predictive models are tailored for in-hospital use during labor and rely on parameters that are often unavailable in resource-limited or home-based settings. In this study, we conduct a pilot investigation to examine the feasibility of using 3D body shape for CS risk assessment for future applications with more affordable general devices. We propose a novel multi-view-based Transformer network, MvBody, which predicts CS risk using only self-reported medical data and 3D optical body scans obtained between the 31st and 38th weeks of gestation. To enhance training efficiency and model generalizability in data-scarce environments, we incorporate a metric learning loss into the network. Compared to widely used machine learning models and the latest advanced 3D analysis methods, our method demonstrates superior performance, achieving an accuracy of 84.62% and an Area Under the Receiver Operating Characteristic Curve (AUC-ROC) of 0.724 on the independent test set. To improve transparency and trust in the model's predictions, we apply the Integrated Gradients algorithm to provide theoretically grounded explanations of the model's decision-making process. Our results indicate that pre-pregnancy weight, maternal age, obstetric history, previous CS history, and body shape, particularly around the head and shoulders, are key contributors to CS risk prediction.
Multimodal large language models (MLLMs) have demonstrated remarkable progress on cross-modal reasoning tasks, yet they continue to suffer from hallucinations in long-chain reasoning processes. In this work, we revisit hallucination in MLLMs from the perspective of reasoning generation dynamics. We argue that entropy is not merely a static measure of uncertainty but a structured signal that reflects how modality information is integrated throughout decoding. Through systematic analysis, we identify two characteristic entropy patterns associated with hallucination behaviors: (1) a generally high-confidence regime corresponds to premature convergence to inappropriate multimodal interactions; and (2) local abrupt entropy transitions are associated with reasoning instability and hallucination onset. Building on these observations, we propose an entropy-aware self-introspective framework for MLLM reasoning. Our method continuously tracks entropy dynamics during decoding and performs targeted visual re-alignment when suspicious hallucination states are detected, encouraging the model to re-examine salient visual evidence at critical reasoning stages. Extensive experiments across six multimodal reasoning benchmarks spanning nine distinct evaluation settings demonstrate that our approach delivers robust improvements in reasoning accuracy and hallucination robustness, while providing new insights into the generation dynamics underlying MLLM failures. The code is available at: https://github.com/jden4524/SelfRetrospectiveDecoding.
Video editors often work with large collections of fragmented footage and must select and organize relevant clips into a coherent story. However, many existing video editing and summarization methods assume a temporally ordered source video and aim to preserve its original narrative and temporal structure. In this paper, we introduce Clips2Story, a training-free, LLM-based pipeline that enables users to create keyword-specified short videos from a pool of video clips. Given a pool of clips and a user-specified keyword, we first extract text-based multimodal descriptors for each clip and retrieve the clips most relevant to the keyword. We then provide the textual descriptors of these candidate clips to an LLM, which selects and arranges them into an editable storyboard with connective narrations. Finally, we assemble the selected clips and retrieve accompanying visuals for the narrations to compose the output video. To evaluate the proposed pipeline, we construct a synthetic evaluation dataset from 100 long-form videos across five genres by segmenting each video into short clips using a scene-change detection model and shuffling the resulting clips to remove their temporal order. Through objective evaluation and qualitative examples, we demonstrate that Clips2Story can effectively retrieve keyword-relevant clips and compose coherent storyboards based on user-specified keywords. Human evaluation further shows that Clips2Story outperforms a strong baseline in terms of narrative coherence, keyword alignment, and overall realism.
Identity-preserving video generation aims to synthesize high-quality and visually realistic videos from textual and visual conditions while faithfully maintaining the subject's identity across diverse motions. Prior methods have extensively introduced reference-guided control signals and identity-aware conditioning to improve facial alignment from reference images. However, improving static identity alignment alone creates a fundamental tension between identity fidelity and temporal controllability, which frequently causes identity drift or motion suppression under large pose variations and multi-segment sequential actions. To address this, we propose Chronos, a framework that unifies single-segment facial identity preservation and multi-segment sequential action generation under a common temporal formulation. Specifically, Chronos integrates Semantic Prompt Anchoring to adaptively refine the user prompt, Visual Frame Anchoring to transform conditions into visually grounded keyframe anchors for visual guidance, and Metric-Guided Candidate Routing to select the highest-quality videos from heterogeneous generators via multi-dimensional evaluation. Extensive evaluations demonstrate the superiority of our approach, which achieved first place in both Track 1 and Track 2 of the ACM MM 2026 Identity-Preserving Video Generation Challenge, demonstrating its effectiveness across both facial identity preservation and sequential action generation settings.
Scalable video coding (SVC) encodes a video into a layered bitstream of a base layer and one or more enhancement layers, enabling decoding at different bitrate/quality/resolution operating points for diverse devices and network conditions. SVC has been incorporated into major video coding standards and has recently attracted growing interest for both scene-agnostic and scene-adaptive neural video codecs. Among the latter, implicit neural representation (INR) based codecs overfit a compact neural network to an individual video, offering fast decoding and competitive coding efficiency. However, research on scalable INR-based compression remains in its infancy: existing methods introduce additional network layers, which couple the bitrate with the decoding complexity and cannot match strong scalable/non-scalable codecs. This paper proposes S-NVRC, a scalable INR-based video codec that jointly supports fine-grained bitrate and decoding complexity scalability from a single embedded bitstream. It adopts a coarse-to-fine prefix for feature grids and a nested prefix for network layers, which scale bitrate and decoding complexity, respectively. With a single encoding, S-NVRC spans a wide range of bitrate and decoding complexity and outperforms SHM-12.4 and the multi-layer VTM-20.0 by 43.7% and 5.6% in BD-rate on the UVG dataset.
Clustering faces by identity in long, continuous video streams is a challenging task that serves as a building block for human-centric video analysis. The majority of existing face clustering models are offline, i.e., they assume the entire data to be available altogether. In many practical scenarios, however, the entire data is either unavailable or poses computational challenges to be processed in its entirety. A handful of online methods that exist rely on geometric visual features and simple thresholding techniques, which fail when the faces exhibit significant appearance variations in long, unconstrained videos. To this end, we present VISTA, the first vision language framework for online face clustering in long videos. VISTA leverages semantic reasoning in a controlled, uncertainty aware fashion to maintain both high cluster purity and long range identity continuity. This makes it robust to the variations in illumination, pose, and costume changes that the faces and characters exhibit in long real world videos. Extensive experiments on the VPCD benchmark dataset (with 15 full episodes from The Big Bang Theory [2007-2019], Buffy the Vampire Slayer [1997-2003], and Sherlock [2010-2017]) demonstrate that VISTA achieves a robust precision and recall balance, consistently improving over the strongest matched online unsupervised baseline (COFC) under identical detector, embeddings, and evaluation protocol. Code and supplementary material: https://github.com/SkyJiashu/VISTA.
User-generated videos, including opinion vlogs and video reviews, provide a rich source of people's attitudes toward products, services, and social topics. Understanding the sentiment expressed by speakers is important for analyzing online opinions, as transcripts alone may not capture the attitude and intensity conveyed through vocal tone and facial expressions. Multimodal sentiment analysis (MSA) addresses this need by integrating textual, acoustic, and visual cues. However, these cues are often subtle, noisy, and inconsistent across modalities. Existing local affective cue modeling methods typically operate within individual modalities and overlook global contexts from other modalities. This may cause cross-modal affective cue inconsistency. Hierarchical global-local fusion methods integrate global semantics with fine-grained local affective cues. However, they commonly determine the relative contributions of the two representations implicitly, preventing the global-local contributions from adapting to the sample-dependent reliability of local cues and resulting in either insufficient use of informative local cues or excessive interference from unreliable ones. To address these issues, we propose DGC-Net, a Dynamic Gating and Global-Guided Compensation Network for MSA. DGC-Net mitigates cross-modal affective cue inconsistency through cross-modal contribution-aware dynamic expert routing. This mechanism uses auxiliary global contexts to guide local expert selection. Moreover, global-guided dynamic compensation fusion alleviates sample-dependent global-local contribution imbalance while preserving global semantic as the primary anchor and adaptively incorporating expert-refined local cues. Experiments on five multimodal benchmark datasets demonstrate the effectiveness and general applicability of DGC-Net, and ablation studies verify the contribution of each proposed component.
Coarse-to-fine image-to-point-cloud (I2P) registration risks discarding correct but ambiguous patch pairs, while retaining more candidates repeats fine matching over overlapping patches. SparseGraph-I2P aims to improve registration recall by increasing the inlier ratio at the pose solver, using sensor or monocular depth. A Coarse Hypothesis Graph combines appearance with depth-derived first- and second-order compatibility to select a fixed budget of patch pairs. Sparse Fine Matching decodes each queried pixel once and skips pixel--point comparisons covered by an ancestor patch paired with the same point-cloud region. With sensor depth, depth-aware filtering ranks correspondences by SC2 spectral support for a single EPnP solve. With monocular depth, depth or inverse depth is calibrated from correspondence geometry before filtering. SparseGraph-I2P achieves the highest registration recall and lowest latency among the compared methods on RGB-D Scenes V2 and 7-Scenes with sensor depth. With predicted depth, it retains the highest recall on RGB-D Scenes V2 at an additional calibration cost. Code will be released.