While pre-trained multimodal representations (e.g., CLIP) have shown impressive capabilities, they exhibit significant compositional vulnerabilities leading to counterintuitive judgments.We introduce Multimodal Adversarial Compositionality (MAC), a benchmark that leverages large language models (LLMs) to generate deceptive text samples to exploit these vulnerabilities across different modalities and evaluates them through both sample-wise attack success rate and group-wise entropy-based diversity.To improve zero-shot methods, we propose a self-training approach that leverages rejectionsampling fine-tuning with diversity-promoting filtering, which enhances both attack success rate and sample diversity.Using smaller language models like Llama-3.1-8B, our approach demonstrates superior performance in revealing compositional vulnerabilities across various multimodal representations, including images, videos, and audios.

The rapid growth of video-text data presents challenges in storage and computation during training. Online learning, which processes streaming data in real-time, offers a promising solution to these issues while also allowing swift adaptations in scenarios demanding real-time responsiveness. One strategy to enhance the efficiency and effectiveness of learning involves identifying and prioritizing data that enhances performance on target downstream tasks. We propose Relevance and Specificity-based online filtering framework (ReSpec) that selects data based on four criteria: (i) modality alignment for clean data, (ii) task relevance for target focused data, (iii) specificity for informative and detailed data, and (iv) efficiency for low-latency processing. Relevance is determined by the probabilistic alignment of incoming data with downstream tasks, while specificity employs the distance to a root embedding representing the least specific data as an efficient proxy for informativeness. By establishing reference points from target task data, ReSpec filters incoming data in real-time, eliminating the need for extensive storage and compute. Evaluating on large-scale datasets WebVid2M and VideoCC3M, ReSpec attains state-of-the-art performance on five zero-shot video retrieval tasks, using as little as 5% of the data while incurring minimal compute. The source code is available at https://github.com/cdjkim/ReSpec.

GUI agents powered by LLMs show promise in interacting with diverse digital environments.Among these, video games offer a valuable testbed due to their varied interfaces, with adventure games posing additional challenges through complex, narrative-driven interactions.Existing game benchmarks, however, lack diversity and rarely evaluate agents on completing entire storylines.To address this, we introduce FlashAdventure, a benchmark of 34 Flashbased adventure games designed to test full story arc completion and tackle the observationbehavior gap: the challenge of remembering and acting on earlier gameplay information.We also propose CUA-as-a-Judge, an automated gameplay evaluator, and COAST, an agentic framework leveraging long-term clue memory to better plan and solve sequential tasks.Experiments show current GUI agents struggle with full story arcs, while COAST improves milestone completion by bridging the observationbehavior gap.Nonetheless, a marked discrepancy between humans and best-performing agents warrants continued research efforts to narrow this divide. * Equal contribution. †Work done during an internship at KRAFTON. Flash-Based Adventure GamesInput GUI Agent (Operator) Gameplay

Spatial audio is essential for enhancing the immersiveness of audio-visual experiences, yet its production typically demands complex recording systems and specialized expertise. In this work, we address a novel problem of generating first-order ambisonics, a widely used spatial audio format, directly from silent videos. To support this task, we introduce YT-Ambigen, a dataset comprising 102K 5-second YouTube video clips paired with corresponding first-order ambisonics. We also propose new evaluation metrics to assess the spatial aspect of generated audio based on audio energy maps and saliency metrics. Furthermore, we present Video-to-Spatial Audio Generation (ViSAGe), an end-to-end framework that generates first-order ambisonics from silent video frames by leveraging CLIP visual features, autoregressive neural audio codec modeling with both directional and visual guidance. Experimental results demonstrate that ViSAGe produces plausible and coherent first-order ambisonics, outperforming two-stage approaches consisting of video-to-audio generation and audio spatialization. Qualitative examples further illustrate that ViSAGe generates temporally aligned high-quality spatial audio that adapts to viewpoint changes.

People continuously perceive and interact with their surroundings based on underlying intentions that drive their exploration and behaviors. While research in egocentric user and scene understanding has focused primarily on motion and contact-based interaction, forecasting human visual perception itself remains less explored despite its fundamental role in guiding human actions and its implications for AR/VR and assistive technologies. We address the challenge of egocentric 3D visual span forecasting, predicting where a person's visual perception will focus next within their three-dimensional environment. To this end, we propose EgoSpanLift, a novel method that transforms egocentric visual span forecasting from 2D image planes to 3D scenes. EgoSpanLift converts SLAM-derived keypoints into gaze-compatible geometry and extracts volumetric visual span regions. We further combine EgoSpanLift with 3D U-Net and unidirectional transformers, enabling spatio-temporal fusion to efficiently predict future visual span in the 3D grid. In addition, we curate a comprehensive benchmark from raw egocentric multisensory data, creating a testbed with 364.6K samples for 3D visual span forecasting. Our approach outperforms competitive baselines for egocentric gaze anticipation and 3D localization, while achieving comparable results even when projected back onto 2D image planes without additional 2D-specific training.

Language models are capable of commonsense reasoning: while domain-specific models can learn from explicit knowledge (e.g. commonsense graphs [6] ethical norms [25]), and larger models like GPT-3 [7] mani-fest broad commonsense reasoning capacity. Can their knowledge be extended to multimodal inputs such as images and audio without paired domain data? In this work, we propose‡ESPER (Extending Sensory PErception with Reinforcement learning) which enables text-only pretrained models to address multimodal tasks such as visual commonsense reasoning. Our key novelty is to use rein-forcement learning to align multimodal inputs to language model generations without direct supervision: for example, our reward optimization relies only on cosine similarity derived from CLIP [52] and requires no additional paired (image, text) data. Experiments demonstrate that ESPER outperforms baselines and prior work on a variety of multimodal text generation tasks ranging from captioning to commonsense reasoning; these include a new benchmark we collect and release, the ESP dataset, which tasks models with generating the text of several different domains for each image. Our code and data are publicly released at https://github.com/JiwanChung/esper.

Sound can convey significant information for spatial reasoning in our daily lives. To endow deep networks with such ability, we address the challenge of dense indoor prediction with sound in both 2D and 3D via cross-modal knowledge distillation. In this work, we propose a Spatial Alignment via Matching (SAM) distillation framework that elicits local correspondence between the two modalities in vision-to-audio knowledge transfer. SAM integrates audio features with visually coherent learnable spatial embeddings to resolve inconsistencies in multiple layers of a student model. Our approach does not rely on a specific input representation, allowing for flexibility in the input shapes or dimensions without performance degradation. With a newly curated benchmark named Dense Auditory Prediction of Surroundings (DAPS), we are the first to tackle dense indoor prediction of omnidirectional surroundings in both 2D and 3D with audio observations. Specifically, for audio-based depth estimation, semantic segmentation, and challenging 3D scene reconstruction, the proposed distillation framework consistently achieves state-of-the-art performance across various metrics and backbone architectures.

Previous models for vision-to-language generation tasks usually pretrain a visual encoder and a language generator in the respective domains and jointly finetune them with the target task. However, this direct transfer practice may suffer from the discord between visual specificity and language fluency since they are often separately trained from large corpora of visual and text data with no common ground. In this work, we claim that a transitional adaptation task is required between pretraining and finetuning to harmonize the visual encoder and the language model for challenging downstream target tasks like visual storytelling. We propose a novel approach named Transitional Adaptation of Pre-trained Model (TAPM) that adapts the multi-modal modules to each other with a simpler alignment task between visual inputs only with no need for text labels. Through extensive experiments, we show that the adaptation step significantly improves the performance of multiple language models for sequential video and image captioning tasks. We achieve new state-of-the-art performance on both language metrics and human evaluation in the multi-sentence description task of LSMDC 2019 [50] and the image storytelling task of VIST [18]. Our experiments reveal that this improvement in caption quality does not depend on the specific choice of language models.

360° videos convey holistic views for the surroundings of a scene. It provides audio-visual cues beyond predetermined normal field of views and displays distinctive spatial relations on a sphere. However, previous benchmark tasks for panoramic videos are still limited to evaluate the semantic understanding of audio-visual relationships or spherical spatial property in surroundings. We propose a novel benchmark named Pano-AVQA as a large-scale grounded audio-visual question answering dataset on panoramic videos. Using 5.4K 360° video clips harvested online, we collect two types of novel question-answer pairs with bounding-box grounding: spherical spatial relation QAs and audio-visual relation QAs. We train several transformer-based models from Pano-AVQA, where the results suggest that our proposed spherical spatial embeddings and multimodal training objectives fairly contribute to a better semantic understanding of the panoramic surroundings on the dataset.

We develop a system which generates summaries from seniors' indoor-activity videos captured by a social robot to help remote family members know their seniors' daily activities at home. Unlike the traditional video summarization datasets, indoor videos captured from a moving robot poses additional challenges, namely, (i) the video sequences are very long (ii) a significant number of videoframes contain no-subject or with subjects at ill-posed locations and scales (iii) most of the well-posed frames contain highly redundant information. To address this problem, we propose to exploit pose estimation for detecting people in frames. This guides the robot to follow the user and capture effective videos. We use person identification to distinguish a target senior from other people. We also make use of action recognition to analyze seniors' major activities at different moments, and develop a video summarization method to select diverse and representative keyframes as summaries.