Can Sound Replace Vision in LLaVA With Token Substitution?

While multimodal systems have achieved impressive advances, they typically rely on text-aligned representations rather than directly integrating audio and visual inputs. This reliance can limit the use of acoustic information in tasks requiring nuanced audio understanding. In response, SoundCLIP explores direct audio-visual integration within multimodal large language models (MLLMs) by substituting CLIP's visual tokens with audio representations and selecting sound-relevant patch tokens in models such as LLaVA. We investigate two configurations: (1) projecting audio features into CLIP's visual manifold via a multilayer perceptron trained with InfoNCE on paired audio-video segments, and (2) preserving raw audio embeddings with minimal dimensional adjustments. Experiments with five state-of-the-art audio encoders reveal a fundamental trade-off. While audio-to-video retrieval performance increases dramatically (up to 44 percentage points in Top-1 accuracy) when audio is projected into CLIP's space, text generation quality declines. Encoders pre-trained with text supervision (CLAP, Whisper, ImageBind) maintain stronger generative capabilities than those focused primarily on audiovisual alignment (Wav2CLIP, AudioCLIP), highlighting the value of language exposure for generation tasks. We introduce WhisperCLIP, an architecture that fuses intermediate representations from Whisper, as well as AudioVisual Event Evaluation (AVE-2), a dataset of 580,147 three-second audiovisual clips with fine-grained alignment annotations. Our findings challenge the assumption that stronger cross-modal alignment necessarily benefits all multimodal tasks; instead, a Pareto frontier emerges wherein optimal performance depends on balancing retrieval accuracy with text generation quality. Codes and datasets: https://github.com/ali-vosoughi/SoundCLIP.

MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness

Understanding perspective is fundamental to human visual perception, yet the extent to which multimodal large language models (MLLMs) internalize perspective geometry remains unclear. We introduce MMPerspective, the first benchmark specifically designed to systematically evaluate MLLMs' understanding of perspective through 10 carefully crafted tasks across three complementary dimensions: Perspective Perception, Reasoning, and Robustness. Our benchmark comprises 2,711 real-world and synthetic image instances with 5,083 question-answer pairs that probe key capabilities, such as vanishing point perception and counting, perspective type reasoning, line relationship understanding in 3D space, invariance to perspective-preserving transformations, etc. Through a comprehensive evaluation of 43 state-of-the-art MLLMs, we uncover significant limitations: while models demonstrate competence on surface-level perceptual tasks, they struggle with compositional reasoning and maintaining spatial consistency under perturbations. Our analysis further reveals intriguing patterns between model architecture, scale, and perspective capabilities, highlighting both robustness bottlenecks and the benefits of chain-of-thought prompting. MMPerspective establishes a valuable testbed for diagnosing and advancing spatial understanding in vision-language systems. Resources available at: https://yunlong10.github.io/MMPerspective/

$I^2G$: Generating Instructional Illustrations via Text-Conditioned Diffusion

The effective communication of procedural knowledge remains a significant challenge in natural language processing (NLP), as purely textual instructions often fail to convey complex physical actions and spatial relationships. We address this limitation by proposing a language-driven framework that translates procedural text into coherent visual instructions. Our approach models the linguistic structure of instructional content by decomposing it into goal statements and sequential steps, then conditioning visual generation on these linguistic elements. We introduce three key innovations: (1) a constituency parser-based text encoding mechanism that preserves semantic completeness even with lengthy instructions, (2) a pairwise discourse coherence model that maintains consistency across instruction sequences, and (3) a novel evaluation protocol specifically designed for procedural language-to-image alignment. Our experiments across three instructional datasets (HTStep, CaptainCook4D, and WikiAll) demonstrate that our method significantly outperforms existing baselines in generating visuals that accurately reflect the linguistic content and sequential nature of instructions. This work contributes to the growing body of research on grounding procedural language in visual content, with applications spanning education, task guidance, and multimodal language understanding.

Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting

We present CAT-V (Caption AnyThing in Video), a training-free framework for fine-grained object-centric video captioning that enables detailed descriptions of user-selected objects through time. CAT-V integrates three key components: a Segmenter based on SAMURAI for precise object segmentation across frames, a Temporal Analyzer powered by TRACE-Uni for accurate event boundary detection and temporal analysis, and a Captioner using InternVL-2.5 for generating detailed object-centric descriptions. Through spatiotemporal visual prompts and chain-of-thought reasoning, our framework generates detailed, temporally-aware descriptions of objects' attributes, actions, statuses, interactions, and environmental contexts without requiring additional training data. CAT-V supports flexible user interactions through various visual prompts (points, bounding boxes, and irregular regions) and maintains temporal sensitivity by tracking object states and interactions across different time segments. Our approach addresses limitations of existing video captioning methods, which either produce overly abstract descriptions or lack object-level precision, enabling fine-grained, object-specific descriptions while maintaining temporal coherence and spatial accuracy. The GitHub repository for this project is available at https://github.com/yunlong10/CAT-V

VERIFY: A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelity

Visual reasoning is central to human cognition, enabling individuals to interpret and abstractly understand their environment. Although recent Multimodal Large Language Models (MLLMs) have demonstrated impressive performance across language and vision-language tasks, existing benchmarks primarily measure recognition-based skills and inadequately assess true visual reasoning capabilities. To bridge this critical gap, we introduce VERIFY, a benchmark explicitly designed to isolate and rigorously evaluate the visual reasoning capabilities of state-of-the-art MLLMs. VERIFY compels models to reason primarily from visual information, providing minimal textual context to reduce reliance on domain-specific knowledge and linguistic biases. Each problem is accompanied by a human-annotated reasoning path, making it the first to provide in-depth evaluation of model decision-making processes. Additionally, we propose novel metrics that assess visual reasoning fidelity beyond mere accuracy, highlighting critical imbalances in current model reasoning patterns. Our comprehensive benchmarking of leading MLLMs uncovers significant limitations, underscoring the need for a balanced and holistic approach to both perception and reasoning. For more teaser and testing, visit our project page (https://verify-eqh.pages.dev/).

Quality Over Quantity? LLM-Based Curation for a Data-Efficient Audio-Video Foundation Model

Integrating audio and visual data for training multimodal foundational models remains challenging. We present Audio-Video Vector Alignment (AVVA), which aligns audiovisual (AV) scene content beyond mere temporal synchronization via a Large Language Model (LLM)-based data curation pipeline. Specifically, AVVA scores and selects high-quality training clips using Whisper (speech-based audio foundation model) for audio and DINOv2 for video within a dual-encoder contrastive learning framework. Evaluations on AudioCaps, VALOR, and VGGSound demonstrate that this approach can achieve significant accuracy gains with substantially less curated data. For instance, AVVA yields a 7.6% improvement in top-1 accuracy for audio-to-video retrieval on VGGSound compared to ImageBind, despite training on only 192 hours of carefully filtered data (vs. 5800+ hours). Moreover, an ablation study highlights that trading data quantity for data quality improves performance, yielding respective top-3 accuracy increases of 47.8, 48.4, and 58.0 percentage points on AudioCaps, VALOR, and VGGSound over uncurated baselines. While these results underscore AVVA's data efficiency, we also discuss the overhead of LLM-driven curation and how it may be scaled or approximated in larger domains. Overall, AVVA provides a viable path toward more robust, text-free audiovisual learning with improved retrieval accuracy.

Enhancing Graph Attention Neural Network Performance for Marijuana Consumption Classification through Large-scale Augmented Granger Causality (lsAGC) Analysis of Functional MR Images

In the present research, the effectiveness of large-scale Augmented Granger Causality (lsAGC) as a tool for gauging brain network connectivity was examined to differentiate between marijuana users and typical controls by utilizing resting-state functional Magnetic Resonance Imaging (fMRI). The relationship between marijuana consumption and alterations in brain network connectivity is a recognized fact in scientific literature. This study probes how lsAGC can accurately discern these changes. The technique used integrates dimension reduction with the augmentation of source time-series in a model that predicts time-series, which helps in estimating the directed causal relationships among fMRI time-series. As a multivariate approach, lsAGC uncovers the connection of the inherent dynamic system while considering all other time-series. A dataset of 60 adults with an ADHD diagnosis during childhood, drawn from the Addiction Connectome Preprocessed Initiative (ACPI), was used in the study. The brain connections assessed by lsAGC were utilized as classification attributes. A Graph Attention Neural Network (GAT) was chosen to carry out the classification task, particularly for its ability to harness graph-based data and recognize intricate interactions between brain regions, making it appropriate for fMRI-based brain connectivity data. The performance was analyzed using a five-fold cross-validation system. The average accuracy achieved by the correlation coefficient method was roughly 52.98%, with a 1.65 standard deviation, whereas the lsAGC approach yielded an average accuracy of 61.47%, with a standard deviation of 1.44. The suggested method enhances the body of knowledge in the field of neuroimaging-based classification and emphasizes the necessity to consider directed causal connections in brain network connectivity analysis when studying marijuana's effects on the brain.

EAGLE: Egocentric AGgregated Language-video Engine

The rapid evolution of egocentric video analysis brings new insights into understanding human activities and intentions from a first-person perspective. Despite this progress, the fragmentation in tasks like action recognition, procedure learning, and moment retrieval, \etc, coupled with inconsistent annotations and isolated model development, hinders a holistic interpretation of video content. In response, we introduce the EAGLE (Egocentric AGgregated Language-video Engine) model and the EAGLE-400K dataset to provide a unified framework that integrates various egocentric video understanding tasks. EAGLE-400K, the \textit{first} large-scale instruction-tuning dataset tailored for egocentric video, features 400K diverse samples to enhance a broad spectrum of tasks from activity recognition to procedure knowledge learning. Moreover, EAGLE, a strong video multimodal large language model (MLLM), is designed to effectively capture both spatial and temporal information. In addition, we propose a set of evaluation metrics designed to facilitate a thorough assessment of MLLM for egocentric video understanding. Our extensive experiments demonstrate EAGLE's superior performance over existing models, highlighting its ability to balance task-specific understanding with holistic video interpretation. With EAGLE, we aim to pave the way for research opportunities and practical applications in real-world scenarios.

OSCaR: Object State Captioning and State Change Representation

The capability of intelligent models to extrapolate and comprehend changes in object states is a crucial yet demanding aspect of AI research, particularly through the lens of human interaction in real-world settings. This task involves describing complex visual environments, identifying active objects, and interpreting their changes as conveyed through language. Traditional methods, which isolate object captioning and state change detection, offer a limited view of dynamic environments. Moreover, relying on a small set of symbolic words to represent changes has restricted the expressiveness of language. To address these challenges, in this paper, we introduce the Object State Captioning and State Change Representation (OSCaR) dataset and benchmark. OSCaR consists of 14,084 annotated video segments with nearly 1,000 unique objects from various egocentric video collections. It sets a new testbed for evaluating multimodal large language models (MLLMs). Our experiments demonstrate that while MLLMs show some skill, they lack a full understanding of object state changes. The benchmark includes a fine-tuned model that, despite initial capabilities, requires significant improvements in accuracy and generalization ability for effective understanding of these changes. Our code and dataset are available at https://github.com/nguyennm1024/OSCaR.

Learning Audio Concepts from Counterfactual Natural Language

Conventional audio classification relied on predefined classes, lacking the ability to learn from free-form text. Recent methods unlock learning joint audio-text embeddings from raw audio-text pairs describing audio in natural language. Despite recent advancements, there is little exploration of systematic methods to train models for recognizing sound events and sources in alternative scenarios, such as distinguishing fireworks from gunshots at outdoor events in similar situations. This study introduces causal reasoning and counterfactual analysis in the audio domain. We use counterfactual instances and include them in our model across different aspects. Our model considers acoustic characteristics and sound source information from human-annotated reference texts. To validate the effectiveness of our model, we conducted pre-training utilizing multiple audio captioning datasets. We then evaluate with several common downstream tasks, demonstrating the merits of the proposed method as one of the first works leveraging counterfactual information in audio domain. Specifically, the top-1 accuracy in open-ended language-based audio retrieval task increased by more than 43%.