Related papers: X-MIC: Cross-Modal Instance Conditioning for Egoce…

Vision Language Models (VLMs) encode multimodal inputs over large, complex, and difficult-to-interpret architectures, which limit transparency and trust. We propose a Multimodal Inversion for Model Interpretation and Conceptualization…

This paper introduces our solution, XM-ALIGN (Unified Cross-Modal Embedding Alignment Framework), proposed for the FAME challenge at ICASSP 2026. Our framework combines explicit and implicit alignment mechanisms, significantly improving…

Given a gallery of uncaptioned video sequences, this paper considers the task of retrieving videos based on their relevance to an unseen text query. To compensate for the lack of annotations, we rely instead on a related video gallery…

Vision-language models (VLMs) are capable of recognizing unseen actions. However, existing VLMs lack intrinsic understanding of procedural action concepts. Hence, they overfit to fixed labels and are not invariant to unseen action synonyms.…

We explore leveraging large multi-modal models (LMMs) and text2image models to build a more general embodied agent. LMMs excel in planning long-horizon tasks over symbolic abstractions but struggle with grounding in the physical world,…

We introduce X-VILA, an omni-modality model designed to extend the capabilities of large language models (LLMs) by incorporating image, video, and audio modalities. By aligning modality-specific encoders with LLM inputs and diffusion…

Robotic arm manipulation in data-scarce settings is a highly challenging task due to the complex embodiment dynamics and diverse contexts. Recent video-based approaches have shown great promise in capturing and transferring the temporal and…

Vision-language models (VLMs) have shown powerful capabilities in visual question answering and reasoning tasks by combining visual representations with the abstract skill set large language models (LLMs) learn during pretraining. Vision,…

Can Video-LLMs achieve consistent temporal understanding when videos capture the same event from different viewpoints? To study this, we introduce EgoExo-Con (Consistency), a benchmark of comprehensively synchronized egocentric and…

From Vision-Language-Action (VLA) systems to robotics, existing egocentric datasets primarily focus on action recognition tasks, while largely overlooking the inherent role of motion analysis in sports and other fast-movement scenarios. To…

Current pre-trained vison-language models (PVLMs) achieve excellent performance on a range of multi-modal datasets. Recent work has aimed at building multilingual models, and a range of novel multilingual multi-modal datasets have been…

Egocentric video-language pretraining is a crucial step in advancing the understanding of hand-object interactions in first-person scenarios. Despite successes on existing testbeds, we find that current EgoVLMs can be easily misled by…

Leveraging the effective visual-text alignment and static generalizability from CLIP, recent video learners adopt CLIP initialization with further regularization or recombination for generalization in open-vocabulary action recognition…

This research aims to comprehensively explore building a multimodal foundation model for egocentric video understanding. To achieve this goal, we work on three fronts. First, as there is a lack of QA data for egocentric video understanding,…

Understanding fine-grained temporal dynamics is crucial in egocentric videos, where continuous streams capture frequent, close-up interactions with objects. In this work, we bring to light that current egocentric video question-answering…

Multimodal learning plays a critical role in e-commerce recommendation platforms today, enabling accurate recommendations and product understanding. However, existing vision-language models, such as CLIP, face key challenges in e-commerce…

This paper proposes Video-Teller, a video-language foundation model that leverages multi-modal fusion and fine-grained modality alignment to significantly enhance the video-to-text generation task. Video-Teller boosts the training…

CLIP has demonstrated strong generalization in visual domains through natural language supervision, even for video action recognition. However, most existing approaches that adapt CLIP for action recognition have primarily focused on…

Utilizing vision and language models (VLMs) pre-trained on large-scale image-text pairs is becoming a promising paradigm for open-vocabulary visual recognition. In this work, we extend this paradigm by leveraging motion and audio that…

Understanding egocentric videos plays a vital role for embodied intelligence. Recent multi-modal large language models (MLLMs) can accept both visual and audio inputs. However, due to the challenge of obtaining text labels with coherent…