相关论文: When and What: Diffusion-Grounded VideoLLM with En…
Recent advancements in Large Language Models (LLMs) have expanded their capabilities to multimodal contexts, including comprehensive video understanding. However, processing extensive videos such as 24-hour CCTV footage or full-length films…
Diffusion large language models (dLLMs) are emerging as promising alternatives to autoregressive (AR) LLMs. Recently, this paradigm has been extended to multimodal tasks, leading to the development of diffusion multimodal large language…
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…
Multimodal large language models (MLLMs) have achieved remarkable progress in video understanding. However, seemingly plausible outputs often suffer from poor visual and temporal grounding: a model may fabricate object existence, assign…
Latent Action Models (LAMs) enable the learning of world models from unlabeled video by inferring abstract actions between consecutive frames. However, LAMs face a fundamental trade-off between action abstraction and generation fidelity.…
Recent Video Large Language Models (Video-LLMs) have shown strong multimodal reasoning capabilities, yet remain challenged by video understanding tasks that require consistent temporal ordering and causal coherence. Many parameter-efficient…
Video Temporal Grounding (VTG) aims to extract relevant video segments based on a given natural language query. Recently, zero-shot VTG methods have gained attention by leveraging pretrained vision-language models (VLMs) to localize target…
Recent advancements in text-to-image diffusion models have yielded impressive results in generating realistic and diverse images. However, these models still struggle with complex prompts, such as those that involve numeracy and spatial…
Accurately estimating task progress is critical for embodied agents to plan and execute long-horizon, multi-step tasks. Despite promising advances, existing Vision-Language Models (VLMs) based methods primarily leverage their video…
As the development of large-scale Generative AI models evolve beyond text (1D) generation to include image (2D) and video (3D) generation, processing spatial and temporal information presents unique challenges to quality, performance, and…
What makes a video task uniquely suited for videos, beyond what can be understood from a single image? Building on recent progress in self-supervised image-language models, we revisit this question in the context of video and language…
We propose a novel framework for open-ended video question answering that enhances reasoning depth and robustness in complex real-world scenarios, as benchmarked on the CVRR-ES dataset. Existing Video-Large Multimodal Models (Video-LMMs)…
Recent advances in multimodal large language models (MLLMs) have enabled image-based question-answering capabilities. However, a key limitation is the use of CLIP as the visual encoder; while it can capture coarse global information, it…
The remarkable progress in text-to-video diffusion models enables the generation of photorealistic videos, although the content of these generated videos often includes unnatural movement or deformation, reverse playback, and motionless…
Video Temporal Grounding (VTG), the task of localizing video segments from text queries, struggles in open-world settings due to limited dataset scale and semantic diversity, causing performance gaps between common and rare concepts. To…
Large language models (LLMs) have demonstrated exceptional capabilities in text understanding, which has paved the way for their expansion into video LLMs (Vid-LLMs) to analyze video data. However, current Vid-LLMs struggle to…
The integration of Large Language Models (LLMs) with visual encoders has recently shown promising performance in visual understanding tasks, leveraging their inherent capability to comprehend and generate human-like text for visual…
Logit Lens is a widely adopted method for mechanistic interpretability of transformer-based language models, enabling the analysis of how internal representations evolve across layers by projecting them into the output vocabulary space.…
Leveraging the generative ability of image diffusion models offers great potential for zero-shot video-to-video translation. The key lies in how to maintain temporal consistency across generated video frames by image diffusion models.…
Video-and-language pre-training has shown promising improvements on various downstream tasks. Most previous methods capture cross-modal interactions with a transformer-based multimodal encoder, not fully addressing the misalignment between…