Related papers: Atom: Efficient On-Device Video-Language Pipelines…
On-device Deep Neural Network (DNN) training has been recognized as crucial for privacy-preserving machine learning at the edge. However, the intensive training workload and limited onboard computing resources pose significant challenges to…
Large Language Models (LLMs) stand out for their impressive performance in intricate language modeling tasks. However, their demanding computational and memory needs pose obstacles for broad use on edge devices. Quantization is then…
Recently, text-to-motion models have opened new possibilities for creating realistic human motion with greater efficiency and flexibility. However, aligning motion generation with event-level textual descriptions presents unique challenges…
Performing Retrieval-Augmented Generation (RAG) directly on mobile devices is promising for data privacy and responsiveness but is hindered by the architectural constraints of mobile NPUs. Specifically, current hardware struggles with the…
We present Liquid, an auto-regressive generation paradigm that seamlessly integrates visual comprehension and generation by tokenizing images into discrete codes and learning these code embeddings alongside text tokens within a shared…
The goal in episodic memory (EM) is to search a long egocentric video to answer a natural language query (e.g., "where did I leave my purse?"). Existing EM methods exhaustively extract expensive fixed-length clip features to look everywhere…
The ability to quickly and accurately compute properties from atomic simulations is critical for advancing a large number of applications in chemistry and materials science including drug discovery, energy storage, and semiconductor…
The explosive growth of video streaming presents challenges in achieving high accuracy and low training costs for video-language retrieval. However, existing methods rely on large-scale pre-training to improve video retrieval performance,…
Open-vocabulary semantic segmentation (OVSS) is fundamentally hampered by the coarse, image-level representations of CLIP, which lack precise pixel-level details. Existing training-free methods attempt to resolve this by either importing…
Recent advances in video captioning are driven by large-scale pretrained models, which follow the standard "pre-training followed by fine-tuning" paradigm, where the full model is fine-tuned for downstream tasks. Although effective, this…
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…
This paper addresses the challenges of Online Action Recognition (OAR), a framework that involves instantaneous analysis and classification of behaviors in video streams. OAR must operate under stringent latency constraints, making it an…
Augmented Language Models (ALMs) blend the reasoning capabilities of Large Language Models (LLMs) with tools that allow for knowledge retrieval and action execution. Existing ALM systems trigger LLM thought processes while pulling…
Recent image restoration methods have produced significant advancements using deep learning. However, existing methods tend to treat the whole image as a single entity, failing to account for the distinct objects in the image that exhibit…
Video-and-language understanding has a variety of applications in the industry, such as video question answering, text-video retrieval, and multi-label classification. Existing video-and-language understanding methods generally adopt heavy…
We introduce OmChat, a model designed to excel in handling long contexts and video understanding tasks. OmChat's new architecture standardizes how different visual inputs are processed, making it more efficient and adaptable. It uses a…
Universal video understanding requires modeling fine-grained visual and audio information over time in diverse real-world scenarios. However, the performance of existing models is primarily constrained by video-instruction data that…
Recent transformer-based architectures have shown impressive results in the field of image segmentation. Thanks to their flexibility, they obtain outstanding performance in multiple segmentation tasks, such as semantic and panoptic, under a…
Embodied Chain-of-Thought (ECoT) reasoning enhances vision-language-action (VLA) models by improving performance and interpretability through intermediate reasoning steps. However, its sequential autoregressive token generation introduces…
Fine-grained video action recognition can be conceptualized as a video-text matching problem. Previous approaches often rely on global video semantics to consolidate video embeddings, which can lead to misalignment in video-text pairs due…