Search Results for author:
Found 10 papers, 6 papers with code
Clapper: Compact Learning and Video Representation in VLMs
Designing VLMs for video inputs requires effectively modeling the temporal dimension (i. e. capturing dependencies across frames) and balancing the processing of short and long videos.
MatterTune: An Integrated, User-Friendly Platform for Fine-Tuning Atomistic Foundation Models to Accelerate Materials Simulation and Discovery
Conversely, this also results in high data requirements for these models, hindering their application to problems which are data sparse which are common in this domain.
Pix2Cap-COCO: Advancing Visual Comprehension via Pixel-Level Captioning
The experimental results demonstrate that Pix2Cap-COCO is a particularly challenging dataset, as it requires models to excel in both fine-grained visual understanding and detailed language generation.
FOCUS: Towards Universal Foreground Segmentation
Foreground segmentation is a fundamental task in computer vision, encompassing various subdivision tasks.
Ranked #1 on
Salient Object Detection
on PASCAL-S
Focus Anywhere for Fine-grained Multi-page Document Understanding
Modern LVLMs still struggle to achieve fine-grained document understanding, such as OCR/translation/caption for regions of interest to the user, tasks that require the context of the entire page, or even multiple pages.
OneChart: Purify the Chart Structural Extraction via One Auxiliary Token
To address this, we propose OneChart: a reliable agent specifically devised for the structural extraction of chart information.
Small Language Model Meets with Reinforced Vision Vocabulary
In Vary-toy, we introduce an improved vision vocabulary, allowing the model to not only possess all features of Vary but also gather more generality.
Ranked #213 on
Visual Question Answering
on MM-Vet
Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models
Accordingly, we propose Vary, an efficient and effective method to scale up the vision vocabulary of LVLMs.
Ranked #148 on
Visual Question Answering
on MM-Vet
Merlin:Empowering Multimodal LLMs with Foresight Minds
Then, FIT requires MLLMs to first predict trajectories of related objects and then reason about potential future events based on them.
Ranked #164 on
Visual Question Answering
on MM-Vet
