Related papers: 3D-Aware Vision-Language Models Fine-Tuning with G…

Medical vision-language models (Med-VLMs) have shown impressive results in tasks such as report generation and visual question answering, but they still face several limitations. Most notably, they underutilize patient metadata and lack…

Effectively understanding urban scenes requires fine-grained spatial reasoning about objects, layouts, and depth cues. However, how well current vision-language models (VLMs), pretrained on general scenes, transfer these abilities to urban…

Large Vision Language Models (LVLMs) have shown strong capabilities in understanding and analyzing visual scenes across various domains. However, in the context of autonomous driving, their limited comprehension of 3D environments restricts…

Large-scale Vision-Language Models (VLMs) encode rich multimodal semantics that are highly beneficial for fine-grained visual categorization (FGVC). However, their prohibitive computational cost hinders practical deployment in…

Vision-language models (VLMs) exhibit a striking paradox: they can generate executable code that reconstructs a 3D scene from geometric primitives with correct object counts, classes, and approximate positions, yet the same models fail at…

Vision-Language Models (VLMs) have demonstrated strong performance on multimodal reasoning tasks, but their deployment remains challenging due to high inference latency and computational cost, particularly when processing high-resolution…

In recent times, the standard practice for developing MLLMs is to feed features from vision encoder(s) into the LLM and train with natural language supervision. This approach often causes models to lean towards language comprehension and…

Vision language models (VLMs) have shown remarkable capabilities in integrating linguistic and visual reasoning but remain fundamentally limited in understanding dynamic spatiotemporal interactions. Humans effortlessly track and reason…

Vision language models (VLM) have demonstrated remarkable performance across various downstream tasks. However, understanding fine-grained visual-linguistic concepts, such as attributes and inter-object relationships, remains a significant…

Vision-Language-Action (VLA) models have emerged as a promising framework for enabling generalist robots capable of perceiving, reasoning, and acting in the real world. These models usually build upon pretrained Vision-Language Models…

Aligning visual features with language embeddings is a key challenge in vision-language models (VLMs). The performance of such models hinges on having a good connector that maps visual features generated by a vision encoder to a shared…

We present a practical distillation approach to fine-tune LLMs for invoking tools in real-time applications. We focus on visual editing tasks; specifically, we modify images and videos by interpreting user stylistic requests, specified in…

Detecting 3D objects from multi-view images is a fundamental problem in 3D computer vision. Recently, significant breakthrough has been made in multi-view 3D detection tasks. However, the unprecedented detection performance of these vision…

While vision language models (VLMs) excel in 2D semantic visual understanding, their ability to quantitatively reason about 3D spatial relationships remains under-explored, due to the deficiency of 2D images' spatial representation ability.…

Semantic distillation in radiance fields has spurred significant advances in open-vocabulary robot policies, e.g., in manipulation and navigation, founded on pretrained semantics from large vision models. While prior work has demonstrated…

Understanding and reasoning about spatial relationships is a fundamental capability for Visual Question Answering (VQA) and robotics. While Vision Language Models (VLM) have demonstrated remarkable performance in certain VQA benchmarks,…

Understanding visually situated language requires interpreting complex layouts of textual and visual elements. Pre-processing tools, such as optical character recognition (OCR), can map document image inputs to textual tokens, then large…

Existing 3D reconstruction methods utilize guidances such as 2D images, 3D point clouds, shape contours and single semantics to recover the 3D surface, which limits the creative exploration of 3D modeling. In this paper, we propose a novel…

Score distillation sampling (SDS), the methodology in which the score from pretrained 2D diffusion models is distilled into 3D representation, has recently brought significant advancements in text-to-3D generation task. However, this…

Large Foundation Models like Dust3r can produce high quality outputs such as pointmaps, camera intrinsics, and depth estimation, given stereo-image pairs as input. However, the application of these outputs on tasks like Visual Localization…