相关论文: Stitch and Tell: A Structured Multimodal Data Augm…

Text-to-image synthesis has achieved high-quality results with recent advances in diffusion models. However, text input alone has high spatial ambiguity and limited user controllability. Most existing methods allow spatial control through…

Spatial intelligence is crucial for vision--language models (VLMs) in the physical world, yet many benchmarks evaluate largely unconstrained scenes where models can exploit 2D shortcuts. We introduce SSI-Bench, a VQA benchmark for spatial…

Vision-language models (VLMs) enable open-ended visual question answering but remain prone to hallucinations. We present HEDGE, a unified framework for hallucination detection that combines controlled visual perturbations, semantic…

Dynamic urban environments are often captured by cameras placed at spatially separated locations with little or no view overlap. However, most existing 4D reconstruction methods assume densely overlapping views. When applied to such sparse…

Vision-Language Models (VLMs) have made significant strides in static image understanding but continue to face critical hurdles in spatiotemporal reasoning. A major bottleneck is "multi-image reasoning hallucination", where a massive…

Visual Spatial Description (VSD) aims to generate texts that describe the spatial relationships between objects within images. Traditional visual spatial relationship classification (VSRC) methods typically output the spatial relationship…

We introduce SEE&TREK, the first training-free prompting framework tailored to enhance the spatial understanding of Multimodal Large Language Models (MLLMS) under vision-only constraints. While prior efforts have incorporated modalities…

Image steganography is the technique of embedding secret information within images. The development of deep learning has led to significant advances in this field. However, existing methods often struggle to balance image quality, embedding…

The recent surge of foundation models in computer vision and natural language processing opens up perspectives in utilizing multi-modal clinical data to train large models with strong generalizability. Yet pathological image datasets often…

Visual Text-to-Speech (VTTS) aims to take the environmental image as the prompt to synthesize the reverberant speech for the spoken content. The challenge of this task lies in understanding the spatial environment from the image. Many…

Modeling visual data as tokens (i.e., image patches) using attention mechanisms, feed-forward networks or convolutions has been highly effective in recent years. Such methods usually have a common pipeline: a tokenization method, followed…

Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to navigate unknown, continuous spaces based on natural language instructions. Compared to discrete settings, VLN-CE poses two core perception challenges.…

Existing audio-driven visual dubbing methods have achieved great success. Despite this, we observe that the semantic ambiguity between spatial and temporal domains significantly degrades the synthesis stability for the dynamic faces. We…

Vision-language models (VLMs) achieve strong performance on spatial reasoning benchmarks, yet it remains unclear whether this reflects structured 3D understanding or reliance on statistical shortcuts in natural images. We introduce a…

Recent advances in language model interpretability using sparse autoencoders (SAEs) have yet to effectively translate to the visual domain, mainly due to the difficulty and ambiguity of labeling visual concepts. In this paper, we introduce…

Large Language Models (LLMs) falter in multi-step interactions -- often hallucinating, repeating actions, or misinterpreting user corrections -- due to reliance on linear, unstructured context. This fragility stems from the lack of…

While many text-to-audio systems produce monophonic or fixed-stereo outputs, generating audio with user-defined spatial properties remains a challenge. Existing deep learning-based spatialization methods often rely on latent-space…

Spatial reasoning -- the ability to perceive and reason about relationships in space -- advances vision-language models (VLMs) from visual perception toward spatial semantic understanding. Existing approaches either revisit local image…

Deep learning relies heavily on data augmentation to mitigate limited data, especially in medical imaging. Recent multimodal learning integrates text and images for segmentation, known as referring or text-guided image segmentation.…

Vision language models (VLMs) are increasingly capable of reasoning over images, but robust visual reasoning often requires re-grounding intermediate steps in the underlying visual evidence. Recent approaches typically rely on external…