Related papers: Funny-Valen-Tine: Planning Solution Distribution E…

Vision transformers (ViTs) have emerged as a prevalent architecture for vision tasks owing to their impressive performance. However, when it comes to handling long token sequences, especially in dense prediction tasks that require…

Protein-ligand scoring is an important step in a structure-based drug design pipeline. Selecting a correct binding pose and predicting the binding affinity of a protein-ligand complex enables effective virtual screening. Machine learning…

Human visual reasoning is characterized by an ability to identify abstract patterns from only a small number of examples, and to systematically generalize those patterns to novel inputs. This capacity depends in large part on our ability to…

Recent research has made the surprising finding that state-of-the-art deep learning models sometimes fail to generalize to small variations of the input. Adversarial training has been shown to be an effective approach to overcome this…

Visual transformation reasoning (VTR) is a vital cognitive capability that empowers intelligent agents to understand dynamic scenes, model causal relationships, and predict future states, and thereby guiding actions and laying the…

Continual learning (CL) with long-tailed data distributions remains a critical challenge for real-world AI systems, where models must sequentially adapt to new classes while retaining knowledge of old ones, despite severe class imbalance.…

"Thinking in pictures," [1] i.e., spatial-temporal reasoning, effortless and instantaneous for humans, is believed to be a significant ability to perform logical induction and a crucial factor in the intellectual history of technology…

While multi-modal Visual Language Models (VLMs) have demonstrated significant success across various domains, the integration of VLMs into recommendation and retrieval systems remains a challenge, due to issues like training objective…

Visual In-Context Learning (VICL) enables adaptively solving vision tasks by leveraging pixel demonstrations, mimicking human-like task completion through analogy. Prompt selection is critical in VICL, but current methods assume the…

Vision-Language Models (VLMs), such as CLIP, exhibit strong image-text comprehension abilities, facilitating advances in several downstream tasks such as zero-shot image classification, image-text retrieval, and text-to-image generation.…

Humans possess multimodal literacy, allowing them to actively integrate information from various modalities to form reasoning. Faced with challenges like lexical ambiguity in text, we supplement this with other modalities, such as thumbnail…

Image-text matching has been a hot research topic bridging the vision and language areas. It remains challenging because the current representation of image usually lacks global semantic concepts as in its corresponding text caption. To…

Recent strides in multimodal large language models (MLLMs) have significantly advanced their performance in many reasoning tasks. However, Abstract Visual Reasoning (AVR) remains a critical challenge, primarily due to limitations in…

In language reasoning, longer chains of thought consistently yield better performance, which naturally suggests that visual latent reasoning may likewise benefit from longer latent sequences. However, we discover a counterintuitive…

Long-context reasoning has significantly empowered large language models (LLMs) to tackle complex tasks, yet it introduces severe efficiency bottlenecks due to the computational complexity. Existing efficient approaches often rely on…

This work introduces VERSE, a methodology for analyzing and improving Vision-Language Models applied to Visually-rich Document Understanding by exploring their visual embedding space. VERSE enables the visualization of latent…

Convolutional neural networks (CNNs) define the current state-of-the-art for image recognition. With their emerging popularity, especially for critical applications like medical image analysis or self-driving cars, confirmability is…

Reinforcement learning (RL) with verifiable rewards has become a standard post-training stage for boosting visual reasoning in vision-language models, yet it remains unclear what capabilities RL actually improves compared with supervised…

Despite significant progress in Visual-Language-Action (VLA), in highly complex and dynamic environments that involve real-time unpredictable interactions (such as 3D open worlds and large-scale PvP games), existing approaches remain…

While deep learning has led to huge progress in complex image classification tasks like ImageNet, unexpected failure modes, e.g. via spurious features, call into question how reliably these classifiers work in the wild. Furthermore, for…