Out of distribution (OOD) robustness in autonomous driving is often reduced to a single number, hiding what breaks a policy. We decompose environments along fiv...
Reconstructing a structured vector-graphics representation from a rasterized floorplan image is typically an important prerequisite for computational tasks invo...
Multi-finger robotic hand manipulation and grasping are challenging due to the high-dimensional action space and the difficulty of acquiring large-scale trainin...
Recent advancements in image generation models have enabled the prediction of future Graphical User Interface (GUI) states based on user instructions. However, ...
While world models have emerged as a cornerstone of embodied intelligence by enabling agents to reason about environmental dynamics through action-conditioned p...
markdown !VSSFlow demo imagehttps://9to5mac.com/wp-content/uploads/sites/6/2026/02/vssflow-fi.jpg?quality=82&strip=all&w=1600 VSSFlow – A Unified Audio Generati...
O Que Eu Fiz e Por Quê Neste trabalho eu exercitei a criação de um processo de reconhecimento de imagens usando duas abordagens diferentes de inteligência arti...
Overview Finding tiny objects in images is challenging because they occupy only a few pixels and can be missed by methods that expect larger shapes. Traditiona...
Chain-of-Thought reasoning is widely used to improve the interpretability of multimodal large language models (MLLMs), yet the faithfulness of the generated rea...
Overview FlappyHand is a hands‑free interactive game inspired by the classic Flappy Bird. The character is controlled using hand gestures captured by your webc...
Multimodal large language models (MLLMs) have rapidly advanced, yet their adoption in medicine remains limited by gaps in domain coverage, modality alignment, a...
Cinematic video production requires control over scene-subject composition and camera movement, but live-action shooting remains costly due to the need for cons...
Being able to simulate the outcomes of actions in varied environments will revolutionize the development of generalist agents at scale. However, modeling these ...
The classification performance of deep neural networks relies strongly on access to large, accurately annotated datasets. In medical imaging, however, obtaining...
Vision capabilities in vision large language models (VLLMs) have consistently lagged behind their linguistic capabilities. In particular, numerous benchmark stu...
Fully unsupervised segmentation pipelines naively seek the most salient object, should this be present. As a result, most of the methods reported in the literat...
Multimodal Diffusion Transformers (MMDiTs) for text-to-image generation maintain separate text and image branches, with bidirectional information flow between t...
The smoothness of the transformer architecture has been extensively studied in the context of generalization, training stability, and adversarial robustness. Ho...
While large-scale text-to-image diffusion models continue to improve in visual quality, their increasing scale has widened the gap between state-of-the-art mode...
Instructional video editing applies edits to an input video using only text prompts, enabling intuitive natural-language control. Despite rapid progress, most m...
Insect vision supports complex behaviors including associative learning, navigation, and object detection, and has long motivated computational models for under...
The Moore-Penrose Pseudo-inverse (PInv) serves as the fundamental solution for linear systems. In this paper, we propose a natural generalization of PInv to the...
Adapting large pretrained models to new tasks efficiently and continually is crucial for real-world deployment but remains challenging due to catastrophic forge...
Multi-image spatial reasoning remains challenging for current multimodal large language models (MLLMs). While single-view perception is inherently 2D, reasoning...
Multimodal Large Language Models (MLLMs) have made remarkable progress in multimodal perception and reasoning by bridging vision and language. However, most exi...
To complete assignments provided by humans in natural language, robots must interpret commands, generate and answer relevant questions for scene understanding, ...
Recent progress in spatial reasoning with Multimodal Large Language Models (MLLMs) increasingly leverages geometric priors from 3D encoders. However, most exist...
Humans rarely plan whole-body interactions with objects at the level of explicit whole-body movements. High-level intentions, such as affordance, define the goa...
Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improves candidate...
Vision Foundation Models (VFMs) have achieved remarkable success when applied to various downstream 2D tasks. Despite their effectiveness, they often exhibit a ...
Recent approaches to real-time long video generation typically employ streaming tuning strategies, attempting to train a long-context student using a short-cont...
The rapid advancement of visual generation models has outpaced traditional evaluation approaches, necessitating the adoption of Vision-Language Models as surrog...
Lingo‑Live started with a frustration many of us have felt: trying to copy text from a YouTube video or any on‑screen content is impossible. Most of us end up e...
In this paper, we present a neuro-inspired approach to reservoir computing (RC) in which a network of in vitro cultured cortical neurons serves as the physical ...
Post-training with Reinforcement Learning (RL) has substantially improved reasoning in Large Language Models (LLMs) via test-time scaling. However, extending th...
Dense point tracking is a fundamental problem in computer vision, with applications ranging from video analysis to robotic manipulation. State-of-the-art tracke...
We introduce PerpetualWonder, a hybrid generative simulator that enables long-horizon, action-conditioned 4D scene generation from a single image. Current works...
Recent work has shown that diffusion models can generate high-quality images by operating directly on SSL patch features rather than pixel-space latents. Howeve...
Current autoregressive Vision Language Models (VLMs) usually rely on a large number of visual tokens to represent images, resulting in a need for more compute e...
Pose and motion priors play a crucial role in humanoid robotics. Although such priors have been widely studied in human motion recovery (HMR) domain with a rang...
With the advancement of 3D scanning technologies, point clouds have become fundamental for representing 3D spatial data, with applications that span across vari...
Our theoretical understanding of neural networks is lagging behind their empirical success. One of the important unexplained phenomena is why and how, during th...
Human nail diseases are gradually observed over all age groups, especially among older individuals, often going ignored until they become severe. Early detectio...
Accurate risk stratification of precancerous polyps during routine colonoscopy screenings is essential for lowering the risk of developing colorectal cancer (CR...
Event cameras offer a considerable alternative to RGB cameras in many scenarios. While there are recent works on event-based novel-view synthesis, dense 3D mesh...
In pre-production, filmmakers and 3D animation experts must rapidly prototype ideas to explore a film's possibilities before fullscale production, yet conventio...
High-quality scientific illustrations are crucial for effectively communicating complex scientific and technical concepts, yet their manual creation remains a w...
Diffusion-based editing models have emerged as a powerful tool for semantic image and video manipulation. However, existing models lack a mechanism for smoothly...
