Related papers: DataEvolver: Let Your Data Build and Improve Itsel…

End-to-end autonomous driving has received increasing attention due to its potential to learn from large amounts of data. However, most existing methods are still open-loop and suffer from weak scalability, lack of high-order interactions,…

Agent-based editing models have substantially advanced interactive experiences, processing quality, and creative flexibility. However, two critical challenges persist: (1) instruction hallucination, text-only chain-of-thought (CoT)…

Large language models are transforming systems research by automating the discovery of performance-critical algorithms for computer systems. Despite plausible codes generated by LLMs, producing solutions that meet the stringent correctness…

Long-horizon robotic manipulation remains challenging for Vision-Language-Action (VLA) models despite recent progress in zero-shot generalization and simulation-to-real-world transfer. Current VLA models suffer from stage hallucination,…

Reinforcement learning for LLM agents is typically conducted on a static data distribution, which fails to adapt to the agent's evolving behavior and leads to poor coverage of complex environment interactions. To address these challenges,…

Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving. However, there still lacks a driving-targeted dense geometry perception model that can adapt to different scenarios and camera…

Recently, Dynamic Vision Sensors (DVSs) sparked a lot of interest due to their inherent advantages over conventional RGB cameras. These advantages include a low latency, a high dynamic range and a low energy consumption. Nevertheless, the…

Understanding dynamics from visual observations is a challenging problem that requires disentangling individual objects from the scene and learning their interactions. While recent object-centric models can successfully decompose a scene…

Common knowledge indicates that the process of constructing image datasets usually depends on the time-intensive and inefficient method of manual collection and annotation. Large models offer a solution via data generation. Nonetheless,…

Endoscopic diagnosis is an iterative process in which clinicians progressively acquire, compare, and verify local visual evidence before reaching a conclusion. Current AI systems do not adequately support this process because fine-grained…

Traditional clustering techniques often rely solely on similarity in the input data, limiting their ability to capture structural or semantic constraints that are critical in many domains. We introduce the Domain Aware Rule Triggered…

Data analysts often need to iterate between data transformations and chart designs to create rich visualizations for exploratory data analysis. Although many AI-powered systems have been introduced to reduce the effort of visualization…

While image editing has advanced rapidly, video editing remains less explored, facing challenges in consistency, control, and generalization. We study the design space of data, architecture, and control, and introduce \emph{EasyV2V}, a…

While instruction-based image editing is emerging, extending it to 360$^\circ$ panoramas introduces additional challenges. Existing methods often produce implausible results in both equirectangular projections (ERP) and perspective views.…

Closed-loop simulation is a core component of autonomous vehicle (AV) development, enabling scalable testing, training, and safety validation before real-world deployment. Neural scene reconstruction converts driving logs into interactive…

The proliferation of optical, electron, and scanning probe microscopies gives rise to large volumes of imaging data of objects as diversified as cells, bacteria, pollen, to nanoparticles and atoms and molecules. In most cases, the…

Object-centric event data represent processes from the point of view of all the involved object types. This perspective has gained interest in recent years as it supports the analysis of processes that previously could not be adequately…

Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned codebook. However, they…

Self-evolution of multimodal large language models (MLLMs) remains a critical challenge: pseudo-label-based methods suffer from progressive quality degradation as model predictions drift, while template-based methods are confined to a…

Visual Autoregressive (VAR) models have recently garnered significant attention for their innovative next-scale prediction paradigm, offering notable advantages in both inference efficiency and image quality compared to traditional…