相关论文: Multi-Agent Synergy-Driven Iterative Visual Narrat…

We present PREVIS, a visual analytics tool, enhancing machine learning performance analysis in engineering applications. The presented toolchain allows for a direct comparison of regression models. In addition, we provide a methodology to…

Novel view synthesis (NVS) from a single image is highly ill-posed due to large unobserved regions, especially for views that deviate significantly from the input. While existing methods focus on consistency between the source and generated…

We unveil that internal representations in large language models (LLMs) serve as reliable proxies of learned knowledge, and propose RECALL, a novel representation-aware model merging framework for continual learning without access to…

Reinforcement learning with verifiable rewards (RLVR) has proven effective in eliciting complex reasoning in large language models (LLMs). However, standard RLVR training often leads to excessively verbose processes (in reasoning tasks) and…

Recent advancements in differentiable rendering and 3D reasoning have driven exciting results in novel view synthesis from a single image. Despite realistic results, methods are limited to relatively small view change. In order to…

Long-form visual storytelling requires maintaining continuity across shots, including consistent characters, stable environments, and smooth scene transitions. While existing generative models can produce strong individual frames, they fail…

Audio Descriptions (ADs) convey essential on-screen information, allowing visually impaired audiences to follow videos. To be effective, ADs must form a coherent sequence that helps listeners to visualise the unfolding scene, rather than…

Conventional physically based rendering (PBR) pipelines generate photorealistic images through computationally intensive light transport simulations. Although recent deep learning approaches leverage diffusion model priors with geometry…

Dramatic progress has been witnessed in basic vision tasks involving low-level perception, such as object recognition, detection, and tracking. Unfortunately, there is still an enormous performance gap between artificial vision systems and…

Reconstructing a dynamic scene from image inputs is a fundamental computer vision task with many downstream applications. Despite recent advancements, existing approaches still struggle to achieve high-quality reconstructions from unseen…

Photorealistic rendering of dynamic humans is an important ability for telepresence systems, virtual shopping, synthetic data generation, and more. Recently, neural rendering methods, which combine techniques from computer graphics and…

Persuasion dialogue systems reflect the machine's ability to make strategic moves beyond verbal communication, and therefore differentiate themselves from task-oriented or open-domain dialogue systems and have their own unique values.…

Scene graph generation (SGG) analyzes images to extract meaningful information about objects and their relationships. In the dynamic visual world, it is crucial for AI systems to continuously detect new objects and establish their…

Human creative ideation involves both exploration of diverse ideas (divergence) and selective synthesis of explored ideas into coherent combinations (convergence). While processes of divergence and convergence are often interleaved and…

Synthetic data has become increasingly important for training large language models, especially when real data is scarce, expensive, or privacy-sensitive. Many such generation tasks require coordinated multi-agent workflows, where…

In both observational data and randomized control trials, researchers select statistical models to articulate how the outcome of interest varies with combinations of observable covariates. Choosing a model that is too simple can obfuscate…

Program synthesis from incomplete specifications (e.g. input-output examples) has gained popularity and found real-world applications, primarily due to its ease-of-use. Since this technology is often used in an interactive setting,…

Text-to-multiview (T2MV) diffusion models have shown great promise in generating multiple views of a scene from a single text prompt. While few-step backbones enable real-time T2MV generation, they often compromise key aspects of generation…

Automatic related work generation (RWG) can save people's time and effort when writing a draft of related work section (RWS) for further revision. However, existing methods for RWG always suffer from shallow comprehension due to taking the…

Reinforcement learning (RL) has become the dominant paradigm for improving the performance of language models on complex reasoning tasks. Despite the substantial empirical gains demonstrated by RL-based training methods like GRPO, a…