Generative Adversarial Networks and Image Synthesis

Neueste Paper

• VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding

  Zhihao He, Tieyuan Chen, Kangyu Wang, Ziran Qin, Yang Shao, Chaofan Gan, Shijie Li, Zuxuan Wu, Weiyao Lin · 27. Januar 2026

  Standard Autoregressive Video LLMs inevitably suffer from causal masking biases that hinder global spatiotemporal modeling, leading to suboptimal understanding efficiency. We propose VidLaDA, a Video LLM based on Diffusion Language Model utilizing bidirectional attention to capture bidirectional dep…

• treaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding

  Zhongyu Xiao, Zhiwei Hao, Jianyuan Guo, Yong Luo, Jia Liu, Jie Xu, Han Hu · 27. Januar 2026

  Diffusion Large Language Models (dLLMs) offer a compelling paradigm for natural language generation, leveraging parallel decoding and bidirectional attention to achieve superior global coherence compared to autoregressive models. While recent works have accelerated inference via KV cache reuse or he…

• BoRP: Bootstrapped Regression Probing for Scalable and Human-Aligned LLM Evaluation

  Peng Sun, Xiangyu Zhang, Duan Wu · 27. Januar 2026

  Accurate evaluation of user satisfaction is critical for iterative development of conversational AI. However, for open-ended assistants, traditional A/B testing lacks reliable metrics: explicit feedback is sparse, while implicit metrics are ambiguous. To bridge this gap, we introduce BoRP (Bootstrap…

• Diversified Scaling Inference in Time Series Foundation Models

  Ruijin Hua, Zichuan Liu, Kun Zhang, Yiyuan Yang · 27. Januar 2026

  The advancement of Time Series Foundation Models (TSFMs) has been driven primarily by large-scale pre-training, but inference-time compute potential remains largely untapped. This work systematically investigates two questions: how do TSFMs behave under standard sampling-based inference scaling, and…

• The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation

  Chenyu Mu, Xin He, Qu Yang, Wanshun Chen, Jiadi Yao, Huang Liu, Zihao Yi, Bo Zhao, Xingyu Chen, Ruotian Ma, Fanghua Ye, Erkun Yang, Cheng Deng, Zhaopeng Tu, Xiaolong Li, Linus · 27. Januar 2026

  Recent advances in video generation have produced models capable of synthesizing stunning visual content from simple text prompts. However, these models struggle to generate long-form, coherent narratives from high-level concepts like dialogue, revealing a ``semantic gap'' between a creative idea an…

• Boltzmann-GPT: Bridging Energy-Based World Models and Language Generation

  Junichiro Niimi · 27. Januar 2026

  Large Language Models (LLMs) generate fluent text, yet whether they truly understand the world or merely produce plausible language about it remains contested. We propose an architectural principle, the mouth is not the brain, that explicitly separates world models from language models. Our architec…

• NeRF-MIR: Towards High-Quality Restoration of Masked Images with Neural Radiance Fields

  Xianliang Huang, Zhizhou Zhong, Shuhang Chen, Yi Xu, Juhong Guan, Shuigeng Zhou · 27. Januar 2026

  Neural Radiance Fields (NeRF) have demonstrated remarkable performance in novel view synthesis. However, there is much improvement room on restoring 3D scenes based on NeRF from corrupted images, which are common in natural scene captures and can significantly impact the effectiveness of NeRF. This …

• Distillation-Enabled Knowledge Alignment for Generative Semantic Communications of AIGC Images

  Jingzhi Hu, Geoffrey Ye Li · 27. Januar 2026

  Due to the surging amount of AI-generated images, its provisioning to edges and mobile users from the cloud incurs substantial traffic on networks. Generative semantic communication (GSC) offers a promising solution by transmitting highly compact information, i.e., prompt text and latent representat…

• Towards Interpretable Deep Generative Models via Causal Representation Learning

  Gemma E. Moran, Bryon Aragam · 27. Januar 2026

  Recent developments in generative artificial intelligence (AI) rely on machine learning techniques such as deep learning and generative modeling to achieve state-of-the-art performance across wide-ranging domains. These methods' surprising performance is due in part to their ability to learn implici…

• A Mechanistic View on Video Generation as World Models: State and Dynamics

  Luozhou Wang, Zhifei Chen, Yihua Du, Dongyu Yan, Wenhang Ge, Guibao Shen, Xinli Xu, Leyi Wu, Man Chen, Tianshuo Xu, Peiran Ren, Xin Tao, Pengfei Wan, Ying-Cong Chen · 27. Januar 2026

  Large-scale video generation models have demonstrated emergent physical coherence, positioning them as potential world models. However, a gap remains between contemporary "stateless" video architectures and classic state-centric world model theories. This work bridges this gap by proposing a novel t…

• MV-S2V: Multi-View Subject-Consistent Video Generation

  Ziyang Song, Xinyu Gong, Bangya Liu, Zelin Zhao · 27. Januar 2026

  Existing Subject-to-Video Generation (S2V) methods have achieved high-fidelity and subject-consistent video generation, yet remain constrained to single-view subject references. This limitation renders the S2V task reducible to an S2I + I2V pipeline, failing to exploit the full potential of video su…

• Text-to-Image Diffusion Models Cannot Count, and Prompt Refinement Cannot Help

  Xuyang Guo, Jiayan Huo, Yingyu Liang, Zhenmei Shi, Zhao Song, Jiahao Zhang, Zhen Zhuang · 26. Januar 2026

  Generative modeling is widely regarded as one of the most essential problems in today's AI community, with text-to-image generation having gained unprecedented real-world impacts. Among various approaches, diffusion models have achieved remarkable success and have become the de facto solution for te…

• ViSymRe: Vision Multimodal Symbolic Regression

  Da Li, Junping Yin, Jin Xu, Xinxin Li, Juan Zhang · 26. Januar 2026

  Extracting interpretable equations from observational datasets to describe complex natural phenomena is one of the core goals of artificial intelligence. This field is known as symbolic regression (SR). In recent years, Transformer-based paradigms have become a new trend in SR, addressing the well-k…

• Reward-Forcing: Autoregressive Video Generation with Reward Feedback

  Jingran Zhang, Ning Li, Yuanhao Ban, Andrew Bai, Justin Cui · 26. Januar 2026

  While most prior work in video generation relies on bidirectional architectures, recent efforts have sought to adapt these models into autoregressive variants to support near real-time generation. However, such adaptations often depend heavily on teacher models, which can limit performance, particul…

• LoL: Longer than Longer, Scaling Video Generation to Hour

  Justin Cui, Jie Wu, Ming Li, Tao Yang, Xiaojie Li, Rui Wang, Andrew Bai, Yuanhao Ban, Cho-Jui Hsieh · 26. Januar 2026

  Recent research in long-form video generation has shifted from bidirectional to autoregressive models, yet these methods commonly suffer from error accumulation and a loss of long-term coherence. While attention sink frames have been introduced to mitigate this performance decay, they often induce a…

• AnyView: Synthesizing Any Novel View in Dynamic Scenes

  Basile Van Hoorick, Dian Chen, Shun Iwase, Pavel Tokmakov, Muhammad Zubair Irshad, Igor Vasiljevic, Swati Gupta, Fangzhou Cheng, Sergey Zakharov, Vitor Campagnolo Guizilini · 26. Januar 2026

  Modern generative video models excel at producing convincing, high-quality outputs, but struggle to maintain multi-view and spatiotemporal consistency in highly dynamic real-world environments. In this work, we introduce \textbf{AnyView}, a diffusion-based video generation framework for \emph{dynami…

• Memory-V2V: Augmenting Video-to-Video Diffusion Models with Memory

  Dohun Lee, Chun-Hao Paul Huang, Xuelin Chen, Jong Chul Ye, Duygu Ceylan, Hyeonho Jeong · 26. Januar 2026

  Recent foundational video-to-video diffusion models have achieved impressive results in editing user provided videos by modifying appearance, motion, or camera movement. However, real-world video editing is often an iterative process, where users refine results across multiple rounds of interaction.…

• Sim-to-Real Transfer via a Style-Identified Cycle Consistent Generative Adversarial Network: Zero-Shot Deployment on Robotic Manipulators through Visual Domain Adaptation

  Luc\'ia G\"uitta-L\'opez, Lionel G\"uitta-L\'opez, Jaime Boal, \'Alvaro Jes\'us L\'opez-L\'opez · 26. Januar 2026

  The sample efficiency challenge in Deep Reinforcement Learning (DRL) compromises its industrial adoption due to the high cost and time demands of real-world training. Virtual environments offer a cost-effective alternative for training DRL agents, but the transfer of learned policies to real setups …

• AutoRegressive Generation with B-rep Holistic Token Sequence Representation

  Jiahao Li, Yunpeng Bai, Yongkang Dai, Hao Guo, Hongping Gan, Yilei Shi · 26. Januar 2026

  Previous representation and generation approaches for the B-rep relied on graph-based representations that disentangle geometric and topological features through decoupled computational pipelines, thereby precluding the application of sequence-based generative frameworks, such as transformer archite…

• Ambient Dataloops: Generative Models for Dataset Refinement

  Adri\'an Rodr\'iguez-Mu\~noz, William Daspit, Adam Klivans, Antonio Torralba, Constantinos Daskalakis, Giannis Daras · 23. Januar 2026

  We propose Ambient Dataloops, an iterative framework for refining datasets that makes it easier for diffusion models to learn the underlying data distribution. Modern datasets contain samples of highly varying quality, and training directly on such heterogeneous data often yields suboptimal models. …

• CASL: Concept-Aligned Sparse Latents for Interpreting Diffusion Models

  Zhenghao He, Guangzhi Xiong, Boyang Wang, Sanchit Sinha, Aidong Zhang · 23. Januar 2026

  Internal activations of diffusion models encode rich semantic information, but interpreting such representations remains challenging. While Sparse Autoencoders (SAEs) have shown promise in disentangling latent representations, existing SAE-based methods for diffusion model understanding rely on unsu…

• ViSymRe: Vision-guided Multimodal Symbolic Regression

  Da Li, Junping Yin, Jin Xu, Xinxin Li, Juan Zhang · 23. Januar 2026

  Extracting simple mathematical expression from an observational dataset to describe complex natural phenomena is one of the core objectives of artificial intelligence (AI). This field is known as symbolic regression (SR). Traditional SR models are based on genetic programming (GP) or reinforcement l…

• Low-Dimensional Adaptation of Rectified Flow: A New Perspective through the Lens of Diffusion and Stochastic Localization

  Saptarshi Roy, Alessandro Rinaldo, Purnamrita Sarkar · 23. Januar 2026

  In recent years, Rectified flow (RF) has gained considerable popularity largely due to its generation efficiency and state-of-the-art performance. In this paper, we investigate the degree to which RF automatically adapts to the intrinsic low dimensionality of the support of the target distribution t…

• Iterative Amortized Hierarchical VAE

  Simon W. Penninga, Ruud J. G. van Sloun · 23. Januar 2026

  In this paper we propose the Iterative Amortized Hierarchical Variational Autoencoder (IA-HVAE), which expands on amortized inference with a hybrid scheme containing an initial amortized guess and iterative refinement with decoder gradients. We achieve this by creating a linearly separable decoder i…

• Why Inference in Large Models Becomes Decomposable After Training

  Jidong Jin · 23. Januar 2026

  Inference in large-scale AI models is typically performed on dense parameter matrices, leading to inference cost and system complexity that scale unsustainably with model size. This limitation does not arise from insufficient model capacity, but from treating post-training inference systems as monol…