相关论文: SCALAR: Scale-wise Controllable Visual Autoregress…
In this paper, we propose a novel controllable text-to-image generative adversarial network (ControlGAN), which can effectively synthesise high-quality images and also control parts of the image generation according to natural language…
Deep neural networks achieve impressive performance but remain difficult to interpret and control. We present SALVE (Sparse Autoencoder-Latent Vector Editing), a unified "discover, validate, and control" framework that bridges mechanistic…
Despite significant progress in text-to-image generation, aligning outputs with complex prompts remains challenging, particularly for fine-grained semantics and spatial relations. This difficulty stems from the feed-forward nature of…
Masked autoregressive models (MAR) have emerged as a powerful paradigm for image and video generation, combining the flexibility of masked modeling with the expressiveness of continuous tokenizers. However, when sampling individual frames,…
Modern vision-language models (VLMs) can act as generative OCR engines, yet open-ended decoding can expose rare but consequential failures. We identify a core deployment misalignment in generative OCR. Autoregressive decoding favors…
Analyzing unsteady fluid flows often requires access to the full distribution of possible temporal states, yet conventional PDE solvers are computationally prohibitive and learned time-stepping surrogates quickly accumulate error over long…
We present Variational Self-Supervised Learning (VSSL), a novel framework that combines variational inference with self-supervised learning to enable efficient, decoder-free representation learning. Unlike traditional VAEs that rely on…
Recent advances in neural-based generative modeling have reignited the hopes of having computer systems capable of conversing with humans and able to understand natural language. The employment of deep neural architectures has been largely…
Class-conditional generative models have emerged as accurate and robust classifiers, with diffusion models demonstrating clear advantages over other visual generative paradigms, including autoregressive (AR) models. In this work, we revisit…
Autoregressive conditional image generation algorithms are capable of generating photorealistic images that are consistent with given textual or image conditions, and have great potential for a wide range of applications. Nevertheless, the…
The raster-ordered image token sequence exhibits a significant Euclidean distance between index-adjacent tokens at line breaks, making it unsuitable for autoregressive generation. To address this issue, this paper proposes Direction-Aware…
Zero-shot skeleton-based action recognition (ZSAR) aims to recognize action classes without any training skeletons from those classes, relying instead on auxiliary semantics from text. Existing approaches frequently depend on explicit…
Coarse-guided visual generation, which synthesizes fine visual samples from degraded or low-fidelity coarse references, is essential for various real-world applications. While training-based approaches are effective, they are inherently…
In this work, we investigate the capability of generating images from pre-trained diffusion models at much higher resolutions than the training image sizes. In addition, the generated images should have arbitrary image aspect ratios. When…
Autoregressive (AR) models for image generation typically adopt a two-stage paradigm of vector quantization and raster-scan ``next-token prediction", inspired by its great success in language modeling. However, due to the huge modality gap,…
In this paper, we present SCALAR (Symbolic Conjecture and LLM-Assisted Reasoning), a neurosymbolic framework for automated conjecture generation in quantum circuit analysis built on top of the CUDA-Q open source framework. The system…
Paired image-text data with subtle variations in-between (e.g., people holding surfboards vs. people holding shovels) hold the promise of producing Vision-Language Models with proper compositional understanding. Synthesizing such training…
Despite recent advancements in 3D generation methods, achieving controllability still remains a challenging issue. Current approaches utilizing score-distillation sampling are hindered by laborious procedures that consume a significant…
We introduce layered controllable video generation, where we, without any supervision, decompose the initial frame of a video into foreground and background layers, with which the user can control the video generation process by simply…
Generative modeling of high-dimensional data is a key problem in machine learning. Successful approaches include latent variable models and autoregressive models. The complementary strengths of these approaches, to model global and local…