相关论文: From "What" to "How": Constrained Reasoning for Au…
Robotic assistance in scientific laboratories requires procedurally correct long-horizon manipulation, reliable execution under limited supervision, and robustness in low-demonstration regimes. Such conditions greatly challenge end-to-end…
Existing super-resolution (SR) models primarily focus on restoring local texture details, often neglecting the global semantic information within the scene. This oversight can lead to the omission of crucial semantic details or the…
Despite the remarkable progress of image captioning, existing captioners typically lack the controllable capability to generate desired image captions, e.g., describing the image in a rough or detailed manner, in a factual or emotional…
Conditional text-to-image generation is an active area of research, with many possible applications. Existing research has primarily focused on generating a single image from available conditioning information in one step. One practical…
Existing multimodal large language models have achieved high-fidelity visual perception and exploratory visual generation. However, a precision paradox persists in complex reasoning tasks: optical perception systems transcribe symbols…
Recent works have made notable advancements in enhancing unified models for text-to-image generation through the Chain-of-Thought (CoT). However, these reasoning methods separate the processes of understanding and generation, which limits…
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…
Recent progress in multimodal reasoning has been significantly advanced by textual Chain-of-Thought (CoT), a paradigm where models conduct reasoning within language. This text-centric approach, however, treats vision as a static, initial…
Autoregressive models for text sometimes generate repetitive and low-quality output because errors accumulate during the steps of generation. This issue is often attributed to exposure bias - the difference between how a model is trained,…
Recent advances in multi-modal large language models (MLLMs) and chain-of-thought (CoT) reasoning have led to significant progress in image and text generation tasks. However, the field of 3D human pose generation still faces critical…
Computer vision is hard because of a large variability in lighting, shape, and texture; in addition the image signal is non-additive due to occlusion. Generative models promised to account for this variability by accurately modelling the…
State-of-the-art T2I models are capable of generating high-resolution images given textual prompts. However, they still struggle with accurately depicting compositional scenes that specify multiple objects, attributes, and spatial…
Despite recent advancements in text-to-image models, achieving semantically accurate images in text-to-image diffusion models is a persistent challenge. While existing initial latent optimization methods have demonstrated impressive…
Text-to-image models produce images that align well with natural language prompts, but compositional generation has long been a central challenge. Models often struggle to satisfy multiple concepts within a single prompt, frequently…
Generative models are increasingly powerful, yet users struggle to guide them through prompts. The generative process is difficult to control and unpredictable, and user instructions may be ambiguous or under-specified. Prior prompt…
Recursive Self-Improvement (RSI) enables intelligence systems to autonomously refine their capabilities. This paper explores the application of RSI in text-to-image diffusion models, addressing the challenge of training collapse caused by…
The unified autoregressive (AR) model excels at multimodal understanding and generation. However, its full potential in the domain of customized image generation has yet to be fully realized. Existing customization approaches for unified AR…
Recent studies have demonstrated the efficacy of using Reinforcement Learning (RL) in building reasoning models that articulate chains of thoughts prior to producing final answers. However, despite ongoing advances that aim at enabling…
Controllable image generation has always been one of the core demands in image generation, aiming to create images that are both creative and logical while satisfying additional specified conditions. In the post-AIGC era, controllable…
The Transformer architecture excels in a variety of language modeling tasks, outperforming traditional neural architectures such as RNN and LSTM. This is partially due to its elimination of recurrent connections, which allows for parallel…