相关论文: TeEFusion: Blending Text Embeddings to Distill Cla…

Significant advances have been made in the sampling efficiency of diffusion models and flow matching models, driven by Consistency Distillation (CD), which trains a student model to mimic the output of a teacher model at a later timestep.…

Large language models (LLMs) have made impressive strides in mathematical reasoning, often fine-tuned using rejection sampling that retains only correct reasoning trajectories. While effective, this paradigm treats supervision as a binary…

We present BlenderFusion, a generative visual compositing framework that synthesizes new scenes by recomposing objects, camera, and background. It follows a layering-editing-compositing pipeline: (i) segmenting and converting visual inputs…

Human preference alignment presents a critical yet underexplored challenge for diffusion models in text-to-3D generation. Existing solutions typically require task-specific fine-tuning, posing significant hurdles in data-scarce 3D domains.…

Recent text-to-image diffusion models have significantly improved visual quality and text alignment. However, generating a sequence of images while preserving consistent character identity across diverse scene descriptions remains a…

Recent advances in distilling expensive diffusion models into efficient few-step generators show significant promise. However, these methods typically demand substantial computational resources and extended training periods, limiting…

While diffusion distillation has enabled one-step generation through methods like Variational Score Distillation, adapting distilled models to emerging new controls -- such as novel structural constraints or latest user preferences --…

Dataset distillation or condensation refers to compressing a large-scale dataset into a much smaller one, enabling models trained on this synthetic dataset to generalize effectively on real data. Tackling this challenge, as defined, relies…

Although remarkable progress has been made in recent years, current multi-exposure image fusion (MEF) research is still bounded by the lack of real ground truth, objective evaluation function, and robust fusion strategy. In this paper, we…

The increasing demand to process long and high-resolution videos significantly burdens Large Vision-Language Models (LVLMs) due to the enormous number of visual tokens. Existing token reduction methods primarily prune tokens based on…

The performance of autoregressive models on natural language generation tasks has dramatically improved due to the adoption of deep, self-attentive architectures. However, these gains have come at the cost of hindering inference speed,…

The widespread use of large language models has resulted in a multitude of tokenizers and embedding spaces, making knowledge transfer in prompt discovery tasks difficult. In this work, we propose FUSE (Flexible Unification of Semantic…

Dataset distillation (DD) aims to synthesize compact training sets that enable models to achieve high accuracy with significantly fewer samples. Recent diffusion-based DD methods commonly introduce semantic guidance through late-stage…

Recent breakthroughs in text-to-image diffusion models have significantly advanced the generation of high-fidelity, photo-realistic images from textual descriptions. Yet, these models often struggle with interpreting spatial arrangements…

We propose CatVersion, an inversion-based method that learns the personalized concept through a handful of examples. Subsequently, users can utilize text prompts to generate images that embody the personalized concept, thereby achieving…

Recent advances in large language models (LLMs) have intensified efforts to fuse heterogeneous open-source models into a unified system that inherits their complementary strengths. Existing logit-based fusion methods maintain inference…

Diffusion models often exhibit inconsistent sample quality due to stochastic variations inherent in their sampling trajectories. Although training-based fine-tuning (e.g. DDPO [1]) and inference-time alignment techniques[2] aim to improve…

Diffusion models generate synthetic images through an iterative refinement process. However, the misalignment between the simulation-free objective and the iterative process often causes accumulated gradient error along the sampling…

The generation of high-quality, diverse, and prompt-aligned images is a central goal in image-generating diffusion models. The popular classifier-free guidance (CFG) approach improves quality and alignment at the cost of reduced variation,…

Recently Data-Free Knowledge Distillation (DFKD) has garnered attention and can transfer knowledge from a teacher neural network to a student neural network without requiring any access to training data. Although diffusion models are adept…