Related papers: One Pass Is Not Enough: Recursive Latent Refinemen…

Retrieval-augmented generation (RAG) has shown impressive capability in providing reliable answer predictions and addressing hallucination problems. A typical RAG implementation uses powerful retrieval models to extract external information…

While diffusion models dominate the field of visual generation, they are computationally inefficient, applying a uniform computational effort regardless of different complexity. In contrast, autoregressive (AR) models are inherently…

Current image editing methods primarily utilize DDIM Inversion, employing a two-branch diffusion approach to preserve the attributes and layout of the original image. However, these methods encounter challenges with non-rigid edits, which…

Continual learning aims to incrementally acquire new concepts in data streams while resisting forgetting previous knowledge. With the rise of powerful pre-trained models (PTMs), there is a growing interest in training incremental learning…

Recently, large language models (LLMs) have demonstrated excellent performance, inspiring researchers to explore their use in automating register transfer level (RTL) code generation and improving hardware design efficiency. However, the…

The vanilla GAN (Goodfellow et al. 2014) suffers from mode collapse deeply, which usually manifests as that the images generated by generators tend to have a high similarity amongst them, even though their corresponding latent vectors have…

Large language models (LLMs) have recently shown strong progress on scientific reasoning, yet two major bottlenecks remain. First, explicit retrieval fragments reasoning, imposing a hidden "tool tax" of extra tokens and steps. Second,…

Catastrophic forgetting poses a fundamental challenge in continual learning, particularly when models are quantized for deployment efficiency. We systematically investigate the interplay between quantization precision (FP16, INT8, INT4) and…

In image restoration, single-step discriminative mappings often lack fine details via expectation learning, whereas generative paradigms suffer from inefficient multi-step sampling and noise-residual coupling. To address this dilemma, we…

Current multi-modal image fusion methods typically rely on task-specific models, leading to high training costs and limited scalability. While generative methods provide a unified modeling perspective, they often suffer from slow inference…

Transition Matching (TM) is an emerging paradigm for generative modeling that generalizes diffusion and flow-matching models as well as continuous-state autoregressive models. TM, similar to previous paradigms, gradually transforms noise…

Recent advances in text-to-image (T2I) generation have greatly improved visual quality, yet producing images that appear visually authentic to real-world photography remains challenging. This is partly due to biases in existing evaluation…

Multi-slice magnetic resonance images of the fetal brain are usually contaminated by severe and arbitrary fetal and maternal motion. Hence, stable and robust motion correction is necessary to reconstruct high-resolution 3D fetal brain…

Precise, object-aware control over visual content is essential for advanced image editing and compositional generation. Yet, most existing approaches operate on entire images holistically, limiting the ability to isolate and manipulate…

LLMs for code generation are commonly evaluated in repeated-sampling settings using Pass@k, where multiple candidate programs are executed against unit tests under a finite sampling budget. While recent verifier-based reinforcement learning…

Irregular Multivariate Time Series (IMTS) are characterized by uneven intervals between consecutive timestamps, which carry sampling pattern information valuable and informative for learning temporal and variable dependencies. In addition,…

While dense retrieval models, which embed queries and documents into a shared low-dimensional space, have gained widespread popularity, they were shown to exhibit important theoretical limitations and considerably lag behind traditional…

Fr\'echet Inception Distance (FID), computed with an ImageNet pretrained Inception-v3 network, is widely used as a state-of-the-art evaluation metric for generative models. It assumes that feature vectors from Inception-v3 follow a…

Iterative refinement -- start with a random guess, then iteratively improve the guess -- is a useful paradigm for representation learning because it offers a way to break symmetries among equally plausible explanations for the data. This…

Current video generation models suffer from high computational latency, making real-time applications prohibitively costly. In this paper, we address this limitation by exploiting the temporal redundancy inherent in video latent patches. To…