Related papers: VFM-VAE: Vision Foundation Models Can Be Good Toke…

Video Face Enhancement (VFE) aims to restore high-quality facial regions from degraded video sequences, enabling a wide range of practical applications. Despite substantial progress in the field, current methods that primarily rely on video…

Efficient image tokenization with high compression ratios remains a critical challenge for training generative models. We present SoftVQ-VAE, a continuous image tokenizer that leverages soft categorical posteriors to aggregate multiple…

Visual tokenizers play a crucial role in diffusion models. The dimensionality of latent space governs both reconstruction fidelity and the semantic expressiveness of the latent feature. However, a fundamental trade-off is inherent between…

Force sensing is a crucial modality for Vision-Language-Action (VLA) frameworks, as it enables fine-grained perception and dexterous manipulation in contact-rich tasks. We present Force-Distilled VLA (FD-VLA), a novel framework that…

Autoregressive language models decode left-to-right with irreversible commitments, limiting revision during multi-step reasoning. We propose \textbf{VDLM}, a modular variable diffusion language model that separates semantic planning from…

Representation autoencoders that reuse frozen pretrained vision encoders as visual tokenizers have achieved strong reconstruction and generation quality. However, existing methods universally extract features from only the last encoder…

We introduce LTX-Video, a transformer-based latent diffusion model that adopts a holistic approach to video generation by seamlessly integrating the responsibilities of the Video-VAE and the denoising transformer. Unlike existing methods,…

Continual learning enables large language models to adapt to evolving tasks without retraining from scratch, yet catastrophic forgetting remains a central obstacle. Among continual learning methods, regularization-based approaches are…

As the boosting development of large vision-language models like Contrastive Language-Image Pre-training (CLIP), many CLIP-like methods have shown impressive abilities on visual recognition, especially in low-data regimes scenes. However,…

Diffusion models achieve state-of-the-art image generation but remain computationally costly due to iterative denoising. Latent-space models like Stable Diffusion reduce overhead yet lose fine detail, while retrieval-augmented methods…

Multimodal image matching seeks pixel-level correspondences between images of different modalities, crucial for cross-modal perception, fusion and analysis. However, the significant appearance differences between modalities make this task…

Text-to-image generation via Stable Diffusion models (SDM) have demonstrated remarkable capabilities. However, their computational intensity, particularly in the iterative denoising process, hinders real-time deployment in latency-sensitive…

By embedding discrete representations into a continuous latent space, we can leverage continuous-space latent diffusion models to handle generative modeling of discrete data. However, despite their initial success, most latent diffusion…

Diffusion language models offer parallel token generation and inherent bidirectionality, promising more efficient and powerful sequence modeling compared to autoregressive approaches. However, state-of-the-art diffusion models (e.g., Dream…

Separating shared and independent features is crucial for multi-phase contrast-enhanced (CE) MRI synthesis. However, existing methods use deep autoencoder generators with low parameter efficiency and lack interpretable training strategies.…

In the past decade, image foundation models (IFMs) have achieved unprecedented progress. However, the potential of directly using IFMs for video self-supervised representation learning has largely been overlooked. In this study, we propose…

Latent diffusion models offer an attractive alternative to discrete diffusion for non-autoregressive text generation by operating on continuous text representations and denoising entire sequences in parallel. The major challenge in latent…

Masked image modeling (MIM) performs strongly in pre-training large vision Transformers (ViTs). However, small models that are critical for real-world applications cannot or only marginally benefit from this pre-training approach. In this…

Foundation models, despite their robust zero-shot capabilities, remain vulnerable to spurious correlations and 'Clever Hans' strategies. Existing mitigation methods often rely on unavailable group labels or computationally expensive…

Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However, it remains underexplored whether these representations,…