Related papers: KAGE-Bench: Fast Known-Axis Visual Generalization …

Discrete autoregressive (AR) text-to-image (T2I) models pair a VQ tokenizer with an AR policy, and current post-training pipelines optimize only the policy while keeping the VQ decoder frozen. Recent diffusion T2I work, exemplified by…

We propose Confidence-Guided Token Merging (Co-Me), an acceleration mechanism for visual geometric transformers without retraining or finetuning the base model. Co-Me distilled a light-weight confidence predictor to rank tokens by…

Dynamic graphs with ordered sequences of events between nodes are prevalent in real-world industrial applications such as e-commerce and social platforms. However, representation learning for dynamic graphs has posed great computational…

Generative adversarial networks (GANs) nowadays are capable of producing images of incredible realism. One concern raised is whether the state-of-the-art GAN's learned distribution still suffers from mode collapse, and what to do if so.…

Vision-Language Navigation in Continuous Environments (VLNCE), where an agent follows instructions and moves freely to reach a destination, is a key research problem in embodied AI. However, most existing approaches are sensitive to…

Recent advances in Vision-Language Models (VLMs) have enabled unified understanding across text and images, yet equipping these models with robust image generation capabilities remains challenging. Existing approaches often rely on…

Training vision-based manipulation policies that are robust across diverse visual environments remains an important and unresolved challenge in robot learning. Current approaches often sidestep the problem by relying on invariant…

Autonomous agents often require multiple strategies to solve complex tasks, but determining when to switch between strategies remains challenging. This research introduces a reinforcement learning technique to learn switching thresholds…

Despite the remarkable success of Deep RL in learning control policies from raw pixels, the resulting models do not generalize. We demonstrate that a trained agent fails completely when facing small visual changes, and that…

In daily life, graphic symbols, such as traffic signs and brand logos, are ubiquitously utilized around us due to its intuitive expression beyond language boundary. We tackle an open-set graphic symbol recognition problem by one-shot…

The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard reconstruction-based training paradigm produces a latent space that is biased towards low-level information,…

Given a graph G where each node is associated with a set of attributes, attributed network embedding (ANE) maps each node v in G to a compact vector Xv, which can be used in downstream machine learning tasks. Ideally, Xv should capture node…

Visual generative models (e.g., diffusion models) typically operate in compressed latent spaces to balance training efficiency and sample quality. In parallel, there has been growing interest in leveraging high-quality pre-trained visual…

Conventional 2D pose estimation models are constrained by their design to specific object categories. This limits their applicability to predefined objects. To overcome these limitations, category-agnostic pose estimation (CAPE) emerged as…

Visual tokenizers are pivotal in multimodal large models, acting as bridges between continuous inputs and discrete tokens. Nevertheless, training high-compression-rate VQ-VAEs remains computationally demanding, often necessitating thousands…

Collaborative driving systems leverage vehicle-to-everything (V2X) communication for multi-agent collaborative perception to enhance driving safety, yet they remain constrained by scarce annotated real-world V2X driving datasets and limited…

Visual perception connects high-level semantic understanding to pixel-level perception, but most existing settings assume that the decisive evidence for identifying a target is already in the image or frozen model knowledge. We study a more…

A variational autoencoder (VAE) is a probabilistic machine learning framework for posterior inference that projects an input set of high-dimensional data to a lower-dimensional, latent space. The latent space learned with a VAE offers…

We propose ViC-MAE, a model that combines both Masked AutoEncoders (MAE) and contrastive learning. ViC-MAE is trained using a global featured obtained by pooling the local representations learned under an MAE reconstruction loss and…

Vehicle-to-Everything (V2X) collaborative perception extends sensing beyond single vehicle limits through transmission. However, as more agents participate, existing frameworks face two key challenges: (1) the participating agents are…