17 accepted papers
Reinforcement learning (RL) has recently achieved remarkable success in eliciting visual reasoning within Multimodal Large Language Models (MLLMs). However, existing approaches typically train separate models for different tasks and treat image and video reasoning as disjoint domains. This results i
A fundamental dilemma in generative modeling persists: iterative diffusion models achieve outstanding fidelity, but at a significant computational cost, while efficient few-step alternatives are constrained by a hard quality ceiling. This conflict between generation steps and output quality arises f
Most Video-Large Language Models (Video-LLMs) adopt an encoder-decoder framework, where a vision encoder extracts frame-wise features for processing by a language model. However, this approach incurs high computational costs, introduces resolution biases, and struggles to capture fine-grained multim…
While Diffusion Models (DM) exhibit remarkable performance across various image generative tasks, they nonetheless reflect the inherent bias presented in the training set.As DMs are now widely used in real-world applications, these biases could perpetuate a distorted worldview and hinder opportuniti…
High-quality image-text data is critical in enhancing Vision-Language Models (VLMs), but traditional image-based pretraining approaches face limitations. These methods are resource-intensive, relying on curated, high-quality interleaved data that is costly and challenging to collect at scale. Additi…
The weakly-supervised audio-visual video parsing (AVVP) aims to predict all modality-specific events and locate their temporal boundaries. Despite significant progress, due to the limitations of the weakly-supervised and the deficiencies of the model architecture, existing methods are lacking in sim…
We introduce native-resolution image synthesis, a novel paradigm in generative modeling capable of synthesizing images at arbitrary resolutions and aspect ratios. This approach overcomes the limitations of standard fixed-resolution, square-image methods by inherently handling variable-length visual…
This study introduces soft joints to non-Euclidean (non-E) origami structures, leveraging the deformation capabilities of soft silicone membranes while maintaining structural rigidity. This integration extends the motion space, showcasing bistable characteristics and adjustable stiffness. A comprehe
This work introduces Multimodal Context (MiCo), a scalable pretraining framework designed to advance omni-modal intelligence--an AI system capable of understanding and learning from multiple modalities to achieve universal representation learning. MiCo allows for efficient scaling of both the number…
In this paper, we present a novel system for Human-Robot Interactive Creation of Artworks (HRICA). Different from previous robot painters, HRICA allows a human user and a robot to alternately draw strokes on a canvas, to collaboratively create a portrait drawing through frequent interactions. The ke…
We propose to improve transformers of a specific modality with irrelevant data from other modalities e.g. improve an ImageNet model with audio or point cloud datasets. We would like to highlight that the data samples of the target modality are irrelevant to the other modalities which distinguishes o…
Multimodal large language models (MLLMs) have gained significant attention due to their strong multimodal understanding capability. However existing works rely heavily on modality-specific encoders which usually differ in architecture and are limited to common modalities. In this paper we present On…
"Online vectorized High-Definition (HD) map construction is critical for downstream prediction and planning. Recent efforts have built strong baselines for this task, however, geometric shapes and relations of instances in road systems are still under-explored, such as parallelism, perpendicular, re…
Most 3D generation research focuses on up-projecting 2D foundation models into the 3D space either by minimizing 2D Score Distillation Sampling (SDS) loss or fine-tuning on multi-view datasets. Without explicit 3D priors these methods often lead to geometric anomalies and multi-view inconsistency. R…
Large-kernel convolutional neural networks (ConvNets) have recently received extensive research attention but two unresolved and critical issues demand further investigation. 1) The architectures of existing large-kernel ConvNets largely follow the design principles of conventional ConvNets or trans…
Net-winged midge larvae (genus Liponeura) can achieve robust attachment and crawl on the slippery surface in the fast stream. This remarkable capability is endowed by the rapid and reversible adhesive suckers on their abdomen. Previous studies reveal that two components play essential roles for adhe
"Visible-Infrared Re-Identification (VI-ReID) is challenging in image retrievals. The modality discrepancy will easily make huge intra-class variations. Most existing methods either bridge different modalities through modality-invariance or generate the intermediate modality for better performance.…