12 accepted papers
Solving partial differential equations (PDEs) on shapes underpins many shape analysis and engineering tasks; yet, prevailing PDE solvers operate on polygonal/triangle meshes while modern 3D assets increasingly live as neural representations. This mismatch leaves no suitable method to solve surface P
Graph anomaly detection methods aim to distinguish anomalous nodes. While prior methods characterize anomalies through increased variation in the spectral energy distributions, they overlook those that result in decreased variation, i.e., camouflaged anomalies that appear normal. We show that this t…
Existing table understanding methods face challenges due to complex table structures and intricate logical reasoning. While supervised finetuning (SFT) dominates existing research, reinforcement learning (RL), such as Group Relative Policy Optimization (GRPO), has shown promise but struggled with lo
"We present a new approach for generating 3D house wireframes with semantic enrichment using an autoregressive model. Unlike conventional generative models that independently process vertices, edges, and faces, our approach employs a unified wire-based representation for improved coherence in learni…
"Collaborative perception effectively expands the perception range of agents by sharing perceptual information, and it addresses the occlusion problem in single-vehicle perception. Most of the existing works are based on the assumption of perception model homogeneity. However, in actual collaboratio…
Information extraction (IE) encounters challenges due to the variety of schemas and objectives that differ across tasks. Recent advancements hint at the potential for universal approaches to model such tasks, referred to as Universal Information Extraction (UIE). While handling diverse tasks in one…
"Untrained networks inspired by deep image priors have shown promising capabilities in recovering high-quality images from noisy or partial measurements without requiring training sets. Their success is widely attributed to implicit regularization due to the spectral bias of suitable network archite…
The use of multi-agent reinforcement learning (MARL) methods in coordinating traffic lights (CTL) has become increasingly popular, treating each intersection as an agent. However, existing MARL approaches either treat each agent absolutely homogeneous, i.e., same network and parameter for each agent…
Deep Image Prior (DIP) shows that some network architectures inherently tend towards generating smooth images while resisting noise, a phenomenon known as spectral bias. Image denoising is a natural application of this property. Although denoising with DIP mitigates the need for large training sets,…
"We present UrbanScene3D, a large-scale data platform for research of urban scene perception and reconstruction. UrbanScene3D contains over 128k high-resolution images covering 16 scenes including large-scale real urban regions and synthetic cities with 136 km2 area in total. The dataset also contai…
Finger motion tracking has a number of applications in user-interfaces, sports analytics, medical rehabilitation and sign language translation. This paper presents a system called FinGTrAC that shows the feasibility of fine grained finger gesture tracking using low intrusive wearable sensor platform…
This paper reports on a novel 3D-printed polymeric compliant constant-force buffering gripping mechanism. The motivation of this work is to develop a buffering gripping mechanism to avoid the damage of manipulated biological object induced by excessive displacement output. The presented zero-stiffne…