19 accepted papers
Modern large-scale neural networks are often trained and released in multiple sizes to accommodate diverse inference budgets. To improve efficiency, recent work has explored *model upscaling*: initializing larger models from trained smaller ones in order to transfer knowledge and accelerate converge…
Code language models (LMs) represent valuable intellectual property (IP) as their training involves immense investments, including large-scale code corpora, proprietary annotations, extensive computational resources, and specialized designs. Hence the threat of model IP infringements such as unautho…
Low-Rank Adaptation (LoRA) is a standard tool for parameter-efficient finetuning of large models. While it induces a small memory footprint, its training dynamics can be surprisingly complex as they depend on several hyperparameters such as initialization, adapter rank, and learning rate. In particu…
Long video generation with Diffusion Transformers (DiTs) is bottlenecked by the quadratic scaling of full attention with sequence length. Since attention is highly redundant, outputs are dominated by a small subset of query–key pairs. Existing sparse methods rely on blockwise coarse estimation, whos…
Subject-driven text-to-image (T2I) customization has drawn significant interest in academia and industry. This task enables pre-trained models to generate novel images based on unique subjects. Existing studies adopt a self-reconstructive perspective, focusing on capturing all details of a single im…
Diffusion models are widely recognized for their ability to generate high-fidelity images. Despite the excellent performance and scalability of the Diffusion Transformer (DiT) architecture, it applies fixed compression across different image regions during the diffusion process, disregarding the nat…
Animation colorization is a crucial part of real animation industry production. Long animation colorization has high labor costs. Therefore, automated long animation colorization based on the video generation model has significant research value. Existing studies are limited to short-term colorizati…
Adapter-based Multilingual Neural Machine Translation (MNMT) has become a significant approach in low-resource language translation by mitigating data imbalances between high-resource and low-resource language pairs and reducing training costs. However, existing adapter-based methods lack generaliza…
Rich user-item interactions are essential for building reliable recommender systems, as they reflect user preference patterns. However, minor language news recommendation platforms suffer from limited interactions due to a small user base. A natural solution is to apply well-established English reco…
Text-guided 3D editing aims to locally modify 3D objects based on editing prompts, which has significant potential for applications in 3D game and film domains. Existing methods typically follow a view-agnostic paradigm: editing 2D view images indiscriminately and projecting them back into 3D space.…
In the era of data-driven decision-making, the complexity of data analysis necessitates advanced expertise and tools of data science, presenting significant challenges even for specialists. Large Language Models (LLMs) have emerged as promising aids as data science agents, assisting humans in data a…
Graph Anomaly Detection (GAD) has surfaced as a significant field of research, predominantly due to its substantial influence in production environments. Although existing approaches for node anomaly detection have shown effectiveness, they have yet to fully address two major challenges: operating i…
Continuous prompt tuning has gained significant attention for its ability to train only continuous prompts while freezing the language model. This approach greatly reduces the training time and storage for downstream tasks. In this work, we delve into the hierarchical relationship between the prompt…
This paper presents a novel uncrewed aerial vehicle (UAV) design named HALO, which stands for “harmless aerial limber robot”. HALO uses a swashplateless mechanism to generate a moment for pitch and roll control without requiring additional actuators such as servo, reducing the number of components n…
The emergence of low-cost, small form factor and light-weight solid-state LiDAR sensors have brought new opportunities for autonomous unmanned aerial vehicles (UAVs) by advancing navigation safety and computation efficiency. Yet the successful developments of LiDAR-based UAVs must rely on extensive
Fish exhibit impressive locomotive performance and agility in complex underwater environments, using their undulating tails and pectoral fins for propulsion and maneuverability. Replicating these abilities in robotic fish is challenging; existing designs focus on either fast swimming or directional
Accurate self and relative state estimation are the critical preconditions for completing swarm tasks, e.g., collaborative autonomous exploration, target tracking, search and rescue. This paper proposes Swarm-LIO: a fully decentralized state estimation method for aerial swarm systems, in which each…
In this paper, we propose a novel swashplateless-elevon actuation (SEA) for dual-rotor tail-sitter vertical takeoff and landing (VTOL) unmanned aerial vehicles (UAVs). In contrast to the conventional elevon actuation (CEA) which controls both pitch and yaw using elevons, the SEA adopts swash-platele…
To ensure patient safety, many hospitals have implemented rapid response process to provide care to acute patients who experience acute physiological deterioration. However, those patients sometimes have to wait for a long time before an appropriate decision can be made, due to low availability of c