Related papers: Quality-Driven Disorder Handling for M-way Sliding…
We introduce StreamDiffusion, a real-time diffusion pipeline designed for interactive image generation. Existing diffusion models are adept at creating images from text or image prompts, yet they often fall short in real-time interaction.…
Current motion-conditioned video generation methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction. We present MotionStream, enabling sub-second latency with up to 29 FPS…
Communication networks are time-varying and hence, fair sharing of network resources among the users in such a dynamic environment is a challenging task. In this context, a time-varying network model is designed and the shortest user's…
Big Data are rapidly produced from various heterogeneous data sources. They are of different types (text, image, video or audio) and have different levels of reliability and completeness. One of the most interesting architectures that deal…
Normalizing flow is a generative modeling approach with efficient sampling. However, Flow-based models suffer two issues: 1) If the target distribution is manifold, due to the unmatch between the dimensions of the latent target distribution…
Concept drift in learning and classification occurs when the statistical properties of either the data features or target change over time; evidence of drift has appeared in search data, medical research, malware, web data, and video. Drift…
Scaling global aggregations is a challenge for exactly-once stream processing systems. Current systems implement these either by computing the aggregation in a single task instance, or by static aggregation trees, which limits scalability…
Cardinality constrained submodular function maximization, which aims to select a subset of size at most $k$ to maximize a monotone submodular utility function, is the key in many data mining and machine learning applications such as data…
Fault tolerance is a property which needs deeper consideration when dealing with streaming jobs requiring high levels of availability and low-latency processing even in case of failures where Quality-of-Service constraints must be adhered…
Distributed optimization finds applications in large-scale machine learning, data processing and classification over multi-agent networks. In real-world scenarios, the communication network of agents may encounter latency that may affect…
Asynchronous federated learning aims to solve the straggler problem in heterogeneous environments, i.e., clients have small computational capacities that could cause aggregation delay. The principle of asynchronous federated learning is to…
Software-Defined Networking (SDN) introduces a centralized network control and management by separating the data plane from the control plane which facilitates traffic flow monitoring, security analysis and policy formulation. However, it…
Service platforms must determine rules for matching heterogeneous demand (customers) and supply (workers) that arrive randomly over time and may be lost if forced to wait too long for a match. Our objective is to maximize the cumulative…
The proliferation of GPS-enabled devices has led to the development of numerous location-based services. These services need to process massive amounts of spatial data in real-time. The current scale of spatial data cannot be handled using…
Score Distillation Sampling (SDS) is a recent but already widely popular method that relies on an image diffusion model to control optimization problems using text prompts. In this paper, we conduct an in-depth analysis of the SDS loss…
Integrating the outputs of multiple classifiers via combiners or meta-learners has led to substantial improvements in several difficult pattern recognition problems. In the typical setting investigated till now, each classifier is trained…
Modeling network traffic is gaining importance in order to counter modern threats of ever increasing sophistication. It is though surprisingly difficult and costly to construct reliable classifiers on top of telemetry data due to the…
Performance analysis of queueing networks is one of the most challenging areas of queueing theory. Barring very specialized models such as product-form type queueing networks, there exist very few results which provide provable…
Federated Learning (FL) is a distributed machine learning (ML) paradigm, aiming to train a global model by exploiting the decentralized data across millions of edge devices. Compared with centralized learning, FL preserves the clients'…
Large language models for vertical domains are bottlenecked by the scarcity of complex, domain-specific task-oriented dialogues. Existing data acquisition pipelines face a persistent trilemma: expert annotation is expensive, real-world…