Related papers: Real-time Event Joining in Practice With Kafka and…
Modern distributed systems demand low-latency, fault-tolerant event processing that exceeds traditional messaging architecture limits. While frameworks including Apache Kafka, RabbitMQ, Apache Pulsar, NATS JetStream, and serverless event…
In nonlinear dynamical systems, tipping refers to a critical transition from one steady state to another, typically catastrophic, steady state, often resulting from a saddle-node bifurcation. Recently, the machine-learning framework of…
Prior work has established Test-Time Training (TTT) as a general framework to further improve a trained model at test time. Before making a prediction on each test instance, the model is first trained on the same instance using a…
Existing serverless data analytics systems rely on external storage services like S3 for data shuffling and communication between cloud functions. While this approach provides the elasticity benefits of serverless computing, it incurs…
Big data analytics is gaining massive momentum in the last few years. Applying machine learning models to big data has become an implicit requirement or an expectation for most analysis tasks, especially on high-stakes applications.Typical…
Maintaining web-services is a mission-critical task where any down-time means loss of revenue and reputation (of being a reliable service provider). In the current competitive web services market, such a loss of reputation causes extensive…
Optical flow provides information on relative motion that is an important component in many computer vision pipelines. Neural networks provide high accuracy optical flow, yet their complexity is often prohibitive for application at the edge…
Training large Deep Neural Network (DNN) models at scale often encounters straggler issues, mostly in communications due to network congestion, RNIC/switch defects, or topological asymmetry. Under advanced pipeline parallelism, even minor…
The growing demand for real-time processing tasks is driving the need for multi-model inference pipelines on edge devices. However, cost-effectively deploying these pipelines while optimizing Quality of Service (QoS) and costs poses…
Vision-language-action (VLA) models have demonstrated exceptional performance in natural language-driven perception and control. However, the high computational cost of VLA models poses significant efficiency challenges, particularly for…
In recent years, deep reinforcement learning has emerged as a technique to solve closed-loop flow control problems. Employing simulation-based environments in reinforcement learning enables a priori end-to-end optimization of the control…
Deploying Large Language Models (LLMs) in streaming applications such as multi-round dialogue, where long interactions are expected, is urgently needed but poses two major challenges. Firstly, during the decoding stage, caching previous…
Popular video training methods mainly operate on a fixed number of tokens sampled from a predetermined spatiotemporal grid, resulting in sub-optimal accuracy-computation trade-offs due to inherent video redundancy. They also lack…
The widespread adoption of AI in industry is often hampered by its limited robustness when faced with scenarios absent from training data, leading to prediction bias and vulnerabilities. To address this, we propose a novel streaming…
AI deployment increasingly resembles a pipeline of data transformation, fine-tuning, and agent interactions rather than a monolithic LLM job; recent examples include RLHF/RLAIF training and agentic workflows. To cope with this shift, we…
Despite rapid advancements in lifelong learning (LLL) research, a large body of research mainly focuses on improving the performance in the existing \textit{static} continual learning (CL) setups. These methods lack the ability to succeed…
Input pipelines, which ingest and transform input data, are an essential part of training Machine Learning (ML) models. However, it is challenging to implement efficient input pipelines, as it requires reasoning about parallelism,…
Operationalizing AI has become a major endeavor in both research and industry. Automated, operationalized pipelines that manage the AI application lifecycle will form a significant part of tomorrow's infrastructure workloads. To optimize…
Recent advancements in discrete token-based speech generation have highlighted the importance of token-to-waveform generation for audio quality, particularly in real-time interactions. Traditional frameworks integrating semantic tokens with…
Diffusion models have revolutionized generative tasks through high-fidelity outputs, yet flow matching (FM) offers faster inference and empirical performance gains. However, current foundation FM models are computationally prohibitive for…