Related papers: Pangu-ACE: Adaptive Cascaded Experts for Education…

A/B testing is the foundation of decision-making in online platforms, yet social products often suffer from network interference: user interactions cause treatment effects to spill over into the control group. Such spillovers bias causal…

Existing Reward Models (RMs), typically trained on general preference data, struggle in Retrieval Augmented Generation (RAG) settings, which require judging responses for faithfulness to retrieved context, relevance to the user query,…

We designed a Retrieval-Augmented Generation (RAG) system to provide large language models with relevant documents for answering domain-specific questions about Pittsburgh and Carnegie Mellon University (CMU). We extracted over 1,800…

With new accelerator hardware for DNN, the computing power for AI applications has increased rapidly. However, as DNN algorithms become more complex and optimized for specific applications, latency requirements remain challenging, and it is…

Cascade is a widely used approach that rejects obvious negative samples at early stages for learning better classifier and faster inference. This paper presents chained cascade network (CC-Net). In this CC-Net, the cascaded classifier at a…

In modern GPU inference, cache efficiency remains a major bottleneck, and heuristic policies such as \textsc{LRU} can perform far worse than the offline optimum. Existing learning-based caching systems improve hit rates mainly through…

Federated learning is a prime candidate for distributed machine learning at the network edge due to the low communication complexity and privacy protection among other attractive properties. However, existing algorithms face issues with…

Motivated by packet routing in computer networks, online queuing systems are composed of queues receiving packets at different rates. Repeatedly, they send packets to servers, each of them treating only at most one packet at a time. In the…

Extreme learning machine (ELM) as an emerging branch of shallow networks has shown its excellent generalization and fast learning speed. However, for blended data, the robustness of ELM is weak because its weights and biases of hidden nodes…

Timestep sampling $p(t)$ is a central design choice in Flow Matching models, yet common practice increasingly favors static middle-biased distributions (e.g., Logit-Normal). We show that this choice induces a speed--quality trade-off:…

The task of point cloud upsampling (PCU) is to generate dense and uniform point clouds from sparse input captured by 3D sensors like LiDAR, holding potential applications in real yet is still a challenging task. Existing deep learning-based…

Retrieval-augmented generation (RAG) systems trained using reinforcement learning (RL) with reasoning are hampered by inefficient context management, where long, noisy retrieved documents increase costs and degrade performance. We introduce…

The sprint-based iterative approach in the Agile software development method allows continuous feedback and adaptation. One of the crucial Agile software development activities is the sprint planning session where developers estimate the…

A P300 ERP-based Brain-Computer Interface (BCI) speller is an assistive communication tool. It searches for the P300 event-related potential (ERP) elicited by target stimuli, distinguishing it from the neural responses to non-target stimuli…

Sentence embeddings are a foundational component for semantic search, clustering, classification, and retrieval-augmented generation. This paper presents embeddingmagibu-200m, a Turkish-focused sentence embedding model that produces…

Accurate and efficient access to laboratory protocols is essential in Anatomical Pathology (AP), where up to 70% of medical decisions depend on laboratory diagnoses. However, static documentation such as printed manuals or PDFs is often…

Most existing end-to-end Table Question Answering (Table QA) models consist of a two-stage framework with a retriever to select relevant table candidates from a corpus and a reader to locate the correct answers from table candidates. Even…

Multi-hop question answering requires aggregating information from multiple documents, a critical capability for knowledge-intensive applications. A fundamental challenge lies in efficiently identifying the minimal relevant document set…

Speculative decoding has emerged as a powerful method to improve latency and throughput in hosting large language models. However, most existing implementations focus on generating a single sequence. Real-world generative AI applications…

Distributed control systems require high reliability and availability guarantees despite often being deployed at the edge of network infrastructure. Edge computing resources are less secure and less reliable than centralized resources in…