Computer Science
In many urban planning projects, social planners require the construction of a bridge to connect two regions separated by obstacles such as rivers or highways. This paper studies the mechanism design problem for locating a bridge between…
Distilling a fine-tuned teacher into a LoRA-adapted student is a standard recipe for parameter-efficient compression, but output-level KD does not explicitly control which rank-$r$ weight subspace the adapter occupies. We propose…
We present HiFA4, a post-training operator-level design that executes both QK^T and PV in FlashAttention as 4-bit HIF4 Cube GEMMs for LLM inference on Ascend NPUs, while maintaining the online softmax state in FP16. To our knowledge, HiFA4…
Classic models cast information seeking as iterative foraging: formulate a keyword query, scan results, reformulate, gather across sources, synthesize. We ask what happens when a conversational assistant is inserted into that episode.…
Large language models (LLMs) have recently emerged as powerful backbones for recommender systems by reformulating recommendation as a token-level generation task. Despite their promise, we identify a pervasive yet underexplored issue:…
Convolutional Neural Network (CNN) and Vision Transformer (ViT) for image classification exploit a dense grid of pixels containing redundant information. Consequently, for a larger image dataset, CNNs and ViTs face deployability challenges…
Generative models have changed how machine learning represents complex data distributions, especially in language and vision, yet many real-world systems are observed instead as continuous, high-dimensional, and noisy sensor time series.…
This report describes our approach to the Efficient Qwen Competition, where the goal is to enable low-latency serving of Qwen3.5-4B on a resource-constrained NVIDIA A10G GPU. Our system combines a quantized target model with speculative…
In this work we propose an efficient deferred software rasterization pipeline for real-time rendering of strand-based hair using hair meshes. Hair plays a crucial role in creating expressive 3D characters, yet strand-based approaches are…
Future sixth generation (6G) communications are expected to support robotic control tasks in applications such as industrial automation and emergency response, where sensors, computing units, and robots are interconnected via nervous…
The growing demand for privacy-preserving, data-intensive applications such as IoT, augmented reality, and autonomous systems positions Federated Learning (FL) as a key enabler in 6G networks. Over-the-Air FL (OTA-FL) leverages the…
Kraj\v{c}i, Liu, Mike\v{s}, and Moser proved in 2015 that the redundancy of binary Shannon-Fano coding is always below one bit. We sharpen this to a bound depending on the largest source probability $p_1$: an explicit seven-piece envelope…
Global reanalysis products such as ERA5-Land provide spatially complete weather fields but at resolutions too coarse for local applications, particularly in mountainous regions where temperature can vary by several degrees over short…
Federated Learning (FL) is fundamentally challenged by statistical heterogeneity, where non-identically distributed (non-IID) data induces client drift that severely hampers global convergence. While existing approaches attempt to mitigate…
Intelligent industrial maintenance critically relies on reliable fault diagnosis of rotating machinery. However, it faces formidable challenges from unknown fault types and domain shifts induced by varying operating conditions, which is…
This paper investigates the causal rate-distortion function for networked control systems with multiple encoders and a single decoder, a longstanding open problem in information and control theory. While previous work has explored the…
Federated Learning (FL) enables decentralized training without data sharing, but suffers from statistical heterogeneity across clients, leading to client drift, poor generalization, and sharp minima compared to centralized training.…
Recent work showed that language models represent character counts on curved 1D manifolds, with attention heads performing geometric transformations to enable computation. We test whether this generalizes across four ordinal tasks (bracket…
Vision-based deep reinforcement learning involves dealing with high-dimensional inputs of image information. It is crucial to abstract effective states from high-dimensional image inputs and limited samples for sample-efficient…
Adversarial attacks guide and provide additional training and test data for both adversarial training and adversarial robustness validation, and expose the 'piecewise linearity' of deep learning based models. Since adversarial attacks and…