Related papers: QUADS: QUAntized Distillation Framework for Effici…

Quantum Layout Synthesis (QLS) is a critical compilation stage that adapts quantum circuits to hardware constraints with an objective of minimizing the SWAP overhead. While heuristic tools demonstrate good efficiency, they often produce…

Large Language Models (LLMs) have recently demonstrated strong potential for cybersecurity question answering (QA), supporting decision-making in real-time threat detection and response workflows. However, their substantial computational…

Knowledge distillation offers a transformative pathway to developing powerful, yet efficient, small language models (SLMs) suitable for resource-constrained environments. In this paper, we benchmark the performance and computational cost of…

Low latency speech human-machine communication is becoming increasingly necessary as speech technology advances quickly in the last decade. One of the primary factors behind the advancement of speech technology is self-supervised learning.…

Prior work has shown that, on small amounts of training data, syntactic neural language models learn structurally sensitive generalisations more successfully than sequential language models. However, their computational complexity renders…

Quantization has emerged as a mainstream approach for deploying Large Language Models (LLMs) on resource-constrained devices, yet compressing precision below 4-bit typically causes severe performance degradation or prohibitive retraining…

Spoken language understanding (SLU) system usually consists of various pipeline components, where each component heavily relies on the results of its upstream ones. For example, Intent detection (ID), and slot filling (SF) require its…

This work proposes a grammar-based chunking strategy that segments input streams into semantically complete units by parsing dependency relations (e.g., noun phrase boundaries, verb-object structures) and punctuation features. The method…

Structured data question answering (QA), including table QA, Knowledge Graph (KG) QA, and temporal KG QA, is a pivotal research area. Advances in large language models (LLMs) have driven significant progress in unified structural QA…

Large-scale models (LSMs) can be an effective framework for semantic representation and understanding, thereby providing a suitable tool for designing semantic communication (SC) systems. However, their direct deployment is often hindered…

Flow-matching models have enabled high-quality text-to-speech synthesis, but their iterative sampling process during inference incurs substantial computational cost. Although distillation is widely used to reduce the number of inference…

Quantum technologies rely on high-quality resource states, such as maximally entangled or private states, which are indispensable for quantum communication and cryptography. In practice, however, these states are inevitably degraded by…

Previous studies have proved that cross-lingual knowledge distillation can significantly improve the performance of pre-trained models for cross-lingual similarity matching tasks. However, the student model needs to be large in this…

Model compression is increasingly essential for deploying large language models (LLMs), yet existing comparative studies largely focus on pruning and quantization evaluated primarily on knowledge-centric benchmarks. Thus, we introduce…

Diffusion transformers exhibit remarkable video generation capability, yet their prohibitive computational and memory costs hinder practical deployment. Model quantization and attention sparsification are two promising directions for…

Recognition of overlapped speech has been a highly challenging task to date. State-of-the-art multi-channel speech separation system are becoming increasingly complex and expensive for practical applications. To this end, low-bit neural…

Text-to-image generation via Stable Diffusion models (SDM) have demonstrated remarkable capabilities. However, their computational intensity, particularly in the iterative denoising process, hinders real-time deployment in latency-sensitive…

This technical report presents quantization-aware distillation (QAD) and our best practices for recovering accuracy of NVFP4-quantized large language models (LLMs) and vision-language models (VLMs). QAD distills a full-precision teacher…

Large Language Models (LLMs) have shown impressive results on a variety of text understanding tasks. Search queries though pose a unique challenge, given their short-length and lack of nuance or context. Complicated feature engineering…

As supervised fine-tuning (SFT) evolves from a lightweight post-training step into a compute-intensive phase rivaling mid-training in scale, data efficiency has become critical for aligning large language models (LLMs) under tight budgets.…