Related papers: Quantization-Aware Distillation for NVFP4 Inferenc…
The visual-question localized-answering (VQLA) system can serve as a knowledgeable assistant in surgical education. Except for providing text-based answers, the VQLA system can highlight the interested region for better surgical scene…
Large-scale pre-trained sequence-to-sequence models like BART and T5 achieve state-of-the-art performance on many generative NLP tasks. However, such models pose a great challenge in resource-constrained scenarios owing to their large…
Dense visual prediction tasks, such as detection and segmentation, are crucial for time-critical applications (e.g., autonomous driving and video surveillance). While deep models achieve strong performance, their efficiency remains a…
Question answering (QA) models are well-known to exploit data bias, e.g., the language prior in visual QA and the position bias in reading comprehension. Recent debiasing methods achieve good out-of-distribution (OOD) generalizability with…
Spoken question answering (SQA) is a challenging task that requires the machine to fully understand the complex spoken documents. Automatic speech recognition (ASR) plays a significant role in the development of QA systems. However, the…
Knowledge Distillation (KD) compresses computationally expensive pre-trained language models (PLMs) by transferring their knowledge to smaller models, allowing their use in resource-constrained or real-time settings. However, most smaller…
Recently, transformer-based language models such as BERT have shown tremendous performance improvement for a range of natural language processing tasks. However, these language models usually are computation expensive and memory intensive…
Knowledge distillation (KD) is generally considered as a technique for performing model compression and learned-label smoothing. However, in this paper, we study and investigate the KD approach from a new perspective: we study its efficacy…
Capability distillation applies knowledge distillation to selected model capabilities, aiming to compress a large language model (LLM) into a smaller one while preserving the abilities needed for a downstream task. However, most existing…
Knowledge Distillation (KD) is a promising technique for reducing the high computational demand of large language models (LLMs). However, previous KD methods are primarily applied to white-box classification models or training small models…
Knowledge distillation which learns a lightweight student model by distilling knowledge from a cumbersome teacher model is an attractive approach for learning compact deep neural networks (DNNs). Recent works further improve student network…
The powerful generalization of Vision-Language-Action (VLA) models is bottlenecked by their heavy reliance on massive, redundant, and unevenly valued datasets, hindering their widespread application. Existing model-centric optimization…
This paper presents a comprehensive analysis of quantization techniques for optimizing Large Language Models (LLMs), specifically focusing on Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT). Through empirical…
Knowledge distillation (KD) is a key technique for compressing large-scale language models (LLMs), yet prevailing logit-based methods typically employ static strategies that are misaligned with the dynamic learning process of student…
For large language models (LLMs), post-training quantization (PTQ) can significantly reduce memory footprint and computational overhead. Model quantization is rapidly evolving. Though many papers report breakthrough results, they are often…
Adapting pretrained language models (LMs) into vision-language models (VLMs) can degrade their native linguistic capability due to representation shift and cross-modal interference introduced during multimodal adaptation. Such loss is…
Large Language Models (LLMs) have shown promising performance in knowledge-intensive reasoning tasks that require a compound understanding of knowledge. However, deployment of the LLMs in real-world applications can be challenging due to…
Deploying Vision-Language Models (VLMs) on edge devices (e.g., smartphones and robots) is crucial for enabling low-latency and privacy-preserving intelligent applications. Given the resource constraints of these devices, quantization offers…
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…
Vision-Language Models (VLMs) achieve strong multimodal performance but are costly to deploy, and post-training quantization often causes significant accuracy loss. Despite its potential, quantization-aware training for VLMs remains…