14 accepted papers
AutoRegressive Visual Generation (ARVG) models retain an architecture compatible with language models, while achieving performance comparable to diffusion-based models. Quantization is commonly employed in neural networks to reduce model size and computational latency. However, applying quantization…
Large Language Models infuse newfound vigor into the advancement of the medical domain, yet the scarcity of data poses a significant bottleneck hindering community progress. In this paper, we release the largest ever medical Question Answering (QA) dataset with 26 Million QA pairs named Huatuo-26M.…
The rapid advancement of visual generative models necessitates efficient and reliable evaluation methods. Arena platform, which gathers user votes on model comparisons, can rank models with human preferences. However, traditional Arena methods, while established, require an excessive number of compa…
Multimodal large language models (MLLMs) have broadened the scope of AI applications. Existing automatic evaluation methodologies for MLLMs are mainly limited in evaluating objective queries without considering real-world user experiences, inadequately addressing the nuances of creative and associat…
This paper is devoted to the development of a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addressed by current mainstream models. Significant concerns emerge when addressing cultural sensitivity and local values. T…
Large Language Models (LLMs) provide a possibility to make a great breakthrough in medicine. The establishment of a standardized medical benchmark becomes a fundamental cornerstone to measure progression. However, medical environments in different regions have their local characteristics, e.g., the…
Unsupervised cross-lingual transfer involves transferring knowledge between languages without explicit supervision. Although numerous studies have been conducted to improve performance in such tasks by focusing on cross-lingual knowledge, particularly lexical and syntactic knowledge, current approac…
This paper presents a locomotion controller for a novel human-augmented legged robot, the Centaur robot, which is primarily developed to extend the human's ability to carry load. For such a human-robot walking system, there are requirements for the robot to maintain a balanced posture, provide a pro
Language is the principal tool for human communication, in which humor is one of the most attractive parts. Producing natural language like humans using computers, a.k.a, Natural Language Generation (NLG), has been widely used for dialogue systems, chatbots, machine translation, as well as computer-…
Open intent classification, which aims to correctly classify the known intents into their corresponding classes while identifying the new unknown (open) intents, is an essential but challenging task in dialogue systems. In this paper, we introduce novel K-center contrastive learning and adjustable d…
In this paper, we present HuatuoGPT, a Large Language Model (LLM) for medical consultation. The core recipe of HuatuoGPT is to leverage both distilled data from **ChatGPT** and real-world data from **doctors** in the supervised fine-tuning stage. This is not only because purely using **ChatGPT**-di…
Walking with load is a common task in daily life and disaster rescue. Long-term load carriage may cause irreversible damage to the human body. Although remarkable progress has been made in the field of wearable robots, it is still far from avoiding interference to human legs, which will lead to ener…
As an external manifestation of human emotions, expression recognition plays an important role in human-computer interaction. Although existing expression recognition methods performs perfectly on constrained frontal faces, there are still many challenges in expression recognition in natural scenes…
This paper describes a high-frame-rate (HFR) vision system that can detect multiple objects in an image of 512 × 512 pixels at 12,000 frames per seconds (fps). An optimized algorithm is proposed based on conventional Histograms of Oriented Gradient (HOG) descriptor and Support Vector Machine (SVM) c…