Xiaoxue Cheng
YOU?
Author Swipe
View article: ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Search
ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Search Open
Designing protein sequences that fold into a target 3D structure, known as protein inverse folding, is a fundamental challenge in protein engineering. While recent deep learning methods have achieved impressive performance by recovering na…
View article: Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking
Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking Open
Large language models (LLMs) demonstrate exceptional capabilities, yet still face the hallucination issue. Typical text generation approaches adopt an auto-regressive generation without deliberate reasoning, which often results in untrustw…
View article: Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems
Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems Open
Recently, slow-thinking reasoning systems, such as o1, have demonstrated remarkable capabilities in solving complex reasoning tasks. These systems typically engage in an extended thinking process before responding to a query, allowing them…
View article: Enhancing LLM Reasoning with Reward-guided Tree Search
Enhancing LLM Reasoning with Reward-guided Tree Search Open
Recently, test-time scaling has garnered significant attention from the research community, largely due to the substantial advancements of the o1 model released by OpenAI. By allocating more computational resources during the inference pha…
View article: ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting
ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting Open
Chain-of-Thought (CoT) prompting can enhance the reasoning capabilities of large language models (LLMs), establishing itself as a primary approach to solving complex reasoning tasks. Existing CoT synthesis approaches usually focus on simpl…
View article: The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models
The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models Open
In the era of large language models (LLMs), hallucination (i.e., the tendency to generate factually incorrect content) poses great challenge to trustworthy and reliable deployment of LLMs in real-world applications. To tackle the LLM hallu…
View article: Graphene Oxide Sheets Decorated with Octahedral Molybdenum Cluster Complexes for Enhanced Photoinactivation of <i>Staphylococcus aureus</i>
Graphene Oxide Sheets Decorated with Octahedral Molybdenum Cluster Complexes for Enhanced Photoinactivation of <i>Staphylococcus aureus</i> Open
The emergence of multidrug-resistant microbial pathogens poses a significant threat, severely limiting the options for effective antibiotic therapy. This challenge can be overcome through the photoinactivation of pathogenic bacteria using …
View article: HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models Open
Large language models (LLMs), such as ChatGPT, are prone to generate hallucinations, i.e., content that conflicts with the source or cannot be verified by the factual knowledge. To understand what types of content and to which extent LLMs …
View article: Digitization of Museum Curation Through Incorporating Virtual Reality Technology
Digitization of Museum Curation Through Incorporating Virtual Reality Technology Open
Virtual reality technology has grown increasingly valuable as a result of the wave of digitization and the arrival of the information era, and it is highly regarded by people from all walks of life.Along with the social economy of the nati…
View article: Research on the Development of the Palace Museum Based on Social Media
Research on the Development of the Palace Museum Based on Social Media Open
In the modern day, social media-based museums' communication capacities play a significant part in bridging the formation of relationships between the museum and its visitors.In order to study the communication model of museums, academics …
View article: HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models Open
Large language models (LLMs), such as ChatGPT, are prone to generate hallucinations, i.e., content that conflicts with the source or cannot be verified by the factual knowledge. To understand what types of content and to which extent LLMs …
View article: TextBox 2.0: A Text Generation Library with Pre-trained Language Models
TextBox 2.0: A Text Generation Library with Pre-trained Language Models Open
To facilitate research on text generation, this paper presents a comprehensive and unified library, TextBox 2.0, focusing on the use of pre-trained language models (PLMs). To be comprehensive, our library covers $13$ common text generation…
View article: WITHDRAWN: The Catalytic Pyrolysis Mechanism of Cellulose On ZSM-5: Based On Py-GC/MS And Density Functional Theory
WITHDRAWN: The Catalytic Pyrolysis Mechanism of Cellulose On ZSM-5: Based On Py-GC/MS And Density Functional Theory Open
Cellulose is one of the main components of terrestrial biomass. In this study, a zeolite catalyst (ZSM-5) was used to catalyze the pyrolysis of cellulose. The components produced during pyrolysis were tested by Py-GC/MS, and the pyrolysis …
View article: Establishment and verification of longitudinal aerodynamic model of tandem wing aircraft
Establishment and verification of longitudinal aerodynamic model of tandem wing aircraft Open
This paper clarified the contribution of front wing and rear wing to the longitudinal aerodynamic derivative by analyzing the characteristics of tandem wing aircraft. By combining the structure and aerodynamic simulation data of the aircra…