36 citations · 60 across the 19 of their papers we have counts for
21 papers
Making AI Scientists Auditable from Evidence to Claim
Zijian Wang, Hanqi Li, Ziyue Yang +17
AI research systems can report improved results without establishing that the tested implementation matches the method described in their conclusions. We introduce Xcientist, a res…
DeepSurvey: Agent-Oriented Automated Survey Generation with Analytical Depth and Citation Reliability
Ziyue Yang, Da Ma, Hanqi Li +8
As scientific literature grows rapidly and research increasingly involves AI agents, automated survey generation has become a key capability for both agents and human researchers.…
CharTool: Tool-Integrated Visual Reasoning for Chart Understanding
Situo Zhang, Yifan Zhang, Zichen Zhu +6
Charts are ubiquitous in scientific and financial literature for presenting structured data. However, chart reasoning remains challenging for multimodal large language models (MLLM…
PACER: Blockwise Pre-verification for Speculative Decoding with Adaptive Length
Situo Zhang, Yifan Zhang, Zichen Zhu +5
Speculative decoding (SD) is a powerful technique for accelerating the inference process of large language models (LLMs) without sacrificing accuracy. Typically, SD employs a small…
PaperGuide: Making Small Language-Model Paper-Reading Agents More Efficient
Zijian Wang, Tiancheng Huang, Hanqi Li +3
The accelerating growth of the scientific literature makes it increasingly difficult for researchers to track new advances through manual reading alone. Recent progress in large la…
ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge
Zihan Zhao, Ziping Wan, Lu Chen +12
Atomized chemical knowledge, such as functional group information of molecules and reactions, plays a pivotal intermediate role in the reasoning process that connects molecular str…
Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations
Da Ma, Gonghu Shang, Zhi Chen +6
Instruction tuning improves the ability of large language models (LLMs) to follow diverse human instructions, but achieving strong performance on specific target tasks remains chal…
AdaEAGLE: Optimizing Speculative Decoding via Explicit Modeling of Adaptive Draft Structures
Situo Zhang, Hankun Wang, Da Ma +4
Speculative Decoding (SD) is a popular lossless technique for accelerating the inference of Large Language Models (LLMs). We show that the decoding speed of SD frameworks with stat…
Reducing Tool Hallucination via Reliability Alignment
Hongshen Xu, Zichen Zhu, Lei Pan +6
Large Language Models (LLMs) have expanded their capabilities beyond language generation to interact with external tools, enabling automation and real-world applications. However,…
Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity
Da Ma, Lu Chen, Situo Zhang +8
The rapid expansion of context window sizes in Large Language Models~(LLMs) has enabled them to tackle increasingly complex tasks involving lengthy documents. However, this progres…
SciDFM: A Large Language Model with Mixture-of-Experts for Science
Liangtai Sun, Danyu Luo, Da Ma +7
Recently, there has been a significant upsurge of interest in leveraging large language models (LLMs) to assist scientific discovery. However, most LLMs only focus on general scien…
Evolving Subnetwork Training for Large Language Models
Hanqi Li, Lu Chen, Da Ma +3
Large language models have ushered in a new era of artificial intelligence research. However, their substantial training costs hinder further development and widespread adoption. I…
Sparsity-Accelerated Training for Large Language Models
Da Ma, Lu Chen, Pengyu Wang +6
Large language models (LLMs) have demonstrated proficiency across various natural language processing (NLP) tasks but often require additional training, such as continual pre-train…
Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback
Hongshen Xu, Zichen Zhu, Situo Zhang +4
Large Language Models (LLMs) often generate erroneous outputs, known as hallucinations, due to their limitations in discerning questions beyond their knowledge scope. While address…
Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding
Hongshen Xu, Lu Chen, Zihan Zhao +4
The growing prevalence of visually rich documents, such as webpages and scanned/digital-born documents (images, PDFs, etc.), has led to increased interest in automatic document und…
Developing ChemDFM as a large language foundation model for chemistry
Zihan Zhao, Da Ma, Lu Chen +11
Artificial intelligence (AI) has played an increasingly important role in chemical research. However, most models currently used in chemistry are specialist models that require tra…
ASTormer: An AST Structure-aware Transformer Decoder for Text-to-SQL
Ruisheng Cao, Hanchong Zhang, Hongshen Xu +4
Text-to-SQL aims to generate an executable SQL program given the user utterance and the corresponding database schema. To ensure the well-formedness of output SQLs, one prominent a…
SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research
Liangtai Sun, Yang Han, Zihan Zhao +5
Recently, there has been growing interest in using Large Language Models (LLMs) for scientific research. Numerous benchmarks have been proposed to evaluate the ability of LLMs for…
DFM: Dialogue Foundation Model for Universal Large-Scale Dialogue-Oriented Task Learning
Zhi Chen, Jijia Bao, Lu Chen +10
Building a universal conversational agent has been a long-standing goal of the dialogue research community. Most previous works only focus on a small set of dialogue tasks. In this…
Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL
Zhi Chen, Lu Chen, Hanqi Li +4
Recently, Text-to-SQL for multi-turn dialogue has attracted great interest. Here, the user input of the current turn is parsed into the corresponding SQL query of the appropriate d…
Developing a Process in Architecting Microservice Infrastructure with Docker, Kubernetes, and Istio
Yujing Wang, Darrel Ma
As an application usage grows, its owner scales up vertically by replacing old machines with more powerful ones. This methodology is expensive and leads to resource waste. In respo…