51 citations · 55 across the 9 of their papers we have counts for
10 papers
PyFi: Toward Pyramid-like Financial Image Understanding for VLMs via Adversarial Agents
Yuqun Zhang, Yuxuan Zhao, Sijia Chen
This paper proposes PyFi, a novel framework for pyramid-like financial image understanding that enables vision language models (VLMs) to reason through question chains in a progres…
KAT-Coder Technical Report
Zizheng Zhan, Ken Deng, Jinghui Wang +37
Recent advances in large language models (LLMs) have enabled progress in agentic coding, where models autonomously reason, plan, and act within interactive software development wor…
HiPO: Hybrid Policy Optimization for Dynamic Reasoning in LLMs
Ken Deng, Zizheng Zhan, Wen Xiang +25
Large Language Models (LLMs) increasingly rely on Chain-of-Thought (CoT) reasoning to improve accuracy on complex tasks. However, always generating lengthy reasoning traces is inef…
SK2Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to Skin
Hanzhuo Tan, Weihao Li, Xiaolong Tian +4
Large Language Models (LLMs) have emerged as a promising approach for binary decompilation. However, the existing LLM-based decompilers still are somewhat limited in effectively pr…
Decompile-Bench: Million-Scale Binary-Source Function Pairs for Real-World Binary Decompilation
Hanzhuo Tan, Xiaolong Tian, Hanrui Qi +6
Recent advances in LLM-based decompilers have been shown effective to convert low-level binaries into human-readable source code. However, there still lacks a comprehensive benchma…
OASIS: Order-Augmented Strategy for Improved Code Search
Zuchen Gao, Zizheng Zhan, Xianming Li +6
Code embeddings capture the semantic representations of code and are crucial for various code-related large language model (LLM) applications, such as code search. Previous trainin…
Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?
Qingyuan Liang, Zhao Zhang, Zeyu Sun +9
Grammar serves as a cornerstone in programming languages and software engineering, providing frameworks to define the syntactic space and program structure. Existing research demon…
Prompt-based Code Completion via Multi-Retrieval Augmented Generation
Hanzhuo Tan, Qi Luo, Ling Jiang +4
Automated code completion, aiming at generating subsequent tokens from unfinished code, has been significantly benefited from recent progress in pre-trained Large Language Models (…
LLM4Decompile: Decompiling Binary Code with Large Language Models
Hanzhuo Tan, Qi Luo, Jing Li +1
Decompilation aims to convert binary code to high-level source code, but traditional tools like Ghidra often produce results that are difficult to read and execute. Motivated by th…
BinaryAI: Binary Software Composition Analysis via Intelligent Binary Source Code Matching
Ling Jiang, Junwen An, Huihui Huang +4
While third-party libraries are extensively reused to enhance productivity during software development, they can also introduce potential security risks such as vulnerability propa…