collaborators

7 papers

cs.AI2026

LongDocBench: Benchmarking TOC Hierarchy and Contextual Relationship Recovery in Long Documents

Yuefeng Zou, Yichen Lu, Jingxiao Yang +5

Parsing visual documents into machine-readable representations is fundamental to document intelligence. Existing benchmarks focus on page-level element recognition, reading order,…

cs.DB2026

AgenticDataBench: A Comprehensive Benchmark for Data Agents

Zhaoyan Sun, Shan Zhong, Daizhou Wen +10

Data science aims to derive actionable insights from heterogeneous raw data, unlocking the value of the massive amounts of data generated in modern society. Automating this process…

cs.CL2026

Every Step Counts: Step-Level Credit Assignment for Tool-Integrated Text-to-SQL

Yaxun Dai, Baolin Sun, Junying Wang +6

Tool-integrated Text-to-SQL parsing has emerged as a promising paradigm, framing SQL generation as a sequential decision-making process interleaved with tool execution. However, ex…

cs.LG2026

Fast NF4 Dequantization Kernels for Large Language Model Inference

Xiangbo Qi, Chaoyi Jiang, Murali Annavaram

Large language models (LLMs) have grown beyond the memory capacity of single GPU devices, necessitating quantization techniques for practical deployment. While NF4 (4-bit NormalFlo…

cs.CL2025

Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scaling

Pengfei Wang, Baolin Sun, Xuemei Dong +7

State-of-the-art (SOTA) Text-to-SQL methods still lag significantly behind human experts on challenging benchmarks like BIRD. Current approaches that explore test-time scaling lack…

cs.CE2025

Agentar-DeepFinance-100K: A Large-Scale Financial Dataset via Systematic Chain-of-Thought Synthesis Optimization

Xiaoke Zhao, Zhaowen Zhou, Lin Chen +12

Recent advancements in large language models (LLMs) have demonstrated remarkable general reasoning capabilities, holding significant potential for applications in the financial dom…