1 citations · 1 across the 17 of their papers we have counts for
19 papers
MemTrace: State-Consistent Memory for Long-Horizon Coding Agents
Hongming Xu, Le Zhou, ZhongHe Jin +5
As coding agents take on long-horizon software evolution tasks spanning multiple files and stages, longer execution trajectories introduce two coupled challenges: (1) accumulated h…
CRAFT: An Agentic Spreadsheet Form Filling System with Template Awareness
Leyao Gu, Yingjie Xiong, Zirui Tang +5
Spreadsheet form filling requires agents to consolidate external evidence, ground values to precise cells, and preserve irregular template structure. Errors in early edits can over…
The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
Yi Duan, Ying Liu, Zirui Tang +32
Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improveme…
Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks
Boxiu Li, Zimo Wen, Yijia Fan +24
Long-horizon reasoning requires an agentic runtime that can persist when evidence supports its current approach and pivot when measurements reveal failure, hidden constraints, or a…
TEngineDB-V: An OLAP-Native Vector Search System for Large- Workloads at Tencent
Xufei Wu, Pengcheng Zhang, Yitong Song +11
Vector search systems are essential infrastructure for modern data-driven applications. Large- analytical vector search, which retrieves -- results for analytics (…
CLIP: Lightweight Cosine-Law-Based Inverted-List Pruning for IVF-Based Vector Search
Yitong Song, Shuhang Lu, Pengcheng Zhang +1
Vector search has become a core component of modern multimodal retrieval systems. Among existing methods, inverted file (IVF)-based methods are widely adopted due to their scalabil…
OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers
Siyuan Li, Jiabao Pan, Yumou Liu +9
Optimizer selection for large-scale model training has become a system-level design decision constrained jointly by compute, memory, tuning budget, and task diversity, yet the land…
Are We Ready For An Agent-Native Memory System?
Wei Zhou, Xuanhe Zhou, Shaokun Han +5
Memory for large language model (LLM) agents has rapidly evolved from simple retrieval-augmented mechanisms into a data management system that supports persistent information stora…
X+Slides: Benchmarking Audience-Conditioned Slide Generation
Haodong Chen, Xuanhe Zhou, Wei Zhou +6
Automatically generating slide decks from source documents is an important application of large language models (LLMs). Existing benchmarks primarily assess slide completeness and…
Mechanism-Guided Selective Unlearning for RLVR-Induced Reasoning
Chenyu Zhou, Qiliang Jiang, Shuning Wu +1
We propose MAST (Mechanism-Aligned Selective Targeting), a mechanism-guided method for unlearning RLVR-induced reasoning with substantially lower collateral damage than standard fu…
SetupX: Can LLM Agents Learn from Past Failures in Functionality-Correct Code Repository Setup?
Zihang Zhou, Ziqian Ren, Yukai Wu +7
Functionality-correct repository setup aims to configure execution environments (e.g., dependencies, build scripts) to successfully execute a repository's documented features. It p…
MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing
Bangrui Xu, Ziyang Miao, Xuanhe Zhou +7
VLM-based OCR models have become the de facto choice for document parsing, as they can accurately extract page-level elements (e.g., paragraphs within individual pages) together wi…
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
Bin Wang, Tianyao He, Linke Ouyang +40
Current document parsing methods advance primarily through model architecture innovation, while systematic engineering of training data remains underexplored. Yet state-of-the-art…
ByteHouse: ByteDance's Cloud-Native Data Warehouse for Real-Time Multimodal Data Analytics
Yuxing Han, Yu Lin, Yifeng Dong +13
With the rapid rise of intelligent data services, modern enterprises increasingly require efficient, multimodal, and cost-effective data analytics infrastructures. However, in Byte…
FireRed-OCR Technical Report
Hao Wu, Haoran Lou, Xinyue Li +19
We present FireRed-OCR, a systematic framework to specialize general VLMs into high-performance OCR models. Large Vision-Language Models (VLMs) have demonstrated impressive general…
Disk-Resident Graph ANN Search: An Experimental Evaluation
Xiaoyu Chen, Jinxiu Qu, Yitong Song +7
As data volumes grow while memory capacity remains limited, disk-resident graph-based approximate nearest neighbor (ANN) methods have become a practical alternative to memory-resid…
Qute: Towards Quantum-Native Database
Muzhi Chen, Xuanhe Zhou, Wei Zhou +7
This paper envisions a quantum database (Qute) that treats quantum computation as a first-class execution option. Unlike prior simulation-based methods that either run quantum algo…
ST-Raptor: An Agentic System for Semi-Structured Table QA
Jinxiu Qu, Zirui Tang, Hongzhang Huang +7
Semi-structured table question answering (QA) is a challenging task that requires (1) precise extraction of cell contents and positions and (2) accurate recovery of key implicit lo…
Vector Search for the Future: From Memory-Resident, Static Heterogeneous Storage, to Cloud-Native Architectures
Yitong Song, Xuanhe Zhou, Christian S. Jensen +1
Vector search (VS) has become a fundamental component in multimodal data management, enabling core functionalities such as image, video, and code retrieval. As vector data scales r…