10 papers
SWE-Stream: Scaling Executable Training Data for SWE Agents via Progressive Construction and Elastic Streaming
Chengyang Liu, Wen Yang, Shifeng Chen +5
Software engineering agents have advanced rapidly, but scaling their training remains constrained by the limited availability of high-quality executable tasks. Development historie…
Taming the Thinker: Conditional Entropy Shaping for Adaptive LLM Reasoning
Shuyu Wei, Jian Sun, Delai Qiu +6
Entropy-based deep reasoning has emerged as a promising direction for improving the reasoning capabilities of Large Language Models (LLMs), but existing methods often either increa…
LaTER: Efficient Test-Time Reasoning via Latent Exploration and Explicit Verification
Xuan Li, Yining Wang, Yuchen Liu +7
Chain-of-thought (CoT) reasoning improves large language models (LLMs) on difficult tasks, but it also makes inference expensive because every intermediate step must be generated a…
Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing
Fuyuan Liu, Dianyu Yu, He Ren +10
Accurate document parsing requires both robust content recognition and a stable parser interface. In explicit Document Layout Analysis (DLA) pipelines, downstream parsers do not co…
PARL: Position-Aware Relation Learning Network for Document Layout Analysis
Fuyuan Liu, Dianyu Yu, He Ren +10
Document layout analysis aims to detect and categorize structural elements (e.g., titles, tables, figures) in scanned or digital documents. Popular methods often rely on high-quali…
FocalOrder: Focal Preference Optimization for Reading Order Detection
Fuyuan Liu, Dianyu Yu, He Ren +10
Reading order detection is the foundation of document understanding. Most existing methods rely on uniform supervision, implicitly assuming a constant difficulty distribution acros…
BayesRAG: Probabilistic Mutual Evidence Corroboration for Multimodal Retrieval-Augmented Generation
Xuan Li, Yining Wang, Haocai Luo +6
Retrieval-Augmented Generation (RAG) has become a pivotal paradigm for Large Language Models (LLMs), yet current approaches struggle with visually rich documents by treating text a…
VAPO: End-to-end Slide-Enhanced Speech Recognition with Omni-modal Large Language Models
Rui Hu, Delai Qiu, Yining Wang +2
Omni-modal large language models (OLLMs) offer a promising end-to-end solution for slide-enhanced speech recognition due to their inherent multimodal capabilities. However, we foun…
Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Models
Rui Hu, Delai Qiu, Shuyu Wei +4
Omnimodal Large Language Models (OLLMs) have shown significant progress in integrating vision and text, but still struggle with integrating vision and audio, often exhibiting subop…
Contextual Dictionary Lookup for Knowledge Graph Completion
Jining Wang, Delai Qiu, YouMing Liu +4
Knowledge graph completion (KGC) aims to solve the incompleteness of knowledge graphs (KGs) by predicting missing links from known triples, numbers of knowledge graph embedding (KG…