6 papers
ASH: Agents that Self-Hone via Embodied Learning
Benjamin Schneider, Xavier Schneider, Victor Zhong +1
Long-horizon embodied tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrations, neither of which scales. We i…
StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs
Jialin Yang, Dongfu Jiang, Lipeng He +17
As Large Language Models (LLMs) become integral to software development workflows, their ability to generate structured outputs has become critically important. We introduce Struct…
SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding
Songcheng Cai, Zhiheng Lyu, Yuansheng Ni +13
Agentic repository-level code understanding is essential for automating complex software engineering tasks, yet the field lacks reliable benchmarks. Existing evaluations often over…
VideoScore2: Think before You Score in Generative Video Evaluation
Xuan He, Dongfu Jiang, Ping Nie +21
Recent advances in text-to-video generation have produced increasingly realistic and diverse content, yet evaluating such videos remains a fundamental challenge due to their multi-…
QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design
Benjamin Schneider, Dongfu Jiang, Chao Du +2
Long-video understanding has emerged as a crucial capability in real-world applications such as video surveillance, meeting summarization, educational lecture analysis, and sports…
ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations
Yubo Wang, Xueguang Ma, Ping Nie +7
Academic writing requires both coherent text generation and precise citation of relevant literature. Although recent Retrieval-Augmented Generation (RAG) systems have significantly…