arXiv
ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation
Repository-level code generation requires implementing target functions while accounting for complex cross-file depen...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action ag...
arXiv
Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Prediction
Recent progress in 3D human pose estimation has made markerless recovery of skeletal motion increasingly accurate and...
arXiv
Validity of LLMs as data annotators: AMALIA on authority
A national language model offers a linguistic community its own instrument for measuring what its citizens say and va...
arXiv
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs
Post-training quantization is widely used to deploy large language models in resource-constrained settings, yet its e...
arXiv
Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows
Large language model (LLM) applications increasingly use explicit workflows for tool use, retrieval, branching, check...
arXiv
AUTOPILOT VQA: Benchmarking Vision-Language Models for Incident-Centric Dashcam Understanding
Recent advances in Vision-Language Models, Large Language Models, and Multimodal Large Language Models have improved ...
arXiv
Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graph
While UMAP is widely used for exploring high-dimensional data, typical workflows focus on its lower-dimensional embed...
arXiv
Using AI-based Learning Assistants in Higher Education: A Large-Scale Descriptive Analysis
In this study, we present a large-scale descriptive analysis of the use of an AI-based learning assistant (Syntea) in...
arXiv
SLORR: Simple and Efficient In-Training Low-Rank Regularization
Low-rank factorization is widely used to compress neural networks, but modern models are often not naturally amenable...
arXiv
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pie...
arXiv
OpenCoF: Learning to Reason Through Video Generation
Reasoning has become a core capability for large models, especially when reliable decisions require understanding log...