会员服务
From Seeing to Reporting: A Theory of Reliable Visual Set Generation in Vision-Language Models
Arxiv
0+阅读 · 10月18日
Star Light, Star Bright: Can Multimodal Models Parse an Astronomy Visual Question Answering Dataset Right?
Arxiv
0+阅读 · 10月15日
TVPara: Paralinguistic Captioning of Expressive TV-Series Speech in Complex Acoustic Environments
Arxiv
0+阅读 · 10月14日
Read, Parse, Describe: Unified Document Parsing with Visual Element Description Generation
Arxiv
0+阅读 · 10月14日
REA: From Correct LLM Judgments to Safe Decision Delivery
Arxiv
0+阅读 · 10月12日
SAGA: Score-Weighted Adaptive Generation Alignment for Low-Resource Nordic Language Models
Arxiv
0+阅读 · 10月13日
XYBench: Can LLMs Respond Pragmatically to Queries with Misconceptions?
Arxiv
0+阅读 · 9月6日
PARSE: Provenance-Aware Retrieval Sanitization for Professional Domain LLM Agents
Arxiv
0+阅读 · 9月12日
Strengthening LargeRDFBench for Interoperable Federated SPARQL Evaluation
Arxiv
0+阅读 · 8月31日
CRAFT: Fine-Tuning Pre-hoc Explainability in AI-native 6G RAN
Arxiv
0+阅读 · 9月1日
Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling
Arxiv
0+阅读 · 8月31日
VoiceCodeBench: Evaluating Exact Structured-Token Recovery in Automatic Speech Recognition
Arxiv
0+阅读 · 8月28日
Environment-Sensitive Lexicographic Disambiguation for Contextual Parsing
Arxiv
0+阅读 · 7月6日
PhotoHOI: Synthesizing 3D Hand-Object Interactions from a Single RGB Photograph
Arxiv
0+阅读 · 8月3日
PhotoHOI: Synthesizing 3D Hand-Object Interactions from a Single RGB Photograph
Arxiv
0+阅读 · 8月6日
参考链接
微信扫码咨询专知VIP会员
Top