arXiv
ERUnderstand: Evaluating Vision-Language Models on Structured ER Diagrams
Entity-Relationship Diagrams (ERDs) are central to conceptual database design, yet they are typically available only ...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Efficient LLM-Generated Shuttling Compilers for Complex Trapped-Ion Architectures
Trapped-ion quantum computers rely on shuttling compilers, which cast an input algorithm into a sequence of ion-qubit...
arXiv
DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data
Pretraining data processing is critical to the downstream performance of Large Language Models (LLMs). However, many ...
arXiv
The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation
Multi-turn long-horizon planning is critical for foundation model agents, yet how to fundamentally improve it remains...
arXiv
KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability
Computer vision models have become highly effective for medical applications, yet their black-box nature continues to...
arXiv
Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
On-policy distillation (OPD) adapts diffusion models by querying a teacher along trajectories generated by the curren...
arXiv
ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding
Multimodal large language models (MLLMs) hold immense potential to revolutionize clinical practice, yet deploying the...
HuggingFace
OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation
Recent generative models are moving beyond silent video or standalone audio synthesis toward the joint generation of ...
HuggingFace
From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search
Agentic search enables large language models to solve knowledge-intensive tasks by interleaving multi-step reasoning ...
HuggingFace
DecoupleMix: Decoupled Ratio Search and Convex Allocation for Scalable VLM Data Recipes
While data curation for Vision Language Models (VLMs) is increasingly active, public practice for constructing pretra...
HuggingFace
JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents
Creative AI is moving from single-step asset generation toward long-horizon multimodal production. Although recent ge...
HuggingFace
Kimi K3: Open Frontier Intelligence
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision ...