HuggingFace
WorldDiT: A Unified Diffusion Architecture for World and Action Modeling
Many recent robot policies pursue stronger control by using large pretrained vision-language models (VLMs) as the act...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models
Large Vision-Language Models (LVLMs) remain bottlenecked by massive computational footprints, precluding their deploy...
HuggingFace
TILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic Reward
Recent advances in powerful text-to-image generation models have made it increasingly important to develop test-time ...
HuggingFace
Bitcoin Price Direction Prediction via Regime-Aware Multi-Modal Fusion of Social Sentiment and Technical Features
Bitcoin price prediction on sub-daily timescales is a hard open problem in computational finance. Bitcoin exhibits fa...
arXiv
Agentic Permissions Policy Algebra for Taint Confinement in LLM Agents
Autonomous LLM agents processing mixed-confidentiality data face severe security risks from prompt injection attacks ...
arXiv
Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects
The wide-scale use of sparse autoencoders (SAEs) as interpretability tools is limited by inconsistent links between S...
arXiv
Efficiency Matters in Autonomous Research
AI-driven autonomous research (AR) systems are becoming increasingly effective across a broad range of tasks. Their p...
arXiv
Reason-Mediated Behavioral Models for Auditing LLM Social Simulators
Large language models are increasingly used as social simulators, including as synthetic survey respondents. Most eva...
arXiv
A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility
Scientific user facilities accumulate decades of operational knowledge that no single search index covers: electronic...
arXiv
Eviction as Estimation: A Fixed-Lag Smoothing View of Test-Time Memory, and When Measuring Beats Accumulating
A language model with a bounded working memory must repeatedly decide which stored items to keep. Every deployed meth...
arXiv
Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification
Multi-modal classification leverages complementary information across diverse data sources to enhance predictive perf...
arXiv
Denial of Deadline: Network-Driven Accuracy Collapse in Distributed Inference Pipelines
Inference systems increasingly combine a fast path that returns predictions within the application's latency deadline...