HuggingFace
Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model
Standard vision-language models (VLMs) suffer from Moravec's paradox: they excel at complex offline visual reasoning ...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition
Recovering an editable design file from a raster image is a common and costly bottleneck in modern design workflows, ...
HuggingFace
Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion
We present a reproducible pipeline for mapping Common Vulnerabilities and Exposures (CVEs) to MITRE ATT&CK Enterprise...
HuggingFace
Novel Claim or Déjà Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-Checking
Multimodal automated fact-checking (MAFC) verifies claims by retrieving and reasoning over external evidence. However...
HuggingFace
Pass the Baton: Trajectory-Relayed On-Policy Distillation
On-policy distillation (OPD) grounds token-level supervision in the student's own trajectory, yet suffers from prefix...
HuggingFace
MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities
Any-to-any models predict any modality from any combination of others within a single network, a formulation used in ...
HuggingFace
Parallel Decoding Distillation for Fast Image and Video Generation
Generation in video diffusion or flow models is computationally expensive due to the slow and iterative sampling proc...
HuggingFace
Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control
Joint-Embedding Predictive Architectures (JEPAs) learn world models by predicting in representation space rather than...
HuggingFace
VisualPatchWorld: Code World Models as Latent Structured Representations for Planning
Different research lines use the term world model in different ways, yet they share a common aim: to capture how the ...
HuggingFace
Where Quality Breaks in Compressed Short-Text Generation: Staged Bottleneck Localization
Compressed short-text generators can fail in two different places: the codec may discard information before generatio...
HuggingFace
TRACE: Business Rule-Grounded Reasoning Curriculum for Knowledge-Preserving Parametric Tool Retrieval in Enterprise LLMs
Parametric retrieval enables LLMs to retrieve tools implicitly by assigning each API a unique virtual token and train...
HuggingFace
A Vocabulary for Multi-Agent Automated Research Systems
We introduce a vocabulary for automated research systems built from one or more agents to make their design choices e...