AI Research Brief
Search
Methodology
中文
Gated DeltaNet-2 Splits the Gate, Maestro Outscores GPT-5
10 selected from 374 papers
Featured
Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning
score 10
入选 HF Daily Papers; HF 热度: 32 upvotes (+4); 有代码实现; 关键词(1): fine-tuning
TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
score 10
入选 HF Daily Papers; HF 热度: 167 upvotes (+4); 有代码实现; 关键词(1): pre-training
Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?
score 10
入选 HF Daily Papers; HF 热度: 158 upvotes (+4); 有代码实现; 关键词(1): reasoning
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
score 10
入选 HF Daily Papers; HF 热度: 37 upvotes (+4); 有代码实现; 关键词(2): reasoning, open-source
Forecasting Scientific Progress with Artificial Intelligence
score 10
入选 HF Daily Papers; HF 热度: 34 upvotes (+4); 有代码实现; 关键词(1): reasoning
Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving
score 7
入选 HF Daily Papers; HF 热度: 22 upvotes (+4)
SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation
score 10
入选 HF Daily Papers; HF 热度: 24 upvotes (+4); 有代码实现; 关键词(4): compression, deployment, finetuning, reasoning
SceneAligner: 3D-Grounded Floorplan Localization in the Wild
score 8
入选 HF Daily Papers; HF 热度: 5 upvotes (+2); 有代码实现; 关键词(1): fine-tuning
Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles
score 9
入选 HF Daily Papers; HF 热度: 18 upvotes (+3); 有代码实现; 关键词(3): lightweight, latency, reasoning
Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
score 10
入选 HF Daily Papers; HF 热度: 20 upvotes (+4); 有代码实现; 关键词(2): mamba, reasoning