SimWAM Hits 91.5 as LoRA Cuts Memory 43.9%

Featured

• SimWAM: A Simple World Action Model for End-to-End Autonomous Driving score 10
  入选 HF Daily Papers; HF 热度: 102 upvotes (+4); 有代码实现; 关键词(2): lightweight, latency
• YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Family score 8
  入选 HF Daily Papers; HF 热度: 20 upvotes (+4); 关键词(3): deployment, real-time, fine-tuning
• Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection score 9
  入选 HF Daily Papers; HF 热度: 11 upvotes (+3); 有代码实现; 关键词(2): reasoning, open-source
• Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events score 6
  入选 HF Daily Papers; HF 热度: 4 upvotes (+1); 有代码实现
• Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination score 5
  入选 HF Daily Papers; HF 热度: 4 upvotes (+1); 关键词(1): pretraining
• Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding score 5
  入选 HF Daily Papers; HF 热度: 3 upvotes (+1); 关键词(2): reasoning, open-source

Also Worth Noting

• Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence score 5
  入选 HF Daily Papers; HF 热度: 3 upvotes (+1); 关键词(5): distillation, serving, reasoning, vision-language, embodied