Executable Rubrics Cut Evaluation Latency by Up to 320×

Also Worth Noting

• LiST: Local-Simplex Test-Time LoRA Fusion score 4
  关键词(1): vision-language; 顶会接收: EMNLP
• GTA-RAG: Graph-Trajectory-Augmented Reinforcement Learning for Multi-Turn Retrieval-Augmented Reasoning score 4
  关键词(5): GRPO, retrieval-augmented, RAG, agentic, reasoning; 顶会接收: EMNLP
• ExecRubrics: Executable Tool-Augmented Rubrics for Verifiable and Efficient Long-Form Evaluation score 4
  关键词(1): latency; 顶会接收: EMNLP
• Addressing the Selection Problem in Explainable AI score 3
  机构: xAI
• Context-Aware Cluster Decoding: Semantic Anchor-Driven Coherence in dMLLMs score 3
  顶会接收: EMNLP
• Who Pays More for Safety? Measuring the Disparate Cost of Safety Alignment across Languages score 3
  顶会接收: EMNLP
• TRACE: Temporal Retrieval with Anchored and Convergent Evidence for Long-Horizon Video Understanding score 3
  顶会接收: EMNLP
• GET: Generative Embedding Translation for Medical Image Segmentation score 3
  顶会接收: ECCV