Michael Bendersky

Inference Scaling for Long-Context Retrieval Augmented Generation

Integrating Planning into Single-Turn Long-Form Text Generation

Knowledge Distillation with Perturbed Loss: From a Vanilla Teacher to a Proxy Teacher

Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning

Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting

Non-Intrusive Adaptation: Input-Centric Parameter-efficient Fine-Tuning for Versatile Multimodal Modeling