Papers with brute-force search
Operational Advice for Dense and Sparse Retrievers: HNSW, Flat, or Inverted Indexes? (2025.acl-industry)
Copied to clipboard
| Challenge: | Currently, practitioners working on dense retrieval face a bewildering number of choices. |
| Approach: | They propose a framework for thinking about retrieval in terms of nearest-neighbor search over vector representations where these representations can be dense (typically called embeddings, generated from transformers) or flat (with brute-force search) |
| Outcome: | The proposed model explicates tradeoffs between HNSW and flat indexes from the perspectives of indexing time, query evaluation performance, and retrieval quality. |
Learning to Predict Task Transferability via Soft Prompt (2023.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that fine-tuning pretrained language models on helpful intermediate tasks yields further gains. |
| Approach: | They propose to train an affinity scoring function to predict transferability between tasks by conditioning on task embeddings. |
| Outcome: | The proposed method efficiently identifies beneficial tasks for transfer learning. |
MAVIS: Multi-Agent Video Retrieval via Structured Video Understanding (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for video retrieval rely on embedding-based full-corpus scanning, but there is a bottleneck in semantic asymmetry and computational redundancy. |
| Approach: | They propose a multi-agent framework that rethinks retrieval as cooperative reasoning . they parse raw videos into a structured semantic library, enabling explicit attribute-level indexing . |
| Outcome: | The proposed framework bridges the granularity mismatch gap by parsing raw videos into a structured semantic library . it employs a Logic-aware Debate mechanism with a strict veto protocol . the proposed framework achieves competitive performance without task-specific fine-tuning . |