Orion Weller presents new frontiers in information retrieval, focusing on how instruction following and reasoning capabilities from large language models can be integrated into retrieval systems. He introduces Promptriever, a fast embedder that can follow instructions, and Rank1, a powerful but slower reasoning reranker, demonstrating their ability to unlock new types of queries and significantly improve performance. 00:00 - New Frontiers in IR: Instruction Following and Reasoning 00:07 - Language Models (LLMs) & Their Key Capabilities 00:20 - Instruction Following 00:57 - Reasoning (Test-Time Compute) 01:41 - Bridging LLMs to Information Retrieval (IR) 01:52 - Evolution of Search (Google 1999 vs. Today) 02:17 - SearchGPT and Its Limitations 02:38 - Search Hasn't Changed Fundamentally 03:16 - Keyword Search (Traditional IR) 04:11 - Semantic Search (Modern IR) 04:38 - Instruction-Based Search (Proposed IR) 05:25 - Challenge: Reranking Alone Isn't Enough 06:02 - Prompt & Reasoning-Based Search (Advanced IR) 06:42 - What is an Instruction in IR? (Attributes & NLU) 07:31 - Call to Action: Prompt Retrievers Like LLMs 07:46 - Introducing Promptriever & Rank1 08:23 - Bi-Encoder vs. Cross-Encoder Architecture 09:10 - Can We Make Promptable Retrievers? (Promptriever's Idea) 10:08 - Generating Synthetic Instructions 10:34 - Promptriever Experimental Settings 11:20 - Promptriever Evaluation Data (FollowIR & InstructIR) 12:28 - Promptriever Instruction Following Results 12:59 - Promptriever Results: Out-of-Domain (OOD) with Generic Prompts 13:10 - Promptriever: Generic Prompt Examples 13:58 - Promptriever Performance with Generic Prompts (BEIR OOD) 14:44 - Promptriever: Robustness to Paraphrased Prompts 15:16 - Promptriever Summary 16:04 - Introducing Rank1 (Test-Time Compute for IR) 16:22 - Test-Time Compute in LLMs (O1 AIME example) 17:08 - What Does Test-Time Compute Look Like in IR? (Rank1 Example) 18:01 - Rank1 Evaluation Data (BRIGHT dataset) 18:50 - Rank1: Example of Model Reasoning (Leetcode Problem) 19:35 - Rank1 Results (BRIGHT, NevIR, mFollowIR) 20:15 - Rank1: Direct Comparison of Reasoning Chain 20:33 - Rank1: Finding New Relevant Documents (DL19/DL20) 21:05 - Re-judging Old Data (Explanation) 22:05 - Rank1 Summary 22:37 - The Goal: IR That Works Like LLMs 22:56 - Implications for Downstream Users 23:36 - Open Data/Open Source & Contact Info 23:45 - Q&A Session - Promptriever & Bi-Encoder 24:23 - Q&A Session - Operationalizing Promptriever 26:04 - Q&A Session - Cross-Encoder Integration 26:33 - Q&A Session - Meta-Search/Human-Provided Prompts 27:56 - Q&A Session - Rank1 vs. Frontier Reasoning Models 28:07 - Clarification on Rank1's Training Focus 28:30 - How Rank1 Compares to O3/Gemini 29:32 - Q&A Session - Fine-Tuning Rank1 30:19 - Q&A Session - Where to Find the Models 30:45 - Conclusion of Q&A