Learning to Route in Visual Space via Multi-Step Embedding Retrieval
cs.AI, cs.IR
Submitted: 2026-09-30
Updated: 2026-10-01
Sources
- PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation
- LoRA: Low-Rank Adaptation of Large Language Models
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
- Representation Learning with Contrastive Predictive Coding
- Proximal Policy Optimization Algorithms
- Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini
- Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval
- ReAct: Synergizing Reasoning and Acting in Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems