Learning Multimodal Embeddings with Evidence-Aligned Readout
cs.CV, cs.IR
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- Qwen3-VL Technical Report
- Why do LLMs attend to the first token?
- ExpThink: Experience-Guided Reinforcement Learning for Adaptive Chain-of-Thought Compression
- Omni-Streaming Thinking
- LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger
- Claim-Level Rubric Rewards for Video Caption Reinforcement Learning
- GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
- Towards Spatial Supersensing in the Wild
- Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models
- Octopus: Agentic Multimodal Reasoning with Six-Capability Orchestration
- PLUME: Latent Reasoning Based Universal Multimodal Embedding
- Dynamic Residual Encoding with Slide-Level Contrastive Learning for End-to-End Whole Slide Image Representation
- Unveiling Fine-Grained Visual Traces: Evaluating Multimodal Interleaved Reasoning Chains in Multimodal STEM Tasks
- IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams
- Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
- Reasoning Guided Embeddings: Leveraging MLLM Reasoning for Improved Multimodal Retrieval
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- Beyond Chain-of-Thought: Rewrite as a Universal Interface for Generative Multimodal Embeddings
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models