Latent-Lens: Visual Perception in Small Language Models Through Latent Communication
cs.LG, cs.AI
Submitted: 2026-10-30
Updated: 2026-10-30
Comments: Published at NeurIPS 2026
Code: https://github.com/QwenLM/Qwen2
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
- Enabling Agents to Communicate Entirely in Latent Space
- LoRA: Low-Rank Adaptation of Large Language Models
- Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent Collaboration
- Graph Convolutional Reinforcement Learning
- Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems
- TinyLlama: An Open-Source Small Language Model
- LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
- Cache-to-Cache: Direct Semantic Communication Between Large Language Models
- NeuralTSNE: A Python Package for the Dimensionality Reduction of Molecular Dynamics Data Using Neural Networks
- TinyLLaVA: A Framework of Small-scale Large Multimodal Models
- Why do AI agents communicate in human language?
- MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis