Lens3D: Target-Conditioned Visual Foveation for Fine-Grained 3D Understanding
cs.CV
Submitted: 2026-10-05
Updated: 2026-10-05
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding
- 3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding
- ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning
- A Brief Overview: On-Policy Self-Distillation In Large Language Models
- Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes
- An Embodied Generalist Agent in 3D World
- LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness
- ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding
- CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models
- Distilling the Knowledge in a Neural Network
- Unifying distillation and privileged information
- Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
- OpenAI GPT-5 System Card
- Gemini: A Family of Highly Capable Multimodal Models
- Qwen3.5-Omni Technical Report
- Qwen3-VL Technical Report
- Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers
- Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning
- Grounded 3D-LLM with Referent Tokens
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