DSRS: Teaching MLLMs to Perceive, Reason, and Segment in Complex Driving Scenes
cs.CV
Submitted: 2026-11-04
Updated: 2026-11-04
Terminology
Sources
- Reasoning Segmentation for Images and Videos: A Survey
- How to Enable LLM with 3D Capacity? A Survey of Spatial Reasoning in LLM
- A Survey of Large Language Model-Powered Spatial Intelligence Across Scales: Advances in Embodied Agents, Smart Cities, and Earth Science
- DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models
- DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving
- Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models
- ControlThinker: Unveiling Latent Semantics for Controllable Image Generation through Visual Reasoning
- Layer Normalization
- SAM 3: Segment Anything with Concepts
- VLA-3D: A Dataset for 3D Semantic Scene Understanding and Navigation
- Grounded 3D-LLM with Referent Tokens
- ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenes
- SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes
- Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving
- Extending Large Vision-Language Model for Diverse Interactive Tasks in Autonomous Driving
- DriveAction: A Benchmark for Exploring Human-like Driving Decisions in VLA Models
- One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos
- StAR: Segment Anything Reasoner
- Seg-ReSearch: Segmentation with Interleaved Reasoning and External Search
- Logic-RAG: Augmenting Large Multimodal Models with Visual-Spatial Knowledge for Road Scene Understanding
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs