Awesome Multimodal Modeling [Covers MLLM, UMM, and NMM]

Official implementation for "HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions".

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

Official implementation for "Language-Conditioned World Modeling for Visual Navigation"

Official implementation of paper "Unified World Models: Memory-Augmented Planning and Foresight for Visual Navigation"

Official implementation of Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions (NeurIPS DB Track'24 Spotlight).

[CVPR 2026] ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Maps

[ICLR 2026] RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning

🌐 Event Camera Vision in the Era of Large Models: A Survey

🌐 Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems

🌐 Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future

[CVPR 2026 Oral] WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World

Learning to Remove Lens Flare in Event Camera

[CVPR 2026 Highlight] U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences

"Paper2Slides: From Paper to Presentation in One Click"

[NeurIPS 2025 DB Track] 3EED: Ground Everything Everywhere in 3D

[NeurIPS 2025] SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understanding

Official Repo for Paper <EditMGT Unleashing the Potential of Masked Generative Transformer in Image Editing>

[NeurIPS 2025] Deep Memory Backtracking for Long Video Understanding

A list of works on evaluation of visual generation models, including evaluation metrics, models, and systems

[AAAI 2026 Oral] LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences

Official Competition Toolkit for The 2025 RoboSense Challenge

Official implementation of "Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence"

[ICCV 2025] Perspective-Invariant 3D Object Detection

[ACL 2026 Findings, ICCV 2025 Workshop Outstanding Paper Award] VChain: Chain-of-Visual-Thought for Reasoning in Video Generation

AevaScenes Python SDK

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

[SIGGRAPH Asia 2025] WorldExplorer: Towards Generating Fully Navigable 3D Scenes