Gait Recognition in the Wild: A Large-Scale Benchmark and NAS-Based Baseline.

InsightDrive: Insight Scene Representation for End-to-End Autonomous Driving.

Bidirectional Prototype-Reward co-Evolution for Test-Time Adaptation of Vision-Language Models.

Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model.

WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation.

Stereo Anything: Unifying Stereo Matching with Large-Scale Mixed Data.

DriveMLLM: A Benchmark for Spatial Understanding with Multimodal Large Language Models in Autonomous Driving.

AdvDiffuser: Generating Adversarial Safety-Critical Driving Scenarios via Guided Diffusion.

LightStereo: Channel Boost Is All Your Need for Efficient 2D Cost Aggregation.

Instruct Large Language Models to Drive like Humans.

MaskFuser: Masked Fusion of Joint Multi-Modal Tokenization for End-to-End Autonomous Driving.

GenAD: Generative End-to-End Autonomous Driving.

OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline.

Multi-Prompt with Depth Partitioned Cross-Modal Learning.

A Simple Baseline for Supervised Surround-view Depth Estimation.

DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation.

Gait Recognition in the Wild: A Benchmark.

GaitStrip: Gait Recognition via Effective Strip-based Feature Representations and Multi-Level Framework.