GUIAuditor: Enabling Post-hoc Child Safety Forensics via Action-Guided GUI Provenance on Mobile Devices
SLICEChat: Progressive In-Encoder Token Pruning for Whole-Slide Pathology Language Models
1
PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing
Fingerprinting Multimodal Large Language Models
Region-Level Policy Optimization for Fine-grained MLLM Perception
UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation
2
VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control
HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness
OmniHarness: Harnessing Generalizable Visual Generation via Symbolic Policy Learning
1
Embodied-BenchForge: A Closed-Loop Agentic Workflow for Embodied Benchmark Construction
1
ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding
VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification
MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads
ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding
