Video, Demos and Posters
Posters
ReMindView-Bench
Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective (ECCV 2026)
FreezeAsGuard
FreezeAsGuard: Mitigating Illegal Adaptation of Diffusion Models via Selective Tensor Freezing (LifeGenIP Workshop at ECCV 2026)
InfiniBench
InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity (CVPR 2026)
Attribution-based Sparse Activation
Attribution-based Sparse Activation in Large Language Models (MLSys 2026)
ProGait
ProGait: A Multi-Purpose Video Dataset and Benchmark for Transfemoral Prosthesis Users (ICCV 2025)
PhyT2V
PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation (CVPR 2025)
GreenTrainer
Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation (ICLR 2024)
Video & Demos
Teasers
FreezeAsGuard
FreezeAsGuard: Mitigating Illegal Adaptation of Diffusion Models via Selective Tensor Freezing
ElasticTrainer
ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection
PTEase
PTEase: Objective Airway Examination for Pulmonary Telemedicine using Commodity Smartphones
TransFi
TransFi: emulating custom wireless physical layer from commodity wifi
Paper Presentations
SpiroSonic
SpiroSonic: Monitoring Human Lung Function via Acoustic Sensing on Commodity Smartphones
AgileNN
Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI
Smartphone GPU Side Channel
Eavesdropping User Credentials via GPU Side Channels on Smartphones
