Seminar 2025

MAMBA-Based Weakly Supervised Medical Image Segmentation with Cross-Modal Textual Information

MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm

3DGazeNet: Generalizing 3D Gaze 

Estimation with Weak-Supervision from Synthetic Views

A Time Series is Worth 64 Words: Long-term Forecasting with Transformers (PatchTST)

Smart Insole: Predicting 3D human pose from foot pressure

Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation

Architcture of YOLO

TIP: Tabular-Image Pre-training for Multimodal Classification with Incomplete Data

Can Prompt Learning Benefit Radiology Report Generation?

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

JOINED : Prior Guided Multi-task Learning for Joint Optic Disc/Cup Segmentation and Fovea Detection

Honeybee: Locality-enhanced Projector for Multimodal LLM

Smart Insole

Dance Generation Flow

DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control

VGGT: Visual Geometry Grounded Transformer

Noise-Consistent Siamese-Diffusion for Medical Image Synthesis and Segmentation

Noisy Label

Show and Segment: Universal Medical Image Segmentation via In-Context Learning

Are we using appropriate segmentation metrics?

Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models

NLP: A Survey

VOLO: Vision Outlooker for Visual Recognition

Video Grounding: Debias strategy

UnSeGArmaNet: Unsupervised Image Segmentation using Graph Neural Networks with Convolutional ARMA Filters

Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation

Medical Phrase Grounding with Region-Phrase

Context Contrastive Alignment

Optimizing Diffusion Noise Can Serve As Universal Motion Priors

CleanDIFT: Diffusion Features without Noise

Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors

Beyond Adapting SAM: Towards End-to-End Ultrasound Image Segmentation via Auto Prompting

Local-Global Video-Text Interactions for Temporal Grounding

Human Motion Diffusion Model

Large Language Diffusion Models

3D Gaussian Splatting

for Real-Time Radiance Field Rendering

Global Context Vision Transformers

Early Research in Continual Learning

Research Introduction: Segmentation

DETRs Beat YOLOs on Real-time Object Detection

METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens

Low-Contrast-Enhanced Contrastive Learning for Semi-Supervised Endoscopic Image Segmentation

Feature Importance