🏢 Hong Kong University of Science and Technology

This work proposes FACL, a novel loss function for precipitation nowcasting, improving forecast sharpness and meteorological skill without sacrificing accuracy.

Fast Graph Sharpness-Aware Minimization (FGSAM) accelerates few-shot node classification by cleverly combining GNNs and MLPs for efficient, high-performing training.

Era3D: High-resolution multiview diffusion using efficient row-wise attention, generates high-quality multiview images from single views, overcoming prior limitations.

MoE-BiEntIRL: A novel explainable inverse reinforcement learning method enhances GNN robustness against diverse social media attacks by reconstructing attacker policies and generating more robust trai…

Dual Risk Minimization (DRM) improves fine-tuned zero-shot models’ robustness by combining empirical and worst-case risk minimization, using LLMs to identify core features, achieving state-of-the-art …

DSA, a novel automated framework, discovers optimal sparsity allocation for layer-wise LLM pruning, achieving significant performance gains across various models and tasks.

DiffHammer unveils weaknesses in diffusion-based adversarial defenses by introducing a novel attack bypassing existing evaluation limitations, leading to more robust security solutions.

DEL: Learns 3D particle dynamics from 2D images via physics-informed neural rendering, exceeding existing methods’ accuracy and robustness.

Decentralized noncooperative games with coupled decision-dependent distributions are analyzed, providing novel equilibrium concepts, uniqueness conditions, and a decentralized algorithm with sublinear…

D2R2: A novel diffusion-based model for tabular few-shot learning, achieves state-of-the-art results by leveraging semantic knowledge and distance matching.

CoMat: Aligning text-to-image diffusion models using image-to-text concept matching for superior text-image alignment.

CigTime generates corrective motion instructions from motion pairs using motion editing and large language models. This innovative approach improves upon baselines by leveraging motion triplets for f…

ChatCam empowers users to control cameras via natural language, using CineGPT for text-conditioned trajectory generation and an Anchor Determinator for precise placement, enabling high-quality video r…

GPTrack: A novel unsupervised framework enhances cardiac motion tracking by using sequential Gaussian processes and bidirectional recurrence, improving accuracy and efficiency.

Attraos: a novel long-term time series forecasting model leveraging chaos theory, significantly outperforms existing methods by utilizing attractor dynamics for efficient and accurate prediction.

ANAH-v2 tackles LLM hallucination by introducing a self-training framework that iteratively scales annotation datasets and improves annotator accuracy, achieving state-of-the-art results.

Adaptive Passive-Aggressive framework with Side information (APAS) significantly boosts online regression accuracy by dynamically adjusting thresholds and integrating side information, leading to supe…

Adaptive Domain Learning (ADL) efficiently trains a cross-domain RAW image denoising model using limited target data and existing source data by intelligently discarding harmful source data and levera…

Constrained Markov Decision Processes (CMDPs) get an improved sample complexity bound of Õ(1/ε) via a new algorithm, surpassing the existing O(1/ε²) bound.

Bifröst: A novel 3D-aware framework for instruction-based image compositing, leveraging depth maps and an MLLM for high-fidelity results.