🏢 Shanghai Jiao Tong University

Link-MoE boosts link prediction accuracy by strategically selecting the best model for each node pair, surpassing single-model approaches.

MECD: A new task and dataset unlocks multi-event causal discovery in videos, enabling a novel framework that outperforms existing models by efficiently identifying causal relationships between chronol…

MC-DiT: A novel training paradigm for masked diffusion models achieving state-of-the-art image generation by leveraging clean-to-clean reconstruction.

MADIFF: Offline multi-agent learning uses attention-based diffusion models to achieve effective coordination and teammate modeling, outperforming existing methods.

CurrMask: a novel curriculum masking paradigm for offline RL, achieving superior zero-shot and fine-tuning performance by dynamically adjusting masking schemes during pretraining, enabling versatile s…

CryptoANFNet accelerates solving cryptographic problems by 50x using a novel graph neural network and ANF representation, outperforming existing methods in accuracy.

InteractTraj: Generating realistic, interactive traffic trajectories from natural language!

Lambda: A novel framework tackles entity alignment challenges with unlabeled dangling entities using GNN-based encoding, spectral contrastive learning, and an iterative PU learning algorithm, achievin…

Boosting Out-of-Distribution Detection with Kernel PCA!

Transformer model initialization dramatically affects whether it reasons or memorizes, impacting performance on compositional tasks.

A new algorithm, AOGS, achieves significantly lower regret in two-sided matching markets by cleverly integrating exploration and exploitation, thus removing the dependence on the number of arms (K) in…

HuRef: Generate unique, human-readable fingerprints for LLMs to protect copyright without exposing model parameters or impeding training.

Humanoid robot learns to rearrange objects using vision and language instructions, achieving remarkable success on diverse tasks in a novel dataset.

WeatherGFT generalizes weather forecasts to finer temporal scales using a physics-AI hybrid model, achieving state-of-the-art performance and 30-minute forecast capability with only hourly training da…

Part-Aware Diffusion Model (PA-Diffusion) enables precise and efficient manipulation of articulated objects in real images by using abstract 3D models and dynamic feature maps, overcoming limitations …

FuseAnyPart: Swap facial parts seamlessly using multiple reference images via diffusion, achieving high-fidelity results.

Few-shot diffusion models efficiently generate customized images; this paper provides the first theoretical explanation, proving improved approximation and optimization bounds, escaping the curse of d…

Fast T2T: Optimization Consistency Boosts Diffusion-Based Combinatorial Optimization!

Face2QR: A unified framework generates aesthetically pleasing, scannable QR codes that faithfully preserve facial features, solving the conflict between aesthetics, identity, and scannability.

Novel trajectory volatility score (TV Score) significantly improves out-of-distribution detection in mathematical reasoning by leveraging dynamic embedding trajectories, outperforming existing GLM met…