Posters

PromptFolio optimizes federated learning of vision-language models by combining global and local prompts, improving generalization and personalization, as proven theoretically and empirically.

FedGCDR, a novel federated graph learning framework, tackles cross-domain recommendation challenges by securely leveraging positive knowledge from multiple sources while mitigating negative transfer a…

FlexLoRA: Efficient Federated Fine-tuning of LLMs for Heterogeneous Tasks and Resources.

FEDORA, a novel algorithm, enables high-quality policy learning in federated offline reinforcement learning by leveraging the collective wisdom of diverse client datasets without data sharing.

BlackFed: Privacy-preserving federated semantic segmentation using zero/first-order optimization, avoiding gradient/weight sharing!

Federated Behavioural Planes visualize client behavior in federated learning, enabling robust aggregation and enhanced security against malicious clients.

FedAvP enhances federated learning’s privacy by sharing only augmentation policies, improving performance in diverse settings.

New feature-level adversarial attacks disrupt visible-infrared person re-identification (VIReID) systems by cleverly aligning and manipulating features to cause incorrect ranking results.

FastSurvival unveils computationally efficient methods for training Cox Proportional Hazards models, achieving high precision and overcoming convergence issues of previous algorithms.

FASTopic: a pretrained transformer-based topic model achieving superior speed, adaptivity, stability, and transferability compared to existing methods.

FasterDiT accelerates Diffusion Transformers training 7x without architecture modification by analyzing SNR probability density functions and implementing a new supervision method.

Speed up repeated evasion attacks on tree ensembles by 36x using feature perturbation insights!

This research dramatically accelerates neighborhood attention, a cost-effective self-attention mechanism, through novel GEMM-based and fused kernel implementations, boosting performance by up to 1759%…

Revolutionizing graph analysis, this paper introduces a novel framework for efficiently solving graph diffusion equations, achieving up to a hundred-fold speed improvement and enabling faster graph ne…

Faster Diffusion achieves significant speedups in diffusion model inference by cleverly reusing encoder features and enabling parallel processing, eliminating the need for computationally expensive di…

Faster differentially private top-k selection achieved via a novel joint exponential mechanism with pruning, reducing time complexity from O(dk) to O(d+k²/ɛlnd).

Faster algorithms achieve optimal excess risk in user-level private stochastic convex optimization, overcoming limitations of prior methods without restrictive assumptions.

Faster primal-dual algorithms achieve order-optimal complexity for convex optimization with strongly convex constraints, improving convergence rates and solving large-scale problems efficiently.

FastDrag: One-step image manipulation using generative models, drastically improving editing speed without sacrificing quality.

FAST, a novel dual-tier few-shot learning paradigm, significantly boosts whole slide image (WSI) classification accuracy by efficiently using limited annotations and all available WSIs.