Posters

Even a few data changes can break the Benjamini-Hochberg (BH) procedure, a widely used multiple testing method, highlighting a critical vulnerability.

Learnware systems enable model reuse; this paper proves RKME specifications protect developers’ training data while enabling effective model identification.

Latent Diffusion Transformers (DiTs) achieve almost-linear time training and inference through low-rank gradient approximations and efficient criteria, overcoming high dimensionality challenges.

This paper presents novel, efficient algorithms and formulations for Sparse Canonical Correlation Analysis (SCCA), a method that improves the interpretability of traditional CCA. SCCA is especially us…

Softmax-DPO boosts LM-based recommender performance by directly optimizing for personalized ranking using a novel loss function that incorporates multiple negative samples, significantly outperforming…

This paper reveals the surprising computational hardness of achieving fairness in low-rank approximation while offering efficient approximation algorithms.

Weak LLMs can accurately supervise strong LLMs via debate, outperforming simpler consultancy methods, especially in information-asymmetric tasks.

Two novel sampling strategies for spectral model sharding in federated learning minimize approximation error and create unbiased estimators, improving performance on various datasets.

Graph representation learning’s structural vulnerabilities are proven and mitigated via noisy aggregation, revealing crucial privacy-utility trade-offs.

DNNs are powerful but lack the clear semantics of PGMs. This paper innovatively constructs infinite tree-structured PGMs that exactly correspond to DNNs, revealing that DNN forward propagation approxi…

Autoregressively trained transformers surprisingly learn algorithms during pretraining, enabling in-context learning; this paper reveals when and why this ‘mesa-optimization’ happens.

MM-Det, a novel algorithm, uses multimodal learning and spatiotemporal attention to detect diffusion-generated videos, achieving state-of-the-art performance on the new DVF dataset.

Researchers achieve state-of-the-art image generation by disentangling semantic and control metadata in diffusion models and optimizing pre-training across resolutions.

Effortlessly boost large language model performance by dynamically fusing knowledge from smaller, task-specific models – achieving near full fine-tuning results with minimal computational cost!

Unlocking the scaling secrets of structured state-space models, this research identifies novel scaling rules for improved stability, generalization, and hyperparameter transferability, revolutionizing…

Researchers enhanced Generative Flow Network training by introducing variance-reducing control variates for divergence-based learning objectives, accelerating convergence and improving accuracy.

New algorithms achieve near-optimal differentially private U-statistic estimation, significantly improving accuracy over existing methods.

This paper presents novel measures quantifying data easiness for DP subspace estimation, supporting them with improved upper and lower bounds and a practical algorithm.

Adam optimizer achieves near-optimal convergence in non-convex scenarios with unbounded gradients and relaxed noise assumptions, improving its theoretical understanding and practical application.

This paper introduces novel autoregressive sampling and hybrid training strategies for score-based diffusion models, significantly boosting PDE forecasting and assimilation accuracy.