Posters

DRAGO: A novel primal-dual algorithm delivers faster, state-of-the-art convergence for distributionally robust optimization.

DRACO, a denoising-reconstruction autoencoder, revolutionizes cryo-EM by leveraging a large-scale dataset and hybrid training for superior image denoising and downstream task performance.

Doubly Mild Generalization (DMG) improves offline reinforcement learning by selectively leveraging generalization beyond training data, achieving state-of-the-art results.

Doubly hierarchical geometric representations enable realistic human hairstyle generation by separating low and high-frequency details in hair strands, resulting in high-quality, detailed virtual hair…

DOPPLER, a novel low-pass filter, significantly enhances differentially private (DP) optimizer performance by reducing the impact of privacy noise, bridging the gap between DP and non-DP training.

Boost federated learning efficiency! This paper introduces novel algorithms that cleverly combine gradient compression with random reshuffling, significantly reducing communication complexity and impr…

DomainGallery: Few-shot domain-driven image generation via attribute-centric finetuning, solving key issues of previous works by introducing attribute erasure, disentanglement, regularization, and enh…

KGD: a novel knowledge graph distillation technique empowers large-vocabulary object detectors with superior cross-domain object classification, achieving state-of-the-art performance.

This paper introduces ActiveACRE, a model that uses LLMs and probabilistic inference to infer natural language rules through online experimentation, demonstrating higher accuracy than existing methods…

DOGS: Distributed-Oriented Gaussian Splatting accelerates large-scale 3D reconstruction by distributing the training of 3D Gaussian Splatting models across multiple machines, achieving 6x faster train…

DoFIT: A novel domain-aware framework significantly reduces catastrophic forgetting in federated instruction tuning by finely aggregating overlapping weights and using a proximal perturbation initiali…

DOFEN: Deep Oblivious Forest Ensemble achieves state-of-the-art performance on tabular data by using a novel DNN architecture inspired by oblivious decision trees, surpassing other DNNs.

A few high-performing agents using efficient sampling strategies can significantly boost the overall convergence speed of distributed machine learning algorithms, surpassing the performance of many mo…

Zero-shot online action detection gets a boost! OV-OAD leverages vision-language models and text supervision to achieve impressive performance on various benchmarks without relying on manual annotati…

LLMs’ reasoning abilities are assessed via a novel framework that leverages probabilities of causation, revealing that while capable, their understanding of causality falls short of human-level reason…

Achieving egalitarian fairness in federated learning without sacrificing stability is possible; this paper derives optimal fairness bounds considering clients’ altruism and network topology.

DoDont, a novel algorithm, uses instruction videos to guide unsupervised skill discovery, effectively learning desirable behaviors while avoiding undesirable ones in complex continuous control tasks.

LLMs’ fact retrieval is easily manipulated by context, highlighting their associative memory behavior; this paper studies this with transformers, showing how self-attention and value matrices support …

LLMs prioritize task completion over full world-state understanding by using goal-oriented abstractions.

DN-4DGS: Real-time dynamic scene rendering is revolutionized by a denoised deformable network with temporal-spatial aggregation, achieving state-of-the-art quality.