Posters

New algorithms achieve optimal regret bounds for contextual dynamic pricing under minimal assumptions, improving revenue management with better price adjustments.

Unified framework for imprecise label learning handles noisy, partial, and semi-supervised data, improving model training efficiency and accuracy.

PropEn: a novel framework for implicitly guided design optimization that leverages ‘matching’ to boost efficiency by matching samples and approximating the gradient without a discriminator.

Weighted pretrained features implicitly regularize models, and this paper reveals equivalent paths between weighting schemes and ridge regularization, enabling efficient hyperparameter tuning.

Boosting deep learning generalization, this work unveils SAM’s implicit regularization using ‘balancedness’, a new metric. A resource-efficient variant, BAR, achieves 95% computational savings with i…

Decentralized Gradient Descent achieves statistically optimal sparse model learning via implicit regularization, even with communication-efficient truncation.

Researchers reveal implicit optimization biases in next-token prediction for language models, showing how gradient descent selects solutions based on data sparsity and a novel margin concept, impactin…

Frozen LLMs surprisingly excel at multimodal tasks; this paper reveals that their success stems from an implicit multimodal alignment effect, paving the way for efficient LMMs.

Mirror descent’s implicit bias on separable data is formally characterized, revealing convergence towards a maximum margin classifier determined by the potential’s ‘horizon function’.

ImOV3D: Revolutionizing open-vocabulary 3D object detection by learning from 2D images alone!

Immiscible Diffusion boosts diffusion model training efficiency up to 3x by cleverly assigning noise to images, preventing the mixing of data in noise space and thus improving optimization.

This study presents a novel Inverse Reinforcement Learning (IRL) approach for fine-tuning large language models, offering improved performance and generation diversity compared to standard methods.

IMAGPose: A unified framework generating high-fidelity person images from single or multiple source images & poses, addressing existing methods’ limitations.

Researchers create ‘images that sound’—visual spectrograms looking like natural images and sounding like natural audio—by cleverly composing pre-trained image and audio diffusion models in a shared la…

VLScore: a novel image-aware metric revolutionizes medical report evaluation by jointly assessing textual and visual similarities, significantly improving alignment with radiologist assessments.

Leveraging image understanding models for image tokenizer training dramatically boosts image generation quality, achieving state-of-the-art results.

aSeqDIP: A new unsupervised image reconstruction method using sequential deep image priors, achieving competitive performance with fewer data needs and faster runtimes.

ICDiff, a novel Image Copy Detection system, tackles the unique challenge of identifying replicated content in diffusion model outputs, introducing a specialized dataset and deep embedding method for …

IllumiNeRF: Relightable 3D reconstruction without inverse rendering using image diffusion and NeRF.

IF-Font: Revolutionary font generation using Ideographic Description Sequences (IDS) to surpass state-of-the-art methods in style transfer, especially for unique styles.