Posters

Unlocking the full potential of multi-modal in-context learning requires understanding its core factors. This research systematically explores these factors, highlighting the importance of a multi-mod…

Diffusion guidance, a common generative modeling technique, is shown to not sample from its intended distribution; instead, it heavily biases samples towards the boundary of the conditional distributi…

Using tropical geometry, researchers reveal that ReLU-activated message-passing GNNs learn continuous piecewise linear functions, highlighting their expressivity limits and paving the way for enhanced…

WeiPer enhances OOD detection by cleverly perturbing class projections, creating a richer representation that improves various existing methods and achieves state-of-the-art results.

Optimal fault-tolerant asynchronous machine learning is achieved via a novel weighted robust aggregation framework, ensuring efficient training despite Byzantine failures and heterogeneous resources.

Weight Diffusion (W-Diff) masters evolving domain generalization by using conditional diffusion models to learn classifier weight evolution patterns, enabling superior generalization to unseen future …

Weight decay in deep learning surprisingly induces low-rank attention layers, potentially harming performance but offering optimization strategies for large language models.

LLM-powered data curation boosts web-scale visual entity recognition!

Align LLMs efficiently via test-time search using smaller models!

SPLAT, a new benchmark using situation puzzles, effectively evaluates and elicits lateral thinking in LLMs through a multi-turn player-judge framework, revealing significant performance improvements o…

This paper introduces a novel method for evaluating weakly supervised models using Fréchet bounds, providing reliable performance bounds without ground truth labels.

WaveAttack: A new backdoor attack method leveraging asymmetric frequency obfuscation for high stealthiness and effectiveness in Deep Neural Networks.

WATT: a novel test-time adaptation method boosts CLIP’s performance on domain shifted images by cleverly averaging weights from multiple text prompts, achieving state-of-the-art results without extra …

WaterMax: a novel LLM watermarking scheme achieving high detectability and preserving text quality by cleverly generating multiple texts and selecting the most suitable one.

LLM-based agents are vulnerable to diverse backdoor attacks that manipulate their reasoning and outputs, highlighting the urgent need for targeted defenses.

Wasserstein Gradient Boosting (WGBoost) extends gradient boosting to handle probability distributions as outputs, enabling more robust and informative predictions in various applications.

This paper introduces Causally Fair DRO, a novel framework for robust optimization that addresses individual fairness concerns by incorporating causal structures and sensitive attributes, providing th…

Wasserstein Distance-based Knowledge Distillation (WKD) rivals KL-divergence by leveraging rich category interrelations and handling non-overlapping distributions, significantly boosting performance i…

This paper proves that Čech persistence diagrams converge to the true underlying shape precisely when using Wasserstein distances with p > m, where m is the submanifold dimension, significantly advanc…

Warped Diffusion cleverly adapts image diffusion models for video inverse problems, solving flickering and temporal inconsistency issues by viewing video frames as continuous warping transformations a…