Posters

Focusing on nuclear morphology improves out-of-domain generalization in cancer classification from histopathology images by leveraging nuclear segmentation masks during training.

Deep MIL algorithms’ instance-level learnability is theoretically proven, revealing crucial conditions for success and highlighting gaps in existing models.

More LM calls don’t always mean better results for compound AI; this study reveals performance can initially increase then decrease, highlighting the importance of optimal call number prediction.

Large-scale dataset distillation can be achieved with significantly less soft labels by using class-wise supervision during image synthesis, enabling simple random label pruning and enhancing model ac…

High-degree representations significantly boost the expressiveness of E(3)-equivariant GNNs, overcoming limitations of lower-degree models on symmetric structures, as demonstrated theoretically and em…

ARCHITECT: Generating realistic 3D scenes using hierarchical 2D inpainting!

ARC: a novel generalist graph anomaly detector leveraging in-context learning for efficient, one-for-all anomaly detection across various datasets without retraining.

AR-Pro uses generative models to create counterfactual explanations for anomaly detection, formally specifying what a non-anomalous version should look like and improving interpretability.

This paper unveils the Transformer’s approximation power, deriving explicit Jackson-type rates to reveal its strengths and limitations in handling various sequential relationships.

This paper presents novel algorithms for approximating Pareto-optimal solutions to bi-objective k-clustering problems, achieving provable approximation guarantees and demonstrating effectiveness throu…

Boosting meta-learning, this paper introduces a novel, flexible approach to create approximately equivariant neural processes that outperform both non-equivariant and strictly equivariant counterparts…

AOPU: A novel neural network achieves superior stability in regression network training by approximating the natural gradient, minimizing variance estimation, and enhancing robustness.

Language models (LMs) can now forecast future events as accurately as expert human forecasters! This groundbreaking research unveils a retrieval-augmented LM system surpassing human forecasters in spe…

Boosting image generation: Applying guidance selectively during diffusion model sampling drastically enhances image quality and inference speed, achieving state-of-the-art results.

LLMs’ emotional alignment with humans is assessed using emotion appraisal theory, revealing that while LLMs respond appropriately in some cases, they lack alignment with human emotional behaviors and …

AP-Adapter boosts text-to-image diffusion model generalization by using a two-stage prompt optimization method that leverages large language models and inter-model differences.

AnyFit: Controllable virtual try-on for any attire combination across any scenario, exceeding existing methods in accuracy and scalability.

Any2Policy: a unified multi-modal system enabling robots to perform tasks using diverse instruction and observation modalities (text, image, audio, video, point cloud).

Revolutionizing antibody design, ABDPO uses direct energy-based preference optimization and a pre-trained diffusion model to generate high-quality antibodies with low energy and strong binding affinit…

ANT: An adaptive noise schedule automatically determines optimal noise schedules for time series diffusion models, significantly boosting performance across diverse tasks.