Posters

Boosting diffusion-based human image animation, Test-time Procrustes Calibration (TPC) ensures high-quality outputs by aligning reference and target images, overcoming common compositional misalignmen…

Unsupervised model selection for domain adaptive object detection is achieved via a new Detection Adaptation Score (DAS), effectively selecting optimal models without target labels by leveraging the f…

Stable Diffusion’s text-to-image generation is sped up by 25% by removing text guidance after the initial shape generation, revealing that the [EOS] token is key to early-stage image construction.

Transformers’ in-context learning (ICL) is explained using representation learning, revealing its ICL process as gradient descent on a dual model and offering modifiable attention layers for enhanced …

This work unveils a causal lens on extrapolation, offering theoretical guarantees for accurate predictions on out-of-support data, even with limited target samples.

This paper proposes a novel solution to the transferability problem in inverse reinforcement learning (IRL) using principal angles to measure the similarity between transition laws. It provides suffi…

DNNs learn interactions in two phases: initially removing complex interactions, then gradually learning higher-order ones, leading to overfitting.

ATProt: Adversarial training makes protein interface prediction robust to flexibility!

Causal Representation Editing (CRE) improves safe image generation by precisely removing unsafe concepts from diffusion models, enhancing efficiency and flexibility.

Robust Multimodal Sentiment Analysis (MSA) model, Language-dominated Noise-resistant Learning Network (LNLN), handles incomplete data by correcting dominant modality (language) and using a multimodal …

PixelCLIP: Open-vocabulary semantic segmentation without pixel-level labels! Leveraging unlabeled image masks from Vision Foundation Models and an online clustering algorithm, PixelCLIP achieves imp…

A novel regularized triangle-shaped neural network framework, T-Net, achieves highly accurate and scalable logic circuit generation, significantly outperforming existing methods.

NAM: a novel neuron attribution method for MLLMs, revealing modality-specific semantic knowledge and enabling multi-modal knowledge editing.

Researchers propose Multi-Domain learning for Video Anomaly Detection (MDVAD) to create generalizable models handling conflicting abnormality criteria across diverse datasets, improving accuracy and a…

Med-MICN: a novel end-to-end framework for medical image classification, achieving superior accuracy and multi-dimensional interpretability by aligning neural symbolic reasoning, concept semantics, an…

GroupEXP-DA boosts domain adaptive 3D object detection by using a grouping-exploration strategy to reduce bias in pseudo-label collection and account for multiple factors affecting object perception i…

Greedy algorithms outperform conformal prediction in creating prediction sets that maximize human expert accuracy in classification tasks.

VFair achieves harmless Rawlsian fairness in regression tasks without relying on sensitive demographic data by minimizing the variance of training losses.

Partial2Global: A novel VICL framework achieving globally optimal prompt selection, significantly improving visual in-context learning across various tasks.

FleVRS: One unified model masters standard, promptable, and open-vocabulary visual relationship segmentation, outperforming existing methods.