Posters

FineCLIP boosts fine-grained image understanding by combining real-time self-distillation with semantically rich regional contrastive learning, significantly outperforming existing methods.

Fine-tune personalization in federated learning to beat adversarial clients; collaboration level depends on data heterogeneity and adversary fraction.

This paper presents a novel RL framework that fine-tunes large vision-language models (VLMs) to become effective decision-making agents. By incorporating chain-of-thought reasoning, the framework enab…

Fine-tuning pre-trained models often degrades performance on unseen classes. This work reveals that the problem stems from logit scale discrepancies, not feature loss, and shows that post-processing c…

OLIVINE uses visual foundation models for fine-grained image-to-LiDAR contrastive distillation, mitigating self-conflict issues and improving 3D representation learning.

A new fine-grained dynamic framework jointly optimizes bias and variance for accurate predictions from missing-not-at-random data, surpassing existing methods.

Fine-grained control is added to generative models for IoT sensing data augmentation, tailoring synthetic data to specific application needs by leveraging domain expertise and statistical metrics of s…

Researchers crack the code of in-context learning in Transformers, revealing how architecture, low-rank parameters, and data correlations influence model optimization and generalization.

NEMO pinpoints & deactivates neurons memorizing training data in diffusion models, boosting privacy & image diversity.

First near-optimal reinforcement learning algorithm achieving best policy identification in average-reward MDPs without prior knowledge of complexity.

FINCON: an LLM-based multi-agent system uses conceptual verbal reinforcement for superior financial decision-making, generalizing well across various tasks.

FINALLY achieves studio-like speech enhancement speed and quality using a novel GAN-based approach with WavLM-integrated perceptual loss, outperforming existing diffusion models.

FilterNet: A novel deep learning architecture using learnable frequency filters for superior time series forecasting accuracy and efficiency.

Prompt Adversarial Tuning (PAT) defends against LLM jailbreaking by training a protective prompt prefix. PAT uses adversarial and benign prompts to optimize this prefix, significantly reducing succes…

FIFO-Diffusion generates infinitely long, high-quality videos from text prompts using a pretrained model, solving the challenge of long video generation without retraining.

FIDE, a novel conditional diffusion model, accurately generates time series by inflating high-frequency components, preserving extreme value distributions.

FIARSE dynamically optimizes submodels in federated learning based on parameter importance, improving efficiency and global model accuracy.

FFAM uses feature factorization and gradient weighting to produce high-quality visual explanations for 3D object detectors, improving model interpretability and trust.

FewViewGS: A novel method for high-quality novel view synthesis from sparse images using a multi-stage training scheme and a new locality-preserving regularization for 3D Gaussians.

Few-shot task learning through inverse generative modeling (FTL-IGM) enables AI agents to quickly master new tasks from minimal data by leveraging invertible generative models.