Posters

Object-centric occupancy completion boosts 3D object detection accuracy by using temporal information from long sequences to precisely reconstruct object shapes, particularly for incomplete or distant…

Analog in-memory computing (AIMC) training suffers from asymptotic errors due to asymmetric updates. This paper rigorously proves this limitation, proposes a novel discrete-time model to characterize …

This paper presents a novel framework for estimating bounds on policy effects under unobserved confounding, offering tighter bounds and robust estimators for higher-dimensional data.

Novel covariance-adaptive algorithms achieve optimal gap-free regret bounds for combinatorial semi-bandits, improving efficiency with sampling-based approaches.

This study introduces novel, scalable AI-based planning strategies for controlling misinformation spread in dynamic opinion networks, significantly improving infection rate control.

TEdit: a novel diffusion model edits existing time series to meet specified attribute targets, preserving other properties, solving limitations of prior synthesis methods.

N2: A novel dynamic message-passing GNN tackles message-passing bottlenecks and high computational costs by introducing learnable pseudo-nodes and dynamic pathways in a common state space, achieving s…

TAKFL, a novel federated learning framework, tackles device heterogeneity by independently distilling knowledge from diverse devices and integrating it adaptively, achieving state-of-the-art performan…

This paper introduces novel data augmentation modules that dynamically adjust the frequency characteristics of datasets, preventing neural networks from over-relying on simple frequency-based shortcut…

Calibrated robust fine-tuning boosts vision-language model accuracy and confidence in out-of-distribution scenarios by using a constrained multimodal contrastive loss and self-distillation.

CMCD framework tackles data sparsity in cognitive diagnosis by using monotonic data augmentation to improve accuracy and fairness of diagnostic results.

Deep learning models learn language structure through next-token prediction, but the data requirements remain unclear. This paper reveals that the effective context window, determining learning capaci…

LLMs struggle with simple logical reasoning due to the ‘reversal curse.’ This paper reveals that weight asymmetry during training is the culprit, offering a new theoretical perspective and potential s…

FKEA: a novel, scalable method for reference-free evaluation of generative models’ diversity using random Fourier features, overcoming computational limitations of existing entropy-based scores.

A new self-supervised learning approach, Multi-task Masking (MtM), significantly improves the prediction accuracy of neural population activity by capturing neural dynamics at multiple spatial scales,…

Researchers developed a novel architecture for semantic gaze target detection, achieving state-of-the-art results by simultaneously predicting gaze target localization and semantic label, surpassing e…

ALPHALLM boosts LLM performance in complex reasoning tasks by using imagination, search, and criticism to create a self-improving loop, eliminating the need for extra training data.

Hierarchical Representation Learning Framework (HRLF) significantly improves Multimodal Sentiment Analysis (MSA) accuracy by effectively addressing incomplete data through fine-grained representation …

SGNet cultivates general segmentation models for ultra images by integrating surrounding context, achieving significant performance improvements across various datasets.

Gradient EM for over-parameterized Gaussian Mixture Models globally converges with a sublinear rate, solving a longstanding open problem in machine learning.