Posters

GaussianCube revolutionizes 3D generative modeling with a structured, explicit radiance representation, achieving state-of-the-art results using significantly fewer parameters.

GP-TopK: A novel contextual bandit algorithm uses Gaussian processes with a Kendall kernel for efficient & accurate top-k recommendations, even with limited feedback.

Gaussian Graph Network (GGN) revolutionizes novel view synthesis by efficiently generating generalizable Gaussian representations from multi-view images, achieving superior rendering quality with fewe…

This paper delivers non-asymptotic accuracy bounds for confidence intervals in linear stochastic approximation, leveraging a novel multiplier bootstrap method.

Gated Slot Attention (GSA) enhances linear Transformers for efficient, real-time sequence modeling. GSA uses a two-layer gated linear attention structure linked by softmax, enabling improved memory ca…

GIN, a novel approximate Bayesian inference algorithm, efficiently handles nonlinear state-space models with high-dimensional, noisy observations by disentangling observation and dynamics. Achieving l…

GarmentLab: A new benchmark and simulation platform tackles garment manipulation challenges by offering realistic simulations, diverse assets, and tasks bridging the sim-to-real gap for more robust AI…

GAMap: Zero-shot object goal navigation excels by using multi-scale geometric-affordance guidance, significantly boosting robot success rates in unseen environments.

GACL: a novel exemplar-free technique for generalized analytic continual learning, achieves superior performance by analytically solving the weight-invariant property for handling real-world data.

G3: A novel framework leverages Retrieval-Augmented Generation to achieve highly accurate worldwide image geolocalization, overcoming limitations of existing methods.

G2D: a novel medical VLP framework achieves superior performance in medical image analysis by simultaneously learning global and dense visual features using image-text pairs without extra annotations.

G-Retriever: a novel RAG approach enables conversational interaction with textual graphs, improving graph understanding and question answering efficiency while mitigating hallucination.

FuseMoE, a novel mixture-of-experts transformer, efficiently fuses diverse and incomplete multimodal data, achieving superior predictive performance via a unique Laplace gating function.

FUSE, a novel framework, efficiently predicts continuous fields & estimates discrete parameters in PDEs, significantly improving accuracy and robustness.

This paper introduces a rate-distortion framework for prompt compression in LLMs, bridging the gap between existing methods and optimal performance. By formulating prompt compression as a linear progr…

This research establishes fundamental convergence properties for the widely-used SAM optimization algorithm, significantly advancing our theoretical understanding and practical applications.

Near-optimal algorithms solve convex simple bilevel problems by reformulating them into functionally constrained problems, achieving near-optimal convergence rates.

Constrained sampling solved! New functional gradient flow method (CFG) efficiently samples from constrained probability distributions via a novel boundary condition for gradient flows, achieving prov…

Ex4DGS achieves real-time high-quality dynamic scene rendering using explicit 4D Gaussian representations and keyframe interpolation.

Researchers developed Full Distance Attack (FDA) to generate adversarial patterns effective against pedestrian detectors across all distances, resolving the appearance gap issue between simulated and …