Posters

OccamLLM: LLMs now perform accurate arithmetic in a single step!

Neuroscience-inspired motion energy processing enables human-like zero-shot generalization in figure-ground segmentation, outperforming deep learning models on random dot stimuli.

OASIS, a novel data-centric approach, shapes offline data distributions toward safer, higher-reward policies using a conditional diffusion model, outperforming existing offline safe RL methods.

NVRC: A novel end-to-end neural video codec achieves 23% coding gain over VVC VTM by optimizing representation compression.

This paper presents a novel, efficient method for Jacobian nuclear norm regularization in deep learning, replacing computationally expensive SVDs with equivalent Frobenius norm computations, thereby e…

Researchers created a novel object synthesis method, Adaptive Text-Image Harmony (ATIH), that harmoniously blends image and text inputs to generate creative, composite objects.

RNNs trained on dual-agent path integration develop distinct internal representations compared to single-agent models, exhibiting weaker grid cell responses and enhanced border/band cell activity, wit…

CompILer: A novel prompt-based incremental learner mastering state-object compositions without forgetting, achieving state-of-the-art performance.

By cleverly integrating per-example gradient norm calculations during the backward pass of LayerNorm layers, this research enables efficient and accurate gradient noise scale estimation in Transformer…

Normalize-and-Project (NaP) boosts reinforcement learning by stabilizing layer normalization, preventing plasticity loss, and enabling effective learning rate control.

Normal-GS improves 3D Gaussian Splatting by integrating normal vectors into the rendering pipeline, achieving near state-of-the-art visual quality with accurate surface normals in real-time.

Nonstationary Sparse Spectral Permanental Process (NSSPP) enhances point process modeling by using sparse spectral representations, enabling flexible, efficient, nonstationary kernel learning.

SAGD-IV: a novel functional stochastic gradient descent algorithm for stable nonparametric instrumental variable regression, excelling in handling binary outcomes and various loss functions.

Adaptive algorithm selection for noisy ICA is achieved via a novel nonparametric independence score, improving accuracy and efficiency.

Overparameterized ConvResNets surprisingly excel at prediction; this study proves they efficiently learn smooth functions on low-dimensional manifolds, avoiding the curse of dimensionality.

This paper proposes a novel federated learning algorithm for nonconvex problems on compact smooth manifolds, achieving both computational and communication efficiency while mitigating client drift.

AI models struggle with changing data; this paper introduces Soft Resets, a novel learning approach that uses an adaptive drift to gracefully guide parameters toward initialization, improving adaptabi…

New non-parametric classifiers using expand-and-sparsify representation achieve minimax-optimal convergence, adapting to low-dimensional manifold structure.

A novel semi Forward-Backward Euler scheme provides convergence guarantees for non-geodesically-convex optimization in Wasserstein space, advancing both sampling and optimization.

Non-Euclidean Mixture Model (NMM-GNN) outperforms existing methods by using spherical and hyperbolic spaces to model homophily and social influence in social network embedding, improving link predicti…