Papers on NeurIPS 2024
3D Gaussian Splatting as Markov Chain Monte Carlo
·1616 words·8 mins·
loading
·
loading
3D Vision
🏢 University of British Columbia
Researchers rethink 3D Gaussian Splatting as MCMC sampling, improving rendering quality and Gaussian control via a novel relocation strategy.
3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors
·2090 words·10 mins·
loading
·
loading
3D Vision
🏢 Clemson University
3DGS-Enhancer boosts unbounded 3D Gaussian splatting, generating high-fidelity novel views even with sparse input data using view-consistent 2D diffusion priors.
A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Models
·3928 words·19 mins·
loading
·
loading
🏢 Layer 6 AI
Diffusion models power FLIPD, a fast, single-model LID estimator.
A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise
·223 words·2 mins·
loading
·
loading
🏢 University of Washington
Near-optimal algorithm achieves computationally efficient learning of margin halfspaces with Massart noise, nearly matching theoretical lower bounds.
A Pairwise Pseudo-likelihood Approach for Matrix Completion with Informative Missingness
·1982 words·10 mins·
loading
·
loading
🏢 Texas A&M University
New method recovers low-rank matrices with informative missingness, offering robust, near-optimal performance.
A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention
·2455 words·12 mins·
loading
·
loading
Large Language Models
🏢 EPFL, Lausanne, Switzerland
A solvable model reveals a phase transition in dot-product attention, showing how semantic attention emerges from positional attention with increased data, explaining the qualitative improvements in l…
A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
·2749 words·13 mins·
loading
·
loading
Reinforcement Learning
🏢 Microsoft Research
On-policy deep RL agents suffer from plasticity loss, but this paper introduces ‘regenerative’ methods that consistently mitigate this, improving performance in challenging environments.
A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis
·2721 words·13 mins·
loading
·
loading
Image Classification
🏢 University of Pennsylvania
KnoBo enhances deep learning models for medical image analysis by incorporating knowledge priors from medical textbooks, boosting out-of-domain performance by up to 32.4%.
A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks
·2218 words·11 mins·
loading
·
loading
Multimodal Learning
Vision-Language Models
🏢 Purdue University
SFID, a novel debiasing method, effectively mitigates bias in vision-language models across various tasks without retraining, improving fairness and efficiency.