Title of the paper
Two-line summary of the contribution and scope.
Publications
Search by concept, filter by research direction, then expand any paper for a concise abstract and links. Full list on Google Scholar.
Thematic lists are ranked by estimated matching probability based on each paper's title, abstract, method, and main contribution.
Efficient & Continual Learning
Shared LoRA Subspaces for almost Strict Continual Learning
Theme match99%
A shared-subspace approach toward almost strict continual learning for large models.
EigenLoRAx: Recycling Adapters to Find Principal Subspaces for Resource-Efficient Adaptation and Inference
Theme match98%
Resource-efficient adaptation and inference via adapter recycling.
Abstract, links & BibTeX
Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction
Theme match98%
Hexagonal surface elements with spatially varying color for memory-efficient novel-view synthesis and surface reconstruction.
Adaptive Neural Connections for Sparsity Learning
Theme match97%
Adaptive neural connectivity for sparsity-aware learning.
Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping
Theme match96%
Continual learning with optimal relevance mapping.
The Universal Weight Subspace Hypothesis
Theme match95%
A physics of AI study showing that trained neural networks tend to converge to similar low-rank weight subspaces across datasets and hyperparameters.
iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning
Theme match92%
Incremental neural mesh models for class-incremental learning.
3D Vision & Reconstruction
Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction
Theme match99%
Hexagonal surface elements with spatially varying color for memory-efficient novel-view synthesis and surface reconstruction.
FurE: Efficient Instance-Specific 3D Fur Reconstruction without Animal-Fur Datasets
Theme match99%
Editable strand-based animal fur reconstruction from multiview images, using a compact prior learned from human hair without animal-fur training datasets.
Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation Models Hallucinate
Theme match98%
Failure-aware multiview 3D consistency metrics for hallucination-prone foundation reconstruction models.
Name That Part: 3D Part Segmentation and Naming
Theme match97%
Joint 3D part segmentation and semantic naming.
Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape
Theme match96%
A comprehensive dataset for 3D animal pose and shape.
Scaling 3D Compositional Models for Robust Classification and Pose Estimation
Theme match95%
Scaling compositional models for robust 3D classification and pose.
Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors
Theme match94%
Pose-free sparse-view scene reconstruction using diffusion priors.
Source-Free and Image-Only Unsupervised Domain Adaptation for Category-Level Object Pose Estimation
Theme match93%
Source-free domain adaptation for category-level pose estimation.
TriDiff-4D: Fast 4D Generation through Diffusion-based Triplane Re-posing
Theme match92%
Fast 4D generation through diffusion-based triplane re-posing.
iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning
Theme match90%
Incremental neural mesh models for class-incremental learning.
Learning Part Segmentation from Synthetic Animals
Theme match85%
Part segmentation learned from synthetic animal data.
Perception & Structured Reasoning
Perceptual Taxonomy: Evaluating and Guiding Hierarchical Scene Reasoning in Vision-Language Models
Theme match99%
A framework for evaluating hierarchical scene reasoning in vision-language models.
Name That Part: 3D Part Segmentation and Naming
Theme match98%
Joint 3D part segmentation and semantic naming.
Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape
Theme match96%
A comprehensive dataset for 3D animal pose and shape.
Learning Part Segmentation from Synthetic Animals
Theme match94%
Part segmentation learned from synthetic animal data.
Scaling 3D Compositional Models for Robust Classification and Pose Estimation
Theme match92%
Scaling compositional models for robust 3D classification and pose.
Radar as a Security Measure - Real Time Neural Model based Human Detection and Behaviour Classification
Theme match91%
Real-time neural model-based human detection and behaviour classification.
Abstract, links & BibTeX
FurE: Efficient Instance-Specific 3D Fur Reconstruction without Animal-Fur Datasets
Theme match90%
Editable strand-based animal fur reconstruction from multiview images, using a compact prior learned from human hair without animal-fur training datasets.
Source-Free and Image-Only Unsupervised Domain Adaptation for Category-Level Object Pose Estimation
Theme match89%
Source-free domain adaptation for category-level pose estimation.
A Bayesian Approach to OOD Robustness in Image Classification
Theme match88%
Bayesian OOD robustness in image classification.
iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning
Theme match87%
Incremental neural mesh models for class-incremental learning.
Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors
Theme match86%
Pose-free sparse-view scene reconstruction using diffusion priors.
Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation Models Hallucinate
Theme match85%
Failure-aware multiview 3D consistency metrics for hallucination-prone foundation reconstruction models.
Domain Adaptation
Source-Free and Image-Only Unsupervised Domain Adaptation for Category-Level Object Pose Estimation
Theme match99%
Source-free domain adaptation for category-level pose estimation.
Learning Part Segmentation from Synthetic Animals
Theme match98%
Part segmentation learned from synthetic animal data.
A Bayesian Approach to OOD Robustness in Image Classification
Theme match96%
Bayesian OOD robustness in image classification.
Explainable AI & Physics of AI
The Universal Weight Subspace Hypothesis
Theme match99%
A physics of AI study showing that trained neural networks tend to converge to similar low-rank weight subspaces across datasets and hyperparameters.
Perceptual Taxonomy: Evaluating and Guiding Hierarchical Scene Reasoning in Vision-Language Models
Theme match98%
A framework for evaluating hierarchical scene reasoning in vision-language models.
Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation Models Hallucinate
Theme match94%
Failure-aware multiview 3D consistency metrics for hallucination-prone foundation reconstruction models.
Name That Part: 3D Part Segmentation and Naming
Theme match92%
Joint 3D part segmentation and semantic naming.
Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping
Theme match91%
Continual learning with optimal relevance mapping.
Shared LoRA Subspaces for almost Strict Continual Learning
Theme match90%
A shared-subspace approach toward almost strict continual learning for large models.
EigenLoRAx: Recycling Adapters to Find Principal Subspaces for Resource-Efficient Adaptation and Inference
Theme match88%
Resource-efficient adaptation and inference via adapter recycling.
Abstract, links & BibTeX
Adaptive Neural Connections for Sparsity Learning
Theme match86%
Adaptive neural connectivity for sparsity-aware learning.
A Bayesian Approach to OOD Robustness in Image Classification
Theme match83%
Bayesian OOD robustness in image classification.
Learning Part Segmentation from Synthetic Animals
Theme match80%
Part segmentation learned from synthetic animal data.
Robustness & OOD Generalization
A Bayesian Approach to OOD Robustness in Image Classification
Theme match99%
Bayesian OOD robustness in image classification.
Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation Models Hallucinate
Theme match98%
Failure-aware multiview 3D consistency metrics for hallucination-prone foundation reconstruction models.
Scaling 3D Compositional Models for Robust Classification and Pose Estimation
Theme match97%
Scaling compositional models for robust 3D classification and pose.
Source-Free and Image-Only Unsupervised Domain Adaptation for Category-Level Object Pose Estimation
Theme match95%
Source-free domain adaptation for category-level pose estimation.
iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning
Theme match93%
Incremental neural mesh models for class-incremental learning.
Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors
Theme match91%
Pose-free sparse-view scene reconstruction using diffusion priors.
Generative Models
TriDiff-4D: Fast 4D Generation through Diffusion-based Triplane Re-posing
Theme match99%
Fast 4D generation through diffusion-based triplane re-posing.
Progressive Prompt Detailing for Improved Alignment in Text-to-Image Generative Models
Theme match98%
Improved alignment in text-to-image generative models.
Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors
Theme match97%
Pose-free sparse-view scene reconstruction using diffusion priors.
A Bayesian Approach to OOD Robustness in Image Classification
Theme match91%
Bayesian OOD robustness in image classification.
FurE: Efficient Instance-Specific 3D Fur Reconstruction without Animal-Fur Datasets
Theme match88%
Editable strand-based animal fur reconstruction from multiview images, using a compact prior learned from human hair without animal-fur training datasets.
Scaling 3D Compositional Models for Robust Classification and Pose Estimation
Theme match76%
Scaling compositional models for robust 3D classification and pose.
Security & Systems
Timing Attack Analysis on AES on Modern Processors
Theme match99%
Timing attack analysis on AES on modern processors.
Abstract, links & BibTeX
Radar as a Security Measure - Real Time Neural Model based Human Detection and Behaviour Classification
Theme match96%
Real-time neural model-based human detection and behaviour classification.
Abstract, links & BibTeX
An Offline Outdoor Navigation System with Full Privacy
Theme match94%
Offline outdoor navigation with full privacy.
Abstract, links & BibTeX
2026
Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction
Hexagonal surface elements with spatially varying color for memory-efficient novel-view synthesis and surface reconstruction.
FurE: Efficient Instance-Specific 3D Fur Reconstruction without Animal-Fur Datasets
Editable strand-based animal fur reconstruction from multiview images, using a compact prior learned from human hair without animal-fur training datasets.
Shared LoRA Subspaces for almost Strict Continual Learning
A shared-subspace approach toward almost strict continual learning for large models.
Perceptual Taxonomy: Evaluating and Guiding Hierarchical Scene Reasoning in Vision-Language Models
A framework for evaluating hierarchical scene reasoning in vision-language models.
Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation Models Hallucinate
Failure-aware multiview 3D consistency metrics for hallucination-prone foundation reconstruction models.
Name That Part: 3D Part Segmentation and Naming
Joint 3D part segmentation and semantic naming.
2025
The Universal Weight Subspace Hypothesis
A physics of AI study showing that trained neural networks tend to converge to similar low-rank weight subspaces across datasets and hyperparameters.
Scaling 3D Compositional Models for Robust Classification and Pose Estimation
Scaling compositional models for robust 3D classification and pose.
TriDiff-4D: Fast 4D Generation through Diffusion-based Triplane Re-posing
Fast 4D generation through diffusion-based triplane re-posing.
Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors
Pose-free sparse-view scene reconstruction using diffusion priors.
Progressive Prompt Detailing for Improved Alignment in Text-to-Image Generative Models
Improved alignment in text-to-image generative models.
EigenLoRAx: Recycling Adapters to Find Principal Subspaces for Resource-Efficient Adaptation and Inference
Resource-efficient adaptation and inference via adapter recycling.
Abstract, links & BibTeX
2024
iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning
Incremental neural mesh models for class-incremental learning.
Learning Part Segmentation from Synthetic Animals
Part segmentation learned from synthetic animal data.
Source-Free and Image-Only Unsupervised Domain Adaptation for Category-Level Object Pose Estimation
Source-free domain adaptation for category-level pose estimation.
A Bayesian Approach to OOD Robustness in Image Classification
Bayesian OOD robustness in image classification.
2023
Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape
A comprehensive dataset for 3D animal pose and shape.
2021
Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping
Continual learning with optimal relevance mapping.
2020
Adaptive Neural Connections for Sparsity Learning
Adaptive neural connectivity for sparsity-aware learning.
2019
Radar as a Security Measure - Real Time Neural Model based Human Detection and Behaviour Classification
Real-time neural model-based human detection and behaviour classification.
Abstract, links & BibTeX
2017
An Offline Outdoor Navigation System with Full Privacy
Offline outdoor navigation with full privacy.
Abstract, links & BibTeX
Timing Attack Analysis on AES on Modern Processors
Timing attack analysis on AES on modern processors.
Abstract, links & BibTeX
No matching publications. Try a broader term or switch filters.