PaperHub
影响力指数
67.68/100
前 3%
全站排名 #1,953
发表论文27 篇
平均评分4.7
年均产出9.0 篇/年

Luc Van Gool

Full Professor@Sofia Un. St. Kliment Ohridski·BG·OpenReview
研究方向

deep learning · vision-language models · robotics · computer vision · image segmentation · object tracking · 3D vision · object recognition

5.0
16

Rethinking Expressivity and Degradation-Awareness in Attention for All-in-One Blind Image Restoration

ICLR 2026Poster
5.0
26

EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark

ICLR 2026Poster
5.0
19

LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models

ICLR 2026Poster
通讯
4.7
27

OmniLens++: Blind Lens Aberration Correction via Large LensLib Pre-Training and Latent PSF Representation

ICLR 2026Rejected
4.5
18

Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold Regularization

ICLR 2026Poster
4.4
21

EReLiFM: Evidential Reliability-Aware Residual Flow Meta-Learning for Open-Set Domain Generalization under Noisy Labels

ICLR 2026Rejected
3.7
7

GeoVLM-R1: Reinforcement Fine-Tuning for Improved Remote Sensing Reasoning

ICLR 2026Withdrawn
3.5
16

Simulating Mixed State Dynamics to Enable Differentiable Quantum Architecture Search

ICLR 2026Rejected
通讯
3.2
22

EarthMind: Leveraging Cross-Sensor Data for Advanced Earth Observation Interpretation with a Unified Multimodal LLM

ICLR 2026Rejected
3.0
6

SIGHT: Synthesizing Image-Text Conditioned and Geometry-Guided 3D Hand-Object Trajectories

ICLR 2026Rejected
三作
3.0
5

Scaling Open-world Multiple Object Tracking

ICLR 2026Withdrawn
通讯
2.5
5

Accelerating Vision Transformers with Drop-in Depthwise Convolution

ICLR 2026Withdrawn
通讯
2.5
5

RoHOI: Robustness Benchmark for Human-Object Interaction Detection

ICLR 2026Withdrawn
7.3
20

Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking

ICLR 2025Spotlight
6.7
12

Leveraging Driver Field-of-View for Multimodal Ego-Trajectory Prediction

ICLR 2025Poster
6.4
28

StateSpaceDiffuser: Bringing Long Context to Diffusion World Models

NeurIPS 2025Poster
通讯
6.4
24

Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection

NeurIPS 2025Poster
6.0
26

LangHOPS: Language Grounded Hierarchical Open-Vocabulary Part Segmentation

NeurIPS 2025Poster
通讯
4.5
22

SIGHT: Single-Image Conditioned Generation of Hand Trajectories for Hand-Object Interaction

ICLR 2025Rejected
4.5
5

Minimizing Dependence between Embedding Dimensions with Adversarial Networks

ICLR 2025Withdrawn
通讯
4.5
5

Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians

ICLR 2025Withdrawn
合作者 (20)