Roei Herzig
27 papers · 2018–2026 · 8 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (53) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π₯
Mega-Team Β· Squad
π§¬
Topic Evolution
π€
Dynamic Duo
(19)
π¬
Deep Specialist
(11)
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
β
The Questioner
π
Century Club Β· Bronze
π
Conference Pioneer
ποΈ
Keyword Collector
(110)
Top co-authors
Research topics
Artificial Intelligence
(17)
Core AI
(16)
Deep Learning
(15)
Machine Learning
(14)
Computer Vision
(13)
Analysis
(11)
Learning Types Β· Machine Learning
(10)
Learning Types Β· Deep Learning
(9)
Architectures
(5)
Core Methods
(5)
Learning Paradigms
(4)
Natural Language Processing
(3)
Applications
(2)
Processing
(2)
Techniques
(2)
Keywords
vision-language model
(8)
large multimodal model
(5)
multimodal learning
(5)
action recognition
(5)
few-shot learning
(4)
scene graph
(4)
zero-shot learning
(4)
video understanding
(3)
compositional reasoning
(3)
object detection
(3)
self-supervised learning
(3)
transfer learning
(2)
video transformer
(2)
visual reasoning
(2)
visual question answering
(2)
representation learning
(2)
domain generalization
(1)
image segmentation
(1)
semantic segmentation
(1)
image classification
(1)
Papers
ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding
CVPR 2026
Latent Implicit Visual Reasoning
CVPR 2026
Do What? Teaching Vision-Language-Action Models to Reject the Impossible
EMNLP 2025
Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features
ICCV 2025
Pre-training Auto-regressive Robotic Models with 4D Representations
ICML 2025
Compositional Chain-of-Thought Prompting for Large Multimodal Models
CVPR 2024
ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs
NeurIPS 2024
LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning
CoRL 2024
Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning
NeurIPS 2024
PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers Using Synthetic Scene Data
WACV 2024
Recursive Visual Programming
ECCV 2024
TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering
EMNLP 2024
Unsupervised Universal Image Segmentation
CVPR 2024
Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models
NeurIPS 2023
Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs
EMNLP 2023
Teaching Structured Vision & Language Concepts to Vision & Language Models
CVPR 2023
Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens
NeurIPS 2022
DETReg: Unsupervised Pretraining With Region Priors for Object Detection
CVPR 2022
FETA: Towards Specializing Foundational Models for Expert Task Applications
NeurIPS 2022
Object-Region Video Transformers
CVPR 2022
Unsupervised Domain Generalization by Learning a Bridge Across Domains
CVPR 2022
Compositional Video Synthesis with Action Graphs
ICML 2021
Differentiable Scene Graphs
WACV 2020
Learning Canonical Representations for Scene Graph to Image Generation
ECCV 2020
Something-Else: Compositional Action Recognition With Spatial-Temporal Interaction Networks
CVPR 2020
Precise Detection in Densely Packed Scenes
CVPR 2019
Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction
NeurIPS 2018