MLKDINESC-ID · Lisboa
PeoplePublicationsDissertationsResearch mapNewsEventsOpen positionsReading GroupsSearchMember sign in
Machine Learning and Knowledge Discovery

INESC-ID · Rua Alves Redol 9, 1000-029 Lisboa, Portugal

INESC-IDInstituto Superior TécnicoELLIS Lisbon

Semantic search

Describe a topic in your own words — results are ranked by meaning, not keywords.

all typesPublicationPersonProjectDissertationSoftwareNewsEvent

30 results

Measuring axiomatic identifiability of counterfactual image models
Event match 52%
From Manual to Automated Efficient Fragment Counting in Digital Pathology
Event match 49%
Brain Mapping with Dense Features Grounding Cortical Semantic Selectivity in Natural Images With Vision Transformers
Event match 44%
Invariant Feature Learning for OOD Robust Image Classification Models
Event match 40%
Self-Verification Improves Few-Shot Clinical Information Extraction
Event match 39%
Finding Regions of Interest in Whole Slide Images Using Multiple Instance Learning
Event match 38%
Evaluation and Analysis of Hallucination in Large Vision-Language Models
Event match 34%
VisMin: Visual Minimal-Change Understanding
Event match 33%
When Do We Not Need Larger Vision Models?
Event match 33%
Connecting metrics for shape-texture knowledge in computer vision
Event match 33%
Sanity Checks for Saliency Maps
Event match 33%
High-Resolution Image Synthesis with Latent Diffusion Models
Event match 31%
Visual-RFT: Visual Reinforcement Fine-Tuning
Event match 30%
Cobra Effect in Reference-Free Image Captioning Metrics
Event match 30%
Computing a human-like reaction time metric from stable recurrent vision models
Event match 30%
Explicitly Modeling Pre-Cortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness
Event match 29%
Grounding Language Models to Images for Multimodal Generation
Event match 29%
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
Event match 29%
Conditional Prompt Learning for Vision-Language Models
Event match 28%
Compositional Attention: Disentangling Search and Retrieval
Event match 25%
MLKD Seminar: LLMs for scientific discovery
Event match 24%
FLAVA: A Foundational Language And Vision Alignment Model
Event match 24%
Constrained transformer network for ECG signal processing and arrhythmia classification
Event match 23%
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
Event match 22%
Clinical Camel: An Open Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding
Event match 22%
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Event match 22%
Modular Visual Question Answering via Code Generation
Event match 20%
Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models
Event match 20%
Circuit Tracing: Revealing Computational Graphs in Language Models
Event match 20%
Text-to-Text Multi-view Learning for Passage Re-ranking
Event match 19%