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

Swin Transformer V2: Scaling Up Capacity and Resolution
Event match 47%
Efficient Long-Text Understanding with Short-Text Models
Event match 44%
LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
Event match 37%
Energy Transformer
Event match 35%
∞-Video A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation
Event match 34%
VisMin: Visual Minimal-Change Understanding
Event match 32%
Large Language Model (LLM) as a System of Multiple Expert Agents An Approach to solve the Abstraction and Reasoning Corpus (ARC) Challenge
Event match 32%
Refining Knowledge Distillation for Effective and Efficient Passage Retrieval
Event match 30%
When Do We Not Need Larger Vision Models?
Event match 29%
Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models
Event match 29%
Text-to-Text Multi-view Learning for Passage Re-ranking
Event match 29%
Gecko: Versatile Text Embeddings Distilled from Large Language Models
Event match 29%
LumberChunker: Long-Form Narrative Document Segmentation
Event match 28%
High-Resolution Image Synthesis with Latent Diffusion Models
Event match 28%
Towards General Text Embeddings with Multi-stage Contrastive Learning
Event match 26%
A Contrastive Framework for Neural Text Generation
Event match 26%
Constrained transformer network for ECG signal processing and arrhythmia classification
Event match 26%
Modular Visual Question Answering via Code Generation
Event match 25%
Connecting metrics for shape-texture knowledge in computer vision
Event match 25%
Text Embeddings by Weakly-Supervised Contrastive Pre-training
Event match 24%
Grounding Language Models to Images for Multimodal Generation
Event match 23%
Lost in the Middle: How Language Models Use Long Contexts
Event match 23%
Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Event match 22%
FLAVA: A Foundational Language And Vision Alignment Model
Event match 22%
Chain-of-Verification Reduces Hallucination in Large Language Models
Event match 22%
Revisiting ResNets: Improved Training and Scaling Strategies
Event match 22%
Cobra Effect in Reference-Free Image Captioning Metrics
Event match 21%
Circuit Tracing: Revealing Computational Graphs in Language Models
Event match 21%
Brain Mapping with Dense Features Grounding Cortical Semantic Selectivity in Natural Images With Vision Transformers
Event match 21%
Visual-RFT: Visual Reinforcement Fine-Tuning
Event match 21%