VisionLab Events
HIGHLIGHT
OTHER NEWS
ReViT: Enhancing vision transformers with residual attention
Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can
2 Settembre 2024 Nessun commento
S-GEAR: Semantically Guided Representation Learning for Action Anticipation (ECCV2024)
Action anticipation is forecasting future activity from a partially observed sequence of events. However, this task is exposed to intrinsic future uncertainty and the difficulty
2 Settembre 2024 Nessun commento
23 Agosto 2024 Nessun commento
23 Agosto 2024 Nessun commento
23 Agosto 2024 Nessun commento
23 Agosto 2024 Nessun commento
Computer Vision Conferences
Nvidia News
- Building AI Agents for AR Glasses and XR Devices with NVIDIA XR AI
- Build Your Own Transaction Foundation Model for Financial Intelligence
- Build On-Device AI Companions with the NVIDIA ACE Game Agent SDK and Unreal Engine 5 Plugins
- How to Optimize Transformer-Based Models for Low-Precision Training
- NVIDIA Blackwell Tops MLPerf Training 6.0 with Industry-Leading Scale and Performance
- Fine-Tuning Biological Foundation Models with LoRA Using NVIDIA BioNeMo Recipes
- Boosting MoE Training Throughput with Advanced Fusion Kernels
- Pretrained to Imagine, Fine-Tuned to Act: The Rise of World-Action Models
- NVIDIA Achieves Leading Agentic Coding Performance on First Agentic AI Benchmark
- Deploy Long-Context Reasoning and Agentic Workflows with MiniMax M3 on NVIDIA Accelerated Infrastructure
- One-Click Multi-Tenant Security with NVIDIA Quantum InfiniBand
- Run DiffusionGemma on NVIDIA for Developer-Ready, High-Throughput Text Generation
- Designing Production-Ready Battery Energy Storage Systems for AI Factories
- Delivering Lifecycle Control for AI Infrastructure at Scale with NVIDIA DGX Spark Enterprise Manageability
- Model Quantization: Turn FP8 Checkpoints into High-Performance Inference Engines with NVIDIA TensorRT
Microsoft News
- Ire identifies another LOTUSLITE specimen
- Data Formulator 0.7: AI-powered data analytics for enterprise data
- Extending Human Intelligence Through AI
- Vega: Zero-knowledge proofs for digital identity in the age of AI
- Further Notes on Our Recent Research on AI Delegation and Long-Horizon Reliability
- mimalloc: A new, high-performance, scalable memory allocator for the modern era
- GridSFM: A new, small foundation model for the electric grid
- Advancing AI for materials with MatterSim: experimental synthesis, faster simulation, and multi-task models
- Building realistic electric transmission grid dataset at scale: a pipeline from open dataset
- Microsoft at NSDI 2026: Advances in large-scale networked systems
- Red-teaming a network of agents: Understanding what breaks when AI agents interact at scale
- AutoAdapt: Automated domain adaptation for large language models
- Can we AI our way to a more sustainable world?
- Ideas: Steering AI toward the work future we want
- ADeLe: Predicting and explaining AI performance across tasks
Google AI News
- Generative AI to quantify uncertainty in weather forecasting
- AutoBNN: Probabilistic time series forecasting with compositional bayesian neural networks
- Computer-aided diagnosis for lung cancer screening
- Using AI to expand global access to reliable flood forecasts
- ScreenAI: A visual language model for UI and visually-situated language understanding
- SCIN: A new resource for representative dermatology images
- MELON: Reconstructing 3D objects from images with unknown poses
- HEAL: A framework for health equity assessment of machine learning performance
- Cappy: Outperforming and boosting large multi-task language models with a small scorer
- Talk like a graph: Encoding graphs for large language models
- Chain-of-table: Evolving tables in the reasoning chain for table understanding
- Health-specific embedding tools for dermatology and pathology
- Social learning: Collaborative learning with large language models
- Croissant: a metadata format for ML-ready datasets
- Google at APS 2024