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
- R²D²: Scaling Multimodal Robot Learning with NVIDIA Isaac Lab
- Using Accelerated Computing to Live-Steer Scientific Experiments at Massive Research Facilities
- Automating Inference Optimizations with NVIDIA TensorRT LLM AutoDeploy
- 3 Ways NVFP4 Accelerates AI Training and Inference
- How to Build License-Compliant Synthetic Data Pipelines for AI Model Distillation
- How Painkiller RTX Uses Generative AI to Modernize Game Assets at Scale
- Build with Kimi K2.5 Multimodal VLM Using NVIDIA GPU-Accelerated Endpoints
- How to Build a Document Processing Pipeline for RAG with Nemotron
- Accelerating Long-Context Model Training in JAX and XLA
- Optimizing Communication for Mixture-of-Experts Training with Hybrid Expert Parallel
- Advancing GPU Programming with the CUDA Tile IR Backend for OpenAI Triton
- Establishing a Scalable Sparse Ecosystem with the Universal Sparse Tensor
- Practical Security Guidance for Sandboxing Agentic Workflows and Managing Execution Risk
- Ensuring Balanced GPU Allocation in Kubernetes Clusters with Time-Based Fairshare
- Speeding Up Variable-Length Training with Dynamic Context Parallelism and NVIDIA Megatron Core
Microsoft News
- Rethinking imitation learning with Predictive Inverse Dynamics Models
- Paza: Introducing automatic speech recognition benchmarks and models for low resource languages
- UniRG: Scaling medical imaging report generation with multimodal reinforcement learning
- Multimodal reinforcement learning with agentic verifier for AI agents
- OptiMind: A small language model with optimization expertise
- Agent Lightning: Adding reinforcement learning to AI agents without code rewrites
- Promptions helps make AI prompting more precise with dynamic UI controls
- GigaTIME: Scaling tumor microenvironment modeling using virtual population generated by multimodal AI
- Reducing Privacy leaks in AI: Two approaches to contextual integrity
- Fara-7B: An Efficient Agentic Model for Computer Use
- MMCTAgent: Enabling multimodal reasoning over large video and image collections
- BlueCodeAgent: A blue teaming agent enabled by automated red teaming for CodeGen AI
- When industry knowledge meets PIKE-RAG: The innovation behind Signify’s customer service boost
- Magentic Marketplace: an open-source simulation environment for studying agentic markets
- RedCodeAgent: Automatic red-teaming agent against diverse code agents
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