Model Explainability, Activation Maps, Visual Interpretation, CNN Visualization

T3: Test-Time Model Merging in VLMs for Zero-Shot Medical Imaging Analysis
arxiv.org·5h
👁️Vision Transformers
Flag this post
Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark
paperium.net·10h·
Discuss: DEV
🧠OpenAI
Flag this post
Trace Anything: Representing Any Video in 4D via Trajectory Fields
paperium.net·16h·
Discuss: DEV
🔺Geometric Learning
Flag this post
Machine Learning Fundamentals: Everything I Wish I Knew When I Started
dev.to·1d·
Discuss: DEV
🤖Machine learning
Flag this post
Show HN: Hot or Slop – Visual Turing test on how well humans detect AI images
hotorslop.com·3d·
Discuss: Hacker News
📊Altair
Flag this post
Kimi Linear: An Expressive, Efficient Attention Architecture
arxiviq.substack.com·1d·
Discuss: Substack
🧠OpenAI
Flag this post
ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding
arxiv.org·5h
👁️Vision Transformers
Flag this post
Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model
arxiv.org·5h
👁️Vision Transformers
Flag this post
FOCUS: Efficient Keyframe Selection for Long Video Understanding
arxiv.org·5h
📷OpenCV
Flag this post
FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model
paperium.net·9h·
Discuss: DEV
🧠OpenAI
Flag this post
ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for LargeVision-and-Language Models
paperium.net·1d·
Discuss: DEV
🧠OpenAI
Flag this post
Decoding human safety perception with eye-tracking systems, street view images, and explainable AI
sciencedirect.com·1d
👁Computer vision
Flag this post
Don’t Just Normalize, Batch Normalize! A Guide to Stable Neural Networks
pub.towardsai.net·3h
👁️Vision Transformers
Flag this post
Generating Accurate and Detailed Captions for High-Resolution Images
arxiv.org·5h
🧠OpenAI
Flag this post
A Hybrid Deep Learning and Forensic Approach for Robust Deepfake Detection
arxiv.org·5h
🔥PyTorch
Flag this post
Visual Backdoor Attacks on MLLM Embodied Decision Making via Contrastive Trigger Learning
arxiv.org·5h
🧠OpenAI
Flag this post
LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
dev.to·13h·
Discuss: DEV
🧠OpenAI
Flag this post
Evidence on language model consciousness
lesswrong.com·2d
🤗Hugging Face
Flag this post
Our newest model: Chandra (OCR)
datalab.to·1d·
Discuss: Hacker News
🧠OpenAI
Flag this post