Feeds to Scour
SubscribedAll
Scoured 26595 posts in 93.5 ms
CNNs + VLM outperforms pure VLMs on OCR  📄OCR
interfaze.ai·6d·Hacker News
Adapting TrOCR for Printed Tigrinya Text Recognition: Word-Aware Loss Weighting for Cross-Script Transfer Learning  🤖Paleographic ML
arxiv.org·2d
Images cost 3x more tokens in Claude Opus 4.7  📸TIFF Evolution
claudecodecamp.com·5d·Hacker News
RefAerial: A Benchmark and Approach for Referring Detection in Aerial Images  👁️Perceptual Hashing
arxiv.org·2d
Wan-Image: Pushing the Boundaries of Generative Visual Intelligence  🌀Fractal Compression
arxiv.org·2d
Camera Control for Text-to-Image Generation via Learning Viewpoint Tokens  ⟷Bidirectional Programming
arxiv.org·2d
MESA: A Training-Free Multi-Exemplar Deep Framework for Restoring Ancient Inscription Textures  🤖AI Paleography
arxiv.org·4d
Object Referring-Guided Scanpath Prediction with Perception-Enhanced Vision-Language Models  📊Learned Metrics
arxiv.org·2d
Adaptive Forensic Feature Refinement via Intrinsic Importance Perception  📊Learned Metrics
arxiv.org·4d
Beyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scaling  🗂️Vector Search
arxiv.org·1d
Document-as-Image Representations Fall Short for Scientific Retrieval  🧮Vector Embeddings
arxiv.org·4d
Towards Intelligent Legal Document Analysis: CNN-Driven Classification of Case Law Texts  🧠Machine Learning
arxiv.org·4d
CXR-LT 2026 Challenge: Multi-Center Long-Tailed and Zero Shot Chest X-ray Classification  🧠Machine Learning
arxiv.org·5d
Marrying Text-to-Motion Generation with Skeleton-Based Action Recognition  🌀Riemannian Computing
arxiv.org·4d
KIRA: Knowledge-Intensive Image Retrieval and Reasoning Architecture for Specialized Visual Domains  🗂️Vector Search
arxiv.org·4d
DocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion  🌳Trie Structures
arxiv.org·4d
Cross-Modal Attention Analysis and Optimization in Vision-Language Models: A Study on Visual Reliability  📊Learned Metrics
arxiv.org·4d
DOSE: Data Selection for Multi-Modal LLMs via Off-the-Shelf Models  💻Local LLMs
arxiv.org·4d
Long-Text-to-Image Generation via Compositional Prompt Decomposition  🚀SIMD Text Processing
arxiv.org·4d
Unveiling Fine-Grained Visual Traces: Evaluating Multimodal Interleaved Reasoning Chains in Multimodal STEM Tasks  📊Learned Metrics
arxiv.org·3d

No more posts from matmat's subscribed feeds.

Scour all 24370 feedsLearn more about Feeds

Keyboard Shortcuts

Navigation
Next / previous item
j/k
Open post
oorEnter
Preview post
v
Post Actions
Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s
Recommendations
Add interest / feed
Enter
Not interested
x
Go to
Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help