Show HN: Charl – ML language with native tensors and autograd
charlbase.org·21h·
Discuss: Hacker News
🤖AI
Flag this post
This Camera System Can Focus on Everything, Everywhere, All At Once
petapixel.com·13h
🖼Image
Flag this post
Memory in AI Companions: Implementing Vector-Based Long-Term User State
nsfwcoders.com·3h·
Discuss: DEV
🤖AI
Flag this post
**Technical Challenge:**
dev.to·12h·
Discuss: DEV
🤖AI
Flag this post
How Bias Binds: Measuring Hidden Associations for Bias Control in Text-to-Image Compositions
arxiv.org·5h
🖼Image
Flag this post
DARN: Dynamic Adaptive Regularization Networks for Efficient and Robust Foundation Model Adaptation
arxiv.org·1d
🤖AI
Flag this post
Resilient AI: Making Imperfect Hardware Smarter
dev.to·21h·
Discuss: DEV
🤖AI
Flag this post
ReMoD: Rethinking Modality Contribution in Multimodal Stance Detection via Dual Reasoning
arxiv.org·5h
🖼Image
Flag this post
Brain-Inspired Planning for Better Generalization in Reinforcement Learning
arxiv.org·5h
🤖AI
Flag this post
You Can't Unbake a Cake (or Why Data Isolation in the Age of AI is BASICALLY Impossible)
dev.to·16h·
Discuss: DEV
🤖AI
Flag this post
Sentiment Analysis On YouTube Comments Using Machine Learning Techniques Based On Video Games Content
arxiv.org·5h
🎮Games
Flag this post
PICABench: How Far Are We from Physically Realistic Image Editing?
paperium.net·1d·
Discuss: DEV
🖼Image
Flag this post
Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning
arxiv.org·5h
🤖AI
Flag this post
SDS KoPub VDR: A Benchmark Dataset for Visual Document Retrieval in Korean Public Documents
arxiv.org·1d
🎮Games
Flag this post
SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards
arxiv.org·5h
🤖AI
Flag this post
Active Learning for Animal Re-Identification with Ambiguity-Aware Sampling
arxiv.org·5h
🤖AI
Flag this post
Mapping Reduced Accessibility to WASH Facilities in Rohingya Refugee Camps with Sub-Meter Imagery
arxiv.org·5h
🖼Image
Flag this post
Aligning Attention with Human Rationales for Self-Explaining Hate Speech Detection
arxiv.org·5h
🤖AI
Flag this post
Mono3DVG-EnSD: Enhanced Spatial-aware and Dimension-decoupled Text Encoding for Monocular 3D Visual Grounding
arxiv.org·5h
🖼Image
Flag this post