On the Relationship Between the Choice of Representation and In-Context Learning
arxiv.org·15h
🧠Machine Learning
Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
huggingface.co·1d·
Discuss: Hacker News
🧠Intelligence Compression
NExF: Learning Neural Exposure Fields for View Synthesis
m-niemeyer.github.io·12h·
Discuss: Hacker News
🧠Neural Codecs
Unlocking Image Understanding: A New Path to Visual AI for Everyone
dev.to·1d·
Discuss: DEV
🤖AI Paleography
LogSTOP: Temporal Scores over Prediction Sequences for Matching and Retrieval
arxiv.org·1d
🧠Learned Codecs
Doing Math with Embeddings for Better AI Ad Targeting
ethicalads.io·1d·
Discuss: Hacker News
📊Feed Optimization
To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models
arxiv.org·15h
🤖Advanced OCR
Contrastive Weak-to-strong Generalization
arxiv.org·15h
⧗Information Bottleneck
RND1: Simple, Scalable AR-to-Diffusion Conversion
radicalnumerics.ai·23h·
Discuss: Hacker News
💻Local LLMs
MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding
arxiv.org·15h
🧠Learned Codecs
SliceFine: The Universal Winning-Slice Hypothesis for Pretrained Networks
arxiv.org·15h
🧠Neural Codecs
CIR-CoT: Towards Interpretable Composed Image Retrieval via End-to-End Chain-of-Thought Reasoning
arxiv.org·15h
🧮Vector Embeddings
Optimal Stopping in Latent Diffusion Models
arxiv.org·15h
🧠Machine Learning
Show HN: 1M retail interior image dataset for computer vision (UK/US/EU)
groceryinsight.com·7h·
Discuss: Hacker News
🏺Compression Museums
In-Depth Analysis: "Attention Is All You Need"
dev.to·4h·
Discuss: DEV
🧠Intelligence Compression
TransFIRA: Transfer Learning for Face Image Recognizability Assessment
arxiv.org·1d
🏛Digital humanities
Gaze on the Prize: Shaping Visual Attention with Return-Guided Contrastive Learning
arxiv.org·15h
🧭Content Discovery
Mind the Gap: Quantifying Vocabulary Mismatch in E-Commerce Site Search
searchhub.io·1d·
Discuss: Hacker News
📈Search Quality
Improving Temporal Understanding Logic Consistency in Video-Language Models via Attention Enhancement
arxiv.org·15h
⏱️Interval Parsing
VideoNorms: Benchmarking Cultural Awareness of Video Language Models
arxiv.org·15h
🧠Learned Codecs