Digital Storytelling in the Digitisation of Japanese Botanical Specimens in RBG, Kewโ€™s Collections
digitalorientalist.comยท1d
๐Ÿ›Digital humanities
Teaching Models to Decide When to Retrieve: Adaptive RAG, Part 4
blog.reachsumit.comยท2dยท
Discuss: Hacker News
๐Ÿง Learned Indexing
A PhD in Snapshots
rbharath.github.ioยท2dยท
Discuss: Hacker News
๐Ÿง Machine Learning
The Bit Shift Paradox: How "Optimizing" Can Make Code 6ร— Slower
hackernoon.comยท9h
๐ŸงฎCompute Optimization
Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
arxiv.orgยท9h
๐ŸงฎKolmogorov Complexity
Precision Inertial Navigation via Multi-Modal Sensor Fusion and Adaptive Kalman Filtering
dev.toยท1dยท
Discuss: DEV
๐ŸŒŠStream Processing
Label-Efficient Cross-Modality Generalization for Liver Segmentation in Multi-Phase MRI
arxiv.orgยท1d
๐Ÿค–Advanced OCR
Probing Whisper for Dysarthric Speech in Detection and Assessment
arxiv.orgยท1d
๐ŸŽ™๏ธWhisper
Read Between the Lines: A Benchmark for Uncovering Political Bias in Bangla News Articles
arxiv.orgยท1d
โš™๏ธCompression Benchmarking
When Thinking Drifts: Evidential Grounding for Robust Video Reasoning
arxiv.orgยท9h
๐Ÿ”ฒCellular Automata
Bloom: Designing for LLM-Augmented Behavior Change Interactions
arxiv.orgยท9h
๐ŸŒProtocol Synthesis
Detecting Invariant Manifolds in ReLU-Based RNNs
arxiv.orgยท1d
๐ŸŒ€Riemannian Computing
H1B-KV: Hybrid One-Bit Caches for Memory-Efficient Large Language Model Inference
arxiv.orgยท9h
๐Ÿ’จCache Optimization
SpeechCT-CLIP: Distilling Text-Image Knowledge to Speech for Voice-Native Multimodal CT Analysis
arxiv.orgยท2d
๐ŸŽ™๏ธWhisper
COSMIR: Chain Orchestrated Structured Memory for Iterative Reasoning over Long Context
arxiv.orgยท1d
๐ŸŒ€Brotli Internals
Mapping Patient-Perceived Physician Traits from Nationwide Online Reviews with LLMs
arxiv.orgยท1d
๐Ÿ”Information Retrieval
Discrete Diffusion Models with MLLMs for Unified Medical Multimodal Generation
arxiv.orgยท9h
๐ŸŽ™๏ธWhisper