How to Boost Research Documentation with Speech Processing Tools
cacm.acm.org·6h
📄Document Phonetics
Playing with open source LLMs
alicegg.tech·1d·
Discuss: Hacker News
🌀Brotli Internals
CleANN: Efficient Full Dynamism in Graph-based Approximate Nearest Neighbor Search
arxiv.org·1d
🗂️Vector Databases
TriangleMix: A Lossless and Efficient Attention Pattern for Long Context Prefilling
arxiv.org·15h
🔨Compilers
Helping or Homogenizing? GenAI as a Design Partner to Pre-Service SLPs for Just-in-Time Programming of AAC
arxiv.org·15h
🎙️Whisper
The Shape of $\mathcal{EL}$ Proofs: A Tale of Three Calculi (Extended Version)
arxiv.org·15h
🧮Theorem Proving
SWIFT: A General Sensitive Weight Identification Framework for Fast Sensor-Transfer Pansharpening
arxiv.org·1d
📊Rate-Distortion Theory
Leveraging Fine-Tuned Large Language Models for Interpretable Pancreatic Cystic Lesion Feature Extraction and Risk Categorization
arxiv.org·1d
🧮Kolmogorov Bounds
See Different, Think Better: Visual Variations Mitigating Hallucinations in LVLMs
arxiv.org·15h
📊Learned Metrics
Learning from Limited and Imperfect Data
arxiv.org·15h
🧠Machine Learning
Adversarial Reconstruction Feedback for Robust Fine-grained Generalization
arxiv.org·15h
📊Learned Metrics
MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks
arxiv.org·1d
🎙️Whisper
Mistral-Small-3.2-24B-Instruct-2506 is now available on Amazon Bedrock Marketplace and Amazon SageMaker JumpStart
aws.amazon.com·19h
🌀Brotli Internals
Hyperbolic Genome Embeddings
arxiv.org·15h
🌀Hyperbolic Geometry
Show HN: Send real-time updates to your mobile apps with Stac Framework
github.com·13h·
Discuss: Hacker News
📝Concrete Syntax
Verification Cost Asymmetry in Cognitive Warfare: A Complexity-Theoretic Framework
arxiv.org·15h
🎯Performance Proofs
MetaLab: Few-Shot Game Changer for Image Recognition
arxiv.org·15h
📊Learned Metrics
Multi-Stage Verification-Centric Framework for Mitigating Hallucination in Multi-Modal RAG
arxiv.org·1d
📊Multi-vector RAG
TransPrune: Token Transition Pruning for Efficient Large Vision-Language Model
arxiv.org·1d
📊Learned Metrics
T2VParser: Adaptive Decomposition Tokens for Partial Alignment in Text to Video Retrieval
arxiv.org·1d
📐Vector Similarity