Proving the Infinitude of Primes in Knuckledragger
philipzucker.comยท2d
๐ŸงฎTheorem Proving
CodeQL zero to hero part 5: Debugging queries
github.blogยท17h
๐Ÿ”“Reverse engineering
Astral's ty: A New Blazing-Fast Type Checker for Python
realpython.comยท18h
๐ŸŽฏGradual Typing
RFC 677: Maintenance of duplicate databases (1975)
rfc-editor.orgยท1dยท
Discuss: Hacker News
๐Ÿ›ก๏ธPreservation Proofs
Death of the Novel(ty): Beyond n-Gram Novelty as a Metric for Textual Creativity
arxiv.orgยท1d
๐Ÿง Intelligence Compression
Brain-language fusion enables interactive neural readout and in-silico experimentation
arxiv.orgยท4h
๐Ÿ’ปLocal LLMs
OjaKV: Context-Aware Online Low-Rank KV Cache Compression with Oja's Rule
arxiv.orgยท1d
๐ŸŒŠStreaming Compression
Teaching LLMs to spell with token healing
blog.sweep.devยท3dยท
Discuss: Hacker News
๐Ÿ”Z3 Parsing
FoodSEM: Large Language Model Specialized in Food Named-Entity Linking
arxiv.orgยท1d
๐Ÿ”Information Retrieval
GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs
arxiv.orgยท4h
๐ŸŽ™๏ธWhisper
Quark's Outlines: Python Lists
dev.toยท1dยท
Discuss: DEV
โญAwesome lists
SCORE: A Semantic Evaluation Framework for Generative Document Parsing
arxiv.orgยท5d
๐Ÿ“„Text Chunking
Positional Encoding - Sense of direction for Transformers
dev.toยท1dยท
Discuss: DEV
๐ŸŽฏArithmetic Coding Theory
Hyperspherical Latents Improve Continuous-Token Autoregressive Generation
arxiv.orgยท4h
๐Ÿš€SIMD Text Processing
Dynamic Experts Search: Enhancing Reasoning in Mixture-of-Experts LLMs at Test Time
arxiv.orgยท1d
โœ“Automated Theorem Proving
What Is The Political Content in LLMs' Pre- and Post-Training Data?
arxiv.orgยท1d
๐Ÿ“‹Document Grammar