Scaling Speculative Decoding with Lookahead Reasoning
hao-ai-lab.github.io·1d
🔗Combinatory Logic
A Note on the Theoretical Support to Compute Dimension in Abelian Codes
arxiv.org·20h
⚗️Algebraic Coding
Optimizing NTRU-Prime Hardware Implementation via Dynamic Bit-Width Allocation and Adaptive FFT Scheduling
dev.to·1d·
Discuss: DEV
🌊Stream Ciphers
Program Optimisations via Hylomorphisms for Extraction of Executable Code
drops.dagstuhl.de·19h·
Discuss: Hacker News
👑Coq Tactics
Efficient & Correct Predictive Equivalence for Decision Trees
arxiv.org·20h
🧠Machine Learning
Detecting AI Fakes with Compression Artifacts
dmanco.dev·9h·
Discuss: Hacker News
🖼️JPEG Forensics
Compositional Interface Refinement Through Subtyping in Probabilistic Session Types
arxiv.org·20h
📞Session Types
BusyBeaver(5) is now known to be 47,176,870
scottaaronson.blog·6h
🎞️Tape Combinatorics
Reinforced Generation of Combinatorial Structures: Applications to Complexity Theory
arxiv.org·20h
🎯Performance Proofs
SVeritas: Benchmark for Robust Speaker Verification under Diverse Conditions
arxiv.org·20h
🎵Acoustic Fingerprinting
The Database Zoo: SQL, NoSQL, and the Rise of Specialized Engines
hackernoon.com·22h
🏺Database Archaeology
Writing Our Own Structure: Tries in Haskell & Rust
mmhaskell.com·1d
🌳Trie Structures
QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models
arxiv.org·20h
📊Quantization
GPT-5’s Enhanced Reasoning Comes With a Steep Hidden Cost
thenewstack.io·9h
🔍Concolic Testing
Theory Meets Practice for Bit Vectors Supporting Rank and Select
arxiv.org·20h
🔢Bitwise Algorithms
MoPE: A Mixture of Password Experts for Improving Password Guessing
arxiv.org·20h
🔓Password Cracking
Evaluation Codes in Bottleneck Metrics
arxiv.org·20h
🎯Performance Proofs
Adaptive Qubit-Mapped OFDM for Resilient Wideband Communications
dev.to·1d·
Discuss: DEV
⚛️Quantum Codecs
Huxe: A Personal Intelligence System
huxe.com·6h·
Discuss: Hacker News
🧲Magnetic Domains
Symbol Detection in Inter-Symbol Interference Channels using Expectation Propagation with Channel Shortening
arxiv.org·20h
⚽Sphere Packing