LLMs exploit our tolerance for sloppiness
humprog.org·18h·
Discuss: Hacker News
🧠Intelligence Compression
The REM-arkable Misadventures of LIST
masswerk.at·1d·
Discuss: Hacker News
📺VT100
The First AI Coding Style Guide
github.com·1d·
Discuss: Hacker News
📝Text Compression
An Adaptive Simulated Annealing-Based Machine Learning Approach for Developing an E-Triage Tool for Hospital Emergency Operations
arxiv.org·1d
🧠Machine Learning
Tractable Representation Learning with Probabilistic Circuits
arxiv.org·1d
🧠Neural Codecs
Text-Guided Token Communication for Wireless Image Transmission
arxiv.org·4h
ℹ️Information Theory
Affine Frequency Division Multiplexing Over Wideband Doubly-Dispersive Channels With Time-Scaling Effects
arxiv.org·1d
🎯Performance Proofs
Dynamic Rank Adaptation for Vision-Language Models
arxiv.org·4h
📊Learned Metrics
Toward Efficient Speech Emotion Recognition via Spectral Learning and Attention
arxiv.org·1d
🎧Learned Audio
Exploiting Partial Compliance: The Redact-and-Recover Jailbreak
generalanalysis.com·11h·
Discuss: Hacker News
🧪CBOR Fuzzing
FACT: the Features At Convergence Theorem for neural networks
arxiv.org·4h
🧠Machine Learning
Evaluation of OpenAI o1: Opportunities and Challenges of AGI
arxiv.org·4h
🏗️OAIS Model
Interleaving Logic and Counting
arxiv.org·1d
📜Manuscript Algebras
Controlling Thinking Speed in Reasoning Models
arxiv.org·1d
🧮Constraint SMT
Beyond Communication Overhead: A Multilevel Monte Carlo Approach for Mitigating Compression Bias in Distributed Learning
arxiv.org·4h
⧗Information Bottleneck
Aliasing in Convnets: A Frame-Theoretic Perspective
arxiv.org·4h
👂Psychoacoustic Coding
Feint and Attack: Attention-Based Strategies for Jailbreaking and Protecting LLMs
arxiv.org·4h
🎯Threat Hunting
Beyond cognacy
arxiv.org·1d
📜Binary Philology
Adaptive Variation-Resilient Random Number Generator for Embedded Encryption
arxiv.org·4h
🌊Stream Ciphers
RSRefSeg 2: Decoupling Referring Remote Sensing Image Segmentation with Foundation Models
arxiv.org·4h
📸TIFF Archaeology