No Cap, This Memory Slaps: Breaking Through the OLTP Memory Wall
⚡Hardware Transactional Memory
Flag this post
Speedrunning an RL Environment
⚔️Lean Tactics
Flag this post
Holographic theory of LLMs: explains unbreakable bias and cross-model infection
💻Local LLMs
Flag this post
Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
arxiv.org·2d
💻Local LLMs
Flag this post
From Memorization to Reasoning in the Spectrum of Loss Curvature
arxiv.org·1d
🧠Intelligence Compression
Flag this post
CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration?
arxiv.org·1d
🧠Intelligence Compression
Flag this post
Structure-Aware Fusion with Progressive Injection for Multimodal Molecular Representation Learning
arxiv.org·1d
🔍Vector Forensics
Flag this post
String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse Generation
arxiv.org·3d
🧪Binary Fuzzing
Flag this post
Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning
arxiv.org·2d
🔗Parser Combinators
Flag this post
ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall
🤖AI Curation
Flag this post
How Data Mixing Shapes In-Context Learning: Asymptotic Equivalence for Transformers with MLPs
arxiv.org·14h
🧠Machine Learning
Flag this post
An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation
arxiv.org·14h
✨Effect Handlers
Flag this post
The Limits of Obliviate: Evaluating Unlearning in LLMs via Stimulus-Knowledge Entanglement-Behavior Framework
arxiv.org·14h
🧠Intelligence Compression
Flag this post
Bringing Vision-Language Intelligence to RAG with ColPali
towardsdatascience.com·1d
📝Concrete Syntax
Flag this post
Loading...Loading more...