Understanding Hardness of Vision-Language Compositionality from A Token-level Causal Lens
arxiv.org·1d
🧩Parser Combinators
Flag this post
Speedrunning an RL Environment
🎮Verification Games
Flag this post
RePro: Training Language Models to Faithfully Recycle the Web for Pretraining
📦Module Systems
Flag this post
RAVR: Reference-Answer-guided Variational Reasoning for Large Language Models
arxiv.org·2d
🧩Parser Combinators
Flag this post
Chatbots, My Rules of Engagement
🔀Brzozowski Derivatives
Flag this post
🧠 Soft Architecture (Part B): Emotional Timers and the Code of Care (Part 5 of the SaijinOS series)
🔲Cellular Automata
Flag this post
Introducing Project Telos: Modeling, Measuring, and Intervening on Goal-directed Behavior in AI Systems
lesswrong.com·1d
🔄Finite State Machines
Flag this post
Do LLMs Signal When They're Right? Evidence from Neuron Agreement
arxiv.org·1d
🧩Parser Combinators
Flag this post
Emergent Introspective Awareness in Large Language Models
lesswrong.com·2d
❓Existential Types
Flag this post
Counteracting Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing
arxiv.org·1d
🧮SMT Solvers
Flag this post
A Three-Stage Bayesian Transfer Learning Framework to Improve Predictions in Data-Scarce Domains
arxiv.org·1d
🎯Hindley-Milner
Flag this post
PORTool: Tool-Use LLM Training with Rewarded Tree
arxiv.org·1d
🧩Parser Combinators
Flag this post
Implicature in Interaction: Understanding Implicature Improves Alignment in Human-LLM Interaction
arxiv.org·2d
🔤Language Design
Flag this post
Reasoning Curriculum: Bootstrapping Broad LLM Reasoning from Math
arxiv.org·1d
🧮SMT Solvers
Flag this post
Loading...Loading more...