WTF GENIUS PAPERS Collection Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 409 items • Updated about 11 hours ago • 88
Beyond Solver Verdicts: Generative Reward Models for Autoformalization Paper • 2609.11085 • Published 16 days ago • 34
StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean Paper • 2609.09264 • Published 18 days ago • 9
Forte : Finding Outliers with Representation Typicality Estimation Paper • 2410.01322 • Published Oct 2, 2024 • 2
VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning Paper • 2601.20055 • Published Jan 27 • 7
Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks Paper • 2505.20047 • Published May 26, 2025 • 3
LLM-Drop Collection Resources for studies on redundancy in LLMs, including layer dropping and representation-hierarchy-based pruning. • 16 items • Updated Jul 31 • 7