Pinned Loading
Repositories
- MedKIT Public
MedKIT: Evaluating Knowledge Integration and Generalization in LLMs (NeurIPS 2026 E&D). Dataset: huggingface.co/datasets/bethgelab/MedKIT
- replay-on-demand Public
Replay on Demand (RoD): an emergent curriculum for balancing adaptation and forgetting in continued pretraining
- revenge-bench Public
RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments
- alignment-pattern-analysis Public
Code for the ICLR 2026 paper "Only Brains Align with Brains: Cross-Region Alignment Patterns Expose Limits of Normative Models"
- lit-benchmark Public
Codebase for the LiT Benchmark from "Round-Trip Translation Reveals What Frontier Multilingual Benchmarks Miss"
-
- what-moves-the-eyes Public
Project page for "What Moves the Eyes: Doubling Mechanistic Model Performance Using Deep Networks to Discover and Test Cognitive Hypotheses"
Top languages
Loading…
Most used topics
Loading…