projects

  1. Investigating Model Organism Robustness to Fine-Tuning

    Construction method impact on quirk persistence during untargeted supervised fine-tuning.

  2. Refusal Direction Persistence Through Supervised Fine-Tuning

    Supervised fine-tuning changes refusal behaviour while preserving a causally effective refusal direction.

  3. Evaluating Refusal and Jailbreak Behaviour in Gemma 3

    Behaviour shifts of Gemma 3 27B under safety-focused and role-play instructions.

  4. Tapering Away Normalization in Transformers

    Gated removal of normalization in Transformers for stable training and faster inference.

  5. Detecting RAG Hallucinations with Output Probabilities and Attention

    A short study of whether token probabilities and attention can flag unsupported RAG answers.

  6. Parameter-efficient Adaptation of Tokenizer-free Byte Latent Transformer

    Adapting a tokenizer-free architecture to new languages by retraining only the ~4% "interface" modules and keeping the core transformer fixed.

  7. Circuit Tracing Walk-or-Drive Decisions

    Provide a single word answer. Should I walk/drive to my destination which is {distance} m away

  8. Safe Explicit MPC by Training Neural Networks Through Constrained Optimization

    Fast explicit MPC policies learned while enforcing closed-loop safety during neural network training.

  9. Analysis and Local Convergence Proof of a Constrained Optimization Algorithm for Training Neural Networks

    Local convergence analysis of a primal-dual Adam method for constrained neural network training.

  10. Notes on Interpretability

    An evolving taxonomy of interpretability research

  11. Thermal Runaway Avoidance Using Hamilton–Jacobi Reachability and Model Predictive Control

    Combining Hamilton–Jacobi reachability with MPC to avoid thermal runaway in exothermic batch processes.

  12. WNNM Image Denoising

    Python implementation of weighted nuclear norm minimization (WNNM) and comparison against Gaussian, bilateral, and NLM baselines.

  13. Invariance Constraints for Computational Lithography

    Injecting expert invariances into deep models (CNNs) with exact-fit constraints on critical samples.

  14. Inverse Modeling for Metrology

    Faster, more accurate inverse modeling for semiconductor metrology.