LLM

A machine-executable format that replaces traditional papers with structured, agent-consumable research artifacts capturing logic, code, exploration, and evidence.

A momentum-based, sampling-driven method for scaling textual gradient optimization in LLM prompt engineering, improving performance and efficiency across diverse NLP tasks.

An independent reproduction of Anthropic's emotion vector research using the open-weight Llama 3.1 8B model, with the paper's verbatim 171 emotions, 100 topics, and 64 activities. We confirm 10 of 11 verification criteria, with causal steering r=0.956 closely matching the paper's r=0.85.

A token-level confidence-calibrated negative preference alignment method for LLM unlearning that removes undesirable knowledge without requiring retention data or contrastive pairs.

A framework leveraging formal verification feedback for scalable and interpretable LLM-driven robot planning.

A training-free method that robustifies LLM safety alignment against fine-tuning by extrapolating low-rank safety subspaces, significantly reducing attack success rates while preserving model utility.

A study revealing safety-specific pitfalls of multi-model synthetic preference data in DPO alignment.

The first automated guardrail for agents.

A training-free approach that calibrates chain-of-thought reasoning in LLMs, improving accuracy while reducing computational overhead.

We examined how superficial LLM alignments are thru a linear distillation method.