TraceRouter++: Causal Semantic Routing Realignment via Optimal Transport
cs.CL
Submitted: 2026-11-03
Updated: 2026-11-04
Code: https://github.com/notAI-tech/NudeNet
Terminology
Sources
- GPT-4 Technical Report
- Optimal Transport Depth Up-Scaling
- SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism
- Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
- OR-Bench: An Over-Refusal Benchmark for Large Language Models
- Sparse Autoencoders Find Highly Interpretable Features in Language Models
- Toy Models of Superposition
- CoCA: Regaining Safety-awareness of Multimodal Large Language Models with Constitutional Calibration
- The Llama 3 Herd of Models
- A Single Neuron Works: Precise Concept Erasure in Text-to-Image Diffusion Models
- Prompt-to-Prompt Image Editing with Cross Attention Control
- Adam: A Method for Stochastic Optimization
- AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
- JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
- Progress measures for grokking via mechanistic interpretability
- Circumventing Concept Erasure Methods For Text-to-Image Generative Models
- Safety Alignment Should Be Made More Than Just a Few Tokens Deep
- Side Effects of Erasing Concepts from Diffusion Models
- Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data