HeadEdit: Calibrating Language Model Behavior Through the Frozen Unembedding Matrix
Research
Research News
New papers, breakthroughs and academic AI research
AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation
Research
SimplexUQ: An Evaluation Framework and Benchmark for Conformal Uncertainty on Simplex-Valued Predictions
Research
Overcoming Kernel Redundancy for Scaling Logic Gate Networks
Research
Score the Update, Not the Token: Descent-Aligned Routing for Combinatorial LoRA Experts
Research
MVDG: Efficient Multi-view 3D Disambiguation on Unconstrained Real-World Images
Research
Denoising Surface: Modeling and Predicting Inference Cost for Diffusion LLM Serving
Research
TRACE: Trajectory Return Attribution and Contrastive Erasure for Multi-Turn Safety
Research
An ontology for cross-sectoral crisis management: core and public health modules
Research
Generation Provenance Before Behavior Attribution: Auditing Synthetic Speech Research Objects
Research
Know When to Hold 'em: Correct-Token Retention in Uniform-State Diffusion Language Models
Research
Counting and Min-Cost Encoding for Tokenization in Large Language Models
Research