WEZZEL NEWS

Can Scientific Claims Be Removed from Large Language Models? A Systematic Evaluation of Claim-Level Unlearning

Researchers have proposed a new method called SciUnlearn to remove outdated scientific claims from l...

TreeWY: Speculative Verification for Gated DeltaNet Hybrids

Researchers have proposed TreeWY, a method for verifying and rolling back speculative decoding in hy...

Generalizing Soft Tissue Deformation and Force Prediction Across Material Stiffness and Geometry

Researchers have developed a new AI model for simulating soft tissue deformation and predicting forc...

Deep Learning Models Also Recall Features

Researchers have found that large language models can recall stored information by scaling input act...

Belief Without Behavior: Measuring the Translation of Theory of Mind into Coordinated Social Action in Vision-Language Models

Researchers have created a benchmark to measure how well AI models can translate...

Don't Solve, Just Compare: Tiny Advisors for Runtime Intervention in LLM Agents

Researchers have developed a new approach to improving the reliability of large ...

Evaluating Large Language Model Performance on International Maritime Dangerous Goods Code Compliance

Researchers have created a benchmark to evaluate the performance of large langua...

Socialized Division and Collaboration: Rethinking Class-Incremental Learning under Optimization Conflicts

Researchers have proposed a new approach to class-incremental learning called So...