Research papers and preprints.
Encodes behavioral preferences in evaluator scores to trace models trained through label-only LLM supervision, enabling black-box detection without teacher-generated demonstrations.
Proposes Semantic Consistency Learning for animal re-identification across species, improving cross-species generalization under diverse morphologies and ecological domains.
Introduces OmniManim, a render-feedback-aware framework for generating educational animations with explicit visual planning, structured diagnostics, and localized repair.