This paper introduces CASTER, a gradient-free test-time adaptation method for frozen neural network models that stores source class statistics and…
ReFlowSET is a conditional latent flow-matching framework for converting synthetic aperture radar (SAR) imagery into electro-optical (EO) imagery. Rather than…
This paper introduces credit-addressable reasoning for multimodal geometry tasks, aligning the semantic units used during inference with the learning mechanism…
This paper introduces agentic data cracking, a method that dynamically structures unstructured data as a byproduct of agent reasoning: when…
DramaChain Bench is a benchmark for the complete short-drama production pipeline, spanning script, storyboard, keyframes, shots, and final episodes. It…
This paper finds that on-policy distillation’s teacher supervision contains substantial noise that doesn’t meaningfully affect student performance, and proposes On-Policy…
Lucida converts real indoor scenes into editable 3D simulation environments through a three-stage pipeline: parsing video into scene graphs with…
DreamX-Creator 1.0 is a compact 7-billion-parameter system for unified audio-video generation that jointly processes both modalities using gated cross-modal attention.…
GenFirst addresses latent collapse in end-to-end training of latent generative models by reversing the usual two-stage pipeline: a generation-before-reconstruction strategy…
Normalized Low-Rank Adaptation (NoRA) normalizes the down-projection matrices during LoRA training to improve optimization stability, and can also be applied…
PaperGym converts research papers into AI training environments by extracting evaluation criteria from a paper’s methodology and experiments rather than…
CogEvol is a family of models that automatically generate learning environments by converting course briefs into structured JSON slides or…
