collaborators

5 papers

cs.LG2026

MesaNet: Sequence Modeling by Locally Optimal Test-Time Training

Johannes von Oswald, Nino Scherrer, Seijin Kobayashi +14

Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention. Although widely adopted, transformers require scaling memory and compu…

cs.CV2026

EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation

Songlin Yang, Haobin Zhong, Ruilin Zhang +23

The rapid evolution of generative video foundation models has propelled the field toward professional-grade cinematic synthesis. To achieve such demanding quality, the community tr…

cs.CV2026

Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models

Songlin Yang, Xianghao Kong, Anyi Rao

Unified multimodal models (UMMs) were designed to combine the reasoning ability of large language models (LLMs) with the generation capability of vision models. In practice, howeve…

cs.CV2026

ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation

Songlin Yang, Zhe Wang, Xuyi Yang +7

Text-driven video generation has democratized film creation, but camera control in cinematic multi-shot scenarios remains a significant block. Implicit textual prompts lack precisi…

cs.LG2025

Test-Time Training Done Right

Tianyuan Zhang, Sai Bi, Yicong Hong +6

Test-Time Training (TTT) models context dependencies by adapting part of the model's weights (referred to as fast weights) during inference. This fast weight, akin to recurrent sta…