Yiwen Guo

Ex-Omni-2D generates visually coherent dialogue responses that seamlessly integrate text, speech, and video, all while avoiding the need for extensive multi-modal training data.

Skill-α outperforms traditional skill generation methods by leveraging a novel rollback reward mechanism, leading to significant improvements in agent performance on downstream tasks.

EvolvingWorld reveals that an open-schema framework can drastically enhance the coherence and depth of character and world interactions in long-horizon literary simulations.

MRRG reveals that leveraging multiple evaluative perspectives can significantly enhance the quality of reward signals for LLM optimization, outperforming traditional single-role approaches.

Achieving one-step audio waveform generation with a 17× speedup while preserving quality could revolutionize TTS systems.

Leveraging hidden states from reward models can boost RLHF performance by over 6% on challenging benchmarks, transforming how we utilize reward signals.

Merging concrete visual rollouts with abstract reasoning leads to a 10.6% and 10.9% performance boost on challenging reasoning benchmarks, showcasing the power of hybrid models.

LLMs can compile GUI code, but can't actually *play* it, highlighting a critical gap in their ability to generate logically correct, interactive applications.