Recent Vision-Language-Action (VLA) models increasingly use natural-language instructions to condition autonomous driving behavior. Yet existing closed-loop benchmarks primarily measure route completion, safety, and rule compliance, leaving a fundamental question unresolved: does language actually determine which feasi...
Zi-Han You, Ze-Hua Fan, Wenqi Lyu et al.· 0 citations
A rubric-based audio-grounded evaluation framework that verifies event realization, acoustic attributes, and speech content through fine-grained semantic criteria, and human validation demonstrates that the benchmark achieves stronger alignment with human semantic judgments than conventional global similarity metrics.
Jin-Ting Wang, Yuguang Yang, Shengyu Li et al.· 0 citations
Extensive experiments demonstrate that AnyAudio-Judge not only significantly enhances zero-shot alignment detection compared to state-of-the-art baselines, but also provides precise and interpretable reward signals that substantially improve instruction alignment in downstream reinforcement learning for audio generatio...
Hai-Tao Li, Tian Tan, Yuguang Yang et al.· arXiv.org· 3 citations
Squeeze10-LLM is a staged mixed-precision post-training quantization (PTQ) framework and achieves state-of-the-art performance for sub-2bit weight-only quantization, improving average accuracy from 43% to 56% on six zero-shot classification tasks--a significant boost over existing PTQ methods.
Qingcheng Zhu, Yang-Yang Ren, Lin-Lin Yang et al.· arXiv.org· 1 citation
StageWAM is introduced, which augments a Motus-based World Action Model with Stage-JEPA, a goal-conditioned Joint-Embedding Predictive Architecture (JEPA) predictor, which uses a frozen V-JEPA2 encoder to extract the current-state representation and predicts the latent target of the next inferred stage.
Xiao Liu, Yuguang Yang, Xi Wang et al.· 2 citations· ⚡1
Adaptive-WAM is introduced, a quality-aware multi-exit planner built on a Wan2.2-5B backbone that avoids the iterative classifier-free denoising loop and VAE decoding required for future-video synthesis, while dynamically allocating backbone depth according to trajectory quality.
Sining Ang, Yuguang Yang, Yan Wang· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
