Sen Wang

The paper introduces Token-Aware Gradient Optimization (TAGO), demonstrating that sparse optimization focusing only on high-gradient audio tokens is sufficient for effective jailbreaking of audio language models, making dense updates redundant.

The paper introduces PetroBench, a comprehensive benchmark for evaluating Large Language Models across various domains of petroleum engineering, finding that models perform better on subjective tasks than on objective factual knowledge.

This paper proposes a framework for creating low-latency, interactive generative music AI using distillation in a streaming autoregressive latent space and music-aware consistency objectives.

This paper introduces LingBot-Video, a video pretraining paradigm for embodied intelligence using a DiT-based approach, Mixture-of-Experts framework, and extensive robot-oriented data.