Han Zhao

This work develops lightweight characterization methods to uncover per-chip compute topology and memory affinity and uses the discovered information to make existing fine-grained scheduling asymmetry-aware, considering not only how many resources are allocated but also which physical resources are assigned.

This technical retrospective offers a different account of the CosyVoice lineage, from CosyVoice through CosyVoice 2 and CosyVoice 3 to Qwen-Audio-3.0-TTS, and formalizes this history through four interface dimensions---representation, ownership, availability, and gradient reach---and separate within-paper evidence from cross-paper comparison.

Correctly aligning audio descriptions with representations can boost classification performance by nearly 5 points, revealing the critical role of semantic refinement in audio tasks.

FullDiT not only outperforms leading commercial music generators but also redefines how we approach music rendering by leveraging full-context generation techniques.

Deltoris achieves a staggering 34.2× speedup for real-time VLA inference, revolutionizing how embodied AI can operate on edge devices.

Unified generation of temporally structured audio achieves unprecedented speaker similarity and cross-turn consistency without task-specific branches.

V-Steer boosts the accuracy of language model instruction hierarchies to 92% by intelligently editing cached values without the need for retraining.

Achieve optimal advertising feed re-ranking by baking constraints directly into neural decoding, sidestepping the usual latency and constraint-handling limitations of generative approaches.