activity
20232026
collaborators
Showing 2026Show all

8 papers · 1 filter

cs.SD2026

Which Constraints Are Missing? Ask the Verifier: Graded Rewards for Constraint-Following Music Generation

Haoyue Liu, Ye Chen, Zhichao Wang +3

Constraint-following music generation asks a score to satisfy several user-specified properties at once, each checkable programmatically (key, meter, length, range, final note, rhy…

cs.AI2026

Why Sample What You Can Enumerate? Exact Policy Optimization for Genomic Tool Selection

Haoyue Liu, Xiaoyu Ma, Ye Chen +2

Reinforcement learning over a frozen reasoner has become a common recipe for teaching a policy which external tools to invoke. We show that this recipe becomes structurally mismatc…

cs.AI2026

SEPO: Evidence-Grounded Prompt Optimization via Structural Editing

Xiaoyu Ma, Haoyue Liu, Yiwen Li +4

Existing API-only prompt optimisers are often described as interpretable, but in practice, this usually means only post-hoc inspectability: each iteration still rewrites the prompt…

cs.SD2026

Do SpeechLMs Hear Their Own Opinions? Diagnosing and Mitigating Previous-Belief Contamination in Streaming Emotion Understanding

Haoyue Liu, Zhichao Wang, Ye Chen +2

Streaming emotion understanding uses historical state while continuously interpreting current audio, often feeding the model's previous prediction back as context. We show that thi…

cs.AI2026

Which Negatives Matter? Ask Your Text Encoder: Adaptive Similarity Margins for Dense-Caption Retrieval

Haoyue Liu, Ye Chen, Zhichao Wang +1

Dense-caption retrieval has recently been improved by introducing segmentation, edge maps, LLM-filtered captions, and cross-modal modules into contrastive fine-tuning. However, the…

cs.AI2026

Select Smarter, Not More: Prompt-Aware Evaluation Scheduling with Submodular Guarantees

Xiaoyu Ma, Yiwen Li, Haoyue Liu +4

Automatic prompt optimization (APO) hinges on the quality of its evaluation signal, yet scoring every prompt candidate on the full training set is prohibitively expensive. Existing…