collaborators

7 papers

cs.LG2026

Beyond Solvability: Task Learnability as a Static Prior for LLM RL Post-Training

Ting Zhou, Zhenqing Ling, Daoyuan Chen +4

Reinforcement learning (RL) has become a central post-training paradigm for eliciting reasoning capabilities in large language models, yet uniform task sampling allocates compute w…

cs.LG2026

GEOALIGN: Geometric Rollout Curation for Robust LLM Reinforcement Learning

Ting Zhou, Zhenqing Ling, Yiyang Zhao +2

Online reinforcement learning is widely used to align large language models (LLMs) with reward signals, yet training can be unstable under noisy or misspecified rewards. We identif…

cs.SD2026

Zero-VC: Zero-Lookahead Streaming Voice Conversion via Speaker Anonymization

Yudong Li, Zihao Fang, Junwen Qiu +4

Streaming zero-shot voice conversion struggles to disentangle timbre from linguistic content without degrading utility or inflating latency. Current methods rely on information bot…

cs.CV2026

DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?

Qirui Jiao, Daoyuan Chen, Yilun Huang +3

While recent Text-to-Image (T2I) models show impressive capabilities in synthesizing images from brief descriptions, they struggle with the long, detailed prompts required for prof…

cs.CV2026

HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks

Ting Zhou, Daoyuan Chen, Qirui Jiao +3

Evaluating the nuanced human-centric video understanding capabilities of Multimodal Large Language Models (MLLMs) remains a great challenge, as existing benchmarks often overlook t…

cs.CV2024

Img-Diff: Contrastive Data Synthesis for Multimodal Large Language Models

Qirui Jiao, Daoyuan Chen, Yilun Huang +3

High-performance Multimodal Large Language Models (MLLMs) are heavily dependent on data quality. To advance fine-grained image recognition within MLLMs, we introduce a novel data s…