7 papers
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…
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…
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…
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…
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…
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…