papers

Publications (9)

cs.CV2024

RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models

Xinchen Zhang, Ling Yang, Yaqi Cai +8

Diffusion models have achieved remarkable advancements in text-to-image generation. However, existing models still have many difficulties when faced with multiple-object compositio…

cs.CL2024

Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

Ling Yang, Zhaochen Yu, Tianjun Zhang +5

We introduce Buffer of Thoughts (BoT), a novel and versatile thought-augmented reasoning approach for enhancing accuracy, efficiency and robustness of large language models (LLMs).…

cs.CV2024

Contextualized Diffusion Models for Text-Guided Image and Video Generation

Ling Yang, Zhilong Zhang, Zhaochen Yu +4

Conditional diffusion models have exhibited superior performance in high-fidelity text-guided visual generation and editing. Nevertheless, prevailing text-guided visual diffusion m…

cs.LG2026

Slow-Fast Inference: Training-Free Inference Acceleration via Within-Sentence Support Stability

Xingyu Xie, Zhaochen Yu, Yue Liao +3

Long-context autoregressive decoding remains expensive because each decoding step must repeatedly process a growing history. We observe a consistent pattern during decoding: within…

cs.CV2024

Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs

Ling Yang, Zhaochen Yu, Chenlin Meng +3

Diffusion models have exhibit exceptional performance in text-to-image generation and editing. However, existing methods often face challenges when handling complex text prompts th…

cs.CL2025

SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction

Ling Yang, Zhaochen Yu, Tianjun Zhang +4

Large language models (LLMs) like GPT-4, DeepSeek-R1, and ReasonFlux have shown significant improvements in various reasoning tasks. However, smaller LLMs still struggle with compl…

cs.CL2025

ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates

Ling Yang, Zhaochen Yu, Bin Cui +1

We present that hierarchical LLM reasoning via scaling thought templates can effectively optimize the reasoning search space and outperform the mathematical reasoning capabilities…

cs.CL2025

Demystifying Reinforcement Learning in Agentic Reasoning

Zhaochen Yu, Ling Yang, Jiaru Zou +2

Recently, the emergence of agentic RL has showcased that RL could also effectively improve the agentic reasoning ability of LLMs, yet the key design principles and optimal practice…

cs.CV2024

VideoTetris: Towards Compositional Text-to-Video Generation

Ye Tian, Ling Yang, Haotian Yang +9

Diffusion models have demonstrated great success in text-to-video (T2V) generation. However, existing methods may face challenges when handling complex (long) video generation scen…