3 citations · 9 across the 21 of their papers we have counts for
22 papers
OmniThoughtVis: A Scalable Distillation Pipeline for Deployable Multimodal Reasoning Models
Yuanhao Yue, Chengyu Wang, Yuanjie Lyu +2
Recent multimodal large language models (MLLMs) have shown strong chain-of-thought (CoT) reasoning ability on vision-language tasks, but their direct deployment in real-world syste…
AgenticQwen: Training Small Agentic Language Models with Dual Data Flywheels for Industrial-Scale Tool Use
Yuanjie Lyu, Chengyu Wang, Haonan Zheng +4
Modern industrial applications increasingly demand language models that act as agents, capable of multi-step reasoning and tool use in real-world settings. These tasks are typicall…
Mock Worlds, Real Skills: Building Small Agentic Language Models with Synthetic Tasks, Simulated Environments, and Rubric-Based Rewards
Yuanjie Lyu, Chengyu Wang, Lei Shen +2
Small LLMs often struggle to match the agentic capabilities of large, costly models. While reinforcement learning can help, progress has been limited by two structural bottlenecks:…
Thinking with DistilQwen: A Tale of Four Distilled Reasoning and Reward Model Series
Wenrui Cai, Chengyu Wang, Junbing Yan +2
Recently, the demand for small and efficient reasoning models to support real-world applications has driven the development of knowledge distillation techniques that balance reason…
Student-Centered Distillation Narrows the Agentic Gap Between Small and Large LLMs
Yuanjie Lyu, Chengyu Wang, Jun Huang +1
Large Language Model agents achieve strong performance on multi-step reasoning and tool-use tasks, but their impressive capabilities typically rely on extremely large backbones. Ex…
Encapsulated Composition of Text-to-Image and Text-to-Video Models for High-Quality Video Synthesis
Tongtong Su, Chengyu Wang, Bingyan Liu +2
In recent years, large text-to-video (T2V) synthesis models have garnered considerable attention for their abilities to generate videos from textual descriptions. However, achievin…
Zero-to-Hero: Zero-Shot Initialization Empowering Reference-Based Video Appearance Editing
Tongtong Su, Chengyu Wang, Jun Huang +1
Appearance editing according to user needs is a pivotal task in video editing. Existing text-guided methods often lead to ambiguities regarding user intentions and restrict fine-gr…
Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations
Wenrui Cai, Chengyu Wang, Junbing Yan +2
The emergence of large reasoning models (LRMs) has transformed Natural Language Processing by excelling in complex tasks such as mathematical problem-solving and code generation. T…
Understanding Attention Mechanism in Video Diffusion Models
Bingyan Liu, Chengyu Wang, Tongtong Su +4
Text-to-video (T2V) synthesis models, such as OpenAI's Sora, have garnered significant attention due to their ability to generate high-quality videos from a text prompt. In diffusi…
Enhancing Reasoning Abilities of Small LLMs with Cognitive Alignment
Wenrui Cai, Chengyu Wang, Junbing Yan +2
The reasoning capabilities of large reasoning models (LRMs), such as OpenAI's o1 and DeepSeek-R1, have seen substantial advancements through deep thinking. However, these enhanceme…
Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective
Xiangru Zhu, Penglei Sun, Yaoxian Song +6
Accurate interpretation and visualization of human instructions are crucial for text-to-image (T2I) synthesis. However, current models struggle to capture semantic variations from…
DiffChat: Learning to Chat with Text-to-Image Synthesis Models for Interactive Image Creation
Jiapeng Wang, Chengyu Wang, Tingfeng Cao +2
We present DiffChat, a novel method to align Large Language Models (LLMs) to "chat" with prompt-as-input Text-to-Image Synthesis (TIS) models (e.g., Stable Diffusion) for interacti…
Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing
Bingyan Liu, Chengyu Wang, Tingfeng Cao +2
Deep Text-to-Image Synthesis (TIS) models such as Stable Diffusion have recently gained significant popularity for creative Text-to-image generation. Yet, for domain-specific scena…
Diffutoon: High-Resolution Editable Toon Shading via Diffusion Models
Zhongjie Duan, Chengyu Wang, Cen Chen +2
Toon shading is a type of non-photorealistic rendering task of animation. Its primary purpose is to render objects with a flat and stylized appearance. As diffusion models have asc…
A Contrastive Compositional Benchmark for Text-to-Image Synthesis: A Study with Unified Text-to-Image Fidelity Metrics
Xiangru Zhu, Penglei Sun, Chengyu Wang +4
Text-to-image (T2I) synthesis has recently achieved significant advancements. However, challenges remain in the model's compositionality, which is the ability to create new combina…
Towards Better Parameter-Efficient Fine-Tuning for Large Language Models: A Position Paper
Chengyu Wang, Junbing Yan, Wei Zhang +1
This paper delves into the pressing need in Parameter-Efficient Fine-Tuning (PEFT) for Large Language Models (LLMs). While LLMs possess remarkable capabilities, their extensive par…
FastBlend: a Powerful Model-Free Toolkit Making Video Stylization Easier
Zhongjie Duan, Chengyu Wang, Cen Chen +3
With the emergence of diffusion models and rapid development in image processing, it has become effortless to generate fancy images in tasks such as style transfer and image editin…
Sharing, Teaching and Aligning: Knowledgeable Transfer Learning for Cross-Lingual Machine Reading Comprehension
Tingfeng Cao, Chengyu Wang, Chuanqi Tan +2
In cross-lingual language understanding, machine translation is often utilized to enhance the transferability of models across languages, either by translating the training data fr…
From Complex to Simple: Unraveling the Cognitive Tree for Reasoning with Small Language Models
Junbing Yan, Chengyu Wang, Taolin Zhang +3
Reasoning is a distinctive human capacity, enabling us to address complex problems by breaking them down into a series of manageable cognitive steps. Yet, complex logical reasoning…
BeautifulPrompt: Towards Automatic Prompt Engineering for Text-to-Image Synthesis
Tingfeng Cao, Chengyu Wang, Bingyan Liu +3
Recently, diffusion-based deep generative models (e.g., Stable Diffusion) have shown impressive results in text-to-image synthesis. However, current text-to-image models often requ…
Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding
Jianing Wang, Qiushi Sun, Nuo Chen +4
The recent success of large pre-trained language models (PLMs) heavily hinges on massive labeled data, which typically produces inferior performance in low-resource scenarios. To r…
On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook
Mingyuan Fan, Chengyu Wang, Cen Chen +2
Diffusion models and large language models have emerged as leading-edge generative models, revolutionizing various aspects of human life. However, the practical implementations of…