30 citations · 148 across the 82 of their papers we have counts for
83 papers
Bidirectional Context Self-Distillation for Reinforcement Learning of Skill-Based LLM Agents
Tianjun Pan, Yuan Li, Hongda Wang +8
External natural-language skills provide large language model (LLM) agents with reusable and editable guidance for solving complex tasks. Yet their effectiveness depends not only o…
MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations
Qiming Shi, Yulong Tao, Linbo Jin +10
Large language model agents are increasingly evaluated as autonomous tool users, yet most benchmarks focus on bounded tasks with immediate success criteria. Real-world deployments…
Beyond Solution-Centric Search: Adaptive Inquiry and Knowledge Revision for Autonomous ML Engineering
Shaokang Fu, Yulong Tao, Linbo Jin +7
Long-horizon autonomous research tasks such as machine learning engineering require systems to make interdependent decisions under a limited budget. Existing LLM-based agents typic…
UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models
Jiaqi Wang, Haoge Deng, Ting Pan +5
Uniform Discrete Diffusion Model (UDM) has recently emerged as a promising paradigm for discrete generative modeling; however, its integration with reinforcement learning remains l…
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…
VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoning
Yibo Wang, Yongcheng Jing, Shunyu Liu +5
Long-context reasoning has significantly empowered large language models (LLMs) to tackle complex tasks, yet it introduces severe efficiency bottlenecks due to the computational co…
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:…
Where Does Vision Meet Language? Understanding and Refining Visual Fusion in MLLMs via Contrastive Attention
Shezheng Song, Shasha Li, Shan Zhao +6
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language understanding, yet how they internally integrate visual and textual information remain…
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…
Emu3.5: Native Multimodal Models are World Learners
Yufeng Cui, Honghao Chen, Haoge Deng +20
We introduce Emu3.5, a large-scale multimodal world model that natively predicts the next state across vision and language. Emu3.5 is pre-trained end-to-end with a unified next-tok…
SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models
Chenyu Wang, Paria Rashidinejad, DiJia Su +9
Diffusion large language models (dLLMs) are emerging as an efficient alternative to autoregressive models due to their ability to decode multiple tokens in parallel. However, align…
Shared Neural Space: Unified Precomputed Feature Encoding for Multi-Task and Cross Domain Vision
Jing Li, Oskar Bartosz, Chengyu Wang +3
The majority of AI models in imaging and vision are customized to perform on specific high-precision task. However, this strategy is inefficient for applications with a series of m…
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…
Inducing Causal World Models in LLMs for Zero-Shot Physical Reasoning
Aditya Sharma, Ananya Gupta, Chengyu Wang +2
Large Language Models (LLMs), despite their advanced linguistic capabilities, fundamentally lack an intuitive understanding of physical dynamics, which limits their effectiveness i…
Think, Act, Learn: A Framework for Autonomous Robotic Agents using Closed-Loop Large Language Models
Anjali R. Menon, Rohit K. Sharma, Priya Singh +3
The integration of Large Language Models (LLMs) into robotics has unlocked unprecedented capabilities in high-level task planning. However, most current systems operate in an open-…
Video Event Reasoning and Prediction by Fusing World Knowledge from LLMs with Vision Foundation Models
L'ea Dubois, Klaus Schmidt, Chengyu Wang +3
Current video understanding models excel at recognizing "what" is happening but fall short in high-level cognitive tasks like causal reasoning and future prediction, a limitation r…
MatDecompSDF: High-Fidelity 3D Shape and PBR Material Decomposition from Multi-View Images
Chengyu Wang, Isabella Bennett, Henry Scott +4
We present MatDecompSDF, a novel framework for recovering high-fidelity 3D shapes and decomposing their physically-based material properties from multi-view images. The core challe…
EasyDistill: A Comprehensive Toolkit for Effective Knowledge Distillation of Large Language Models
Chengyu Wang, Junbing Yan, Wenrui Cai +2
In this paper, we present EasyDistill, a comprehensive toolkit designed for effective black-box and white-box knowledge distillation (KD) of large language models (LLMs). Our frame…
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…
DistilQwen2.5: Industrial Practices of Training Distilled Open Lightweight Language Models
Chengyu Wang, Junbing Yan, Yuanhao Yue +1
Enhancing computational efficiency and reducing deployment costs for large language models (LLMs) have become critical challenges in various resource-constrained scenarios. In this…
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…