2 citations · 2 across the 13 of their papers we have counts for
15 papers
RSIgen: Reciprocal Self-Improvement for Agentic Visual Generation
Yidi Liu, Haozhe Wang, Jie Xiao +3
Agentic visual generation produces experience that can improve the native understanding (agent) and generation roles of a unified multimodal backbone, but task success alone does n…
AVA-Encoder: Towards Agent-Native Video Representation Learning
Chuyue Li, Jinpeng Yu, Haozhe Wang +7
Agentic video creation systems remain far from cinematic-grade quality: their underlying models struggle to plan how story, characters, visuals, and sound fit together, and high-qu…
SpecPath: Testing Coding Agents Across Contract-Equivalent Specification Histories
Yangfan Wu, Haozhe Wang, Huanyu Yang +2
Modern coding agents increasingly appear capable of following complex software requirements, yet their success leaves a critical ambiguity: do they resolve the active specification…
Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
Bingnan Li, Haozhe Wang, Haozhong Xiong +5
On-policy distillation (OPD) adapts diffusion models by querying a teacher along trajectories generated by the current student, but how it should behave under classifier-free guida…
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
Haozhe Wang, Weijia Feng, Jinpeng Yu +8
Visual generators excel at rendering, but they confidently fabricate what they do not know. User requests are unbounded, evolving, and deeply long-tailed: new characters, trending…
Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning
Haozhe Wang, Qixin Xu, Changpeng Wang +4
Achieving robust perception-reasoning synergy is a central goal for advanced Vision-Language Models (VLMs). Recent advancements have pursued this goal via architectural designs or…
Starve to Perceive: Taming Lazy Perception in VLMs with Constrained Visual Bandwidth
Yuhuan Wu, Cong Wei, Fangzhen Lin +2
Vision-Language Models (VLMs) deployed as situated agents in high-resolution visual environments require active perception -- the ability to dynamically decide where to look throug…
RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time
Haozhe Wang, Cong Wei, Weiming Ren +3
Most reward models for visual generation reduce rich human judgments to a single unexplained score, discarding the reasoning that underlies preference. We show that teaching reward…
Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining
Zhiyuan Zeng, Yichi Zhang, Yong Shan +11
While Large Language Models (LLMs) have achieved remarkable success in code generation, they often struggle with the deep, long-horizon reasoning required for complex software engi…
SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding
Songcheng Cai, Zhiheng Lyu, Yuansheng Ni +13
Agentic repository-level code understanding is essential for automating complex software engineering tasks, yet the field lacks reliable benchmarks. Existing evaluations often over…
VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
Dongfu Jiang, Yi Lu, Zhuofeng Li +9
Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated success in enhancing LLM reasoning capabilities, but remains limited to single-turn interactions without tool…
Dr. Bench: A Multidimensional Evaluation for Deep Research Agents, from Answers to Reports
Yang Yao, Yixu Wang, Yuxuan Zhang +9
As an embodiment of intelligence evolution toward interconnected architectures, Deep Research Agents (DRAs) systematically exhibit the capabilities in task decomposition, cross-sou…
VideoScore2: Think before You Score in Generative Video Evaluation
Xuan He, Dongfu Jiang, Ping Nie +21
Recent advances in text-to-video generation have produced increasingly realistic and diverse content, yet evaluating such videos remains a fundamental challenge due to their multi-…
StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs
Jialin Yang, Dongfu Jiang, Lipeng He +17
As Large Language Models (LLMs) become integral to software development workflows, their ability to generate structured outputs has become critically important. We introduce Struct…
ACECODER: Acing Coder RL via Automated Test-Case Synthesis
Huaye Zeng, Dongfu Jiang, Haozhe Wang +3
Most progress in recent coder models has been driven by supervised fine-tuning (SFT), while the potential of reinforcement learning (RL) remains largely unexplored, primarily due t…