31 papers
Revealing Structured Heterogeneity
Christopher Turansick
In this paper, we study models of restricted heterogeneity. While the random utility model allows for arbitrary heterogeneity among rational types, we consider the case when an ana…
ReTerm: Recovery Training for Self-Improving Terminal Agents
Wei Xie, Kaituo Feng, Shiming Fu +3
Terminal agents have shown strong abilities in complex coding tasks. However, they often struggle to recover from errors during long-running execution (e.g., command errors, faulty…
EviRover: Reinforcing Agentic Perception Beyond a Glance
Kaixuan Fan, Kaituo Feng, Tianshuo Peng +4
Visual perception is conventionally formulated as a one-shot prediction from a single glance at the image, under the assumption that the image content and the model's parametric kn…
VideoGen-Agent: Reinforcing Video Generation Agents
Binxu Li, Haoyi Duan, Yuhui Zhang +9
Recent advances in video generative models have enabled high-fidelity, temporally coherent video generation. However, these models often struggle to satisfy prompts requiring speci…
Stable-MM-R1: Anchoring Multimodal Reasoning Dynamics via Entropy-Guided Stratification
Yimeng Ye, Shuang Chen, Wenxuan Huang +8
While Reinforcement Learning (RL) effectively incentivizes reasoning in Large Language Models, current pipelines are hindered by training instability and rapid entropy collapse. Th…
AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward
Mingyang Wu, Kaituo Feng, Bohao Li +3
Detailed audio-video joint captioning is essential for multimodal video understanding and generation. However, prior works are constrained by three main limitations: (1) the scarci…
JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents
Yunlong Lin, Zixu Lin, Zhaohu Xing +23
Creative AI is moving from single-step asset generation toward long-horizon multimodal production. Although recent generative models can synthesize high-quality images, videos, aud…
SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation
Zhengbo Jiao, Yiming Cheng, Yilei Jiang +15
Training multimodal search agents to perform multi-hop reasoning remains challenging due to a fundamental structural disconnect: existing pipelines construct training data, search…
UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization
Yaozhi Zheng, Yilei Jiang, Manyuan Zhang +5
Visual-to-Code generation, which transforms scientific plots, vector graphics, and webpages into executable scripts, demands a level of pixel-precise alignment that standard Multim…
DOPD: Dual On-policy Distillation
Xinlei Yu, Gen Li, Qingyi Si +13
On-policy distillation (OPD) offers superior capacity transfer by supervising student-sampled trajectories with dense token-level signals. To furnish high-quality supervision sourc…
InterleaveThinker: Reinforcing Agentic Interleaved Generation
Dian Zheng, Harry Lee, Manyuan Zhang +4
Recent image generators have demonstrated impressive photorealism and instruction-following capabilities in single-image generation and editing. However, constrained by their archi…
Flow-OPD: On-Policy Distillation for Flow Matching Models
Zhen Fang, Wenxuan Huang, Yu Zeng +8
Existing Flow Matching (FM) text-to-image models suffer from two critical bottlenecks under multi-task alignment: the reward sparsity induced by scalar-valued rewards, and the grad…
Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning
Dian Zheng, Manyuan Zhang, Hongyu Li +4
Currently, enhancing Unified Multimodal Models (UMMs) with image understanding, generation, and editing capabilities mainly relies on mixed multi-task training. Due to inherent tas…
From Web to Pixels: Bringing Agentic Search into Visual Perception
Bokang Yang, Xinyi Sun, Kaituo Feng +3
Visual perception connects high-level semantic understanding to pixel-level perception, but most existing settings assume that the decisive evidence for identifying a target is alr…
OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
Shuang Chen, Kaituo Feng, Hangting Chen +7
Deep search has become a crucial capability for frontier multimodal agents, enabling models to solve complex questions through active search, evidence verification, and multi-step…
OpenGame: Open Agentic Coding for Games
Yilei Jiang, Jinyuan Hu, Qianyin Xiao +8
Game development sits at the intersection of creative design and intricate software engineering, demanding the joint orchestration of game engines, real-time loops, and tightly cou…
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
Xinlei Yu, Zhangquan Chen, Yongbo He +36
Latent space is rapidly emerging as a native substrate for language-based models. While modern systems are still commonly understood through explicit token-level generation, an inc…
Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis
Shuang Chen, Quanxin Shou, Hangting Chen +16
Unified multimodal models provide a natural and promising architecture for understanding diverse and complex real-world knowledge while generating high-quality images. However, the…
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Kaituo Feng, Manyuan Zhang, Shuang Chen +7
Recent image generation models have shown strong capabilities in generating high-fidelity and photorealistic images. However, they are fundamentally constrained by frozen internal…
Exploring Reasoning Reward Model for Agents
Kaixuan Fan, Kaituo Feng, Manyuan Zhang +7
Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse…
EditThinker: Unlocking Iterative Reasoning for Any Image Editor
Hongyu Li, Manyuan Zhang, Dian Zheng +11
Instruction-based image editing has emerged as a prominent research area, which, benefiting from image generation foundation models, have achieved high aesthetic quality, making in…
AdaTooler-V: Adaptive Tool-Use for Images and Videos
Chaoyang Wang, Kaituo Feng, Dongyang Chen +8
Recent advances have shown that multimodal large language models (MLLMs) benefit from multimodal interleaved chain-of-thought (CoT) with vision tool interactions. However, existing…
OneThinker: All-in-one Reasoning Model for Image and Video
Kaituo Feng, Manyuan Zhang, Hongyu Li +11
Reinforcement learning (RL) has recently achieved remarkable success in eliciting visual reasoning within Multimodal Large Language Models (MLLMs). However, existing approaches typ…
AIA: Rethinking Architecture Decoupling Strategy In Unified Multimodal Model
Dian Zheng, Manyuan Zhang, Hongyu Li +7
Unified multimodal models for image generation and understanding represent a significant step toward AGI and have attracted widespread attention from researchers. The main challeng…