Yaoqi Ye
Publications
Controllable Video Object Insertion via Multi-View Priors
Video object insertion places a user-specified object in an existing dynamic scene. Existing methods typically condition generation on text or a single reference image. Consequently, object appearance is underconstrained under viewpoint changes, often leading to identity drift, incorrect foreground-background layering, boundary artifacts, and temporal flickering. In this paper, we propose a video object insertion framework that incorporates multi-view object priors to address these limitations. The framework lifts a 2D reference image into a multi-view representation and uses view-consistent conditioning to provide stable identity guidance and view-adaptive appearance cues. A quality-aware weighting mechanism reduces the influence of noisy or imperfect reconstructed views. We further introduce an Integration-Aware Consistency Module that promotes plausible occlusion, clean boundaries, and temporal continuity. Experiments demonstrate that the proposed framework improves visual quality, controllability, identity consistency, and foreground-background integration for video object insertion compared to the baseline methods. Project page: https://polarisxq.github.io/MOVI/.
In-Context Reinforcement Learning for Tool Use in Large Language Models
While large language models (LLMs) exhibit strong reasoning abilities, their performance on complex tasks is often constrained by the limitations of their internal knowledge. A compelling approach to overcome this challenge is to augment these models with external tools -- such as Python interpreters for mathematical computations or search engines for retrieving factual information. However, enabling models to use these tools effectively remains a significant challenge. Existing methods typically rely on cold-start pipelines that begin with supervised fine-tuning (SFT), followed by reinforcement learning (RL). These approaches often require substantial amounts of labeled data for SFT, which is expensive to annotate or synthesize. In this work, we propose In-Context Reinforcement Learning (ICRL), an RL-only framework that eliminates the need for SFT by leveraging few-shot prompting during the rollout stage of RL. Specifically, ICRL introduces in-context examples within the rollout prompts to teach the model how to invoke external tools. Furthermore, as training progresses, the number of in-context examples is gradually reduced, eventually reaching a zero-shot setting where the model learns to call tools independently. We conduct extensive experiments across a range of reasoning and tool-use benchmarks. Results show that ICRL achieves state-of-the-art performance, demonstrating its effectiveness as a scalable, data-efficient alternative to traditional SFT-based pipelines.
ImageEdit-R1: Boosting Multi-Agent Image Editing via Reinforcement Learning
With the rapid advancement of commercial multi-modal models, image editing has garnered significant attention due to its widespread applicability in daily life. Despite impressive progress, existing image editing systems, particularly closed-source or proprietary models, often struggle with complex, indirect, or multi-step user instructions. These limitations hinder their ability to perform nuanced, context-aware edits that align with human intent. In this work, we propose ImageEdit-R1, a multi-agent framework for intelligent image editing that leverages reinforcement learning to coordinate high-level decision-making across a set of specialized, pretrained vision-language and generative agents. Each agent is responsible for distinct capabilities--such as understanding user intent, identifying regions of interest, selecting appropriate editing actions, and synthesizing visual content--while reinforcement learning governs their collaboration to ensure coherent and goal-directed behavior. Unlike existing approaches that rely on monolithic models or hand-crafted pipelines, our method treats image editing as a sequential decision-making problem, enabling dynamic and context-aware editing strategies. Experimental results demonstrate that ImageEdit-R1 consistently outperforms both individual closed-source diffusion models and alternative multi-agent framework baselines across multiple image editing datasets.