Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Suggested from co-authorship
- Yueting ZhuangSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works31 from public data
- AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea261
AnyEdit is presented, a comprehensive multi-modal instruction editing dataset, comprising 2.5 million high-quality editing pairs spanning over 20 editing types and five domains, and shows that AnyEdit consistently boosts the performance of diffusion-based editing models.
- Auto-Encoding Morph-Tokens for Multimodal LLM41
This work proposes encoding images into morph-tokens to serve a dual purpose: for comprehension, they act as visual prompts instructing MLLM to generate texts; for generation, they take on a different, non-conflicting role as complete visual-tokens for image reconstruction, where the missing visual cues are recovered by the MLLM.
- Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning36
Selftok supports reinforcement learning for visual generation with effectiveness comparable to that achieved in LLMs, and is also a SoTA tokenizer that achieves a favorable trade-off between high-quality reconstruction and compression rate.
- STEP: Enhancing Video-LLMs’ Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training33
STEP, a novel graph-guided self-training method that enables Video-LLMs to generate reasoning-rich fine-tuning data from any raw videos to improve itself, achieves superior performance with a minimal amount of self-generated rationale-enriched training samples in both compositional reasoning and comprehensive understanding benchmarks, highlighting the broad applicability and vast potential.
- Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens33
This paper builds a proper visual language by leveraging diffusion timesteps to learn discrete, recursive visual tokens that recursively compensate for the progressive attribute loss in noisy images as timesteps increase, enabling the diffusion model to reconstruct the original image at any timestep.
- 30
- On Path to Multimodal Generalist: General-Level and General-Bench29
This project introduces General-Level, an evaluation framework that defines 5-scale levels of MLLM performance and generality, offering a methodology to compare MLLMs and gauge the progress of existing systems towards more robust multimodal generalists and, ultimately, towards AGI.
- OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning25
OmniWeaving, an omni-level video generation model featuring powerful multimodal composition and reasoning-informed capabilities, is proposed and IntelligentVBench, the first comprehensive benchmark designed to rigorously assess next-level intelligent unified video generation is introduced.
- 24
- Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization for Few-shot Generalization18
SUPMER leverages self-supervised meta-learning with a diverse set of well-designed meta-training tasks to learn a universal prompt initialization for efficient adaptation using only unlabeled data, and jointly meta-learns a gradient regularization function to transform raw gradients into a domain-generalizable direction, thus alleviating the problem of overfitting.
- Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement Learning16
The Phys-AR framework is proposed, which consists of two stages: the first stage uses supervised fine-tuning to transfer symbolic knowledge, while the second stage applies reinforcement learning to optimize the model's reasoning abilities through reward functions based on physical conditions.
- FocusDiff: Advancing Fine-Grained Text-Image Alignment for Autoregressive Visual Generation through RL15
This work proposes FocusDiff, which enhances fine-grained text-image semantic alignment by focusing on subtle differences between similar text-image pairs, and achieves state-of-the-art performance on existing text-to-image benchmarks and significantly outperforms prior methods on PairComp.
- Improving Vision Anomaly Detection With the Guidance of Language Modality12
This paper proposes Cross-modal Guidance (CMG), comprising of Cross-modal Entropy Reduction (CMER) and Cross-modal Linear Embedding (CMLE), to address the issues of redundant information and sparse latent space, respectively.
- Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning11
This paper proposes to enable the collaborative co-evolution of visual comprehension and generation, advancing image generation into an iterative introspective process and introduces a two-stage training approach: supervised fine-tuning teaches the MLLM with the foundational ability to generate genuine CoT for visual generation, while reinforcement learning activates its full potential via an exploration-exploitation trade-off.
- What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities10
OmniBench is introduced, a self-generating, cross-platform, graph-based benchmark with an automated pipeline for synthesizing tasks of controllable complexity through subtask composition and OmniEval, a multidimensional evaluation framework that includes subtask-level evaluation, graph-based metrics, and comprehensive tests across 10 capabilities.
- WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editing9
WiseEdit is introduced, a knowledge-intensive benchmark for comprehensive evaluation of cognition- and creativity-informed image editing, featuring deep task depth and broad knowledge breadth and incorporating three fundamental types of knowledge: Declarative, Procedural, and Metacognitive knowledge.
- Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining8
Iris is introduced, a foundational visual agent that addresses challenges in visual perception through two key innovations: Information-Sensitive Cropping (ISC) and Self-Refining Dual Learning (SRDL).
- I3: I ntent- I ntrospective Retrieval Conditioned on I nstructions7
I3 is introduced, a unified retrieval system that performs Intent-Introspective retrieval across various tasks, conditioned on Instructions without any task-specific training, embodying two key designs: progressive structure pruning and drawback extrapolation-based data refinement.
- Evolving Generalist Virtual Agents with Generative and Associative Memory6
CA3Mem, a framework inspired by the human hippocampus that organizes experiences into a structured memory graph, features two key innovations: a generative memory recombination mechanism that synthesizes novel solutions to drive agent evolution and an associative retrieval algorithm that employs spreading activation to recall a comprehensive and contextually-aware set of experiences.
- 5
- SpatialFusion: Endowing Unified Image Generation with Intrinsic 3D Geometric Awareness2
This paper proposes SpatialFusion, a novel framework that internalizes 3D geometric awareness into unified image generation models and significantly enhances performance on spatially-aware benchmarks, notably outperforming leading models such as GPT-4o.
- OmniMoGen: Unifying Human Motion Generation via Learning from Interleaved Text-Motion Instructions2
Experiments show that OmniMoGen achieves state-of-the-art performance on text-to-motion, motion editing, and AnyContext, exhibiting emerging capabilities such as compositional editing, self-reflective generation, and knowledge-informed generation.
- Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs1
The proposed MIND (Meta-cognitive INtegrated Dynamic Knowledge Editing), a framework that constructs a meta-knowledge memory for self-awareness, employs game-theoretic interactions to monitor knowledge activation, and incorporates label refinement for noise-robust updates, significantly outperforms existing cognitive editing approaches.
- Selftok-Zero: Reinforcement Learning for Visual Generation via Discrete and Autoregressive Visual Tokens1
This work states that existing visual generative models are not yet ready for RL due to the following two fundamental drawbacks that undermine the foundations of RL.
- 1
- –
- –
- –
- –
- –
- Vinci: Deep Thinking in Text-to-Image Generation using Unified Model with Reinforcement Learning–
This work proposes Vinci, a novel framework designed to enable interleaved image generation and understanding through deep reasoning capabilities, and introduces a momentum-based reward function, which dynamically adjusts the reward distribution by considering historical improvements, ensuring the stability of the model across multiple generations.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.