arXiv subjects

Yizhi Song

Publications and source records attributed to Yizhi Song.

At least 19 recordsLinked to original sources

arXiv2026

First-Principles Atomistic Structure and Dynamics of Polyethylene During High-Pressure Radical Polymerization via Machine Learning Force Fields

Polyethylene (PE) is one of the most commonly used synthetic polymers. While the synthesis and processing protocols for PE are well established, precise experimental assignment of microscopic structures at atomistic resolution (i.e., the position of each atom) remains largely limited to highly crystalline systems. This gap is often addressed via computer simulations using empirical interatomic potentials, which use approximate but efficient descriptions of interatomic interactions to reach the length and time scales needed to describe macromolecules. These empirical potentials typically perform well for bulk and/or collective properties but face challenges with chemical realism for complex systems, e.g., during reactive processes. In this work, we address this challenge by combining the computational efficiency of a deep potential (DP) machine-learning force field and the chemical realism of first-principles van der Waals (vdW) corrected hybrid density functional theory (DFT) enabled by a SeA high-throughput framework. Using this approach, we study the structure and dynamics of PE oligomers and polymers in an ethylene solvent under common high-pressure (supercritical) radical polymerization conditions. We found that the local solvation environment of radical-containing PE oligomers converges for chain lengths greater than (n~6), suggesting extensibility of our oligomer-trained MLFF to significantly longer polymers. We then confirmed the extensibility of these models to long PE chains by characterizing the molecular weight scaling of single-chain structure and dynamics, which showed classic good solvent behavior. Our PE MLFF retained a consistent level of fidelity and stability across a wide range of thermodynamic state points and chain lengths, at full atomistic resolution, therefore paving the way towards first-principles-based polymer structure and property prediction.

cond-mat.mtrl-sci↗

arXiv2026

ActWorld: From Explorable to Interactive World Model via Action-Aware Memory

Interactive world models aim to simulate environment dynamics under real-time user actions. However, their action vocabulary is largely confined to navigation: most actions correspond to motion (e.g., walk, turn, look around), while interaction with objects in the scene (e.g., pick up plates, open doors, or trigger physical responses) is either absent, restricted to game domains, or relegated to prompt-to-full-video scenarios. The resulting worlds are visually explorable but not truly actionable. In this work, we present ActWorld, an interactive world model that extends prior navigation-centric generators to support mid-rollout object interaction within a chunk-autoregressive framework. We argue that the navigation-interaction gap stems from two bottlenecks. First, a data bottleneck: the lack of human-object interaction data with accurate, dense labels. Second, a memory bottleneck: recency-biased history compression in existing world models discards the event-transition frames that causally determine subsequent object states, leading to an action-forgetting pathology. On the data side, we construct a 100K interaction video dataset, each annotated with per-chunk captions via chain-of-thought reasoning. On the model side, we introduce a hierarchical action-aware memory design that routes history compression by interaction importance, complemented by a persistent memory bank that maintains event-update and object-identity tokens across long rollouts. Experiments show that ActWorld supports both flexible navigation and rich object interaction within a single model, substantially improving interaction fidelity over navigation-only baselines without sacrificing viewpoint control. Project page is available at https://interactwm.github.io/ActWorld.

cs.CV↗

arXiv2026

LiPUP-MA: A Residential Experience-centric Multi-Agent Framework for Living-in-the-loop Participatory Urban Planning

Participatory Urban Planning (PUP) is increasingly supported by LLM-based agents, yet existing methods largely rely on static preference elicitation and one-shot stakeholder discussions, overlooking the cyclical nature of real-world planning, where residential life, experience collection, and plan adjustment continually interact. We propose Living-in-the-loop Participatory Urban Planning (LiPUP), a closed-loop paradigm that alternates between simulated residential living and experience-driven plan revision, while posing two key challenges: grounding scattered living experience in concrete urban contexts and translating subjective feedback into spatially coherent planning actions. To instantiate LiPUP, we introduce LiPUP-MA, an LLM-based multi-agent framework that constructs a Plan-centric Graph-based Experience Bank to organize urban-grounded residential feedback from living simulation and equips a Spatially-constrained Skill-augmented Planner agent to revise plans by harmonizing experiential, visual, and geospatial evidence. Experiments show that LiPUP-MA consistently outperforms baselines on both conventional static planning metrics and living-based metrics, while iterative LiPUP cycles further improve plan quality.

cs.AI↗

arXiv2026

Understanding the Density Maximum of Water with Machine Learned Potentials

After melting, at ambient pressure, the density of water continues to increase with temperature until it reaches a maximum around 4 °C. For nearly a century, this phenomenon has been qualitatively attributed to a mixture of ordered and disordered structures. Herein, we employ a deep neural network to train a machine learned (ML) interatomic potential for water using electronic structure data from advanced density functional theory. Notably, molecular dynamics simulations with the ML potential reproduce both the experimental water density anomaly and the thermal expansion coefficient. Detailed structural analysis of the computed hydrogen-bond network reveals that the density anomaly arises from an emergent liquid structure that retains nearly ideal tetrahedral coordination at short range but collapses at intermediate range. Our findings point to a more delicate mechanism causing the density maximum than the conventional picture, emphasizing the collective roles of structural orderings at different length scales.

physics.chem-ph↗

arXiv2026

PhysAlign: Physics-Coherent Image-to-Video Generation through Feature and 3D Representation Alignment

Video Diffusion Models (VDMs) offer a promising approach for simulating dynamic scenes and environments, with broad applications in robotics and media generation. However, existing models often generate temporally incoherent content that violates basic physical intuition, significantly limiting their practical applicability. We propose PhysAlign, an efficient framework for physics-coherent image-to-video (I2V) generation that explicitly addresses this limitation. To overcome the critical scarcity of physics-annotated videos, we first construct a fully controllable synthetic data generation pipeline based on rigid-body simulation, yielding a highly-curated dataset with accurate, fine-grained physics and 3D annotations. Leveraging this data, PhysAlign constructs a unified physical latent space by coupling explicit 3D geometry constraints with a Gram-based spatio-temporal relational alignment that extracts kinematic priors from video foundation models. Extensive experiments demonstrate that PhysAlign significantly outperforms existing VDMs on tasks requiring complex physical reasoning and temporal stability, without compromising zero-shot visual quality. PhysAlign shows the potential to bridge the gap between raw visual synthesis and rigid-body kinematics, establishing a practical paradigm for genuinely physics-grounded video generation. The project page is available at https://physalign.github.io/PhysAlign.

cs.CV↗

arXiv2026

ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing

Instruction-driven image editing with unified multimodal generative models has advanced rapidly, yet their underlying visual reasoning remains limited, leading to suboptimal performance on reasoning-centric edits. Reinforcement learning (RL) has been investigated for improving the quality of image editing, but it faces three key challenges: (1) limited reasoning exploration confined to denoising stochasticity, (2) biased reward fusion, and (3) unstable VLM-based instruction rewards. In this work, we propose ThinkRL-Edit, a reasoning-centric RL framework that decouples visual reasoning from image synthesis and expands reasoning exploration beyond denoising. To the end, we introduce Chain-of-Thought (CoT)-based reasoning sampling with planning and reflection stages prior to generation in online sampling, compelling the model to explore multiple semantic hypotheses and validate their plausibility before committing to a visual outcome. To avoid the failures of weighted aggregation, we propose an unbiased chain preference grouping strategy across multiple reward dimensions. Moreover, we replace interval-based VLM scores with a binary checklist, yielding more precise, lower-variance, and interpretable rewards for complex reasoning. Experiments show our method significantly outperforms prior work on reasoning-centric image editing, producing instruction-faithful, visually coherent, and semantically grounded edits.

cs.CV↗

arXiv2026

DuetUI: A Bidirectional Context Loop for Human-Agent Co-Generation of Task-Oriented Interfaces

Large Language Models are reshaping task automation, yet remain limited in complex, multi-step real-world tasks that require aligning with vague user intent and enabling dynamic user override. From a formative study with 12 participants, we found that end-users actively seek to shape task-oriented interfaces rather than relying on one-shot outputs. To address this, we introduce the human-agent co-generation paradigm, materialized in DuetUI. This LLM-empowered system unfolds alongside task progress through a bidirectional context loop-the agent scaffolds the interface by decomposing the task, while the user's direct manipulations implicitly steer the agent's next generation step. In a technical ablation study and a user study with 24 participants, DuetUI improved task efficiency and interface usability, supporting more seamless human-agent collaboration. Our contributions include the proposal of this novel paradigm, the design of a proof-of-concept DuetUI prototype embodying it, and empirical and technical insights from an initial evaluation of how this bidirectional loop may help align agents with human intent and inform future development.

cs.HC↗

arXiv2025

Unveiling the amorphous ice layer during premelting using AFM integrating machine learning

Premelting plays a key role across physics, chemistry, materials and biology sciences but remains poorly understood at the atomic level due to surface characterization limitations. We report the discovery of a novel amorphous ice layer (AIL) preceding the quasi-liquid layer (QLL) during ice premelting, enabled by a machine learning framework integrating atomic force microscopy (AFM) with molecular dynamics simulations. This approach overcomes AFM's depth and signal limitations, allowing for three-dimensional surface structure reconstruction from AFM images. It further enables structural exploration of premelting interfaces across a wide temperature range that are experimentally inaccessible. We identify the AIL, present between 121-180K, displaying disordered two-dimensional hydrogen-bond network with solid-like dynamics. Our findings refine the ice premelting phase diagram and offering new insights into the surface growth dynamic, dissolution and interfacial chemical reactivity. Methodologically, this work establishes a novel framework for AFM-based 3D structural discovery, marking a significant leap in our ability to probe complex disordered interfaces with unprecedented precision and paving the way for future disciplinary research, including surface reconstruction, crystallization, ion solvation, and biomolecular recognition.

cond-mat.mtrl-sci↗

arXiv2025

Generative AI for Cel-Animation: A Survey

Traditional Celluloid (Cel) Animation production pipeline encompasses multiple essential steps, including storyboarding, layout design, keyframe animation, inbetweening, and colorization, which demand substantial manual effort, technical expertise, and significant time investment. These challenges have historically impeded the efficiency and scalability of Cel-Animation production. The rise of generative artificial intelligence (GenAI), encompassing large language models, multimodal models, and diffusion models, offers innovative solutions by automating tasks such as inbetween frame generation, colorization, and storyboard creation. This survey explores how GenAI integration is revolutionizing traditional animation workflows by lowering technical barriers, broadening accessibility for a wider range of creators through tools like AniDoc, ToonCrafter, and AniSora, and enabling artists to focus more on creative expression and artistic innovation. Despite its potential, challenges like visual consistency, stylistic coherence, and ethical considerations persist. Additionally, this paper explores future directions and advancements in AI-assisted animation. For further exploration and resources, please visit our GitHub repository: https://github.com/yunlong10/Awesome-AI4Animation

cs.CV↗

arXiv2025

Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models

Video understanding represents the most challenging frontier in computer vision, requiring models to reason about complex spatiotemporal relationships, long-term dependencies, and multimodal evidence. The recent emergence of Video-Large Multimodal Models (Video-LMMs), which integrate visual encoders with powerful decoder-based language models, has demonstrated remarkable capabilities in video understanding tasks. However, the critical phase that transforms these models from basic perception systems into sophisticated reasoning engines, post-training, remains fragmented across the literature. This survey provides the first comprehensive examination of post-training methodologies for Video-LMMs, encompassing three fundamental pillars: supervised fine-tuning (SFT) with chain-of-thought, reinforcement learning (RL) from verifiable objectives, and test-time scaling (TTS) through enhanced inference computation. We present a structured taxonomy that clarifies the roles, interconnections, and video-specific adaptations of these techniques, addressing unique challenges such as temporal localization, spatiotemporal grounding, long video efficiency, and multimodal evidence integration. Through systematic analysis of representative methods, we synthesize key design principles, insights, and evaluation protocols while identifying critical open challenges in reward design, scalability, and cost-performance optimization. We further curate essential benchmarks, datasets, and metrics to facilitate rigorous assessment of post-training effectiveness. This survey aims to provide researchers and practitioners with a unified framework for advancing Video-LMM capabilities. Additional resources and updates are maintained at: https://github.com/yunlong10/Awesome-Video-LMM-Post-Training

cs.CV↗

arXiv2025

Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation

Multimodal Large Language Models (MLLMs) struggle with accurately capturing camera-object relations, especially for object orientation, camera viewpoint, and camera shots. This stems from the fact that existing MLLMs are trained on images with limited diverse camera-object relations and corresponding textual descriptions. To address this, we propose a synthetic generation pipeline to create large-scale 3D visual instruction datasets. Our framework takes 3D assets as input and uses rendering and diffusion-based image generation models to create photorealistic images preserving precise camera-object relations. Additionally, large language models (LLMs) are used to generate text prompts for guiding visual instruction tuning and controlling image generation. We create Ultimate3D, a dataset of 240K VQAs with precise camera-object annotations, and corresponding benchmark. MLLMs fine-tuned on our proposed dataset outperform commercial models by a large margin, achieving an average accuracy improvement of 33.4% on camera-object relation recognition tasks. Our code, dataset, and benchmark will contribute to broad MLLM applications.

cs.GR↗

arXiv2025

MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models

Recent multimodal image generators such as GPT-4o, Gemini 2.0 Flash, and Gemini 2.5 Pro excel at following complex instructions, editing images and maintaining concept consistency. However, they are still evaluated by disjoint toolkits: text-to-image (T2I) benchmarks that lacks multi-modal conditioning, and customized image generation benchmarks that overlook compositional semantics and common knowledge. We propose MMIG-Bench, a comprehensive Multi-Modal Image Generation Benchmark that unifies these tasks by pairing 4,850 richly annotated text prompts with 1,750 multi-view reference images across 380 subjects, spanning humans, animals, objects, and artistic styles. MMIG-Bench is equipped with a three-level evaluation framework: (1) low-level metrics for visual artifacts and identity preservation of objects; (2) novel Aspect Matching Score (AMS): a VQA-based mid-level metric that delivers fine-grained prompt-image alignment and shows strong correlation with human judgments; and (3) high-level metrics for aesthetics and human preference. Using MMIG-Bench, we benchmark 17 state-of-the-art models, including Gemini 2.5 Pro, FLUX, DreamBooth, and IP-Adapter, and validate our metrics with 32k human ratings, yielding in-depth insights into architecture and data design.

cs.CV↗

arXiv2025

Kubrick: Multimodal Agent Collaborations for Synthetic Video Generation

Text-to-video generation has been dominated by diffusion-based or autoregressive models. These novel models provide plausible versatility, but are criticized for improper physical motion, shading and illumination, camera motion, and temporal consistency. The film industry relies on manually-edited Computer-Generated Imagery (CGI) using 3D modeling software. Human-directed 3D synthetic videos address these shortcomings, but require tight collaboration between movie makers and 3D rendering experts. We introduce an automatic synthetic video generation pipeline based on Vision Large Language Model (VLM) agent collaborations. Given a language description of a video, multiple VLM agents direct various processes of the generation pipeline. They cooperate to create Blender scripts which render a video following the given description. Augmented with Blender-based movie making knowledge, the Director agent decomposes the text-based video description into sub-processes. For each sub-process, the Programmer agent produces Python-based Blender scripts based on function composing and API calling. The Reviewer agent, with knowledge of video reviewing, character motion coordinates, and intermediate screenshots, provides feedback to the Programmer agent. The Programmer agent iteratively improves scripts to yield the best video outcome. Our generated videos show better quality than commercial video generation models in five metrics on video quality and instruction-following performance. Our framework outperforms other approaches in a user study on quality, consistency, and rationality.

cs.CV↗

arXiv2025

Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting

We present CAT-V (Caption AnyThing in Video), a training-free framework for fine-grained object-centric video captioning that enables detailed descriptions of user-selected objects through time. CAT-V integrates three key components: a Segmenter based on SAMURAI for precise object segmentation across frames, a Temporal Analyzer powered by TRACE-Uni for accurate event boundary detection and temporal analysis, and a Captioner using InternVL-2.5 for generating detailed object-centric descriptions. Through spatiotemporal visual prompts and chain-of-thought reasoning, our framework generates detailed, temporally-aware descriptions of objects' attributes, actions, statuses, interactions, and environmental contexts without requiring additional training data. CAT-V supports flexible user interactions through various visual prompts (points, bounding boxes, and irregular regions) and maintains temporal sensitivity by tracking object states and interactions across different time segments. Our approach addresses limitations of existing video captioning methods, which either produce overly abstract descriptions or lack object-level precision, enabling fine-grained, object-specific descriptions while maintaining temporal coherence and spatial accuracy. The GitHub repository for this project is available at https://github.com/yunlong10/CAT-V

cs.CV↗

arXiv2025

GroundingBooth: Grounding Text-to-Image Customization

Recent approaches in text-to-image customization have primarily focused on preserving the identity of the input subject, but often fail to control the spatial location and size of objects. We introduce GroundingBooth, which achieves zero-shot, instance-level spatial grounding on both foreground subjects and background objects in the text-to-image customization task. Our proposed grounding module and subject-grounded cross-attention layer enable the creation of personalized images with accurate layout alignment, identity preservation, and strong text-image coherence. In addition, our model seamlessly supports personalization with multiple subjects. Our model shows strong results in both layout-guided image synthesis and text-to-image customization tasks. The project page is available at https://groundingbooth.github.io.

cs.CV↗

arXiv2025

Pressure-Induced Structural and Dielectric Changes in Liquid Water at Room Temperature

Understanding the pressure-dependent dielectric properties of water is crucial for a wide range of scientific and practical applications. In this study, we employ a deep neural network trained on density functional theory data to investigate the dielectric properties of liquid water at room temperature across a pressure range of 0.1 MPa to 1000 MPa. We observe a nonlinear increase in the static dielectric constant $ε_0$ with increasing pressure, a trend that is qualitatively consistent with experimental observations. This increase in $ε_0$ is primarily attributed to the increase in water density under compression, which enhances collective dipole fluctuations within the hydrogen-bonding network as well as the dielectric response. Despite the increase in $ε_0$, our results reveal a decrease in the Kirkwood correlation factor $G_K$ with increasing pressure. This decrease in $G_K$ is attributed to pressure-induced structural distortions in the hydrogen-bonding network, which weaken dipolar correlations by disrupting the ideal tetrahedral arrangement of water molecules.

cond-mat.mtrl-sci↗

arXiv2024

Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment

Personalized image generation has emerged from the recent advancements in generative models. However, these generated personalized images often suffer from localized artifacts such as incorrect logos, reducing fidelity and fine-grained identity details of the generated results. Furthermore, there is little prior work tackling this problem. To help improve these identity details in the personalized image generation, we introduce a new task: reference-guided artifacts refinement. We present Refine-by-Align, a first-of-its-kind model that employs a diffusion-based framework to address this challenge. Our model consists of two stages: Alignment Stage and Refinement Stage, which share weights of a unified neural network model. Given a generated image, a masked artifact region, and a reference image, the alignment stage identifies and extracts the corresponding regional features in the reference, which are then used by the refinement stage to fix the artifacts. Our model-agnostic pipeline requires no test-time tuning or optimization. It automatically enhances image fidelity and reference identity in the generated image, generalizing well to existing models on various tasks including but not limited to customization, generative compositing, view synthesis, and virtual try-on. Extensive experiments and comparisons demonstrate that our pipeline greatly pushes the boundary of fine details in the image synthesis models.

cs.CV↗

arXiv2024

Thinking Outside the BBox: Unconstrained Generative Object Compositing

Compositing an object into an image involves multiple non-trivial sub-tasks such as object placement and scaling, color/lighting harmonization, viewpoint/geometry adjustment, and shadow/reflection generation. Recent generative image compositing methods leverage diffusion models to handle multiple sub-tasks at once. However, existing models face limitations due to their reliance on masking the original object during training, which constrains their generation to the input mask. Furthermore, obtaining an accurate input mask specifying the location and scale of the object in a new image can be highly challenging. To overcome such limitations, we define a novel problem of unconstrained generative object compositing, i.e., the generation is not bounded by the mask, and train a diffusion-based model on a synthesized paired dataset. Our first-of-its-kind model is able to generate object effects such as shadows and reflections that go beyond the mask, enhancing image realism. Additionally, if an empty mask is provided, our model automatically places the object in diverse natural locations and scales, accelerating the compositing workflow. Our model outperforms existing object placement and compositing models in various quality metrics and user studies.

cs.CV↗