Meta tags:

Headings (most frequently used words):

reviewer, news, publications, projects, honors, awards, internships, professional, activities, ximing, xing, conference, journal, academic, service,

Text of the page (most frequently used words):
and (39), svg (32), vector (32), generation (26), text (22), graphics (19), ximing (19), xing (19), for (18), cvpr (17), with (17), code (16), the (14), qian (14), 2025 (13), #project (13), zhang (13), dong (12), jing (12), svgdreamer (12), models (11), image (11), synthesis (10), diffusion (10), computer (9), learning (9), wang (9), ieee (8), based (8), llms (8), pami (8), vision (7), 2024 (7), paper (7), sketch (7), chuang (7), haitao (7), zhou (7), guided (7), neurips (6), conference (6), level (6), reinforcement (6), research (6), pattern (6), via (6), generate (6), vectorization (6), reason (6), model (5), machine (5), large (5), rendering (5), neural (5), first (5), reasoning (5), control (5), fine (5), 2026 (5), cad (5), diffsketcher (5), introduces (5), semantic (5), driven (5), been (5), training (4), 2021 (4), advancing (4), multimodal (4), differentiable (4), using (4), pytorch (4), svgrender (4), recognition (4), papers (4), dataset (4), thought (4), through (4), blog (4), diversity (4), has (4), accepted (4), his (4), reviewer (3), academic (3), journal (3), transactions (3), reward (3), enhance (3), intern (3), china (3), language (3), huggingface (3), library (3), processing (3), without (3), promptenhancer (3), enhancing (3), grained (3), enables (3), complex (3), structured (3), yandong (3), guan (3), juncheng (3), advanced (3), 2023 (3), svgs (3), svgx (3), core (3), svgfusion (3), space (3), scalable (3), two (3), llm4svg (3), publications (3), art (3), our (3), published (3), beihang (3), university (3), top (2), tier (2), international (2), siggraph (2), professional (2), activities (2), turn (2), user (2), strategies (2), novel (2), understanding (2), beijing (2), tencent (2), hunyuan (2), present (2), internships (2), national (2), scholarship (2), students (2), buaa (2), honors (2), awards (2), networks (2), creation (2), open (2), projects (2), method (2), label (2), noise (2), graph (2), liang (2), about (2), robust (2), stochastic (2), differential (2), equations (2), inversion (2), arxiv (2), controllable (2), coder (2), from (2), chain (2), icme (2), vectorpainter (2), stylized (2), advances (2), information (2), systems (2), pioneered (2), use (2), latent (2), nips (2), editable (2), high (2), quality (2), better (2), shape (2), particle (2), score (2), distillation (2), vpsd (2), sive (2), analysis (2), intelligence (2), generator (2), innovations (2), object (2), component (2), dynamically (2), assigns (2), optimal (2), number (2), primitives (2), capturing (2), details (2), wasting (2), computation (2), adaptive (2), primitive (2), hierarchical (2), hive (2), editability (2), sft (2), understand (2), framework (2), paradigm (2), combining (2), explicit (2), design (2), trained (2), supervised (2), tuning (2), hyperreward (2), drawing (2), dwt (2), ziteng (2), xue (2), this (2), ever (2), news (2), work (2), deep (2), student (2), homepage (2), regular, conferences, journals, service, ijcv, visualization, vcg, eccv, acm, aaai, asia, engineered, session, functions, ppo, policy, optimization, built, agenda, simulator, environments, designed, behavior, cloning, cold, start, efficiency, multi, task, oriented, dialogue, system, algorithm, hangzhou, ant, group, leading, native, llm, architectures, integration, pipelines, developing, approaches, qingyun, program, doctoral, excellence, foundation, phd, docs, generating, support, editing, founder, main, contributor, source, dualgraph, haiyang, liu, free, sdes, zhihao, chongxuan, exemplar, photo, prompt, rewriting, tool, linqing, taming, your, rewriter, valid, outputting, cadquery, python, scripts, approach, xilin, geometric, parametric, multimedia, expo, synthesizes, imitating, strokes, stroke, style, priors, 250k, improves, prompts, performing, within, that, learned, dit, vae, learn, representation, elements, learnable, enabling, tokens, guotao, empowering, t2i, selected, released, state, have, beyond, committed, science, reproducible, actively, contributing, making, cutting, edge, accessible, broader, community, xingxm, interactive, demos, production, ready, libraries, scale, datasets, venues, including, prestigious, some, representative, works, include, being, dedicated, frontiers, content, particular, focus, spans, generative, 2022, software, engineering, advised, professor, currently, working, google, scholar, github, email, interested, invited, talk,

Text of the page (random words):
ximing xing homepage homepage about me news publications projects honors and awards internships professional activities invited talk ximing xing beihang university ph d student at buaa beihang university interested in deep generation and vector art beijing china email huggingface github google scholar ximing xing is a ph d student 2022 present in software engineering at beihang university advised by professor qian yu he is currently a research intern at tencent hunyuan working on multimodal vector graphics large language models he is dedicated to advancing the frontiers of ai driven content creation with a particular focus on the generation and understanding of vector graphics his research spans deep generative models vector art synthesis text to svg generation neural rendering svg diffusion models and multimodal svg llms his work has been published in top tier venues including cvpr 24 25 26 t pami 25 and neurips 23 with his t pami paper being the first svg generation work ever published in this prestigious journal some of his representative works include llms for vector graphics llm4svg reason svg text to svg synthesis svgdreamer svgdreamer vector diffusion models svgfusion sketch synthesis diffsketcher differentiable svg rendering library pytorch svgrender beyond academic publications he is committed to open science and reproducible research actively contributing large scale datasets production ready code libraries and interactive demos on huggingface xingxm svgrender space making cutting edge vector graphics research accessible to the broader community news 2026 03 two papers promptenhancer and reason svg have been accepted by cvpr 2026 2025 02 our paper llm4svg has been accepted by cvpr 2025 2025 02 our paper svgdreamer has been accepted by t pami this is the first paper on svg generation ever published in t pami 2024 02 our paper svgdreamer has been accepted by cvpr 2024 2023 12 we released pytorch svgrender a state of the art library for differentiable svg rendering in pytorch publications selected papers 4 vector graphics synthesis 7 cad generation 1 ️ controllable t2i generation 2 ️ robust machine learning 1 t pami 2025 svgdreamer advancing editability and diversity in text guided svg generation ximing xing qian yu chuang wang haitao zhou jing zhang dong xu tl dr svgdreamer is an advanced text to svg generator with two core innovations hierarchical image vectorization hive enables semantic object level and component level image vectorization and adaptive vector primitive control dynamically assigns the optimal number of vector primitives capturing fine grained details without wasting computation ieee transactions on pattern analysis and machine intelligence t pami 2025 project code blog cvpr 2026 reason svg enhancing structured reasoning for scalable vector graphics generation with reinforcement learning ximing xing ziteng xue yandong guan jing zhang dong xu qian yu tl dr reason svg introduces the first framework to enhance svg generation in llms through a drawing with thought dwt paradigm combining explicit design reasoning with code trained via supervised fine tuning and hyperreward driven reinforcement learning cvpr 2024 svgdreamer text guided svg generation with diffusion model ximing xing chuang wang haitao zhou jing zhang dong xu qian yu tl dr svgdreamer introduces semantic driven image vectorization sive and vector particle based score distillation vpsd to generate editable high quality svgs with better shape control and diversity ieee conference on computer vision and pattern recognition cvpr 24 project code blog nips 2023 diffsketcher text guided vector sketch synthesis through latent diffusion models ximing xing chuang wang haitao zhou jing zhang qian yu dong xu tl dr diffsketcher pioneered the use of diffusion models for text to vector sketch generation advances in neural information processing systems neurips 23 project code vector graphics generation 7 papers cvpr 2026 reason svg enhancing structured reasoning for scalable vector graphics generation with reinforcement learning ximing xing ziteng xue yandong guan jing zhang dong xu qian yu tl dr reason svg introduces the first framework to enhance svg generation in llms through a drawing with thought dwt paradigm combining explicit design reasoning with code trained via supervised fine tuning and hyperreward driven reinforcement learning cvpr 2025 empowering llms to understand and generate complex vector graphics ximing xing juncheng hu guotao liang jing zhang dong xu qian yu tl dr llm4svg introduces learnable svg semantic tokens and a large svgx sft dataset enabling llms to understand and generate complex vector graphics ieee conference on computer vision and pattern recognition cvpr 25 project code svgx sft 1m dataset t pami 2025 svgdreamer advancing editability and diversity in text guided svg generation ximing xing qian yu chuang wang haitao zhou jing zhang dong xu tl dr svgdreamer is an advanced text to svg generator with two core innovations hierarchical image vectorization hive enables semantic object level and component level image vectorization and adaptive vector primitive control dynamically assigns the optimal number of vector primitives capturing fine grained details without wasting computation ieee transactions on pattern analysis and machine intelligence t pami 2025 project code blog arxiv 2024 svgfusion scalable text to svg generation via vector space diffusion ximing xing juncheng hu jing zhang dong xu qian yu tl dr svgfusion improves text to svg generation by using a vp vae to learn a vector representation of svg elements and a vs dit to generate svgs from text prompts by performing diffusion within that learned vector space project code svgx core 250k dataset cvpr 2024 svgdreamer text guided svg generation with diffusion model ximing xing chuang wang haitao zhou jing zhang dong xu qian yu tl dr svgdreamer introduces semantic driven image vectorization sive and vector particle based score distillation vpsd to generate editable high quality svgs with better shape control and diversity ieee conference on computer vision and pattern recognition cvpr 24 project code blog nips 2023 diffsketcher text guided vector sketch synthesis through latent diffusion models ximing xing chuang wang haitao zhou jing zhang qian yu dong xu tl dr diffsketcher pioneered the use of diffusion models for text to vector sketch generation advances in neural information processing systems neurips 23 project code icme 2025 vectorpainter advanced stylized vector graphics synthesis using stroke style priors juncheng hu ximing xing jing zhang qian yu tl dr vectorpainter synthesizes text guided vector graphics by imitating stylized strokes ieee international conference on multimedia expo icme 25 project code parametric generation 1 paper neurips 2025 cad coder text to cad generation with chain of thought and geometric reward yandong guan xilin wang ximing xing jing zhang dong xu qian yu tl dr cad coder enables llms to generate complex valid 3d cad models from text by outputting cadquery python scripts using a novel structured chain of thought approach code model dataset ️ controllable text to image generation 2 papers cvpr 2026 promptenhancer taming your rewriter for text to image generation via fine grained reward linqing wang ximing xing et al tl dr promptenhancer is a user prompt rewriting tool for enhancing text to image generation project code model arxiv inversion by inversion exemplar based sketch to photo synthesis via stochastic differential equations without training ximing xing chuang wang haitao zhou zhihao hu chongxuan li dong xu qian yu tl dr free training for sketch control image synthesis via stochastic differential equations sdes project code ️ robust machine learning 1 paper cvpr 2021 a graph based method for reasoning about label noise haiyang zhang ximing xing liang liu tl dr dualgraph the first method for label noise processing based on graph neural networks ieee conference on computer vision and pattern recognition cvpr 21 projects open source pytorch svgrender a differentiable rendering library for svg creation project founder and main contributor ximing xing tl dr svg differentiable rendering generating vector graphics using neural networks support text to svg image to svg and svg editing project code huggingface docs honors awards 2025 04 academic excellence foundation of buaa for phd students 2024 12 national scholarship for doctoral students 2021 12 national scholarship internships 2025 06 present tencent hunyuan research intern qingyun program beijing china multimodal vector graphics large language models developing novel approaches for multimodal vector graphics understanding and generation with llms advancing the integration of large language models with vector graphics synthesis pipelines leading research on svg native llm architectures and reinforcement learning based training strategies 2021 06 2021 11 ant group machine learning algorithm intern hangzhou china multi turn task oriented dialogue system designed behavior cloning strategies to enhance model cold start training efficiency built an agenda based user simulator for reinforcement learning environments engineered turn level and session level reward functions for ppo based policy optimization professional activities conference reviewer 2025 aaai cvpr siggraph siggraph asia neurips 2024 cvpr eccv neurips acm mm journal reviewer computer vision graphics international journal of computer vision ijcv ieee transactions on visualization and computer graphics t vcg academic service regular reviewer for top tier conferences and journals in ai computer vision and computer graphics