←
Jinpeng Wang191 posts
Jinpeng Wang avatar

Jinpeng Wang

@awinyimgprocess

Professor in Central South University, NUS PHD. Focus on Multi-modality Learning and Data-centric AI.

◷ Joined April 2017▧ 39 Photos and videos
Jinpeng Wang avatar
Jinpeng Wang@awinyimgprocess·22 Oct 2025

Humans see text — but LLMs don’t. I wrote a short blog post exploring how models can perceive text visually rather than tokenize it: 🔗 csu-jpg.github.io/Blog/peopl… From PIXEL, CLIPPO, VisInContext, VIST to DeepSeek-OCR, this is a quick story of how vision-centric modeling is changing how machines read, and a reflection on some of our own small efforts in the past two years.

Jinpeng Wang avatar
Jinpeng Wang@awinyimgprocess·Sep 10

Excited to share 3 papers at #ECCV2026 🎉 🔹 FlowInOne: unifying multimodal generation as image-in, image-out flow matching 📅 Fri 9/11, 16:00–18:00 CEST | ExHall #149 🔹 Glance: one sample distillation model 📅 Sat 9/12, 10:30–12:30 CEST | ExHall #38 🔹 Evaluating and enhancing negation comprehension in remote sensing MLLMs Come by the posters and chat, would love to talk vision-centric MLLMs, multimodal generation, and remote sensing understanding!

Jinpeng Wang avatar
Jinpeng Wang@awinyimgprocess·Jul 7

🧵 ICML 2026 (Seoul) — come say hi! 4 papers from our lab this week: 📌 Today (Jul 8) 14:30 KST, Hall A #314 — TextAtlas5M: a large-scale dataset for dense text image generation 10:45-11:00 KST Oral / poster 14:30-16:15, Hall A #2800 — When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models 📌 Tomorrow (Jul 9) 10:30-12:15 KST, Hall A #314 — Entropy-Aware Dynamic KV Cache Sparsification for Autoregressive Image Generation and Editing 9:30-11:15 KST, Hall A #1302 — Mitigating Error Accumulation in Continuous Navigation via Memory-Augmented Kalman Filtering Spanning text-rich generation, jailbreak/defense, efficient AR generation, and embodied navigation — would love to chat about any of it. Swing by! 🙌 #ICML2026 #MLLM #ImageGeneration

Kevin Lin avatar
⟳ Jinpeng Wang retweeted
Kevin Lin@KevinQHLin·Jun 16

can AI write engaging news that people can trust? introducing ✨Data2Story: a data journalist agent. give it raw data, it generate a verifiable, multimodal article. 🔍verifiable: every claim is evidence-grounded, traces back to data, code, or a cited source. 🔮multimodal: the article is a generative UI — images, videos, audio, interactive charts. not just readable, but trustworthy and playable. 🧵1/N

0:48
Jinpeng Wang avatar
Jinpeng Wang@awinyimgprocess·Jun 2

VJA: ICML 2026 Oral 🚨 Modern image editors understand your drawings, arrows, and scribbles — not just text. We asked: can an attacker use that too? Yes. Introducing VJA: hide a malicious instruction inside the image itself, bypass text-based safety filters entirely. Up to 80.9% attack success on SOTA commercial models. We also built a benchmark (IESBench) + a training-free defense. Paper: arxiv.org/abs/2602.10179 #icml #imageediting #generation

Post attachment
Junchao Yi avatar
⟳ Jinpeng Wang retweeted
Junchao Yi@Junc1i·Apr 9

🔥 Multimodal gen must be text-driven? Meet FlowInOne 🖼️➡️🖼️: Image-in, Image-out 1️⃣ Vision-Centric: no text encoders or bridges. 2️⃣ Continuous evolution: visual Flow Matching. 3️⃣ VisPrompt-5M: across diverse I2I tasks. 📄 arxiv.org/abs/2604.06757 🌐 csu-jpg.github.io/FlowInOne.…

Post attachmentPost attachment
Jinpeng Wang avatar
Jinpeng Wang@awinyimgprocess·3 Dec 2025

Thanks AK for sharing our work. We speed up Qwen-image and Flux Inference speed from 50 steps to less than 10steps. 1 sample is enough for speeding up diffusion model in specific domain. Paper Link: arxiv.org/abs/2512.02899 Code Link: github.com/CSU-JPG/Glance

AK@_akhaliq3 Dec 2025

Glance Accelerating Diffusion Models with 1 Sample

Post attachment
AK avatar
⟳ Jinpeng Wang retweeted
AK@_akhaliq·3 Dec 2025

Glance Accelerating Diffusion Models with 1 Sample

Post attachment
Kevin Lin avatar
⟳ Jinpeng Wang retweeted
Kevin Lin@KevinQHLin·24 Nov 2025

We added Gemini3-Pro #Gemini results on VCode! Check out at csu-jpg.github.io/VCode/ 🏅Gemini3-Pro performs quite well at image2svg. It achieved 52.1 in VCode, surpassing GPT-5's 46.8 (+5.3). Open-sourced at github.com/CSU-JPG/VCode

Post attachmentPost attachment
AK@_akhaliq7 Nov 2025

VCode app is out SVG as Symbolic Visual Representation Turn any image into symbolic SVG

0:25
Jinpeng Wang avatar
Jinpeng Wang@awinyimgprocess·16 Nov 2025

thanks JIQIZHIXIN for sharing our work. We use visual encoder to compress long text.

As LLMs grow to trillions of parameters and context windows stretch to hundreds of thousands of tokens, compute costs explode. Vision Centric Token Compression (Vist) offers a fix — a vision-centric token compression method that mimics human reading. It converts distant context into images for a vision encoder to skim, while the LLM focuses on nearby text. Matching full-context accuracy with 2.3× fewer tokens, Vist slashes FLOPs by 16%, memory by 50%, and outperforms prior compression methods by 7.6% across major benchmarks. Vision-centric Token Compression in Large Language Model NUST, CSU, NFU Paper: arxiv.org/abs/2502.00791 Our report: mp.weixin.qq.com/s/zYnxpBhRs… 📬 #PapersAccepted by Jiqizhixin

Post attachment