Ziwei Liu
@liuziwei7
Followers
11K
Following
4K
Media
225
Statuses
2K
Associate Professor @ NTU - Vision, Learning and Graphics.
Singapore
Joined January 2018
RT @ArxivToday: Ever wanted to smoothly morph one image into another? FreeMorph does it in 30 seconds with no training needed. Works even f….
0
0
0
RT @AINativeF: 5. FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion Model. 🔑 Keywords: FreeMorph, image morphing, tuning-fre….
0
2
0
🤩Tuning-Free Image Morphing🤩. #FreeMorph enables tuning-free generalized image morphing that accommodates inputs with different semantics or layouts @ICCVConference. - Paper @huggingface: - Project: - Code:
0
12
52
RT @HuggingPapers: Image morphing just got a major upgrade!. Introducing FreeMorph: a tuning-free diffusion model that seamlessly blends an….
0
2
0
RT @NaveenManwani17: 🚨 ICCV 2025 Paper Alert 🚨. ➡️Paper Title: FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion Model. 🌟Few….
0
1
0
RT @yukangcao: 🔥Tuning-free 2D image morphing🔥. Tired of complex training and strict semantic/layout demands? . Meet #FreeMorph #ICCV2025:….
0
17
0
RT @ziqi_huang_: Today's VLMs still struggle with cinematic language, like telling a pull-out from a zoom-out. From editing assistants to….
0
6
0
RT @BayCoralee26992: LMM latest research progress | 4. ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models.#AI #Deep….
0
2
0
📽️Expert-Level Cinematic Understanding in VLM📽️. #ShotBench: benchmark covering 8 core cinematography dimensions.#ShotQA: 70k training dataset.#ShotVL: 3B and 7B model surpassing GPT-4o on cinematic understanding. - Project: - Code:
0
16
103
RT @AINativeF: 4. ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models. 🔑 Keywords: AI-driven cinematic understanding,….
0
1
0
RT @TheAITimeline: MMSearch-R1: Incentivizing LMMs to Search. Author's Explanation:. Overview:.MMSearch-R1 introduc….
0
2
0
RT @rohanpaul_ai: Large Multimodal Models (LMMs) struggle with dynamic external knowledge for Visual Question Answering (VQA), leading to h….
0
4
0
RT @gm8xx8: ByteDance introduces MMSearch-R1, a reinforcement learning framework that trains Qwen2.5-VL-7B to perform on-demand multimodal….
0
3
0
RT @RevanthAtmakuri: 🧠 Tired of LMMs acting like overcaffeinated Googlers, these researchers built MMSearch-R1—a reinforcement-trained know….
0
2
0
RT @HuggingPapers: Introducing MMSearch-R1 from ByteDance, a new RL framework that empowers LMMs with on-demand, multi-turn image and text….
0
7
0
🔥Incentivizing LMMs to Search🔥. 🔎MMSearch-R1🔍 is an end-to-end reinforcement learning framework that enables LMMs to perform *on-demand, multi-turn search* in real-world Internet environments. - Paper: - Code: . Thanks @_akhaliq.
3
14
77
RT @Frozen_Burning: #Free4D is accepted to @ICCVConference, see y’all in Honolulu🌺🌴. Free4D is a training-free method for 4D generation fro….
0
9
0
RT @TianqiLiu664: 🔥 Free4D is accepted to #ICCV2025! 🔥.Free4D is a tuning-free framework for 4D scene generation from a single image, with….
0
8
0