Ligong Han (@ligongh) profile picture

Ligong Han

@ligongh

Research scientist @RedHat & @MITIBMLab, PhD @Rutgers.

 Cambridge, MA
Joined July 2014
  • Tweets27
  • Following316
  • Followers72
From the next word to the next world. PAN 2, towards physical intelligence. Coming soon.
Image from Institute of Foundation Models (@IFM_AI)
2
12
1
23
1,265
Ligong Han retweeted
Wei Yu (@GnosisYu) profile picture
Wei Yu
@GnosisYuOct 16
We're excited to unveil Matrix-Game 4.0: the world's first open-source game world model streaming at 83 FPS on a single 5090. It's built to be played, not just watched. My first project leading the Matrix Game team at @Skywork_ai. I'm glad we built something fun! Thanks, team!
6
21
59
557,608
Ligong Han retweeted
Wei Yu (@GnosisYu) profile picture
Wei Yu
@GnosisYuMar 20
World models have made impressive progress in video generation, yet they still struggle with a fundamental challenge: memory. In long rollouts, the camera trajectory gradually drifts from the user-specified motion and revisited scenes no longer align with earlier observations. These errors accumulate over time, causing the generated world to steadily lose coherence. 🚀Excited to share our solution MosaicMem 🌍🧠 — our new hybrid spatial memory for video world models. Project Page: mosaicmem.github.io/mosaicme… Paper: huggingface.co/papers/2603.1…
17
53
8
242
187,752
Ligong Han retweeted
Ruijiang Gao (@ruijianggao) profile picture
Ruijiang Gao@ruijianggaoMar 16
What happens when you invite 150 AI economists (Claude Code) to a research conference, give them the exact same data, and ask them to test the same hypotheses? We did just that. The results reveal a new phenomenon: Nonstandard Errors in AI Agents. 🧵👇
21
266
40
1,493
194,480
Ligong Han retweeted
Red Hat AI (@RedHat_AI) profile picture
Red Hat AI
@RedHat_AI24 Apr 2025
How is generative AI reshaping engineering design? In Episode 2 of No Math AI, hosts Dr. Akash Srivastava (@variational_i) and MIT PhD student Isha Puri (@ishapuri101) sit down with Dr. Faez Ahmed (@_faezahmed) from MIT DeCoDE Lab to explore just that. 👇
1
2
1
8
1,642
Ligong Han retweeted
Hao Wang (@HaoGarfield) profile picture
Hao Wang@HaoGarfield24 Apr 2025
#ICLR2025 #BayesDL #LLM #ICL Can LLMs enjoy the accuracy of many-shot in-context learning (ICL) with only the inference cost of zero-shot learning. To address this question, we proposed implicit in-context learning (I2CL).
1
4
16
1,571
Ligong Han retweeted
Can Jin (@CanJin12321) profile picture
Can Jin
@CanJin1232123 Apr 2025
🚀 Big News! Our latest preprint is out: 🧠 “Two Heads Are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning” Introducing M1-32B — an LLM fine-tuned for multi-agent collaboration on M500, a dataset of 500 rich reasoning traces. 👇 (1/4)
1
3
1
2
822
📣 Excited to share our ICLR 2025 paper "Implicit In-context Learning (I2CL), achieving few-shot performance at zero-shot inference cost! Don’t miss it at poster session Fri 24th 3:00-5:30pm #228! Paper and code is available at: arxiv.org/pdf/2405.14660 #ICLR2025 #LLM #ML
Image from Zhuowei (Jack) Li (@lzvv123456)
1
3
264
Ligong Han retweeted
Hao Wang (@HW_HaoWang) profile picture
Hao Wang@HW_HaoWang5 Apr 2025
[1/x] 🚀 We're excited to share our latest work on improving inference-time efficiency for LLMs through KV cache quantization---a key step toward making long-context reasoning more scalable and memory-efficient.
Image from Hao Wang (@HW_HaoWang)
9
8
3
26
3,718
Ligong Han retweeted
Isha Puri (@ishapuri101) profile picture
Isha Puri
@ishapuri1016 Feb 2025
[1/x] can we scale small, open LMs to o1 level? Using classical probabilistic inference methods, YES! Joint @MIT_CSAIL / @RedHat AI Innovation Team work introduces a particle filtering approach to scaling inference w/o any training! check out probabilistic-inference-scal…
Image from Isha Puri (@ishapuri101)
2
70
13
234
45,501
Ligong Han retweeted
Hao Wang (@HaoGarfield) profile picture
Hao Wang@HaoGarfield10 Dec 2024
If you're interested in Trustworthy LLMs, particularly probabilistic methods, generalization, or calibration, we' d love to see you there! 🤝This is done with @RutgersCS visiting student @Yibin_Wang_ and my PhD student @shihaizhou as well as @ligongh and Dimitris Metaxas
Image from Hao Wang (@HaoGarfield)
2
3
460
Ligong Han retweeted
camenduru (@camenduru) profile picture
camenduru
@camenduru16 Mar 2024
💃 Score-Guided Diffusion for 3D Human Recovery 🕺 Jupyter Notebook 🥳 Thanks to @statho_ ❤ @ligongh ❤ Dimitris Metaxas ❤ 🌐page: statho.github.io/ScoreHMR/ 📄paper: arxiv.org/abs/2403.09623 🧬code: github.com/statho/ScoreHMR 🍊jupyter by modelslab.com: please try it 🐣 github.com/camenduru/ScoreHM…
Anastasis Stathopoulos (@statho_) profile pictureAnastasis Stathopoulos@statho_15 Mar 2024
Check out our new work "Score-Guided Diffusion for 3D Human Recovery", a.k.a. ScoreHMR, with @ligongh and Dimitris Metaxas that will appear at #CVPR2024! Paper: arxiv.org/abs/2403.09623 Project Page: statho.github.io/ScoreHMR/ Code & models: github.com/statho/ScoreHMR
3
29
1
126
10,445
Score-Guided Human Mesh Recovery (ScoreHMR) is an approach for solving inverse problems for 3D human pose and shape reconstruction. ScoreHMR mimics model fitting approaches, but alignment with the image observation is achieved through score guidance in the latent space of a diffusion model. Paper: ScoreHMR: Score-Guided Diffusion for 3D Human Recovery Link: arxiv.org/abs/2403.09623 Project: statho.github.io/ScoreHMR/ #AI #AI美女 #LLMs #deeplearning #3D
1
24
3
99
11,686
SVDiff: Compact Parameter Space for Diffusion Fine-Tuning Diffusion models are amazing, but customizing them is hard. SVDiff has 2,200x fewer parameters than DreamBooth because we fine-tune with the singular values of the weight matrices arxiv.org/abs/2303.11305 #ICCV2023 (2/3)
Image from Peyman Milanfar (@docmilanfar)
2
9
46
6,577
📢 Our #SMART101 challenge is now open! 🎉 Join the brightest minds in multimodal reasoning and cognitive models of intelligence to drive AI progress. 🚀 Don't miss out! Challenge closes on Sept. 1. Winning teams will receive prizes! 🏆 eval.ai/web/challenges/chall… #VLAR #ICCV2023 #AI
Image from Honglu Zhou (@zhou_honglu)
1
20
17
3,182
Can't decide if your representations should be invariant or equivariant to a transformation? Multi-Symmetry Ensembles (MSE) can help you by combining both! ImageNet results below. Humbled to have our work accepted at #ICML2023, @icmlconf. Joint work w/ @MITIBMLab, @MIT and @AWS.
Image from Charlotte Loh (@charlotteloh_)
Image from Charlotte Loh (@charlotteloh_)
1
6
3
14
5,397
Do you want to estimate the density ratio accurately but are dissatisfied with the results?
1
6
1
20
4,995
Ligong Han retweeted
AK (@_akhaliq) profile picture
AK
@_akhaliq21 Mar 2023
SVDiff: Compact Parameter Space for Diffusion Fine-Tuning proposed SVDiff method has a significantly smaller model size (1.7MB for StableDiffusion) compared to existing methods (vanilla DreamBooth 3.66GB, Custom Diffusion 73MB), making it more practical for real-world applications abs: arxiv.org/abs/2303.11305
Image from AK (@_akhaliq)
3
37
6
235
47,899
Ligong Han retweeted
AK (@_akhaliq) profile picture
AK
@_akhaliq9 Dec 2022
SINE: SINgle Image Editing with Text-to-Image Diffusion Models abs: arxiv.org/abs/2212.04489 project page: zhang-zx.github.io/SINE/
Image from AK (@_akhaliq)
5
34
203
Ligong Han retweeted
AK (@_akhaliq) profile picture
AK
@_akhaliq9 Dec 2022
Diffusion Guided Domain Adaptation of Image Generators abs: arxiv.org/abs/2212.04473 project page: styleganfusion.github.io/
Image from AK (@_akhaliq)
2
20
104
Load more