Brian Moser
@bmoser1995
Followers
36
Following
161
Media
6
Statuses
50
Senior Researcher at German Research Center for Artificial Intelligence.
Kaiserslautern, Germany
Joined April 2018
🎉 Our paper “Unlocking Dataset Distillation with Diffusion Models” has been accepted at #NeurIPS 25! We show how to unlock end-to-end dataset distillation through diffusion models by tackling the vanishing gradient problem! 📄 : https://t.co/fRh4MCqL0I
#DiffusionModels
arxiv.org
Dataset distillation seeks to condense datasets into smaller but highly representative synthetic samples. While diffusion models now lead all generative benchmarks, current distillation methods...
0
1
14
Simple vision pretraining by predicting next step embedding. The embedding itself is trained along with this while stop grad is applied when it is used as a target.
4
52
403
#Meta just released SAM Audio: Segment Anything, but for sound. It’s actually so cool: isolate a voice/instrument/noise with a prompt. Now imagine Meta Ray-Ban (probably a feature already in the making): choose the person you want to listen to… and hear only them. #AI
🔉 Introducing SAM Audio, the first unified model that isolates any sound from complex audio mixtures using text, visual, or span prompts. We’re sharing SAM Audio with the community, along with a perception encoder model, benchmarks and research papers, to empower others to
0
0
1
We did some extended research against robot this time!!! Please check it out! SensHRPS: Sensing Comfortable Human-Robot Proxemics and Personal Space With Eye-Tracking https://t.co/vEbAJEtEqk
New publication available in Arxiv!!! SensPS: Sensing Personal Space Comfortable Distance between Human-Human Using Multimodal Sensors https://t.co/L7e15JhqPg
0
1
2
What a transformative experience at #NeurIPS. Lessons learned: - History rhymes: RL and Meta-Learning are back on the menu. - Things move fast and going to move faster. As a scientist, plan your next years carefully! I will definitely. - Networking is king.
0
0
1
This paper is being presented at NeurIPS workshop @neur_reps right now, upper ballroom 6a, 3:35-5:00
An LLM-generated paper is in the top 17% of ICLR submissions in terms of average reviewer score, having received two 8's. The paper has tons of BS jargon and hallucinated references. Fortunately, one reviewer actually looked at the paper and gave it a zero. 1/3
3
7
80
I am an AC for ICLR 2026. One of the papers in my batch was just withdrawn. The authors wrote a brief response, explaining why the reviewers failed at their job. I agree with most of their comments. The authors gave up. They are fed up. Just like many of us. I understand. We
33
207
2K
Please check this/our poster out!!! 🥳
0
1
2
Happy to share that TKG-DM, a training-free chroma key content generation diffusion model was accepted to CVPR 25. Project led by @Oguryu417 Paper: https://t.co/BpV0xFmxrP Code: https://t.co/EohvQ4qzzO
0
5
5
This work has been selected as highlight🥚🥚😎😎
Exciting news! 🎉 Our paper “TKG-DM: Training-free Chroma Key Content Generation Diffusion Model” has been accepted to #CVPR2025! 🥳 Stay tuned for more updates! #AI #DiffusionModel #TKG
0
8
38
Checkout PromptMap, presented at IUI'25, a new interaction style with text-to-image models/data that allows users to freely explore a vast collection of synthetic prompts through a map-like view with semantic zoom. Paper: https://t.co/eYJ6UBHOGK Code: https://t.co/BRHQxjwjTV
0
1
1
Our paper „Distill the Best, Ignore the Rest: Improving Dataset Distillation with Loss-Value-Based Pruning“ got accepted for #IJCNN 2025 :-) In this paper, we showed how #dataset #distillation can profit from #coresets :) arXiv: https://t.co/NCZr3a0DZs
#AI #NeuralNetworks #ML
arxiv.org
Dataset distillation has gained significant interest in recent years, yet existing approaches typically distill from the entire dataset, potentially including non-beneficial samples. We introduce...
0
1
7
Wow! Very cool new method for arbitrary image super-resolution!
We present Thera🔥: The new SOTA arbitrary-scale super-resolution method with built-in anti-aliasing. Our approach introduces Neural Heat Fields, which guarantee exact Gaussian filtering at any scale, enabling continuous image reconstruction without extra computational cost.
0
0
2
Our paper, including an application and a dataset for pupil diameter prediction, got accepted :-) #ETRA #ETRA2025 #eyes #dl #ml
Another paper accepted!!! 🎉 PupilSense: A Novel Application for Webcam-Based Pupil Diameter Estimation has been accepted as a short paper in the ETRA 2025 Short Papers. #ETRA
0
1
2
SpotDiffusion enables fast, high-quality panorama generation by shifting non-overlapping denoising windows, eliminating redundant computations in existing methods. **Original Problem** 🔍: Generating high-resolution panoramas with diffusion models is computationally expensive
2
5
13
Our paper: "Augmenting Online Meetings with Context-Aware Real-time Music Generation" has been accepted in Augmented Humans - Demo paper #AHs This work challenged to see how context-aware music generation supports meeting augmentation. Checkout the paper https://t.co/HYGuhwnHqt
1
3
3
Just presented our work „Dynamic Attention-Guided Diffusion for Image Super-Resolution“ at #WACV2025 to address this and really interesting talks with other great researchers in this field :-) It’s such a cool job :) If you’re interested in the work: https://t.co/A8M0Qg3MZw
0
1
4