Team RAS in 11th ABAW Competition: Multimodal Ambivalence Recognition Approach
Paper โข 2607.14702 โข Published
Gradio-Blocks-Party
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
DmitryRyuminย
authored 2
papers 21 days ago
osansevieroย
authored a
paper about 1 month ago
osansevieroย
submitted a
paper to Daily Papers about 1 month ago
gigantย
authored a
paper 3 months ago
gigantย
submitted a
paper to Daily Papers 3 months ago
gigantย
authored a
paper 3 months ago
Aurelien-Morganย
posted an update 3 months ago
Post
1107
@retrain-pipelines v0.2.0 is out !
I'm at Station F at My booth with GOSIM Paris 2026 today & tomorrow.
Come meet me for a live in-person demo and a chat !
I'm at Station F at My booth with GOSIM Paris 2026 today & tomorrow.
Come meet me for a live in-person demo and a chat !
- 1 reply
Aurelien-Morganย
posted an update 4 months ago
Aurelien-Morganย
posted an update 8 months ago
Post
377
Hey, I went to Hangzhou to talk about
The recording just got released. Go check it out !
https://www.youtube.com/watch?v=nmrMachM5aM
Slides are there :
https://docs.google.com/presentation/d/1hnAzHJ0SbeAOtGJir-iH84RBtXT1OxVT/
retrain-pipelines at the GOSIM Foundation's conference last september.The recording just got released. Go check it out !
https://www.youtube.com/watch?v=nmrMachM5aM
Slides are there :
https://docs.google.com/presentation/d/1hnAzHJ0SbeAOtGJir-iH84RBtXT1OxVT/
- 2 replies
Paper99ย
authored 2
papers 8 months ago
runtime error
2
#10 opened 9 months ago
by 
liangnanying
hystsย
updated a
Space 9 months ago
Kameshrย
authored a
paper 9 months ago
DmitryRyuminย
posted an update 9 months ago
Post
1385
๐๐๏ธ๐ New Research Alert - ICCV 2025 (Poster)! ๐๐๏ธ๐
๐ Title: Is Less More? Exploring Token Condensation as Training-Free Test-Time Adaptation ๐
๐ Description: Token Condensation as Adaptation (TCA) improves the performance and efficiency of Vision Language Models in zero-shot inference by introducing domain anchor tokens.
๐ฅ Authors: Zixin Wang, Dong Gong, Sen Wang, Zi Huang, Yadan Luo
๐ Conference: ICCV, 19 โ 23 Oct, 2025 | Honolulu, Hawai'i, USA ๐บ๐ธ
๐ Paper: Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation (2410.14729)
๐ Repository: https://github.com/Jo-wang/TCA
๐ ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
๐ Added to the Session 1: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/session-1.md
๐ More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
๐ Keywords: #TestTimeAdaptation #TokenCondensation #VisionLanguageModels #TrainingFreeAdaptation #ZeroShotLearning #EfficientAI #AI #ICCV2025 #ResearchHighlight
๐ Title: Is Less More? Exploring Token Condensation as Training-Free Test-Time Adaptation ๐
๐ Description: Token Condensation as Adaptation (TCA) improves the performance and efficiency of Vision Language Models in zero-shot inference by introducing domain anchor tokens.
๐ฅ Authors: Zixin Wang, Dong Gong, Sen Wang, Zi Huang, Yadan Luo
๐ Conference: ICCV, 19 โ 23 Oct, 2025 | Honolulu, Hawai'i, USA ๐บ๐ธ
๐ Paper: Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation (2410.14729)
๐ Repository: https://github.com/Jo-wang/TCA
๐ ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
๐ Added to the Session 1: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/session-1.md
๐ More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
๐ Keywords: #TestTimeAdaptation #TokenCondensation #VisionLanguageModels #TrainingFreeAdaptation #ZeroShotLearning #EfficientAI #AI #ICCV2025 #ResearchHighlight
DmitryRyuminย
posted an update 9 months ago
Post
2518
๐๐๏ธ๐ New Research Alert - ICCV 2025 (Oral)! ๐๐๏ธ๐
๐ Title: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching ๐
๐ Description: The proposed method enhances stereo matching by efficiently combining unbiased monocular priors from vision foundation models. This method addresses misalignment and local optima issues using a binary local ordering map and pixel-wise linear regression.
๐ฅ Authors: Chengtang Yao, Lidong Yu, Zhidan Liu, Jiaxi Zeng, Yuwei Wu, and Yunde Jia
๐ Conference: ICCV, 19 โ 23 Oct, 2025 | Honolulu, Hawai'i, USA ๐บ๐ธ
๐ Paper: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching (2505.14414)
๐ Repository: https://github.com/YaoChengTang/Diving-into-the-Fusion-of-Monocular-Priors-for-Generalized-Stereo-Matching
๐ ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
๐ Added to the 3D Pose Understanding Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/3d-pose-understanding.md
๐ More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
๐ Keywords: #StereoMatching #MonocularDepth #VisionFoundationModels #3DReconstruction #Generalization #AI #ICCV2025 #ResearchHighlight
๐ Title: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching ๐
๐ Description: The proposed method enhances stereo matching by efficiently combining unbiased monocular priors from vision foundation models. This method addresses misalignment and local optima issues using a binary local ordering map and pixel-wise linear regression.
๐ฅ Authors: Chengtang Yao, Lidong Yu, Zhidan Liu, Jiaxi Zeng, Yuwei Wu, and Yunde Jia
๐ Conference: ICCV, 19 โ 23 Oct, 2025 | Honolulu, Hawai'i, USA ๐บ๐ธ
๐ Paper: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching (2505.14414)
๐ Repository: https://github.com/YaoChengTang/Diving-into-the-Fusion-of-Monocular-Priors-for-Generalized-Stereo-Matching
๐ ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
๐ Added to the 3D Pose Understanding Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/3d-pose-understanding.md
๐ More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
๐ Keywords: #StereoMatching #MonocularDepth #VisionFoundationModels #3DReconstruction #Generalization #AI #ICCV2025 #ResearchHighlight
Post
2064
Multilingual Tokenization Showdown
Analyzing 12 LLM Tokenizers Across 204 Languages.
First, I've created a dataset with Wikipedia's "Cat" article text in 272 languages:
Norod78/WikiCat-Multilingual
For each language entry with at least 100 words, I tokenized the text using 12 tokenizers and calculated the "Characters per token" ratio and "Word per token" ratio. The higher this ratio is, the more information each token represents on average for that language (and perhaps allowing the llm to potentially learn more per-parameter if trained on a dataset of that language).
You can see a slideshow summary of the results here:
https://norod.github.io/wikicat-tokenizer-eval/tokenizer-slideshow.html
I hope I interpreted the results correctly, I've made the code available on GitHub so you can re-create the raw results jsonl with this repo:
https://github.com/Norod/wikicat-tokenizer-eval
Post on X:
https://x.com/Norod78/status/1984366900550266999
Analyzing 12 LLM Tokenizers Across 204 Languages.
First, I've created a dataset with Wikipedia's "Cat" article text in 272 languages:
Norod78/WikiCat-Multilingual
For each language entry with at least 100 words, I tokenized the text using 12 tokenizers and calculated the "Characters per token" ratio and "Word per token" ratio. The higher this ratio is, the more information each token represents on average for that language (and perhaps allowing the llm to potentially learn more per-parameter if trained on a dataset of that language).
You can see a slideshow summary of the results here:
https://norod.github.io/wikicat-tokenizer-eval/tokenizer-slideshow.html
I hope I interpreted the results correctly, I've made the code available on GitHub so you can re-create the raw results jsonl with this repo:
https://github.com/Norod/wikicat-tokenizer-eval
Post on X:
https://x.com/Norod78/status/1984366900550266999
DmitryRyuminย
posted an update 9 months ago
Post
2849
๐๐๐ New Research Alert - ICCV 2025 (Oral)! ๐๐ค๐
๐ Title: Understanding Co-speech Gestures in-the-wild ๐
๐ Description: JEGAL is a tri-modal model that learns from gestures, speech and text simultaneously, enabling devices to interpret co-speech gestures in the wild.
๐ฅ Authors: @sindhuhegde , K R Prajwal, Taein Kwon, and Andrew Zisserman
๐ Conference: ICCV, 19 โ 23 Oct, 2025 | Honolulu, Hawai'i, USA ๐บ๐ธ
๐ Paper: Understanding Co-speech Gestures in-the-wild (2503.22668)
๐ Web Page: https://www.robots.ox.ac.uk/~vgg/research/jegal
๐ Repository: https://github.com/Sindhu-Hegde/jegal
๐บ Video: https://www.youtube.com/watch?v=TYFOLKfM-rM
๐ ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
๐ Added to the Human Modeling Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/human-modeling.md
๐ More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
๐ Keywords: #CoSpeechGestures #GestureUnderstanding #TriModalRepresentation #MultimodalLearning #AI #ICCV2025 #ResearchHighlight
๐ Title: Understanding Co-speech Gestures in-the-wild ๐
๐ Description: JEGAL is a tri-modal model that learns from gestures, speech and text simultaneously, enabling devices to interpret co-speech gestures in the wild.
๐ฅ Authors: @sindhuhegde , K R Prajwal, Taein Kwon, and Andrew Zisserman
๐ Conference: ICCV, 19 โ 23 Oct, 2025 | Honolulu, Hawai'i, USA ๐บ๐ธ
๐ Paper: Understanding Co-speech Gestures in-the-wild (2503.22668)
๐ Web Page: https://www.robots.ox.ac.uk/~vgg/research/jegal
๐ Repository: https://github.com/Sindhu-Hegde/jegal
๐บ Video: https://www.youtube.com/watch?v=TYFOLKfM-rM
๐ ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
๐ Added to the Human Modeling Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/human-modeling.md
๐ More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
๐ Keywords: #CoSpeechGestures #GestureUnderstanding #TriModalRepresentation #MultimodalLearning #AI #ICCV2025 #ResearchHighlight
nouamanetaziย
posted an update 9 months ago
Post
5078
After training ๐๐ฆ๐จ๐ฅ๐๐๐ on ๐๐๐ ๐๐๐๐๐ฌ for nearly a month, I've come to realize something most people overlook: ๐ข๐ง๐๐ซ๐๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐ ๐ข๐ฌ ๐ญ๐ก๐ ๐ฆ๐๐ค๐-๐จ๐ซ-๐๐ซ๐๐๐ค ๐๐๐๐ญ๐จ๐ซ ๐ข๐ง ๐๐๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ . ๐ฅ
Everyone talks about model architecture and data quality. And yes, those matter immensely. But here's what nobody tells you: when your training run fails at 2 AM because of mysterious ๐๐๐๐ ๐๐ซ๐ซ๐จ๐ซ๐ฌ, or when your expensive GPU cluster is running at ๐๐% ๐๐๐๐ข๐๐ข๐๐ง๐๐ฒ, the problem isn't your model. It's most probably a ๐ฆ๐ข๐ฌ๐ฎ๐ฌ๐ ๐จ๐ ๐ญ๐ก๐ ๐ก๐๐ซ๐๐ฐ๐๐ซ๐. ๐ ๏ธ
Questions that seemed simple but had no clear answers: Why is ๐๐จ๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ ๐ฌ๐ฅ๐จ๐ฐ๐๐ซ ๐ญ๐ก๐๐ง ๐๐๐ง๐ฌ๐ ๐ฆ๐จ๐๐๐ฅ๐ฌ? Which ๐๐๐๐ ๐๐ฅ๐๐ ๐ฌ should we actually set? How often should we checkpoint without killing throughput?
That's why we built ๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค ๐: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the ๐ข๐ง๐๐ซ๐๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐ ๐ฅ๐๐ฒ๐๐ซ that most teams get wrong.
We validated real vs theoretical bandwidth across the entire stack: ๐๐๐๐ ๐ก๐ข๐ญ๐ญ๐ข๐ง๐ ๐ ๐๐/๐ฌ, ๐๐๐๐ข๐ง๐ค ๐.๐ ๐ซ๐๐๐๐ก๐ข๐ง๐ ๐๐๐ ๐๐/๐ฌ, ๐๐๐๐ ๐๐๐ง๐ ๐๐ญ ๐๐.๐ ๐๐/๐ฌ. Then we ran collective operations across ๐๐๐ ๐๐๐๐ฌ (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from ๐๐๐ ๐๐/๐ฌ on a single node to ๐๐๐-๐๐๐ ๐๐/๐ฌ across 16 nodes.
If you've ever wondered why your training runs are slower than they should be, or you're planning to scale up and want to avoid expensive mistakes, this guide might save you weeks of debugging.
๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค: https://lnkd.in/e5MKXUHS
Shared with โค๏ธ by the HuggingFace team
Everyone talks about model architecture and data quality. And yes, those matter immensely. But here's what nobody tells you: when your training run fails at 2 AM because of mysterious ๐๐๐๐ ๐๐ซ๐ซ๐จ๐ซ๐ฌ, or when your expensive GPU cluster is running at ๐๐% ๐๐๐๐ข๐๐ข๐๐ง๐๐ฒ, the problem isn't your model. It's most probably a ๐ฆ๐ข๐ฌ๐ฎ๐ฌ๐ ๐จ๐ ๐ญ๐ก๐ ๐ก๐๐ซ๐๐ฐ๐๐ซ๐. ๐ ๏ธ
Questions that seemed simple but had no clear answers: Why is ๐๐จ๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ ๐ฌ๐ฅ๐จ๐ฐ๐๐ซ ๐ญ๐ก๐๐ง ๐๐๐ง๐ฌ๐ ๐ฆ๐จ๐๐๐ฅ๐ฌ? Which ๐๐๐๐ ๐๐ฅ๐๐ ๐ฌ should we actually set? How often should we checkpoint without killing throughput?
That's why we built ๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค ๐: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the ๐ข๐ง๐๐ซ๐๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐ ๐ฅ๐๐ฒ๐๐ซ that most teams get wrong.
We validated real vs theoretical bandwidth across the entire stack: ๐๐๐๐ ๐ก๐ข๐ญ๐ญ๐ข๐ง๐ ๐ ๐๐/๐ฌ, ๐๐๐๐ข๐ง๐ค ๐.๐ ๐ซ๐๐๐๐ก๐ข๐ง๐ ๐๐๐ ๐๐/๐ฌ, ๐๐๐๐ ๐๐๐ง๐ ๐๐ญ ๐๐.๐ ๐๐/๐ฌ. Then we ran collective operations across ๐๐๐ ๐๐๐๐ฌ (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from ๐๐๐ ๐๐/๐ฌ on a single node to ๐๐๐-๐๐๐ ๐๐/๐ฌ across 16 nodes.
If you've ever wondered why your training runs are slower than they should be, or you're planning to scale up and want to avoid expensive mistakes, this guide might save you weeks of debugging.
๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค: https://lnkd.in/e5MKXUHS
Shared with โค๏ธ by the HuggingFace team