Team RAS in 9th ABAW Competition: Multimodal Compound Expression Recognition Approach
Paper
โข
2507.02205
โข
Published
AI & ML interests
None defined yet.
Recent Activity
View all activity
DmitryRyuminย
authored
a
paper
about 4 hours ago
DmitryRyuminย
posted
an
update
about 22 hours ago
Post
1833
๐๐ค๐ New Research Alert - ICCV 2025 (Oral)! ๐๐ค๐
๐ Title: Variance-based Pruning for Accelerating and Compressing Trained Networks ๐
๐ Description: The one-shot pruning method efficiently compresses networks, reducing computation and memory usage while retaining almost full performance and requiring minimal fine-tuning.
๐ฅ Authors: Uranik Berisha, Jens Mehnert, and Alexandru Paul Condurache
๐ Conference: ICCV, 19 โ 23 Oct, 2025 | Honolulu, Hawai'i, USA ๐บ๐ธ
๐ Paper: Variance-Based Pruning for Accelerating and Compressing Trained Networks (2507.12988)
๐ ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
๐ Added to the Efficient Learning Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/efficient-learning.md
๐ More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
๐ Keywords: #VarianceBasedPruning #NetworkCompression #ModelAcceleration #EfficientDeepLearning #VisionTransformers #AI #ICCV2025 #ResearchHighlight
๐ Title: Variance-based Pruning for Accelerating and Compressing Trained Networks ๐
๐ Description: The one-shot pruning method efficiently compresses networks, reducing computation and memory usage while retaining almost full performance and requiring minimal fine-tuning.
๐ฅ Authors: Uranik Berisha, Jens Mehnert, and Alexandru Paul Condurache
๐ Conference: ICCV, 19 โ 23 Oct, 2025 | Honolulu, Hawai'i, USA ๐บ๐ธ
๐ Paper: Variance-Based Pruning for Accelerating and Compressing Trained Networks (2507.12988)
๐ ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
๐ Added to the Efficient Learning Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/efficient-learning.md
๐ More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
๐ Keywords: #VarianceBasedPruning #NetworkCompression #ModelAcceleration #EfficientDeepLearning #VisionTransformers #AI #ICCV2025 #ResearchHighlight
nroggendorffย
posted
an
update
2 days ago
Post
3228
Is it hot in here, or is it just me?
-
- 5 replies
DmitryRyuminย
posted
an
update
2 days ago
Post
2608
๐๐๏ธ๐ New Research Alert - ICCV 2025 (Oral)! ๐๐๏ธ๐
๐ Title: Token Activation Map to Visually Explain Multimodal LLMs ๐
๐ Description: The Token Activation Map (TAM) is an advanced explainability method for multimodal LLMs. Using causal inference and a Rank Gaussian Filter, TAM reveals token-level interactions and eliminates redundant activations. The result is clearer, high-quality visualizations that enhance understanding of object localization, reasoning and multimodal alignment across models.
๐ฅ Authors: Yi Li, Hualiang Wang, Xinpeng Ding, Haonan Wang, and Xiaomeng Li
๐ Conference: ICCV, 19 โ 23 Oct, 2025 | Honolulu, Hawai'i, USA ๐บ๐ธ
๐ Paper: Token Activation Map to Visually Explain Multimodal LLMs (2506.23270)
๐ Repository: https://github.com/xmed-lab/TAM
๐ ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
๐ Added to the Multi-Modal Learning Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/multi-modal-learning.md
๐ More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
๐ Keywords: #TokenActivationMap #TAM #CausalInference #VisualReasoning #Multimodal #Explainability #VisionLanguage #LLM #XAI #AI #ICCV2025 #ResearchHighlight
๐ Title: Token Activation Map to Visually Explain Multimodal LLMs ๐
๐ Description: The Token Activation Map (TAM) is an advanced explainability method for multimodal LLMs. Using causal inference and a Rank Gaussian Filter, TAM reveals token-level interactions and eliminates redundant activations. The result is clearer, high-quality visualizations that enhance understanding of object localization, reasoning and multimodal alignment across models.
๐ฅ Authors: Yi Li, Hualiang Wang, Xinpeng Ding, Haonan Wang, and Xiaomeng Li
๐ Conference: ICCV, 19 โ 23 Oct, 2025 | Honolulu, Hawai'i, USA ๐บ๐ธ
๐ Paper: Token Activation Map to Visually Explain Multimodal LLMs (2506.23270)
๐ Repository: https://github.com/xmed-lab/TAM
๐ ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
๐ Added to the Multi-Modal Learning Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/multi-modal-learning.md
๐ More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
๐ Keywords: #TokenActivationMap #TAM #CausalInference #VisualReasoning #Multimodal #Explainability #VisionLanguage #LLM #XAI #AI #ICCV2025 #ResearchHighlight
- 1 reply
Post
1456
Two new tools added to the
Nymbo/Tools MCP server,
GPT-5-Codex proves that for many cases, shell commands really are all you need, and Claude Skills seem to lean into this. The thing is, nothing about the design of Claude Skills actually restricts them to proprietary models!
# File_System
There's a new directory inside the repo called
Files created in the public HF space live in the space's running container, and gets cleared when the space is restarted. When running the server locally, files are actually stored on disk.
# Shell_Exec
What good is a filesystem if you can't execute commands in that filesystem? This tool automatically detects if the server is running on Windows or Linux, and suggests using the appropriate shell (PowerShell/Bash). Both of these new tools require that the agent uses relative paths, rather than absolute paths. I could be convinced to back pedal on this.
# Closing Thoughts
The
File_System and Shell_Exec. You can theoretically do basically anything with these two tools, and it should enable support for many Claude Skills. GPT-5-Codex proves that for many cases, shell commands really are all you need, and Claude Skills seem to lean into this. The thing is, nothing about the design of Claude Skills actually restricts them to proprietary models!
# File_System
There's a new directory inside the repo called
Filesystem, that's the agent's "root". It can perform the following actions : list, read, write, append, mkdir, move, copy, delete, info, help. It's able to keep this all within the scope of one tool call by making the Action field required and all other fields optional. Using a filesystem shouldn't require 15 different tools.Files created in the public HF space live in the space's running container, and gets cleared when the space is restarted. When running the server locally, files are actually stored on disk.
# Shell_Exec
What good is a filesystem if you can't execute commands in that filesystem? This tool automatically detects if the server is running on Windows or Linux, and suggests using the appropriate shell (PowerShell/Bash). Both of these new tools require that the agent uses relative paths, rather than absolute paths. I could be convinced to back pedal on this.
# Closing Thoughts
The
File_System and Shell_Exec tools aren't super polished yet, I'll continue to improve the agent's instructions and UX of using the new tools. Most of my testing was done with gpt-oss-20b and if it messes up, it gets the gist after one failed tool call. It should work perfectly fine for the GPU poor.
- 1 reply
nroggendorffย
posted
an
update
9 days ago
Post
3311
I love getting emails telling me when there's somebody else's active access token in one of my commit SHAs. HF should really only tell you if it is your token, otherwise I could just make a dataset with a bunch of random strings and wait for a valid token.
Also, don't comment about how unlikely this is. I've gotten a warning email about a token I 'leaked' at least four times.
In all cases, it has been in the digest hash.
user,permission,token
nroggendorff,write,hf_...
pepper13,finegrained,hf_...
...,...,...
...Also, don't comment about how unlikely this is. I've gotten a warning email about a token I 'leaked' at least four times.
In all cases, it has been in the digest hash.
-
- 2 replies
Post
412
Tokenization is one of the most important processes in AI - yet many would like to kill it ๐
What's tokenization? The neural networks inside LLMs actually only process numbers, not text: tokenization is the process that makes text readable for them, by converting sentences into lists of numbers.
โก๏ธ For instance, "This is tokenization" would be split into "This | is | token | ization", then each of the parts (tokens) are converted to IDs according to a predefined mapping: for instance "ization" could map to id 2438.
Thus "This is tokenization" can become 1335 | 135 | 2980 | 2438 => now the model can process the sentence!
Most tokenizers today use pre-specified mappings called "vocabularies", generally built about the compression algorithme Byte-Pair Encoding (BPE) that learns from a big corpuses of texts an optimized split to efficiently encode any text from the same distribution into a list token IDs.
๐คจ Now, these current tokenizers have flaws.
For instance, the rigidity of their mapping creates losses ; the prime example being that a tokenizer designed for English (thus optimized for tokens like "has", "been", "clock", etc) will not have the right tokens to approach Burmese, thus being terribly inefficient at it.
Many alternative approaches have emerged as a result: for instance "tokenizer-free tokenizers". One that I really liked was "entropy-based": it monitors the stream of text, and trigger a split whenever the entropy increases too much, i.e. when something "surprising" happens.
But this great article argues that tokenizers are a lesser evil. Read and decide for yourself!
https://huggingface.co/blog/catherinearnett/in-defense-of-tokenizers
What's tokenization? The neural networks inside LLMs actually only process numbers, not text: tokenization is the process that makes text readable for them, by converting sentences into lists of numbers.
โก๏ธ For instance, "This is tokenization" would be split into "This | is | token | ization", then each of the parts (tokens) are converted to IDs according to a predefined mapping: for instance "ization" could map to id 2438.
Thus "This is tokenization" can become 1335 | 135 | 2980 | 2438 => now the model can process the sentence!
Most tokenizers today use pre-specified mappings called "vocabularies", generally built about the compression algorithme Byte-Pair Encoding (BPE) that learns from a big corpuses of texts an optimized split to efficiently encode any text from the same distribution into a list token IDs.
๐คจ Now, these current tokenizers have flaws.
For instance, the rigidity of their mapping creates losses ; the prime example being that a tokenizer designed for English (thus optimized for tokens like "has", "been", "clock", etc) will not have the right tokens to approach Burmese, thus being terribly inefficient at it.
Many alternative approaches have emerged as a result: for instance "tokenizer-free tokenizers". One that I really liked was "entropy-based": it monitors the stream of text, and trigger a split whenever the entropy increases too much, i.e. when something "surprising" happens.
But this great article argues that tokenizers are a lesser evil. Read and decide for yourself!
https://huggingface.co/blog/catherinearnett/in-defense-of-tokenizers
Post
1655
I've made some improvements to my custom Deep_Research tool in the
Nymbo/Tools MCP server. I've added a second LLM process and it still takes less than 1 minute to complete!
The original version of my Deep_Research tool would basically dump up to 50 fetched webpages onto the Researcher model (
# New "Filterer" Process
The new process includes another LLM call before the researcher process. The Filterer (also
# Researcher Context
The Researcher now gets only the relevant webpages, then begins writing the report. When testing with 50 initial results, the researcher would often end up with 10-20 results of relevant context.
It still takes less than a minute to accomplish everything, thanks entirely to Cerebras inference. It now takes about 35-45 seconds to complete once the tool is run.
It's also worth noting that both the Filterer and Researcher now are provided the current time/date before they see the content, reducing hallucinations caused by knowledge cutoffs.
The original version of my Deep_Research tool would basically dump up to 50 fetched webpages onto the Researcher model (
Qwen3-235B), with only a little bit of context shown from each page.# New "Filterer" Process
The new process includes another LLM call before the researcher process. The Filterer (also
Qwen3-235B) gets the query summary and the original 50 pages with low context, and decides which pages are most relevant to the research topic. The Filterer then outputs the URLs to the relevant pages, which are then re-fetched (with more context) and sent to the Researcher.# Researcher Context
The Researcher now gets only the relevant webpages, then begins writing the report. When testing with 50 initial results, the researcher would often end up with 10-20 results of relevant context.
It still takes less than a minute to accomplish everything, thanks entirely to Cerebras inference. It now takes about 35-45 seconds to complete once the tool is run.
It's also worth noting that both the Filterer and Researcher now are provided the current time/date before they see the content, reducing hallucinations caused by knowledge cutoffs.
Post
290
New Technique to Deeply Poison AI on Images and Prove Creative Provenance
I've developed a new method to protect creative work from unauthorized AI training. My Poisonous Shield for Images algorithm embeds a deep, removal-resistant poison into the mathematical structure of your images. It's designed to be toxic to machine learning models, achieving up to 20-348% disruption in AI training convergence in benchmark tests.
Unlike traditional watermarks, this protection survives compression and resizing and is not removed by standard tools. The technique also embeds cryptographic proof of provenance directly into the image, verifying ownership and detecting tampering.
You can see examples and learn more about how and WHY it works better than current methods:
https://severian-poisonous-shield-for-images.static.hf.space
If you are interested in using this technology to protect your work from AI training and unauthorized use, please reach out to me. It is currently in the prototype phase but fully functioning and effective. Still working on expanding it to a production-grade usable app.
This is not intended as a pure self-promotion post. I am genuinely wanting to help creators and want to gauge interest from different communities. I've spent the past year and a half building this from scratch with new math and code to try and solve this massive problem.ย
I've developed a new method to protect creative work from unauthorized AI training. My Poisonous Shield for Images algorithm embeds a deep, removal-resistant poison into the mathematical structure of your images. It's designed to be toxic to machine learning models, achieving up to 20-348% disruption in AI training convergence in benchmark tests.
Unlike traditional watermarks, this protection survives compression and resizing and is not removed by standard tools. The technique also embeds cryptographic proof of provenance directly into the image, verifying ownership and detecting tampering.
You can see examples and learn more about how and WHY it works better than current methods:
https://severian-poisonous-shield-for-images.static.hf.space
If you are interested in using this technology to protect your work from AI training and unauthorized use, please reach out to me. It is currently in the prototype phase but fully functioning and effective. Still working on expanding it to a production-grade usable app.
This is not intended as a pure self-promotion post. I am genuinely wanting to help creators and want to gauge interest from different communities. I've spent the past year and a half building this from scratch with new math and code to try and solve this massive problem.ย
Post
4766
STOP EVERYTHING NOW - we might finally have a radical architecture improvement over Transformers!!! ๐จ
A lone scientist just proposed Tiny Recursive Model (TRM), and it is literally the most impressive model that I've seen this year.
โก๏ธ Tiny Recursive Model is 7M parameters
โก๏ธ On ARC-AGI, it beats flagship models like Gemini-2.5-pro
Consider how wild this is: Gemini-2.5-pro must be over 10,000x bigger
and had 1,000 as many authors ๐ (Alexia is alone on the paper)
What's this sorcery?
In short: it's a very tiny Transformers, but it loops over itself at two different frequencies, updating two latent variables: one for the proposed answer and one for the reasoning.
@AlexiaJM started from the paper Hierarchical Reasoning Model, published a few months ago, that already showed breakthrough improvement on AGI for its small size (27M)
Hierarchical Reasoning Model had introduced one main feature:
๐ Deep supervision
In their model, one part (here one layer) would run at high frequency, and another would be lower frequency, running only every n steps.
They had used a recurrent architecture, where these layers would repeat many times ; but to make it work they had to do many approximations, including not fully backpropagating the loss through all layers.
Alexia studied what was useful and what wasn't, and cleaned the architecture as follows :
Why use a recurrent architecture, when you can just make it a loop?
โก๏ธ She made the network recursive, looping over itself
Why use 2 latent variables ?
โก๏ธ She provides a crystal clear explanation : the one that changes frequently is the reasoning, the one that changes at low frequency is the proposed answer.
โก๏ธ She runs ablation studies to validate that 2 is indeed optimal.
This new setup is a much more elegant way to process reasoning than generating huge chains of tokens as all flagship models currently do.
This might be the breakthrough we've been awaiting for so long!
A lone scientist just proposed Tiny Recursive Model (TRM), and it is literally the most impressive model that I've seen this year.
โก๏ธ Tiny Recursive Model is 7M parameters
โก๏ธ On ARC-AGI, it beats flagship models like Gemini-2.5-pro
Consider how wild this is: Gemini-2.5-pro must be over 10,000x bigger
and had 1,000 as many authors ๐ (Alexia is alone on the paper)
What's this sorcery?
In short: it's a very tiny Transformers, but it loops over itself at two different frequencies, updating two latent variables: one for the proposed answer and one for the reasoning.
@AlexiaJM started from the paper Hierarchical Reasoning Model, published a few months ago, that already showed breakthrough improvement on AGI for its small size (27M)
Hierarchical Reasoning Model had introduced one main feature:
๐ Deep supervision
In their model, one part (here one layer) would run at high frequency, and another would be lower frequency, running only every n steps.
They had used a recurrent architecture, where these layers would repeat many times ; but to make it work they had to do many approximations, including not fully backpropagating the loss through all layers.
Alexia studied what was useful and what wasn't, and cleaned the architecture as follows :
Why use a recurrent architecture, when you can just make it a loop?
โก๏ธ She made the network recursive, looping over itself
Why use 2 latent variables ?
โก๏ธ She provides a crystal clear explanation : the one that changes frequently is the reasoning, the one that changes at low frequency is the proposed answer.
โก๏ธ She runs ablation studies to validate that 2 is indeed optimal.
This new setup is a much more elegant way to process reasoning than generating huge chains of tokens as all flagship models currently do.
This might be the breakthrough we've been awaiting for so long!
- 2 replies
DongfuJiangย
authored
2
papers
19 days ago
Post
3143
MLX port of BDH (Baby Dragon Hatchling) is up!
Iโve ported the BDH ( https://github.com/pathwaycom/bdh ) model to MLX for Apple Silicon. Itโs a faithful conversion of the PyTorch version: same math, same architecture (byte-level vocab, shared weights across layers, ReLU sparsity, RoPE attention with Q=K), with MLX-friendly APIs and a detailed README explaining the few API-level differences and why results are equivalent.
Code, docs, and training script are ready to use. You may need to adjust the training script a bit to fit your own custom dataset. Only tested on M4 so far, but should work perfect for any M1/M2/M3 users out there.
Iโm currently training this MLX build on my Internal Knowledge Map (IKM) dataset Severian/Internal-Knowledge-Map
Trainingโs underway; expect a day or so before I publish weights. When itโs done, Iโll upload the checkpoint to Hugging Face for anyone to test.
Repo: https://github.com/severian42/BDH-MLX
HF model (coming soon): Severian/BDH-MLX
If you try it on your own data, feedback and PRs are welcome.
Iโve ported the BDH ( https://github.com/pathwaycom/bdh ) model to MLX for Apple Silicon. Itโs a faithful conversion of the PyTorch version: same math, same architecture (byte-level vocab, shared weights across layers, ReLU sparsity, RoPE attention with Q=K), with MLX-friendly APIs and a detailed README explaining the few API-level differences and why results are equivalent.
Code, docs, and training script are ready to use. You may need to adjust the training script a bit to fit your own custom dataset. Only tested on M4 so far, but should work perfect for any M1/M2/M3 users out there.
Iโm currently training this MLX build on my Internal Knowledge Map (IKM) dataset Severian/Internal-Knowledge-Map
Trainingโs underway; expect a day or so before I publish weights. When itโs done, Iโll upload the checkpoint to Hugging Face for anyone to test.
Repo: https://github.com/severian42/BDH-MLX
HF model (coming soon): Severian/BDH-MLX
If you try it on your own data, feedback and PRs are welcome.
Post
2953
๐ New blog: Maintain the unmaintainable โ 1M+ Python LOC, 400+ models
How do you stop a million-line library built by thousands of contributors from collapsing under its own weight?
At ๐ค Transformers, we do it with explicit software-engineering tenets, principles that make the codebase hackable at scale.
๐ Inside the post:
โ One Model, One File: readability first โ you can still open a modeling file and see the full logic, top to bottom.
โ Modular Transformers: visible inheritance that cuts maintenance cost by ~15ร while keeping models readable.
โ Config-Driven Performance: FlashAttention, tensor parallelism, and attention scheduling are config-level features, not rewrites.
Written with @lysandre ,@pcuenq and @yonigozlan , this is a deep dive into how Transformers stays fast, open, and maintainable.
Read it here โ transformers-community/Transformers-tenets
How do you stop a million-line library built by thousands of contributors from collapsing under its own weight?
At ๐ค Transformers, we do it with explicit software-engineering tenets, principles that make the codebase hackable at scale.
๐ Inside the post:
โ One Model, One File: readability first โ you can still open a modeling file and see the full logic, top to bottom.
โ Modular Transformers: visible inheritance that cuts maintenance cost by ~15ร while keeping models readable.
โ Config-Driven Performance: FlashAttention, tensor parallelism, and attention scheduling are config-level features, not rewrites.
Written with @lysandre ,@pcuenq and @yonigozlan , this is a deep dive into how Transformers stays fast, open, and maintainable.
Read it here โ transformers-community/Transformers-tenets
Post
2131
Cool stuff these past weeks on huggingface! ๐ค ๐ !
โข ๐Trackio, local-first W&B alternative
https://github.com/gradio-app/trackio/issues
โข ๐EmbeddingGemma, 300M-param, multilingual embeddings, on-device
https://huggingface.co/blog/embeddinggemma
โข ๐ปOpen LLMs in VS Code (Inference Providers)
https://x.com/reach_vb/status/1966185427582497171
โข ๐คSmol2Operator GUI agents
https://huggingface.co/blog/smol2operator
โข ๐ผ๏ธGradio visible watermarking
https://huggingface.co/blog/watermarking-with-gradio
โข ๐Trackio, local-first W&B alternative
https://github.com/gradio-app/trackio/issues
โข ๐EmbeddingGemma, 300M-param, multilingual embeddings, on-device
https://huggingface.co/blog/embeddinggemma
โข ๐ปOpen LLMs in VS Code (Inference Providers)
https://x.com/reach_vb/status/1966185427582497171
โข ๐คSmol2Operator GUI agents
https://huggingface.co/blog/smol2operator
โข ๐ผ๏ธGradio visible watermarking
https://huggingface.co/blog/watermarking-with-gradio
Post
2242
@lunarflu
can you make me out from Hugging Face Discord Community? Because my old email discord was gone yet and all of my email gone too ๐
My Dead Account:
@Blane187
@Ryouko65777
Also delete the account if can ๐
My Dead Account:
@Blane187
@Ryouko65777
Also delete the account if can ๐
-
- 2 replies
Post
606
I have a few Sora-2 invites - 15509N
- 1 reply
nroggendorffย
posted
an
update
26 days ago
Post
417
When're we getting
H100-explorers?
-
- 1 reply
nroggendorffย
posted
an
update
about 1 month ago
Post
3350
I'm sorry, what?
-
- 11 replies
Post
686
the french ministry of culture releases their first conversation datasets on huggingface ๐๐ป
ministere-culture/comparia-conversations
ministere-culture/comparia-conversations