dev-mode-explorers (Dev Mode Explorers)

posted an update 2 days ago

Post

960

🚀👁️🌟 New Research Alert - ICCV 2025 (Poster)! 🌟👁️🚀
📄 Title: Is Less More? Exploring Token Condensation as Training-Free Test-Time Adaptation 🔝

📝 Description: Token Condensation as Adaptation (TCA) improves the performance and efficiency of Vision Language Models in zero-shot inference by introducing domain anchor tokens.

👥 Authors: Zixin Wang, Dong Gong, Sen Wang, Zi Huang, Yadan Luo

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation (2410.14729)

📁 Repository: https://github.com/Jo-wang/TCA

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Session 1: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/session-1.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #TestTimeAdaptation #TokenCondensation #VisionLanguageModels #TrainingFreeAdaptation #ZeroShotLearning #EfficientAI #AI #ICCV2025 #ResearchHighlight

xianbao

authored a paper 4 days ago

RoboChallenge: Large-scale Real-robot Evaluation of Embodied Policies

Paper • 2510.17950 • Published 20 days ago • 4

DmitryRyumin

posted an update 5 days ago

Post

2268

🚀👁️🌟 New Research Alert - ICCV 2025 (Oral)! 🌟👁️🚀
📄 Title: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching 🔝

📝 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.

👥 Authors: Chengtang Yao, Lidong Yu, Zhidan Liu, Jiaxi Zeng, Yuwei Wu, and Yunde Jia

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching (2505.14414)

📁 Repository: https://github.com/YaoChengTang/Diving-into-the-Fusion-of-Monocular-Priors-for-Generalized-Stereo-Matching

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the 3D Pose Understanding Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/3d-pose-understanding.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #StereoMatching #MonocularDepth #VisionFoundationModels #3DReconstruction #Generalization #AI #ICCV2025 #ResearchHighlight

Nymbo

posted an update 7 days ago

Post

402

I've added an 11th tool to the Nymbo/Tools MCP server, it's for your Obsidian_Vault. I'd argue it's far more context-efficient than any other Obsidian MCP I've seen, and doesn't require any plugins. Also some big improvements to the Web_Search and Web_Fetch tools.

# Obsidian_Vault Tool

It's basically a read-only version of the File_System tool, but it works so well for navigating Obsidian without unnecessary context. It supports recursive (full-text) search across the entire vault, and supports offset so the agent can "scroll" through a document without re-consuming tokens.

Run the server locally and set the OBSIDIAN_VAULT_ROOT environment variable to your vault's root path. If you don't use Obsidian, this is perfectly usable as simply a read-only filesystem.

# Web_Search Improvements

The Web_Search tool previously just used DuckDuckGo as a backend search engine, but now it also supports Bing, Brave, Yahoo, and Wikipedia. Default engine is auto which provides results from all backends in recommended order. Still doesn't require any kind of API or auth for Web_Search.

There's also a new date filter to limit results to those created in the past day, week, month, or year. Oh, and uhh, SafeSearch is now off by default :)

# Web_Fetch Improvements

As context-efficient as the Markdown mode is for web browsing, sometimes it does lose important context in the conversion from HTML to Markdown. So I've added a new HTML mode to the Web_Fetch tool that basically executes a cURL request on the URL, returning the full HTML page if necessary.

# A Note on Claude Skills

I've been having fun with the new File_System and Shell_Command tools. Using Claude Skills doesn't currently work in the public HF space because of environment restrictions, but using Skills works perfectly well running locally.

Happy building ~

kitiara666

in dev-mode-explorers/README 7 days ago

Build Failure (apt-get permission denied) in Dev Mode on Gradio + ZeroGpu Space

4

#26 opened 7 days ago by

Archime

DmitryRyumin

posted an update 9 days ago

Post

2784

🚀👌🌟 New Research Alert - ICCV 2025 (Oral)! 🌟🤌🚀
📄 Title: Understanding Co-speech Gestures in-the-wild 🔝

📝 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.

👥 Authors: @sindhuhegde , K R Prajwal, Taein Kwon, and Andrew Zisserman

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Understanding Co-speech Gestures in-the-wild (2503.22668)

🌐 Web Page: https://www.robots.ox.ac.uk/~vgg/research/jegal
📁 Repository: https://github.com/Sindhu-Hegde/jegal
📺 Video: https://www.youtube.com/watch?v=TYFOLKfM-rM

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Human Modeling Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/human-modeling.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #CoSpeechGestures #GestureUnderstanding #TriModalRepresentation #MultimodalLearning #AI #ICCV2025 #ResearchHighlight

DmitryRyumin

posted an update 12 days ago

Post

3907

🚀💡🌟 New Research Alert - ICCV 2025 (Oral)! 🌟🪄🚀
📄 Title: LoftUp: Learning a Coordinate-based Feature Upsampler for Vision Foundation Models 🔝

📝 Description: LoftUp is a coordinate-based transformer that upscales the low-resolution features of VFMs (e.g. DINOv2 and CLIP) using cross-attention and self-distilled pseudo-ground truth (pseudo-GT) from SAM.

👥 Authors: Haiwen Huang, Anpei Chen, Volodymyr Havrylov, Andreas Geiger, and Dan Zhang

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models (2504.14032)

🌐 Github Page: https://andrehuang.github.io/loftup-site
📁 Repository: https://github.com/andrehuang/loftup

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Foundation Models and Representation Learning Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/foundation-models-and-representation-learning.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #LoftUp #VisionFoundationModels #FeatureUpsampling #Cross-AttentionTransformer #CoordinateBasedLearning #SelfDistillation #PseudoGroundTruth #RepresentationLearning #AI #ICCV2025 #ResearchHighlight

mrfakename

posted an update 12 days ago

Post

3187

Trained a model for emotion-controllable TTS based on MiMo audio on LAION's dataset.

Still very early and does have an issue with hallucinating but results seem pretty good so far, given that it is very early into the training run.

Will probably kick off a new run later with some settings tweaked.

Put up a demo here: mrfakename/EmoAct-MiMo

(Turn 🔊 on to hear audio samples)

4 replies

·

DmitryRyumin

posted an update 13 days ago

Post

1918

🚀🏷️🌟 New Research Alert - ICCV 2025 (Oral)! 🌟🧩🚀
📄 Title: Heavy Labels Out! Dataset Distillation with Label Space Lightening 🔝

📝 Description: The HeLlO framework is a new corpus distillation method that removes the need for large soft labels. It uses a lightweight, online image-to-label projector based on CLIP. This projector has been adapted using LoRA-style, parameter-efficient tuning. It has also been initialized with text embeddings.

👥 Authors: @roseannelexie , @Huage001 , Zigeng Chen, Jingwen Ye, and Xinchao Wang

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Heavy Labels Out! Dataset Distillation with Label Space Lightening (2408.08201)

📺 Video: https://www.youtube.com/watch?v=kAyK_3wskgA

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Efficient Learning Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/efficient-learning.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #DatasetDistillation #LabelCompression #CLIP #LoRA #EfficientAI #FoundationModels #AI #ICCV2025 #ResearchHighlight

2 replies

·

DmitryRyumin

authored a paper 13 days ago

Team RAS in 9th ABAW Competition: Multimodal Compound Expression Recognition Approach

Paper • 2507.02205 • Published Jul 2

DmitryRyumin

posted an update 14 days ago

Post

4766

🚀🤖🌟 New Research Alert - ICCV 2025 (Oral)! 🌟🤖🚀
📄 Title: Variance-based Pruning for Accelerating and Compressing Trained Networks 🔝

📝 Description: The one-shot pruning method efficiently compresses networks, reducing computation and memory usage while retaining almost full performance and requiring minimal fine-tuning.

👥 Authors: Uranik Berisha, Jens Mehnert, and Alexandru Paul Condurache

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Variance-Based Pruning for Accelerating and Compressing Trained Networks (2507.12988)

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Efficient Learning Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/efficient-learning.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #VarianceBasedPruning #NetworkCompression #ModelAcceleration #EfficientDeepLearning #VisionTransformers #AI #ICCV2025 #ResearchHighlight

nroggendorff

posted an update 15 days ago

Post

3678

Is it hot in here, or is it just me?

5 replies

·

DmitryRyumin

posted an update 15 days ago

Post

2961

🚀👁️🌟 New Research Alert - ICCV 2025 (Oral)! 🌟👁️🚀
📄 Title: Token Activation Map to Visually Explain Multimodal LLMs 🔝

📝 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.

👥 Authors: Yi Li, Hualiang Wang, Xinpeng Ding, Haonan Wang, and Xiaomeng Li

📅 Conference: ICCV, 19 – 23 Oct, 2025 | Honolulu, Hawai'i, USA 🇺🇸

📄 Paper: Token Activation Map to Visually Explain Multimodal LLMs (2506.23270)

📁 Repository: https://github.com/xmed-lab/TAM

🚀 ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers

🚀 Added to the Multi-Modal Learning Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/multi-modal-learning.md

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #TokenActivationMap #TAM #CausalInference #VisualReasoning #Multimodal #Explainability #VisionLanguage #LLM #XAI #AI #ICCV2025 #ResearchHighlight

2 replies

·

merve

posted an update 20 days ago

Post

5104

deepseek-ai/DeepSeek-OCR is out! 🔥 my take ⤵️
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages

3 replies

·

Nymbo

posted an update 22 days ago

Post

1703

Two new tools added to the Nymbo/Tools MCP server, 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

·

nroggendorff

posted an update 22 days ago

Post

3327

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.

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

·

m-ric

posted an update 26 days ago

Post

533

Tokenization is one of the most important processes in AI - yet many would like to kill it 💀

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.

➡️ 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.

🤨 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

Nymbo

posted an update 27 days ago

Post

1786

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 (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.

Severian

posted an update 29 days ago

Post

319

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.

m-ric

posted an update about 1 month ago

Post

4809

STOP EVERYTHING NOW - we might finally have a radical architecture improvement over Transformers!!! 🚨

A lone scientist just proposed Tiny Recursive Model (TRM), and it is literally the most impressive model that I've seen this year.

➡️ Tiny Recursive Model is 7M parameters
➡️ 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 😂 (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:
🔎 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?
➡️ She made the network recursive, looping over itself

Why use 2 latent variables ?
➡️ 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.
➡️ 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!

3 replies

·

Dev Mode Explorers

AI & ML interests

Recent Activity

RoboChallenge: Large-scale Real-robot Evaluation of Embodied Policies

Build Failure (apt-get permission denied) in Dev Mode on Gradio + ZeroGpu Space

Team RAS in 9th ABAW Competition: Multimodal Compound Expression Recognition Approach

AI & ML interests

Recent Activity

Team members 145

dev-mode-explorers's activity

Build Failure (apt-get permission denied) in Dev Mode on Gradio + ZeroGpu Space