Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting
Paper
β’
2505.19716
β’
Published
β’
5
AI & ML interests
None defined yet.
Recent Activity
View all activity
wubinghengΒ
authored
a
paper
5 days ago
Post
2002
Introducing Voxtral WebGPU: State-of-the-art audio transcription directly in your browser! π€―
π£οΈ Transcribe videos, meeting notes, songs and more
π Runs on-device, meaning no data is sent to a server
π Multilingual (8 languages)
π€ Completely free (forever) & open source
That's right, we're running Mistral's new Voxtral-Mini-3B model 100% locally in-browser on WebGPU, powered by Transformers.js and ONNX Runtime Web! π₯
Try it out yourself! π
webml-community/Voxtral-WebGPU
π£οΈ Transcribe videos, meeting notes, songs and more
π Runs on-device, meaning no data is sent to a server
π Multilingual (8 languages)
π€ Completely free (forever) & open source
That's right, we're running Mistral's new Voxtral-Mini-3B model 100% locally in-browser on WebGPU, powered by Transformers.js and ONNX Runtime Web! π₯
Try it out yourself! π
webml-community/Voxtral-WebGPU
mbrackΒ
authored
a
paper
about 1 month ago
Post
2759
- 1 reply
csabakecskemetiΒ
posted
an
update
about 2 months ago
Post
2839
Has anyone ever backed up a model to a sequential tape drive, or I'm the world first? :D
Just played around with my retro PC that has got a tape driveβdid it just because I can.
Just played around with my retro PC that has got a tape driveβdid it just because I can.
- 5 replies
Post
6885
NEW: Real-time conversational AI models can now run 100% locally in your browser! π€―
π Privacy by design (no data leaves your device)
π° Completely free... forever
π¦ Zero installation required, just visit a website
β‘οΈ Blazingly-fast WebGPU-accelerated inference
Try it out: webml-community/conversational-webgpu
For those interested, here's how it works:
- Silero VAD for voice activity detection
- Whisper for speech recognition
- SmolLM2-1.7B for text generation
- Kokoro for text to speech
Powered by Transformers.js and ONNX Runtime Web! π€ I hope you like it!
π Privacy by design (no data leaves your device)
π° Completely free... forever
π¦ Zero installation required, just visit a website
β‘οΈ Blazingly-fast WebGPU-accelerated inference
Try it out: webml-community/conversational-webgpu
For those interested, here's how it works:
- Silero VAD for voice activity detection
- Whisper for speech recognition
- SmolLM2-1.7B for text generation
- Kokoro for text to speech
Powered by Transformers.js and ONNX Runtime Web! π€ I hope you like it!
- 4 replies
csabakecskemetiΒ
posted
an
update
2 months ago
Post
362
Deepseek R1 0528 Q2 locally.
(I believe it has overthinking it a bit :) )
https://youtu.be/Iqu5s9aFaXA?si=QWZe293iTKf_3ELU
DevQuasar/deepseek-ai.DeepSeek-R1-0528-GGUF
(I believe it has overthinking it a bit :) )
https://youtu.be/Iqu5s9aFaXA?si=QWZe293iTKf_3ELU
DevQuasar/deepseek-ai.DeepSeek-R1-0528-GGUF
Post
7112
Today, we're unveiling two new open-source AI robots! HopeJR for $3,000 & Reachy Mini for $300 π€π€π€
Let's go open-source AI robotics!
Let's go open-source AI robotics!
- 7 replies
mbrackΒ
authored
11
papers
2 months ago
Class Attribute Inference Attacks: Inferring Sensitive Class Information by Diffusion-Based Attribute Manipulations
Paper
β’
2303.09289
β’
Published
β’
2
Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge
Paper
β’
2309.11575
β’
Published
MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation
Paper
β’
2305.15296
β’
Published
β’
1
Mitigating Inappropriateness in Image Generation: Can there be Value in Reflecting the World's Ugliness?
Paper
β’
2305.18398
β’
Published
β’
2
Does CLIP Know My Face?
Paper
β’
2209.07341
β’
Published
β’
1
Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis
Paper
β’
2209.08891
β’
Published
β’
2
The Stable Artist: Steering Semantics in Diffusion Latent Space
Paper
β’
2212.06013
β’
Published
β’
1
LLavaGuard: VLM-based Safeguards for Vision Dataset Curation and Safety Assessment
Paper
β’
2406.05113
β’
Published
β’
3
AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation
Paper
β’
2301.08110
β’
Published
β’
1
SCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering in LLMs
Paper
β’
2411.07122
β’
Published
β’
2
Judging Quality Across Languages: A Multilingual Approach to Pretraining Data Filtering with Language Models
Paper
β’
2505.22232
β’
Published
β’
18
samsjaΒ
authored
a
paper
2 months ago