NVIDIA Releases 3 Million Sample Dataset for OCR, Visual Question Answering, and Captioning Tasks
•
2
AI & ML interests
None defined yet.
Recent Activity
View all activity
Articles
pinned
Running
27
KVPress Leaderboard
🥇
KVPress leaderboard: benchmark KV Cache compression methods
pinned
Running
on
A100
65
Audio Flamingo 3 Demo
🚀
Audio Flamingo 3 Demo
pinned
Running
20
Llm Robustness Leaderboard
🥇
LLM Robustness leaderboard
Sleeping
31
Audio Flamingo 3 Chat
🐠
Audio Flamingo 3 demo for multi-turn multi-audio chat
Running
3
Speech IQ Leaderboard
🗣
speech agentic IQ leaderboard
Running
on
Zero
MCP
106
Addit
⚡
Add objects to images using text prompts
Running
on
Zero
24
Kvpress
🐠
kvpress: LLM KV cache compression made easy
Running
on
L4
17
Canary-Qwen-2.5B
🐤
Transcribe audio and generate responses based on prompts
Running
Synthda Demo
🚀
Short Demo of SynthDa, using the real-real interpolation mtd
Paused
3
Plan2Align Test-Time Multilingual Translation
🌍
Translate text into multiple languages using various methods
Sleeping
37
Audio Flamingo 2
🏃
Audio Flamingo 2 Demo
Running
on
Zero
5
Cosmos Reason1 Demo
🖼
Analyze images and videos for anomalies
Running
on
Zero
273
PartPacker
🪴
Part-level image-to-3D generation.
Runtime error
12
Cosmos-Predict2 14B
🦀
Text-to-Image world model with Cosmos2
Running
Tp 1 Dgx Node Estimator
⚙
for NVIDIA TRDC estimation
Running
on
L40S
18
Difix3D
🚀
Interface to interact with NVIDIA's Difix3D+ model
Running
3
LOTUS VLM Bias
🪷
Leaderboard to societal bias and User preference
Running
on
Zero
422
Parakeet-TDT-0.6b-V2
Transcribe audio files to text with timestamps
Running
on
CPU Upgrade
Cosmos Embed1
🚀
Cosmos-Embed1 demo app
Running
on
Zero
335
Describe Anything
⚡
Describe masked areas in images
Running
13
Eagle2.5 VL
💬
Chat with images and text using Eagle2-VL
Running
on
Zero
36
Canary 1B Flash
🐤
Canary 1B Flash demo
Runtime error
197
Canary 1b
🐤
Transcribe and translate audio into text
Running
22
Radio
📚
Generate image features and segmentations