AI & ML interests
None defined yet.
Recent Activity
Papers
WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks
DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems
Articles
MageBench Leaderboard
This is a leaderboard for magebench
TRELLIS.2
High-fidelity 3D Generation from images
VITRA
Generate 3D hand motion predictions from images
Phi 4 Mini
Demos for Phi-4-mini-instruct model
ThoughtsOrganizer
Transform your spoken thoughts into organized insights
TRELLIS
Scalable and Versatile 3D Generation from images
PhineSpeechTranslator
Break the language barrier
StoriesComeAlive
Transform handwritten moments into spoken memories
Phi 4 Multimodal
Interact with an AI by sending text, images, or audio
Magma Gaming
Magma playing video games
Magma UI
Magma-8B model for UI Agents
OmniParser V2
OmniParser, turn your LLM into GUI agent
Llmlingua 2
Compress text prompts efficiently
OmniParser demo
Convert images of screens to structured elements
HuggingGPT
Engage in multimedia chat with LLMs and ML models
VPTQ Demo
Vector Post Training Quantization Inference Demo
MInference
Generate text responses to user queries
LLMLingua
Compress prompts to speed up language model inference
Visual Chatgpt
ChatGPT Robotics
Promptist
Generate optimized prompts for Stable Diffusion