Benhao Tang

benhaotang

AI & ML interests

Physics Master student in theoretical particle physics at Universität Heidelberg, actively looking into the possibilities of integrating AI into future physics research.

Recent Activity

reacted to abidlabs's post with 🔥 6 days ago

HOW TO ADD MCP SUPPORT TO ANY 🤗 SPACE Gradio now supports MCP! If you want to convert an existing Space, like this one https://huggingface.co/spaces/hexgrad/Kokoro-TTS, so that you can use it with Claude Desktop / Cursor / Cline / TinyAgents / or any LLM that supports MCP, here's all you need to do: 1. Duplicate the Space (in the Settings Tab) 2. Upgrade the Gradio `sdk_version` to `5.28` (in the `README.md`) 3. Set `mcp_server=True` in `launch()` 4. (Optionally) add docstrings to the function so that the LLM knows how to use it, like this: ```py def generate(text, speed=1): """ Convert text to speech audio. Parameters: text (str): The input text to be converted to speech. speed (float, optional): Playback speed of the generated speech. ``` That's it! Now your LLM will be able to talk to you 🤯

reacted to fdaudens's post with 👍 8 days ago

Want to know which AI models are least likely to hallucinate — and how to keep yours from spiking hallucinations by 20%? A new benchmark called Phare, by Giskard, tested leading models across multiple languages, revealing three key findings: 1️⃣ Popular models aren't necessarily factual. Some models ranking highest in user satisfaction benchmarks like LMArena are actually more prone to hallucination. 2️⃣ The way you ask matters - a lot. When users present claims confidently ("My teacher said..."), models are 15% less likely to correct misinformation vs. neutral framing ("I heard..."). 3️⃣ Telling models to "be concise" can increase hallucination by up to 20%. What's also cool is that the full dataset is public - use them to test your own models or dive deeper into the results! H/t @davidberenstein1957 for the link. - Study: https://www.giskard.ai/knowledge/good-answers-are-not-necessarily-factual-answers-an-analysis-of-hallucination-in-leading-llms - Leaderboard: https://phare.giskard.ai/ - Dataset: https://huggingface.co/datasets/giskardai/phare

liked a model 27 days ago

moonshotai/Kimi-VL-A3B-Thinking

View all activity

Organizations

None yet

benhaotang's activity

liked a model 27 days ago

moonshotai/Kimi-VL-A3B-Thinking

Image-Text-to-Text • Updated 19 days ago • 53.1k • 393

liked a Space about 1 month ago

HiDream Ai Full

🏢

Unofficial HiDream-ai Spaces

liked 2 models about 1 month ago

rasbt/llama-3.2-from-scratch

Updated 22 days ago • 271

teapotai/teapotllm

Text2Text Generation • Updated 19 days ago • 2.25k • 169

liked 4 models about 2 months ago

liked a Space about 2 months ago

Sesame CSM

🌱

Conversational speech generation

liked a model about 2 months ago

mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF

Updated Feb 20 • 329 • 1

liked a Space about 2 months ago

Graph Mind

👀

Extract and visualize knowledge graphs from any text

liked a model about 2 months ago

sesame/csm-1b

Text-to-Speech • Updated Mar 16 • 54.2k • 1.99k

liked a Space about 2 months ago

Talk to OpenAI

🗣

Talk to OpenAI using their multimodal API

liked 3 models 2 months ago

deepseek-ai/DeepSeek-R1

Text Generation • Updated Mar 27 • 1.31M • • 12.1k

Qwen/QwQ-32B

Text Generation • Updated Mar 11 • 565k • • 2.75k

CohereLabs/aya-vision-8b

Image-Text-to-Text • Updated 23 days ago • 36.2k • • 283

liked a dataset 3 months ago

driaforall/verifiable-pythonic-function-calling-lite

Viewer • Updated Feb 7 • 16.4k • 146 • 6

liked 2 models 3 months ago

driaforall/Tiny-Agent-a-1.5B

Text Generation • Updated Feb 17 • 83 • 4

Menlo/AlphaMaze-v0.2-1.5B

Text Generation • Updated Feb 24 • 81 • 91

liked a Space 3 months ago

2.56k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters