Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Meet Genesis V2. We’ve introduced "Option-Level Reasoning"—a method that trains models to understand why distractors are incorrect, not just pick the right answer. 📈 The Result: ~30% avg accuracy (competitors ~12%). ✅ Reliability: 99.4% valid, clear answers. Read the paper & get the dataset on Hugging Face:

QVAC

4,546 subscribers

85,228 views • 5 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

AccVideo just dropped on Hugging Face Accelerating Video Diffusion Model with Synthetic Dataset present a efficient distillation method to accelerate video diffusion models with synthetic dataset method is 8.5x faster than HunyuanVideo

AccVideo just dropped on Hugging Face Accelerating Video Diffusion Model with Synthetic Dataset present a efficient distillation method to accelerate video diffusion models with synthetic dataset method is 8.5x faster than HunyuanVideo

AK

20,633 views • 1 year ago

🤯🤯 That's insane! Hugging Face just shipped Data Studio on dataset pages... Ask a question about any dataset, the agent writes and runs a SQL query... then share the result or download as CSV... check it out! 👀 ⤵️ Wow GG Caleb 👏

🤯🤯 That's insane! Hugging Face just shipped Data Studio on dataset pages... Ask a question about any dataset, the agent writes and runs a SQL query... then share the result or download as CSV... check it out! 👀 ⤵️ Wow GG Caleb 👏

Jeff Boudier 🤗

19,703 views • 1 year ago

Neat new system to evolve protein-protein interactions - while altering both sides of the interface! Watch for a description of the clever method, read the paper to get the deets on how these interfaces evolved & predictive models trained on screen data.

Neat new system to evolve protein-protein interactions - while altering both sides of the interface! Watch for a description of the clever method, read the paper to get the deets on how these interfaces evolved & predictive models trained on screen data.

Julia Bauman

58,527 views • 2 years ago

Iman Mirzadeh from Apple Iman Mirzadeh wrote the famous GSM-Symbolic paper a couple of months back which argued that LLMs are learning surface statistics and not genuinely reasoning due to their sensitivity to distractors and out of distribution examples.

Iman Mirzadeh from Apple Iman Mirzadeh wrote the famous GSM-Symbolic paper a couple of months back which argued that LLMs are learning surface statistics and not genuinely reasoning due to their sensitivity to distractors and out of distribution examples.

Machine Learning Street Talk

87,646 views • 1 year ago

Why LLMs are a dead end for human-level intelligence, and especially for Physical AI / Robotics. The next leap isn’t bigger language models. It’s World Models. I just dropped a full 1-hour presentation from Shanghai: “World Models: the ChatGPT moment for robotics?” → Why LLMs hit a wall → Why action-conditioned world models planning in latent space are the real path → Live World Forge demo with LeWorldModel + Hugging Face LeRobot Watch here. The future of intelligence is embodied, not just chatty.

Why LLMs are a dead end for human-level intelligence, and especially for Physical AI / Robotics. The next leap isn’t bigger language models. It’s World Models. I just dropped a full 1-hour presentation from Shanghai: “World Models: the ChatGPT moment for robotics?” → Why LLMs hit a wall → Why action-conditioned world models planning in latent space are the real path → Live World Forge demo with LeWorldModel + Hugging Face LeRobot Watch here. The future of intelligence is embodied, not just chatty.

abdel

32,570 views • 6 days ago

Genesis is not a launchpad, it’s a launch protocol. Which is why we’re thrilled to announce the Genesis SDK, bringing the reliability, trust and transparency of Genesis to launchpads and trading platforms. (1/6)

Genesis is not a launchpad, it’s a launch protocol. Which is why we’re thrilled to announce the Genesis SDK, bringing the reliability, trust and transparency of Genesis to launchpads and trading platforms. (1/6)

Metaplex

112,324 views • 5 months ago

pick the right option and get a treat 😺

pick the right option and get a treat 😺

Antidepressant Content

19,200 views • 5 months ago

Let's talk parsing charts 📊📈. Last week we released ParseBench, the first document OCR benchmark for AI agents. New in ParseBench: ChartDataPointMatch. Most document look at a chart and OCR the caption. Agents need the actual numbers. That's the gap between "OCR'd the text around the chart" and "actually read the chart." More about ParseBench, the GitHub code, Hugging Face dataset, and scientific paper→

Let's talk parsing charts 📊📈. Last week we released ParseBench, the first document OCR benchmark for AI agents. New in ParseBench: ChartDataPointMatch. Most document look at a chart and OCR the caption. Agents need the actual numbers. That's the gap between "OCR'd the text around the chart" and "actually read the chart." More about ParseBench, the GitHub code, Hugging Face dataset, and scientific paper→

LlamaIndex 🦙

13,987 views • 1 month ago

We are releasing Star Elastic - turn ONE reasoning LLM into MANY sizes with a single post-training run. 360× cheaper than pretraining a family of models. 7× better than SOTA compression. Split reasoning capability. Plus elastic budget control that beats the accuracy-latency frontier. Paper: HF models: Thread 👇

We are releasing Star Elastic - turn ONE reasoning LLM into MANY sizes with a single post-training run. 360× cheaper than pretraining a family of models. 7× better than SOTA compression. Split reasoning capability. Plus elastic budget control that beats the accuracy-latency frontier. Paper: HF models: Thread 👇

Pavlo Molchanov

21,518 views • 27 days ago

Introducing Collaborative Reasoner: a framework to improve collaborative reasoning in language models. Collaborative Reasoner paves the way for developing social agents that can partner with humans and other agents. Read the research paper and download the code.

Introducing Collaborative Reasoner: a framework to improve collaborative reasoning in language models. Collaborative Reasoner paves the way for developing social agents that can partner with humans and other agents. Read the research paper and download the code.

AI at Meta

58,387 views • 1 year ago

I'm excited to announce the release of the Naijaweb 🇳🇬 dataset. Naijaweb is a 270,000 (230Million GPT2 tokens) document dataset of webpages which Nigerians have shown interest in, it was cleaned with the same techniques done on the Fineweb dataset by Hugging Face. A thread 🧵..

I'm excited to announce the release of the Naijaweb 🇳🇬 dataset. Naijaweb is a 270,000 (230Million GPT2 tokens) document dataset of webpages which Nigerians have shown interest in, it was cleaned with the same techniques done on the Fineweb dataset by Hugging Face. A thread 🧵..

Saheedniyi

188,121 views • 1 year ago

DeepSite v2 just dropped on Hugging Face

DeepSite v2 just dropped on Hugging Face

AK

31,559 views • 11 months ago

Democratic Socialists and Social Democrats are just the left wing of liberalism. Liberalism is a right wing ideology. We have to make this clear distinction. Also, Liberals are NOT the Left. If you just want guardrails on capitalism or just social welfare programs but not get rid of the system that pushes us to the margins, you're not on the left.

Democratic Socialists and Social Democrats are just the left wing of liberalism. Liberalism is a right wing ideology. We have to make this clear distinction. Also, Liberals are NOT the Left. If you just want guardrails on capitalism or just social welfare programs but not get rid of the system that pushes us to the margins, you're not on the left.

Jaybefaunt🏳️‍🌈

47,691 views • 1 year ago

A Stanford PhD student built a system that turns any research paper into a working AI agent. It's called Paper2Agent. I watched her demo it live and couldn't believe what I was seeing. Here's exactly what happened. She pasted a 40-page NeurIPS paper into the tool. Within seconds it extracted the core method, identified the dataset, and started scaffolding agent code that actually implements the paper's approach. But the wild part was what came next. She typed: "Apply this method to my dataset and answer questions like the paper's author would." The agent didn't just summarize. It ran the methodology. On her own data. And when she asked it why it made certain decisions, it cited the exact sections of the paper. What normally takes a PhD student 3 weeks of implementation just happened in under an hour. She's not smarter than other researchers. She just stopped reading papers and started running them. (Link in the comments)

A Stanford PhD student built a system that turns any research paper into a working AI agent. It's called Paper2Agent. I watched her demo it live and couldn't believe what I was seeing. Here's exactly what happened. She pasted a 40-page NeurIPS paper into the tool. Within seconds it extracted the core method, identified the dataset, and started scaffolding agent code that actually implements the paper's approach. But the wild part was what came next. She typed: "Apply this method to my dataset and answer questions like the paper's author would." The agent didn't just summarize. It ran the methodology. On her own data. And when she asked it why it made certain decisions, it cited the exact sections of the paper. What normally takes a PhD student 3 weeks of implementation just happened in under an hour. She's not smarter than other researchers. She just stopped reading papers and started running them. (Link in the comments)

Ihtesham Ali

67,874 views • 2 months ago

Valve have introduced a new item in their latest CS update, the Genesis Terminal, which allows players to re-roll their item up to 5 times, just to get the option to buy the item that you roll... with some exceeding $1,500 to purchase Wtf is this

Valve have introduced a new item in their latest CS update, the Genesis Terminal, which allows players to re-roll their item up to 5 times, just to get the option to buy the item that you roll... with some exceeding $1,500 to purchase Wtf is this

Jake Lucky

296,026 views • 8 months ago

#BREAKING: Psaki opener: “Today many Americans, maybe a lot of you watching right now, are understandably wondering why he did this [#Maduro capture], and you will not be shocked to learn that the Trump administration does NOT have a clear answer for that question, and you will also not be shocked to learn that they DON’T have a clear answer on the incredibly important question of what comes next…”🤦‍♀️

#BREAKING: Psaki opener: “Today many Americans, maybe a lot of you watching right now, are understandably wondering why he did this [#Maduro capture], and you will not be shocked to learn that the Trump administration does NOT have a clear answer for that question, and you will also not be shocked to learn that they DON’T have a clear answer on the incredibly important question of what comes next…”🤦‍♀️

Emoluments Clause

86,134 views • 5 months ago

The White Death must've been reincarnated as a paper boy with that level of accuracy 😭

The White Death must've been reincarnated as a paper boy with that level of accuracy 😭

internet hall of fame

153,308 views • 2 months ago

Introducing the Daily Papers SKILL.md Enables agents to > read paper content as markdown > search papers > find linked Hugging Face models and datasets > fetch the papers API > and more! Link below ⬇️

Introducing the Daily Papers SKILL.md Enables agents to > read paper content as markdown > search papers > find linked Hugging Face models and datasets > fetch the papers API > and more! Link below ⬇️

DailyPapers

33,987 views • 2 months ago

Just tested the Kimi-VL 3B model on hugging face and it's surprisingly powerful for its size - Outperforms larger models like GPT-4o on key benchmarks - Open source - Strong reasoning capabilities too .

Just tested the Kimi-VL 3B model on hugging face and it's surprisingly powerful for its size - Outperforms larger models like GPT-4o on key benchmarks - Open source - Strong reasoning capabilities too .

AshutoshShrivastava

12,389 views • 1 year ago