正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

At NeurIPS Conference Salah Alzu'bi presented ROMA—our Recursive Open Meta Agent 🧠 ROMA’s innovative architecture results in a 45.6% accuracy on SEAL-0, the hardest SEALQA subset—a new state-of-the-art for open-source reasoning.

Sentient

548,707 subscribers

35,162 次观看 • 7 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Sentient took AI Startup of the Year at the Minsky Awards 🙌 ROMA Search achieved an industry-leading 81.7% accuracy, significantly surpassing competitors on the FRAMES benchmark for multi-step reasoning. On the SEAL-0 benchmark for complex, multi-source reasoning, ROMA with 45.6% accuracy more than doubled the score of Gemini 2.5 Pro (19.8%). ROMA is available on GitHub, try it out today👇

Sentient took AI Startup of the Year at the Minsky Awards 🙌 ROMA Search achieved an industry-leading 81.7% accuracy, significantly surpassing competitors on the FRAMES benchmark for multi-step reasoning. On the SEAL-0 benchmark for complex, multi-source reasoning, ROMA with 45.6% accuracy more than doubled the score of Gemini 2.5 Pro (19.8%). ROMA is available on GitHub, try it out today👇

Sentient

482,992 次观看 • 10 个月前

Introducing: Cohere Transcribe – a new state-of-the-art in open source speech recognition.

Introducing: Cohere Transcribe – a new state-of-the-art in open source speech recognition.

Cohere

612,194 次观看 • 5 个月前

Introducing Agent S2 – Our newest open-source AI agent setting new records in computer & smartphone use! We are seeing Agent S2 solve a whole new range of tasks, pushing the boundaries of AI-driven autonomy. 🔥 Why it’s special: ✅ #1 in OSWorld (34.5% accuracy at 50 steps, surpassing OpenAI’s Operator) ✅ #1 in AndroidWorld (50% accuracy, advancing state-of-the-art by +3.4%) ✅ Fully Open-Source & Free to Use 🔗 Blog: 🔗 Code: 📄 Paper coming soon! Join us & shape the future of personal agents. Start building today! 🛠️

Introducing Agent S2 – Our newest open-source AI agent setting new records in computer & smartphone use! We are seeing Agent S2 solve a whole new range of tasks, pushing the boundaries of AI-driven autonomy. 🔥 Why it’s special: ✅ #1 in OSWorld (34.5% accuracy at 50 steps, surpassing OpenAI’s Operator) ✅ #1 in AndroidWorld (50% accuracy, advancing state-of-the-art by +3.4%) ✅ Fully Open-Source & Free to Use 🔗 Blog: 🔗 Code: 📄 Paper coming soon! Join us & shape the future of personal agents. Start building today! 🛠️

Simular

221,781 次观看 • 1 年前

A couple of days ago, I presented our 1st place solution for the 2025 BEHAVIOR Challenge at NeurIPS Conference . Now, we've open-sourced our solution: code, model weights, and a detailed tech report. Let me unpack what we did 👇

A couple of days ago, I presented our 1st place solution for the 2025 BEHAVIOR Challenge at NeurIPS Conference . Now, we've open-sourced our solution: code, model weights, and a detailed tech report. Let me unpack what we did 👇

Ilia

28,024 次观看 • 8 个月前

The most amazing aspect of DeepSeek Open Source is that just the Reasoning Engine can be isolated and used with any other LLM. In fact you can have a mixture of Reasoning Engines cascade around a problem and then use an Operator type agent AI to function on the the results.

The most amazing aspect of DeepSeek Open Source is that just the Reasoning Engine can be isolated and used with any other LLM. In fact you can have a mixture of Reasoning Engines cascade around a problem and then use an Operator type agent AI to function on the the results.

Brian Roemmele

398,786 次观看 • 1 年前

Introducing EmbeddingGemma: our new open, state-of-the-art embedding model designed for on-device AI 📱

Introducing EmbeddingGemma: our new open, state-of-the-art embedding model designed for on-device AI 📱

Google AI Developers

153,927 次观看 • 11 个月前

Wrapping up the year and coinciding with #NeurIPS2024, today at Meta FAIR we’re releasing a collection of nine new open source AI research artifacts across our work in developing agents, robustness & safety and new architectures. More in the video from Joelle Pineau. All of this work is part of FAIR’s continued work towards the goal of achieving advanced machine intelligence A few highlights from what we’re releasing today: • Meta Motivo: A first-of-its-kind behavioral foundation model that controls the movements of a virtual embodied humanoid agent to perform complex tasks. • Meta Video Seal: a state-of-the art comprehensive framework for neural video watermarking. • Meta Explore Theory-of-Mind: A program-guided adversarial data generation for theory of mind reasoning. • Meta Large Concept Models: A fundamentally different training paradigm for language modeling that decouples reasoning from language representation. And much more! We’re excited to share this work with the research community and look forward to seeing how it inspires new innovation across the field. Details and access to everything released by FAIR today ➡️

Wrapping up the year and coinciding with #NeurIPS2024, today at Meta FAIR we’re releasing a collection of nine new open source AI research artifacts across our work in developing agents, robustness & safety and new architectures. More in the video from Joelle Pineau. All of this work is part of FAIR’s continued work towards the goal of achieving advanced machine intelligence A few highlights from what we’re releasing today: • Meta Motivo: A first-of-its-kind behavioral foundation model that controls the movements of a virtual embodied humanoid agent to perform complex tasks. • Meta Video Seal: a state-of-the art comprehensive framework for neural video watermarking. • Meta Explore Theory-of-Mind: A program-guided adversarial data generation for theory of mind reasoning. • Meta Large Concept Models: A fundamentally different training paradigm for language modeling that decouples reasoning from language representation. And much more! We’re excited to share this work with the research community and look forward to seeing how it inspires new innovation across the field. Details and access to everything released by FAIR today ➡️

AI at Meta

156,123 次观看 • 1 年前

A major flagship addition to the open-source AI Models. Tencent has officially launched Hunyuan Hy3. This could be the most interesting open-source AI releases this year. ✓ 295B MoE architecture ✓ 21B active parameters ✓ 256K context ✓ Strong coding & reasoning ✓ Built for agent workflows ✓ Apache 2.0 license A big step forward for open AI infrastructure. Tencent Hy #Hy3 #Hunyuan #OpenSourceAI

A major flagship addition to the open-source AI Models. Tencent has officially launched Hunyuan Hy3. This could be the most interesting open-source AI releases this year. ✓ 295B MoE architecture ✓ 21B active parameters ✓ 256K context ✓ Strong coding & reasoning ✓ Built for agent workflows ✓ Apache 2.0 license A big step forward for open AI infrastructure. Tencent Hy #Hy3 #Hunyuan #OpenSourceAI

ZOYA ✪

45,196 次观看 • 1 个月前

My morning practice Still preaching Sentient Educator Week 18: Recursive Intelligence in Action Sentient released ROMA v0.2.0, a major leap in multi-agent reasoning. Built on DSPyOSS, it lets AI think recursively breaking big problems into smaller parts, solving them in parallel, and combining results like humans do. It brings faster execution, smarter model routing, and domain-specialized agents pushing Sentient closer to open-source AGI.

My morning practice Still preaching Sentient Educator Week 18: Recursive Intelligence in Action Sentient released ROMA v0.2.0, a major leap in multi-agent reasoning. Built on DSPyOSS, it lets AI think recursively breaking big problems into smaller parts, solving them in parallel, and combining results like humans do. It brings faster execution, smarter model routing, and domain-specialized agents pushing Sentient closer to open-source AGI.

KosiOkorie

39,756 次观看 • 9 个月前

The most effective AI systems don't rely on a single model. Frontier models provide state-of-the-art performance for complex tasks, while routers automatically select lightweight, open-source models for simpler jobs to optimize accuracy, latency, and cost. Learn more:

The most effective AI systems don't rely on a single model. Frontier models provide state-of-the-art performance for complex tasks, while routers automatically select lightweight, open-source models for simpler jobs to optimize accuracy, latency, and cost. Learn more:

NVIDIA AI

12,152 次观看 • 5 个月前

part 4 Gsenti Sentient Sentient Chat Explaining ROMA – Recursive Open Meta-Agent 1. What is ROMA? ROMA is an open-source framework for building meta-agents — systems that can orchestrate multiple smaller agents and tools to solve complex tasks. Instead of letting one AI model handle an entire large problem (which often fails due to complexity), ROMA applies a recursive approach: Parent nodes break a big goal into subtasks. Child nodes handle those subtasks and return results. All results are then combined into a final solution. 2. How does ROMA work? The architecture has four main components: Atomizer – decides whether a task is simple or requires decomposition. Planner – splits the complex task into smaller subtasks. Executor – runs the right tools/agents to complete each subtask. Aggregator – collects and synthesizes all results into one coherent answer. Because each node follows the same recursive logic, ROMA naturally scales as tasks become more complex. 3. Example Use Case – Deep Research Question: “Who are the top 5 NBA players by PPG in a season that have won both an NCAA and an NBA championship?” How ROMA handles it: Atomizer → identifies it as complex → needs decomposition. Planner → breaks it down: (1) find top NBA PPG seasons, (2) check NCAA champions, (3) check NBA champions, (4) combine filters. Executor → runs each search/tool for data. Aggregator → merges the results into the final answer. This creates a transparent, step-by-step reasoning process, unlike “black box” answers. 4. What Problem Does ROMA Solve? In long-horizon tasks, errors accumulate. A model may be 99% accurate at one step. But over 10 steps, success rates collapse due to compounding errors. Current agents are often opaque — hard to see where and why they failed. ROMA solves this by: Breaking tasks into clear logic chains, Making every step traceable, verifiable, and fixable. 5. Why ROMA Matters Open-source → available for anyone to build upon. Community-driven → empowering developers to create advanced multi-agent systems. Scalable → recursive logic adapts naturally to any task complexity. This makes ROMA not just a framework, but a foundation for the next wave of decentralized, transparent AI systems. 6. Learn More 📖 Technical blog: 💻 GitHub repo:

part 4 Gsenti Sentient Sentient Chat Explaining ROMA – Recursive Open Meta-Agent 1. What is ROMA? ROMA is an open-source framework for building meta-agents — systems that can orchestrate multiple smaller agents and tools to solve complex tasks. Instead of letting one AI model handle an entire large problem (which often fails due to complexity), ROMA applies a recursive approach: Parent nodes break a big goal into subtasks. Child nodes handle those subtasks and return results. All results are then combined into a final solution. 2. How does ROMA work? The architecture has four main components: Atomizer – decides whether a task is simple or requires decomposition. Planner – splits the complex task into smaller subtasks. Executor – runs the right tools/agents to complete each subtask. Aggregator – collects and synthesizes all results into one coherent answer. Because each node follows the same recursive logic, ROMA naturally scales as tasks become more complex. 3. Example Use Case – Deep Research Question: “Who are the top 5 NBA players by PPG in a season that have won both an NCAA and an NBA championship?” How ROMA handles it: Atomizer → identifies it as complex → needs decomposition. Planner → breaks it down: (1) find top NBA PPG seasons, (2) check NCAA champions, (3) check NBA champions, (4) combine filters. Executor → runs each search/tool for data. Aggregator → merges the results into the final answer. This creates a transparent, step-by-step reasoning process, unlike “black box” answers. 4. What Problem Does ROMA Solve? In long-horizon tasks, errors accumulate. A model may be 99% accurate at one step. But over 10 steps, success rates collapse due to compounding errors. Current agents are often opaque — hard to see where and why they failed. ROMA solves this by: Breaking tasks into clear logic chains, Making every step traceable, verifiable, and fixable. 5. Why ROMA Matters Open-source → available for anyone to build upon. Community-driven → empowering developers to create advanced multi-agent systems. Scalable → recursive logic adapts naturally to any task complexity. This makes ROMA not just a framework, but a foundation for the next wave of decentralized, transparent AI systems. 6. Learn More 📖 Technical blog: 💻 GitHub repo:

thoai66.ip

16,298 次观看 • 11 个月前

$We partnered with Harvey to train a model for Review Table, achieving state-of-the-art accuracy at a fraction of the cost and latency of frontier alternatives. Review Table is one of Harvey’s highest inference volume products. Training an open source model for production traffic required building a representative eval and understanding how real lawyers use the product. Our teams discuss the research process.$

We partnered with Harvey to train a model for Review Table, achieving state-of-the-art accuracy at a fraction of the cost and latency of frontier alternatives. Review Table is one of Harvey’s highest inference volume products. Training an open source model for production traffic required building a representative eval and understanding how real lawyers use the product. Our teams discuss the research process.

Applied Compute

33,017 次观看 • 12 天前

.SnowflakeDB is thrilled to announce #SnowflakeArctic: A state-of-the-art large language model uniquely designed to be the most open, enterprise-grade LLM on the market. This is a big step forward for open source LLMs. And it’s a big moment for Snowflake in our #AI journey as we continue to build best-in-class enterprise-grade products for our customers. The era of enterprise AI is here. 🚀

.SnowflakeDB is thrilled to announce #SnowflakeArctic: A state-of-the-art large language model uniquely designed to be the most open, enterprise-grade LLM on the market. This is a big step forward for open source LLMs. And it’s a big moment for Snowflake in our #AI journey as we continue to build best-in-class enterprise-grade products for our customers. The era of enterprise AI is here. 🚀

sridhar

243,792 次观看 • 2 年前

Introducing Agent Baseline: a vendor-neutral reference architecture for safely building, deploying, and operating AI agents in enterprise environments. Created with Snyk and Keycard, this open-source framework sets the minimum standard for agent safety:

Introducing Agent Baseline: a vendor-neutral reference architecture for safely building, deploying, and operating AI agents in enterprise environments. Created with Snyk and Keycard, this open-source framework sets the minimum standard for agent safety:

Docker

18,594 次观看 • 27 天前

Run state-of-the-art RAG applications locally on your computer with ollama and use all the fantastic open-source models like llama3, msk's awesome models, or Command R from Cohere With Verba 1.0, we put it all in your hands 🙌 Get on board for a wild open-source ride, we're bridging any moat as open-source is here to win

Run state-of-the-art RAG applications locally on your computer with ollama and use all the fantastic open-source models like llama3, msk's awesome models, or Command R from Cohere With Verba 1.0, we put it all in your hands 🙌 Get on board for a wild open-source ride, we're bridging any moat as open-source is here to win

Philip Vollet

41,450 次观看 • 2 年前

Today, we're launching Orpheus Multilingual, a family of open-source models that makes state-of-the-art TTS accessible to billions of new people! 🌎🌎 (1/5)

Today, we're launching Orpheus Multilingual, a family of open-source models that makes state-of-the-art TTS accessible to billions of new people! 🌎🌎 (1/5)

Elias

77,001 次观看 • 1 年前

Thrilled to see Amazon Web Services making a major contribution to the open source AI community with the launch of the Strands Agents, an open source AI agents SDK! The core of Strands is the simple agentic loop that connects the model and tools together, like the two strands of DNA. This model-driven approach to agent building eliminates the need for complex agent orchestration by embracing the capabilities of state-of-the-art models to plan, chain thoughts, call tools, and reflect. Providing open source tools and interoperability with open source protocols is an important part of our strategy to enable an agentic future. Can't wait to see what you build with Strands!

Thrilled to see Amazon Web Services making a major contribution to the open source AI community with the launch of the Strands Agents, an open source AI agents SDK! The core of Strands is the simple agentic loop that connects the model and tools together, like the two strands of DNA. This model-driven approach to agent building eliminates the need for complex agent orchestration by embracing the capabilities of state-of-the-art models to plan, chain thoughts, call tools, and reflect. Providing open source tools and interoperability with open source protocols is an important part of our strategy to enable an agentic future. Can't wait to see what you build with Strands!

Swami Sivasubramanian

32,185 次观看 • 1 年前

Open-sourcing Introspect: MIT-licensed Deep-Research for your internal data! Works with spreadsheets, databases, PDFs, and web search. Has a remarkably simple architecture – Sonnet agent armed with recursive tool calling and 3 default tools. Best for use-cases where you want to combine insights from SQL with unstructured data + data from the web. Launching a bunch of products built on top of of this soon, but wanted to open-source our core engine to give back to the community! 2 min demo below, links in comments

Open-sourcing Introspect: MIT-licensed Deep-Research for your internal data! Works with spreadsheets, databases, PDFs, and web search. Has a remarkably simple architecture – Sonnet agent armed with recursive tool calling and 3 default tools. Best for use-cases where you want to combine insights from SQL with unstructured data + data from the web. Launching a bunch of products built on top of of this soon, but wanted to open-source our core engine to give back to the community! 2 min demo below, links in comments

Rishabh Srivastava

71,563 次观看 • 1 年前