Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Introducing ♾OmniJARVIS, our latest venture to #AgentGPT, or vision-language-action (VLA) models for open-world instruction-following agents 🦾🕹️ tuning in 👉 by Team CraftJarvis, 🤿⏬

jeasinema's profile picture

Xiaojian Ma

2,402 subscribers

32,562 Aufrufe • vor 2 Jahren •via X (Twitter)

#AgentGPT
LIVE

Anya Rossi• Live Now

Private livecam show

8 Kommentare

Profilbild von Xiaojian Ma
Xiaojian Mavor 2 Jahren

🌟Our key insights into building more versatile VLAs: 💡♾OmniJARVIS emits **behavior token**, a skill representation that emerged from **self-supervised learning (SSL)** on massive replay (gaming, robotics, driving, etc) data. A de-tokenizer policy jointly learned with SSL will turn it into low-level actions. We choose to stay in between VLA down to producing motor commands directly (RT series @xiao_ted @QuanVng and folks, STEVE-1 @Shalev_lif), and VLA remains a task planner (SayCan, DEPS/JARVIS-1). ➡️ It offers a more compact and more situated/semantically richer interface between🧠"agent brain" (reasoning and planning) and the agent's 🏃"motor neurons" while assuring high-frequency motor control(~20Hz). ➡️ It echos Dieter Fox's (@NVIDIARobotics) recent talk at @CMU_Robotics. Yes, ♾OmniJARVIS is precisely the "middle ground" you hinted 🤗🤗

Profilbild von Xiaojian Ma
Xiaojian Mavor 2 Jahren

💡♾OmniJARVIS seeks to do native modeling on "VLA data". The idea is just intuitive: upon the multimodal dialogues being modeled by VLMs/MLMs, we further loop in 🏃**actions**(behaviors) interleaved within these dialogues -- we call this "multimodal interaction data". Technically, this adds a new modality "Action" over vision and language. Why interaction data modeling? This allows the unification of reasoning(self-talk), chat, and control, but the ultimate goal is enabling in-context agent learning😈😈, we're still working on it.

Profilbild von Xiaojian Ma
Xiaojian Mavor 2 Jahren

Just another word for the self-supervised behavior tokenizer/de-tokenizer. It inherits our SSL policy learning framework GROOT ( but adopts a discrete latent space (Finite-Scalar Quantizer @mentzer_f). Checkout my summary on GROOT

Profilbild von Xiaojian Ma
Xiaojian Mavor 2 Jahren

Very quick heads up on the results: 1⃣ Unifying reasoning, chat, and control enable better agent performance, especially on open-world tasks. 2⃣ FSQ-based behavior tokenizer is great! Consistent behaviours✅ Stable training ✅ Fast decoding ✅ 3⃣ ♾OmniJARVIS adheres to scaling law (first time in VLA?)

Profilbild von Xiaojian Ma
Xiaojian Mavor 2 Jahren

Wrapping up here. Calling in the Team CraftJarvis at and @PKU1898: @RealZihaoWang @liu_anji @YitaoLiang @ShaofeiCai. Checkout our series of generalist agent work below JARVIS-1

Profilbild von Xiaojian Ma
Xiaojian Mavor 2 Jahren

LEO

Profilbild von Xiaojian Ma
Xiaojian Mavor 2 Jahren

@AdeenaY8 guess you may be interested! We’ve uploaded it to daily papers 🤩

Profilbild von Martin Andrews
Martin Andrewsvor 2 Jahren

I'll be talking about this (briefly) at tonight's Machine Learning Singapore MeetUp ( One small thing I noticed : The Instruction Following table on the Project Page shows 'higher is better' (where it should be 'lower is better')

Ähnliche Videos

What if robots could improve themselves by learning from their own failures in the real-world? Introducing 𝗣𝗟𝗗 (𝗣𝗿𝗼𝗯𝗲, 𝗟𝗲𝗮𝗿𝗻, 𝗗𝗶𝘀𝘁𝗶𝗹𝗹) — a recipe that enables Vision-Language-Action (VLA) models to self-improve for high-precision manipulation tasks. PLD couples real-world residual reinforcement learning with standard supervised fine-tuning — letting robots discover, recover, and distill their own data flywheel. Quick 🧵
0:59

What if robots could improve themselves by learning from their own failures in the real-world? Introducing 𝗣𝗟𝗗 (𝗣𝗿𝗼𝗯𝗲, 𝗟𝗲𝗮𝗿𝗻, 𝗗𝗶𝘀𝘁𝗶𝗹𝗹) — a recipe that enables Vision-Language-Action (VLA) models to self-improve for high-precision manipulation tasks. PLD couples real-world residual reinforcement learning with standard supervised fine-tuning — letting robots discover, recover, and distill their own data flywheel. Quick 🧵

Wenli Xiao

185,486 Aufrufe • vor 10 Monaten

Vision-language models perform diverse tasks via in-context learning. Time for robots to do the same! Introducing In-Context Robot Transformer (ICRT): a robot policy that learns new tasks by prompting with robot trajectories, without any fine-tuning. [1/N]
0:25

Vision-language models perform diverse tasks via in-context learning. Time for robots to do the same! Introducing In-Context Robot Transformer (ICRT): a robot policy that learns new tasks by prompting with robot trajectories, without any fine-tuning. [1/N]

Max Fu

40,466 Aufrufe • vor 2 Jahren

🚀🚀🚀 Ever wondered what it takes for robots to handle real-world household tasks? long-horizon execution, deformable object dexterity, and unseen object generalization — meet GR-3, ByteDance Seed’s new Vision-Language-Action (VLA) model! GR-3 is a generalizable Vision-Language-Action (VLA) model with strong capabilities in complex long-horizon tasks. It understands unseen abstract concepts, manipulates deformable objects robustly, and adapts to novel settings with minimal human data. ✨ Generalization: Generalizes well to unseen objects, environments, and even instructions with abstract concepts. ✨ Long-Horizon Manipulation: Completes long-horizon tasks with strong instruction-following capabilities. ✨ Deformable Object Manipulation: Manipulate deformable objects robustly. Project Page: Arxiv: #ByteDance #ByteDanceSeed #GR3 #VLA #Robotics #FoundationModels
4:10

🚀🚀🚀 Ever wondered what it takes for robots to handle real-world household tasks? long-horizon execution, deformable object dexterity, and unseen object generalization — meet GR-3, ByteDance Seed’s new Vision-Language-Action (VLA) model! GR-3 is a generalizable Vision-Language-Action (VLA) model with strong capabilities in complex long-horizon tasks. It understands unseen abstract concepts, manipulates deformable objects robustly, and adapts to novel settings with minimal human data. ✨ Generalization: Generalizes well to unseen objects, environments, and even instructions with abstract concepts. ✨ Long-Horizon Manipulation: Completes long-horizon tasks with strong instruction-following capabilities. ✨ Deformable Object Manipulation: Manipulate deformable objects robustly. Project Page: Arxiv: #ByteDance #ByteDanceSeed #GR3 #VLA #Robotics #FoundationModels

Xiao Ma

46,323 Aufrufe • vor 1 Jahr

MolmoAct2 runs zero-shot on an SO-ARM101, no training required 🦾 Ai2 open Action Reasoning Model is now in LeRobot with the full lifecycle covered: fine-tuning (full or LoRA), evaluation, and real-robot deployment. It pairs a Molmo2-ER vision-language backbone with a flow-matching action expert to turn images, language, and proprioceptive state into action chunks. The best part: ready-made checkpoints ship with calibration correction baked in, so you can point it at your SO-100/101 and just watch it work. Inference fits in ~12GB at bf16, and LoRA fine-tuning runs on a single 24GB GPU. Big thanks to the Ai2 team for building this in the open.
0:30

MolmoAct2 runs zero-shot on an SO-ARM101, no training required 🦾 Ai2 open Action Reasoning Model is now in LeRobot with the full lifecycle covered: fine-tuning (full or LoRA), evaluation, and real-robot deployment. It pairs a Molmo2-ER vision-language backbone with a flow-matching action expert to turn images, language, and proprioceptive state into action chunks. The best part: ready-made checkpoints ship with calibration correction baked in, so you can point it at your SO-100/101 and just watch it work. Inference fits in ~12GB at bf16, and LoRA fine-tuning runs on a single 24GB GPU. Big thanks to the Ai2 team for building this in the open.

LeRobot

22,200 Aufrufe • vor 1 Monat

🚀 MiniCPM enters the physical world — enabling robots to understand, remember, and act. We open-source MiniCPM-Robot, our first embodied AI model series, including: 🤖 MiniCPM-RobotManip — a 1.5B general-purpose Vision-Language-Action (VLA) model for robotic manipulation. 🐕 MiniCPM-RobotTrack — a compact model for real-world target tracking. ⚡ PhyAI — a high-performance inference framework built for embodied models. Together, they bring efficient, practical, and open embodied intelligence closer to real-world robots. ⭐ GitHub: 🤗 MiniCPM-RobotManip: 🤗 MiniCPM-RobotTrack:
1:17

🚀 MiniCPM enters the physical world — enabling robots to understand, remember, and act. We open-source MiniCPM-Robot, our first embodied AI model series, including: 🤖 MiniCPM-RobotManip — a 1.5B general-purpose Vision-Language-Action (VLA) model for robotic manipulation. 🐕 MiniCPM-RobotTrack — a compact model for real-world target tracking. ⚡ PhyAI — a high-performance inference framework built for embodied models. Together, they bring efficient, practical, and open embodied intelligence closer to real-world robots. ⭐ GitHub: 🤗 MiniCPM-RobotManip: 🤗 MiniCPM-RobotTrack:

OpenBMB

330,472 Aufrufe • vor 1 Monat

(1/12) Introducing Kite AI: a foundational AI layer to open the world to decentralized intelligence. Built by the team behind ZettaBlock, today we are launching to unlock fair access to essential AI assets: data, models and agents for all. Here's how. 🧵👇
0:25

(1/12) Introducing Kite AI: a foundational AI layer to open the world to decentralized intelligence. Built by the team behind ZettaBlock, today we are launching to unlock fair access to essential AI assets: data, models and agents for all. Here's how. 🧵👇

KITE AI

3,416,691 Aufrufe • vor 1 Jahr

The next evolution: VLA+ models Just yesterday Microsoft Research released Rho-alpha (ρα) – their first robotics model, built on the Phi family. While most Vision-Language-Action (VLA) models stop at vision and language, Rho-alpha adds: ▪️ Tactile sensing to feel objects during manipulation ▪️ Online learning that lets it improve from human corrections (via teleoperation, 3D mouse or other tools) in real-time even after deployment. Both these sides make adaptability central rather than incidental. Microsoft calls it a VLA+ model, positioning it as an extension beyond what current VLA systems support. ➡️ Today Rho-alpha can control dual-arm robot setups to perform tasks such as: • Manipulating the BusyBox following natural-language instructions • Plug insertion • Toolbox packing and object arrangement with bimanual coordination But to understand why this "plus" matters, we need to understand what came before. Here, we'll take you through the entire landscape of VLA models – Gemini Robotics, π0, SmolVLA, Helix, ACoT-VLA and others:
0:24

The next evolution: VLA+ models Just yesterday Microsoft Research released Rho-alpha (ρα) – their first robotics model, built on the Phi family. While most Vision-Language-Action (VLA) models stop at vision and language, Rho-alpha adds: ▪️ Tactile sensing to feel objects during manipulation ▪️ Online learning that lets it improve from human corrections (via teleoperation, 3D mouse or other tools) in real-time even after deployment. Both these sides make adaptability central rather than incidental. Microsoft calls it a VLA+ model, positioning it as an extension beyond what current VLA systems support. ➡️ Today Rho-alpha can control dual-arm robot setups to perform tasks such as: • Manipulating the BusyBox following natural-language instructions • Plug insertion • Toolbox packing and object arrangement with bimanual coordination But to understand why this "plus" matters, we need to understand what came before. Here, we'll take you through the entire landscape of VLA models – Gemini Robotics, π0, SmolVLA, Helix, ACoT-VLA and others:

Turing Post

62,494 Aufrufe • vor 7 Monaten

Yann LeCun (Chief AI Scientist, Meta, Yann LeCun), Pim de Witte (CEO, General Intuition), and Aude Durand (Kyutai, Aude Durand), talk about world models, embodied agents, Yann's new company, and the limitations of LLMs 0:00 - Introduction to World Models 5:00 - Why World Models, Intuition & Introducing Yann's new company 10:00 - Architectures + Merging Language & Interaction Data towards General Agents 20:00 - Open Source, Sovereign AI & kyutai Partnership Keynote for #aiPULSE2025 at Station F in Paris 🇫🇷
29:20

Yann LeCun (Chief AI Scientist, Meta, Yann LeCun), Pim de Witte (CEO, General Intuition), and Aude Durand (Kyutai, Aude Durand), talk about world models, embodied agents, Yann's new company, and the limitations of LLMs 0:00 - Introduction to World Models 5:00 - Why World Models, Intuition & Introducing Yann's new company 10:00 - Architectures + Merging Language & Interaction Data towards General Agents 20:00 - Open Source, Sovereign AI & kyutai Partnership Keynote for #aiPULSE2025 at Station F in Paris 🇫🇷

General Intuition

111,582 Aufrufe • vor 9 Monaten

🔥 #ICRA2026 Best Paper Finalist The era of "robot VLA = single-arm gripper" is ending. Introducing Dexora — the first open-source Vision-Language-Action system for dual-arm, dual-hand, 36-DoF dexterous manipulation. 🦾 Dual Arms 🖐️ Dual Hands 🎯 36 DoF Control 🌍 Open Source Trained on: • 100K simulated trajectories • 10K real-world demonstrations Dexora achieves: ✓ 90%+ success on basic manipulation ✓ Strong dexterous manipulation performance ✓ Cross-embodiment generalization Our key hypothesis: Train on the hardest embodiment. Transfer to simpler robots later. Instead of scaling up gripper policies, we train directly in the most expressive action space and project downward to simpler embodiments. This may be a practical path toward universal robot controllers. 🎥 Demos: 📄 Paper:
2:58

🔥 #ICRA2026 Best Paper Finalist The era of "robot VLA = single-arm gripper" is ending. Introducing Dexora — the first open-source Vision-Language-Action system for dual-arm, dual-hand, 36-DoF dexterous manipulation. 🦾 Dual Arms 🖐️ Dual Hands 🎯 36 DoF Control 🌍 Open Source Trained on: • 100K simulated trajectories • 10K real-world demonstrations Dexora achieves: ✓ 90%+ success on basic manipulation ✓ Strong dexterous manipulation performance ✓ Cross-embodiment generalization Our key hypothesis: Train on the hardest embodiment. Transfer to simpler robots later. Instead of scaling up gripper policies, we train directly in the most expressive action space and project downward to simpler embodiments. This may be a practical path toward universal robot controllers. 🎥 Demos: 📄 Paper:

Hao Zhao

17,474 Aufrufe • vor 2 Monaten

LARP: Language-Agent Role Play for Open-World Games paper page: Language agents have shown impressive problem-solving skills within defined settings and brief timelines. Yet, with the ever-evolving complexities of open-world simulations, there's a pressing need for agents that can flexibly adapt to complex environments and consistently maintain a long-term memory to ensure coherent actions. To bridge the gap between language agents and open-world games, we introduce Language Agent for Role-Playing (LARP), which includes a cognitive architecture that encompasses memory processing and a decision-making assistant, an environment interaction module with a feedback-driven learnable action space, and a postprocessing method that promotes the alignment of various personalities. The LARP framework refines interactions between users and agents, predefined with unique backgrounds and personalities, ultimately enhancing the gaming experience in open-world contexts. Furthermore, it highlights the diverse uses of language models in a range of areas such as entertainment, education, and various simulation scenarios.
1:03

LARP: Language-Agent Role Play for Open-World Games paper page: Language agents have shown impressive problem-solving skills within defined settings and brief timelines. Yet, with the ever-evolving complexities of open-world simulations, there's a pressing need for agents that can flexibly adapt to complex environments and consistently maintain a long-term memory to ensure coherent actions. To bridge the gap between language agents and open-world games, we introduce Language Agent for Role-Playing (LARP), which includes a cognitive architecture that encompasses memory processing and a decision-making assistant, an environment interaction module with a feedback-driven learnable action space, and a postprocessing method that promotes the alignment of various personalities. The LARP framework refines interactions between users and agents, predefined with unique backgrounds and personalities, ultimately enhancing the gaming experience in open-world contexts. Furthermore, it highlights the diverse uses of language models in a range of areas such as entertainment, education, and various simulation scenarios.

AK

143,974 Aufrufe • vor 2 Jahren

Introducing WALL-WM, our open-source World Model for embodied AI and the next piece of our open-source robotics stack. Carving World Action Modeling at the Event Joints Read the blog: Why it matters WALL-WM shifts robot world modeling from fixed-length action chunks to event-grounded video-action pretraining. It learns around events like reaching, contact, grasping, lifting, moving, and placing, so language, vision, and action align more naturally. Why you should care WALL-WM brings together: •Event-grounded VLA pretraining •Prior-aligned video-action architecture •Wan-based video tower + randomly initialized action DiT •Multi-view perception with sight-cone masking, tube patch masking, and Camera RoPE •Event Mode for variable-length execution •Unified Mode with Staircase Decoding •DMuon for large-scale training The goal: help robots learn what physically matters, not just what happens in the next fixed slice of time. Code (coming soon): #opensource #EmbodiedAI
1:45

Introducing WALL-WM, our open-source World Model for embodied AI and the next piece of our open-source robotics stack. Carving World Action Modeling at the Event Joints Read the blog: Why it matters WALL-WM shifts robot world modeling from fixed-length action chunks to event-grounded video-action pretraining. It learns around events like reaching, contact, grasping, lifting, moving, and placing, so language, vision, and action align more naturally. Why you should care WALL-WM brings together: •Event-grounded VLA pretraining •Prior-aligned video-action architecture •Wan-based video tower + randomly initialized action DiT •Multi-view perception with sight-cone masking, tube patch masking, and Camera RoPE •Event Mode for variable-length execution •Unified Mode with Staircase Decoding •DMuon for large-scale training The goal: help robots learn what physically matters, not just what happens in the next fixed slice of time. Code (coming soon): #opensource #EmbodiedAI

X Square Robot

42,165 Aufrufe • vor 3 Monaten

We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.
2:15

We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.

Physical Intelligence

440,982 Aufrufe • vor 5 Monaten

Robot AI brains, aka Vision-Language-Action models, cannot adapt to new tasks as easily as LLMs like Gemini, ChatGPT, or Grok. LLMs can adapt quickly with their in-context learning (ICL) capabilities. But can we inject ICL abilities into a pre-trained VLA like pi0? Yes! Introducing RICL (Retraining for In-Context Learning), our Conference on Robot Learning (CoRL) 2025 paper. Our RICL-pi0 model can adapt to unseen objects, novel motions, and new scenes with just ICL and RAG (retrieval-augmented generation). RICL-pi0 also boosts performance on the long-tail of tasks. A quick 1 minute video summary:
1:03

Robot AI brains, aka Vision-Language-Action models, cannot adapt to new tasks as easily as LLMs like Gemini, ChatGPT, or Grok. LLMs can adapt quickly with their in-context learning (ICL) capabilities. But can we inject ICL abilities into a pre-trained VLA like pi0? Yes! Introducing RICL (Retraining for In-Context Learning), our Conference on Robot Learning (CoRL) 2025 paper. Our RICL-pi0 model can adapt to unseen objects, novel motions, and new scenes with just ICL and RAG (retrieval-augmented generation). RICL-pi0 also boosts performance on the long-tail of tasks. A quick 1 minute video summary:

Kaustubh Sridhar

52,158 Aufrufe • vor 1 Jahr

Introducing the composable reputation API for agents. The FairScale Agent API is now open to any team building on Solana Gate access, transactions and assess credibility in real time. Score any agent or wallet based on behaviour, deployer, counterparties, and network. Use our FairScore, or define your own by weighting features through a custom scoring endpoint.
0:52

Introducing the composable reputation API for agents. The FairScale Agent API is now open to any team building on Solana Gate access, transactions and assess credibility in real time. Score any agent or wallet based on behaviour, deployer, counterparties, and network. Use our FairScore, or define your own by weighting features through a custom scoring endpoint.

FairScale

16,896 Aufrufe • vor 5 Monaten

Can vision-language-action (VLA) models generalize to diverse OOD tasks and align with customized objectives? 🤔 🚀 We introduce GRAPE, a plug-and-play algorithm to generalize robot policies via preference alignment. GRAPE unfolds three benefits to boost the generalizability of VLAs: 👉1. GRAPE aligns VLAs on a trajectory level and endows the model with the ability for global decision-making, instead of merely cloning behavior; 👉2. GRAPE implicitly models reward from both successful and failed trials to boost generalizability to diverse tasks; 👉3. GRAPE adopts a scalable preference synthesis algorithm to rank trajectories with preferences that align with arbitrary objectives. Our experiments on a diverse array of real-world and simulated robotic tasks reveal: 1⃣GRAPE enhances the performance of state-of-the-art VLA models, increasing success rates on in-domain and unseen manipulation tasks by 51.79% and 60.36%; 2⃣GRAPE is versatile to be aligned with diverse objectives and reduce collision rates by 44.31% or rollout length by 11.15% when aligning towards safer or more efficient manipulation policy, respectively. Check out our full project for more details: 🔥 Paper: 🔥 Project: 🔥 Code:
1:06

Can vision-language-action (VLA) models generalize to diverse OOD tasks and align with customized objectives? 🤔 🚀 We introduce GRAPE, a plug-and-play algorithm to generalize robot policies via preference alignment. GRAPE unfolds three benefits to boost the generalizability of VLAs: 👉1. GRAPE aligns VLAs on a trajectory level and endows the model with the ability for global decision-making, instead of merely cloning behavior; 👉2. GRAPE implicitly models reward from both successful and failed trials to boost generalizability to diverse tasks; 👉3. GRAPE adopts a scalable preference synthesis algorithm to rank trajectories with preferences that align with arbitrary objectives. Our experiments on a diverse array of real-world and simulated robotic tasks reveal: 1⃣GRAPE enhances the performance of state-of-the-art VLA models, increasing success rates on in-domain and unseen manipulation tasks by 51.79% and 60.36%; 2⃣GRAPE is versatile to be aligned with diverse objectives and reduce collision rates by 44.31% or rollout length by 11.15% when aligning towards safer or more efficient manipulation policy, respectively. Check out our full project for more details: 🔥 Paper: 🔥 Project: 🔥 Code:

Huaxiu Yao

20,071 Aufrufe • vor 1 Jahr

Scaling vision-language-action (VLA) models to high-DoF dexterous hands has long been a "holy grail" challenge due to the high-dimensional action space and data scarcity. As a wrap up of the year 2025, we are releasing GR-Dexter, a holistic hardware-model-data framework for generalist manipulation on a bimanual dexterous-hand robot. This is the first VLA system to achieve: ✅ High-DoF Control: Managing a 56-DoF bimanual system (21-DoF per hand). ✅ Long-Horizon Tasks with tool use: Vacuuming, bread serving with tongs, and table decluttering. ✅ Open-World Generalization: Robust performance with unseen objects and abstract instructions. Project page: ArXiv:
3:52

Scaling vision-language-action (VLA) models to high-DoF dexterous hands has long been a "holy grail" challenge due to the high-dimensional action space and data scarcity. As a wrap up of the year 2025, we are releasing GR-Dexter, a holistic hardware-model-data framework for generalist manipulation on a bimanual dexterous-hand robot. This is the first VLA system to achieve: ✅ High-DoF Control: Managing a 56-DoF bimanual system (21-DoF per hand). ✅ Long-Horizon Tasks with tool use: Vacuuming, bread serving with tongs, and table decluttering. ✅ Open-World Generalization: Robust performance with unseen objects and abstract instructions. Project page: ArXiv:

Xiao Ma

93,908 Aufrufe • vor 8 Monaten

Introducing Theoriq’s AlphaSwarm! ⚡️ We’re thrilled to give developers access to a starter toolkit for building AI-powered trading agents in DeFi (AiFi)! 🦾 AlphaSwarm streamlines agent and swarm development, making it easier to build, execute, and refine collaborative agents that can analyze real-time market signals, and autonomously execute trades across multiple chains. Check out our latest blog for more details! 👇 You can explore the toolkit directly in Theoriq’s GitHub: Or if you’re a developer interested in building the future of AiFi, join our dev community in Discord:
0:30

Introducing Theoriq’s AlphaSwarm! ⚡️ We’re thrilled to give developers access to a starter toolkit for building AI-powered trading agents in DeFi (AiFi)! 🦾 AlphaSwarm streamlines agent and swarm development, making it easier to build, execute, and refine collaborative agents that can analyze real-time market signals, and autonomously execute trades across multiple chains. Check out our latest blog for more details! 👇 You can explore the toolkit directly in Theoriq’s GitHub: Or if you’re a developer interested in building the future of AiFi, join our dev community in Discord:

Theoriq

103,922 Aufrufe • vor 1 Jahr

World models have a causality problem. Realistic videos are not enough. A world model should predict the future caused by an action, not just a plausible future. We find that many latent-action world models generate convincing videos while barely responding to the supplied action. The root cause lies in Latent Action Models (LAMs): reconstruction objectives entangle action-induced dynamics with action-irrelevant visual changes, producing visually confounded latent actions. Our solution is CD-LAM (Causally Debiased Latent Action Model). It cleanses latent action representations before pre-training begins, requiring zero changes to backbone architectures, latent dimensions, or action interfaces. Key Benchmark Results: - Action Controllability: Cuts action-following error by >30% while simultaneously enhancing visual fidelity. - Extreme Sample Efficiency: Achieves baseline performance in just 3,000 post-training steps instead of 50,000 - a >10x speedup. By removing visual confounding, CD-LAM bridges the gap between passive video prediction and actionable causal intelligence for robotics. The next bottleneck for world models isn’t realism. It’s causality. Paper, project page and additional resources in the reply below. #WorldModels #EmbodiedAI #Robotics #CausalAI
0:53

World models have a causality problem. Realistic videos are not enough. A world model should predict the future caused by an action, not just a plausible future. We find that many latent-action world models generate convincing videos while barely responding to the supplied action. The root cause lies in Latent Action Models (LAMs): reconstruction objectives entangle action-induced dynamics with action-irrelevant visual changes, producing visually confounded latent actions. Our solution is CD-LAM (Causally Debiased Latent Action Model). It cleanses latent action representations before pre-training begins, requiring zero changes to backbone architectures, latent dimensions, or action interfaces. Key Benchmark Results: - Action Controllability: Cuts action-following error by >30% while simultaneously enhancing visual fidelity. - Extreme Sample Efficiency: Achieves baseline performance in just 3,000 post-training steps instead of 50,000 - a >10x speedup. By removing visual confounding, CD-LAM bridges the gap between passive video prediction and actionable causal intelligence for robotics. The next bottleneck for world models isn’t realism. It’s causality. Paper, project page and additional resources in the reply below. #WorldModels #EmbodiedAI #Robotics #CausalAI

Biwei Huang

14,767 Aufrufe • vor 1 Monat

Introducing our unified Voice Agent API! ⚡️ Quickly and easily build voice agents that listen, think, and respond in real-time, as naturally as a human can. Powered by the industry's fastest, most performant speech recognition and voice synthesis models to deliver: -Natural-sounding real-time conversations -Revolutionary interruption handling -Choice of open source, closed source, or BYO LLM -Low cost See our drive-thru agent in action, smoothly handling interruptions and complex orders in the noisy streets of SF. Learn how to get access (🧵)
1:59

Introducing our unified Voice Agent API! ⚡️ Quickly and easily build voice agents that listen, think, and respond in real-time, as naturally as a human can. Powered by the industry's fastest, most performant speech recognition and voice synthesis models to deliver: -Natural-sounding real-time conversations -Revolutionary interruption handling -Choice of open source, closed source, or BYO LLM -Low cost See our drive-thru agent in action, smoothly handling interruptions and complex orders in the noisy streets of SF. Learn how to get access (🧵)

Deepgram

726,214 Aufrufe • vor 1 Jahr