🚨 New: Integrating Harbor (Harbor Framework) for end-to-end Computer-Use... evaluation(for Windows and Linux) at scale with Thinking Machines' Tinker, OSWorld, Daytona, and bare-metal servers. We just added support for Computer Use, Tinker, and OSWorld to Harbor - a framework for evaluating agents and generating RL training data by running large-scale rollouts across parallel sandboxed environments and collecting trajectories for SFT and RL. Repo and blogpost below 👇show more

Introducing RL Environment Creator Skill Now any one can... create RL environments $ npx skills add adithya-s-k/RL_Envs_101 > You can create environments across multiple frameworks like OpenEnv, OpenReward, Verifiers, NemoGym ... > the repo has live working examples of environments that your coding agent can reference > The skill is design to first understand what type of model you are training and create an environment while keeping that in mind ps. There’s a lot more to building RL environments that can be used for training. One major aspect is the data, which this skill can’t directly solve. However, the skill will help with implementing tools, rewards, and other components of an RL environment, making it easier to go from idea to implementation quickly across different frameworks. Let me know if you’d be interested in a detailed, end-to-end blog/tutorial on building an environment and actually training a model for a useful use case.show more

Throughout my journey in developing multimodal models, I’ve always... wanted a framework that lets me plug & play modality encoders/decoders on top of an auto-regressive LLM. I want to prototype fast, try new architectures, and have my demo files scale effortlessly — with full support for parallelism and optimization. Not just to hack⚙️, but also to scale🚀. So finally we built it for ourselves. LMMs-Engine: a lean, efficient framework built to train unified multimodal model at scale. From Qwen LLM, VLM, LLaVA-OV, and WanVideo, to unified models like Qwen-Omni and BAGEL — plus Linear-Attn GDN and research prototypes like RAE and SiT - all under one modular system that seamlessly integrates diverse datasets and optimization strategies. Powered by FSDP2 multi-dim parallelism, Ulysses sequence parallel, Flash-Attention, Liger Kernels, and Native Sparse Attention (also with bonus support for the Muon optimizer for all models).show more

Microsoft presents Windows Agent Arena Evaluating Multi-Modal OS Agents... at Scale discuss: Large language models (LLMs) show remarkable potential to act as computer agents, enhancing human productivity and software accessibility in multi-modal tasks that require planning and reasoning. However, measuring agent performance in realistic environments remains a challenge since: (i) most benchmarks are limited to specific modalities or domains (e.g. text-only, web navigation, Q&A, coding) and (ii) full benchmark evaluations are slow (on order of magnitude of days) given the multi-step sequential nature of tasks. To address these challenges, we introduce the Windows Agent Arena: a reproducible, general environment focusing exclusively on the Windows operating system (OS) where agents can operate freely within a real Windows OS and use the same wide range of applications, tools, and web browsers available to human users when solving tasks. We adapt the OSWorld framework (Xie et al., 2024) to create 150+ diverse Windows tasks across representative domains that require agent abilities in planning, screen understanding, and tool usage. Our benchmark is scalable and can be seamlessly parallelized in Azure for a full benchmark evaluation in as little as 20 minutes. To demonstrate Windows Agent Arena's capabilities, we also introduce a new multi-modal agent, Navi. Our agent achieves a success rate of 19.5% in the Windows domain, compared to 74.5% performance of an unassisted human. Navi also demonstrates strong performance on another popular web-based benchmark, Mind2Web. We offer extensive quantitative and qualitative analysis of Navi's performance, and provide insights into the opportunities for future research in agent development and data generation using Windows Agent Arena.show more

Today, we released Lyra 2.0, a framework for generating... persistent, explorable 3D worlds at scale, from NVIDIA Research. Generating large-scale, complex environments is difficult for AI models. Current models often “forget” what spaces look like and lose track of movement over time, causing objects to shift, blur, or appear inconsistent. This prevents them from creating the reliable 3D environments required for downstream simulations. Lyra 2.0 solves these issues by: ✅ Maintaining per-frame 3D geometry to retrieve past frames and establish spatial correspondences ✅ Using self-augmented training to correct its own temporal drifting. Lyra 2.0 turns an image into a 3D world you can walk through, look back, and drop a robot into for real-time rendering, simulation, and immersive applications. ➡️ Learn more: 📄 Read the paper:show more

New research from Databricks: LLMs Can Learn to Reason... via Off-Policy RL Optimal Advantage-based Policy Optimization with Lagged Inference policy (OAPL) shows you don’t need strict on-policy training to improve reasoning. It matches or beats Group Relative Policy Optimization (GRPO), stays stable with large policy lag, and uses ~3× fewer training generations. For Databricks customers, it’s a simpler, practical, and equally powerful approach to RL that Databricks is pioneering internally — and bringing directly to Databricks customers, so enterprises can improve agents using the same methods we use for our in-house agents, without complex infrastructure changes.show more

BEAMDOJO is a new RL framework developed by Chinese... researchers that teaches humanoid robots to walk on tricky terrains like stepping blocks. It uses a two-stage training process: a specialized reward system, and LiDAR mapping for precise foot placement.show more

The ocean is a natural resource and treasure for... human beings and a blue harbor for marine life. Let's look at the beautiful sea life and listen to the sound of the sea. #sea #ocean #environment #seaprotectionshow more

🚨Current scalable RL algos train a policy w/o value... func, which is limiting with learning in open-ended, non-stationary, dynamic environments. But, how to scale value-based RL with more data/compute is unclear... Not anymore: presenting scaling laws for value-based RL 🧵⬇️show more

We’re incredibly excited to launch Open Benchmarks Grants, a... new program committing $3M in grants to fund new open source benchmarks advancing agentic AI. We’re partnering up with Hugging Face, Together AI, Prime Intellect, Factory HQ, Harbor Framework, and PyTorch to support academic and open-source teams as they define and advance the AI frontier.show more

Meth and harbor freight had something to do with this

It's pretty neat to easily control a Linux computer... in the cloud. For this one, I added an AI sidebar which can control and navigate pages.show more

China just took AI infrastructure underwater. The country has... reportedly launched a wind-powered underwater data center near Shanghai, designed to cool AI servers using seawater instead of traditional cooling systems 🌊🤖 Around 2,000 servers are said to be sealed inside submarine-grade modules, helping reduce land use, water consumption, and cooling energy. The project is powered by offshore wind and built for AI workloads, big data, and large-scale computing. Why it matters? AI is creating massive demand for electricity, cooling, and infrastructure. If underwater data centers prove reliable, they could become a new way to scale AI while using less energy. But the challenge is huge: corrosion, maintenance, sea conditions, and long-term reliability still need to be proven.show more

🤖 ExoBrain is a compute device built for large-scale... AI collaboration, supporting model training, inference, and long-running Agents With a standardized architecture and continuous execution capability, it delivers efficient, reliable compute for AI systems ⚡ From one-time calls to continuous operation, ExoBrain enables AI to execute persistently, produce ongoing outputs, and generate long-term value #ExoBrain #AICompute #AIAgents #AGIshow more

this new AI agent can work for you 24/7... and.. it's 100% free Simular just dropped their computer use AI agent and open sourced it 5 incredible use cases: 1. plan a 7 day from Singapore to Paris trip with a $5k budgetshow more

Generalist robots need multimodal learning—fusing vision, touch, and body... motion to handle unstructured worlds. 🦾 NVIDIA Isaac Lab is a GPU-accelerated, open-source simulation framework for robot learning that unifies physics, rendering, sensing, and parallel computing to train robot policies at scale. Learn more 🔗 #NVIDIAResearchshow more

A Rerun Viewer for the DROID Dataset! DROID: A... Large-Scale In-The-Wild Robot Manipulation Dataset is a robot manipulation dataset by Alexander Khazatsky et al. with 76k demonstration trajectories or 350h of interaction data, collected across 564 scenes and 86 tasks.show more

RL X-mas came early. 🎄 For too long, building... powerful AI agents with Reinforcement Learning has been blocked by GPU scarcity and complex infrastructure. That ends today. Introducing Serverless RL from wandb, powered by CoreWeave! We're making RL accessible to all.show more

Greene: If these Democrat governors and mayors want to... use their federal dollars and use this funding to harbor illegal criminal aliens then, yeah, we're coming after their money, and they don't deserve a single penny of it.show more

"Grok Build" and "Grok Computer" are expected to launch... simultaneously, highly likely as unified desktop applications dropping for both macOS and Windows.show more

🐦Chirpley is excited to share that we are integrating... with Sei 🔴 to enhance the experience for Sei users! First step is making Sei a preferred payment option on our platform, creating added convenience and benefits for the Sei community. Additionally, we aim to position Chirpley as the influencer hub within the Sei ecosystem, fostering opportunities to onboard new users and support the gaming community at scale.show more