Xiaolong Wang
1.5K posts
@xiaolonw
Co-founder of Assured Robot Intelligence (ARI) Associate Professor @UCSDJacobs Postdoc @berkeley_ai PhD @CMU_Robotics
Ever want to have a single policy to control diverse robots as well as different dexterous hands, or to observe the emergent behavior under cross embodiment training? Introducing our #CVPR2026 paper XL-VLA, Cross-Hand Latent Representation for Vision-Language-Action Models.
Ever want to have a single policy to control diverse robots as well as different dexterous hands, or to observe the emergent behavior under cross embodiment training? Introducing our #CVPR2026 paper XL-VLA, Cross-Hand Latent Representation for Vision-Language-Action Models.
Holiday cooking finally ready to serve! 🥳 Introducing DFlash — speculative decoding with block diffusion. 🚀 6.2× lossless speedup on Qwen3-8B ⚡ 2.5× faster than EAGLE-3 Diffusion vs AR doesn’t have to be a fight. At today’s stage: • dLLMs = fast, highly parallel, but lossy • AR LLMs = accurate, sequential, but slow DFlash = diffusion drafts, AR verifies.
Can we bridge the Sim-to-Real gap in complex manipulation without explicit system ID? 🤖 Presenting Contact-Aware Neural Dynamics — a diffusion-based framework that grounds simulation with real-world touch. Implicit Alignment: No tedious parameter tuning. Tactile-Driven: Captures non-smooth contact events. Consistent: Stable predictions in contact-rich tasks.
How to get AI to make discoveries on open scientific problems? Most methods just improve the prompt with more attempts. But the AI itself doesn't improve. With test-time training, AI can continue to learn on the problem it’s trying to solve: test-time-training.github.io/discover.pdf
How to get AI to make discoveries on open scientific problems? Most methods just improve the prompt with more attempts. But the AI itself doesn't improve. With test-time training, AI can continue to learn on the problem it’s trying to solve: test-time-training.github.io/discover.pdf
LLM memory is considered one of the hardest problems in AI. All we have today are endless hacks and workarounds. But the root solution has always been right in front of us. Next-token prediction is already an effective compressor. We don’t need a radical new architecture. The missing piece is to continue training the model at test-time, using context as training data. Our full release of End-to-End Test-Time Training (TTT-E2E) with @NVIDIAAI, @AsteraInstitute, and @StanfordAILab is now available. Blog: nvda.ws/4syfyMN Arxiv: arxiv.org/abs/2512.23675 This has been over a year in the making with @arnuvtandon and an incredible team.
What makes robot hands dexterous? 🤖🖐️ We generate robot hands + control, sim-to-real, in under 24 hours. Paper: Cross-Embodied Co-Design for Dexterous Hands 🔥 Rapid evaluation w/ cross-embodied policies 🦾 Open-source modular hand platform 💡 Automated full-hand generation
Our new paper, “End-to-End Test-Time Training for Long Context,” is a step towards continual learning in language models. We introduce a new method that blurs the boundary between training and inference. At test-time, our model continues learning from given context using the same next-token prediction objective as training. With this end-to-end objective, our model can efficiently compress substantial context into its weights and still use it effectively, unlocking extremely long context windows for complex reasoning and applications in agents and robotics. Paper: test-time-training.github.io/e2e.pdf Code: github.com/test-time-trai…
The Million Robot Bet: Why Enterprise Wins Before Homes Hugh Nguyen, Partner, Automotive Technology & Mobility, @KPMG and @LerrelPinto, Co-Founder, Assured Robot Intelligence (ARI) joined Grayson Brulte on The Road to Autonomy podcast to discuss why the immediate future of humanoid robotics lies in enterprise applications, rather than consumer homes. Episode Chapters 0:00 Humanoid Robot Market 6:44 Humanoid Due Diligence 9:40 Humanoid Value Chain 12:08 Humanoids Size and Hands 1 6:52 Building Humanoids 18:52 Humanoid Personalities 20:24 Managing Humanoid Risk 22:24 Humanoid Fleets 25:36 Humanoid Use Cases 29:58 China 33:20 Humanoid Policy 38:42 Chips 45:44 Deploying Humanoids in the Workplace 49:28 Future of Humanoids
