Loading video...

Video Failed to Load

Go Home

Reasoning VLAs can think. They just can't think fast. Until now. Introducing FlashDrive⚡ 🚀 716 ms → 159 ms on RTX PRO 6000 (up to 5.7×) ✅ Zero accuracy loss FlashDrive = streaming inference + DFlash speculative reasoning + ParoQuant W4A8 Real-time reasoning for autonomous driving is here!

zhijianliu_'s profile picture

Zhijian Liu

6,471 subscribers

164,594 views • 2 months ago •via X (Twitter)

News & PoliticsScience & TechnologySports
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

ParoQuant just got a big upgrade 🚀 ✅ Supports the new Qwen3.5 models ⚡ Now runs on MLX (fast local inference on Apple Silicon) 🧠 Preserves reasoning quality with 4-bit quantization We also built an agent demo running locally on my 4-year-old M2 Max. Can't wait to upgrade to an M5 Max and see what kind of magic we can do. ✨
0:46

ParoQuant just got a big upgrade 🚀 ✅ Supports the new Qwen3.5 models ⚡ Now runs on MLX (fast local inference on Apple Silicon) 🧠 Preserves reasoning quality with 4-bit quantization We also built an agent demo running locally on my 4-year-old M2 Max. Can't wait to upgrade to an M5 Max and see what kind of magic we can do. ✨

Zhijian Liu

49,004 views • 3 months ago

💨 How fast can an autonomous vehicle think? With Alpamayo 1, NVIDIA's 10B-parameter chain-of-thought reasoning model, the distilled version can reason in real time. Hear Marco Pavone (Marco Pavone), Yan Wang, Yurong You, and Wenhao Ding from our AV Research team break down Alpamayo 1 and what's next for reasoning in autonomous driving. 🔁 Watch the replay:
0:33

💨 How fast can an autonomous vehicle think? With Alpamayo 1, NVIDIA's 10B-parameter chain-of-thought reasoning model, the distilled version can reason in real time. Hear Marco Pavone (Marco Pavone), Yan Wang, Yurong You, and Wenhao Ding from our AV Research team break down Alpamayo 1 and what's next for reasoning in autonomous driving. 🔁 Watch the replay:

NVIDIA DRIVE

13,592 views • 4 months ago

Introducing MiniCPM 4.1-8B: First Open-Source Reasoning LLM with Trainable Sparse Attention ✅ Strong Reasoning Capability: Surpasses similar-sized models on 15 tasks! ✅ Fast Generation: 3x decoding speedup for reasoning ✅ Efficient Architecture: Trainable sparse attention, frequency-ranked speculative decoding Download Models: Huggingface: Github: Technical Report: #AI #MiniCPM #LLM #OpenBMB #ArtificialIntelligence #MachineLearning
0:54

Introducing MiniCPM 4.1-8B: First Open-Source Reasoning LLM with Trainable Sparse Attention ✅ Strong Reasoning Capability: Surpasses similar-sized models on 15 tasks! ✅ Fast Generation: 3x decoding speedup for reasoning ✅ Efficient Architecture: Trainable sparse attention, frequency-ranked speculative decoding Download Models: Huggingface: Github: Technical Report: #AI #MiniCPM #LLM #OpenBMB #ArtificialIntelligence #MachineLearning

OpenBMB

19,236 views • 9 months ago

Reasoning LLMs generate very long chains-of-thought, so even small quantization errors add up. With AWQ, Qwen3-4B drops 71.0 → 68.2 on MMLU-Pro (~4% relative loss). 😬 ParoQuant fixes this! It keeps only the critical rotation pairs and fuses everything into a single kernel. Recovers most of the lost reasoning accuracy with minimal overhead — so 4-bit models stay strong at reasoning. 💪💪
0:27

Reasoning LLMs generate very long chains-of-thought, so even small quantization errors add up. With AWQ, Qwen3-4B drops 71.0 → 68.2 on MMLU-Pro (~4% relative loss). 😬 ParoQuant fixes this! It keeps only the critical rotation pairs and fuses everything into a single kernel. Recovers most of the lost reasoning accuracy with minimal overhead — so 4-bit models stay strong at reasoning. 💪💪

Zhijian Liu

170,883 views • 4 months ago

PSA: DeepSeek R1 Distill Llama 70B speculative decoding version is now live on Groq Inc for Dev Tier. We just made fast even faster for instant reasoning. 🏁
0:34

PSA: DeepSeek R1 Distill Llama 70B speculative decoding version is now live on Groq Inc for Dev Tier. We just made fast even faster for instant reasoning. 🏁

Hatice Ozen

44,675 views • 1 year ago

Proteins can now talk. Introducing BioReason-Pro, the first reasoning model for protein function. A thread🧵
0:25

Proteins can now talk. Introducing BioReason-Pro, the first reasoning model for protein function. A thread🧵

Adib @ ICML 🇰🇷

203,139 views • 3 months ago

Understanding OpenAI o1: Noam Brown on integrating reasoning into the model. Takeaways: - Avoid MCTS and current paradigm of using processes outside of the model during inference - Think about how to directly integrate reasoning into the model architecture
0:59

Understanding OpenAI o1: Noam Brown on integrating reasoning into the model. Takeaways: - Avoid MCTS and current paradigm of using processes outside of the model during inference - Think about how to directly integrate reasoning into the model architecture

Casper Hansen

313,291 views • 1 year ago

While others fight, we ship 🚀 Agno’s ReasoningTools are now live on the Playground — giving non-reasoning models the ability to "think", "analyze", and outperform Reasoning Models on Agentic workloads. If you haven't tried `ReasoningTools` yet - you definitely should 👇
1:18

While others fight, we ship 🚀 Agno’s ReasoningTools are now live on the Playground — giving non-reasoning models the ability to "think", "analyze", and outperform Reasoning Models on Agentic workloads. If you haven't tried `ReasoningTools` yet - you definitely should 👇

Ashpreet Bedi

27,864 views • 1 year ago

The next frontier of autonomous driving is unlocked by reasoning models. NVIDIA Alpamayo brings together open AI models with reasoning capabilities, closed-loop simulation tools, and massive real-world driving datasets. Alpamayo 1 is a vision–language–action model that explains its own decisions through explicit reasoning traces, enabling trustworthy, humanlike decision-making. Together with NVIDIA’s Physical AI dataset and AlpaSim simulation, Alpamayo provides the tools and scale required to enable level 4 autonomous vehicles. ▶️ Watch now:
0:45

The next frontier of autonomous driving is unlocked by reasoning models. NVIDIA Alpamayo brings together open AI models with reasoning capabilities, closed-loop simulation tools, and massive real-world driving datasets. Alpamayo 1 is a vision–language–action model that explains its own decisions through explicit reasoning traces, enabling trustworthy, humanlike decision-making. Together with NVIDIA’s Physical AI dataset and AlpaSim simulation, Alpamayo provides the tools and scale required to enable level 4 autonomous vehicles. ▶️ Watch now:

NVIDIA DRIVE

35,324 views • 5 months ago

🚀 GPT‑5 is here: deep reasoning + lightning speed. The leap toward AGI just got real. Recap + takeaways in thread.
1:41

🚀 GPT‑5 is here: deep reasoning + lightning speed. The leap toward AGI just got real. Recap + takeaways in thread.

Garrett Lord

23,834 views • 10 months ago

Flow reversal steering allows "steering" diffusion-based VLAs with high-level actions, for example from VLM reasoning. This also lets us run RL in the diffusion noise space with exploration guided by high-level reasoning: think through a task, then practice it! 👇
0:55

Flow reversal steering allows "steering" diffusion-based VLAs with high-level actions, for example from VLM reasoning. This also lets us run RL in the diffusion noise space with exploration guided by high-level reasoning: think through a task, then practice it! 👇

Sergey Levine

73,360 views • 15 days ago

Introducing Core Sandbox Alpha, the first inference-time learning coding assistant. Every interaction affects reasoning immediately. No RL. No retraining. No fine-tuning.
0:32

Introducing Core Sandbox Alpha, the first inference-time learning coding assistant. Every interaction affects reasoning immediately. No RL. No retraining. No fine-tuning.

Rei

52,608 views • 7 months ago

Embodied chain of thought (ECoT) is a powerful tool to get VLAs to think through problems, but why does it work? In our new work, we analyze various lightweight ECoT-like strategies, including co-training, to see what is the "minimal" amount of reasoning that can boost VLAs 🧵👇
1:08

Embodied chain of thought (ECoT) is a powerful tool to get VLAs to think through problems, but why does it work? In our new work, we analyze various lightweight ECoT-like strategies, including co-training, to see what is the "minimal" amount of reasoning that can boost VLAs 🧵👇

Sergey Levine

22,403 views • 1 year ago

Build Multi Agent Systems with Reasoning and Context Thanks to sonnet-4, we have level 4 autonomous multi-agent systems working. Learn how to add: -> Reasoning Tools (think -> analyze) -> Shared Agentic Context -> Agentic Memory Code below 👇
14:17

Build Multi Agent Systems with Reasoning and Context Thanks to sonnet-4, we have level 4 autonomous multi-agent systems working. Learn how to add: -> Reasoning Tools (think -> analyze) -> Shared Agentic Context -> Agentic Memory Code below 👇

Ashpreet Bedi

38,576 views • 1 year ago

Yesterday at #GoogleIO, we introduced Gemini 2.5 Pro Deep Think 🧠, pushing the frontiers of AI reasoning. This enhanced reasoning mode is built to tackle drastically complex problems – like USAMO problems that stumped previous models. Super proud of the GDM team for this one!
0:30

Yesterday at #GoogleIO, we introduced Gemini 2.5 Pro Deep Think 🧠, pushing the frontiers of AI reasoning. This enhanced reasoning mode is built to tackle drastically complex problems – like USAMO problems that stumped previous models. Super proud of the GDM team for this one!

Oriol Vinyals

86,776 views • 1 year ago

"There is no reasoning" with climate activists, says Carl Higbie. "They think mankind can offset a volcano by installing a new bicycle path."
7:56

"There is no reasoning" with climate activists, says Carl Higbie. "They think mankind can offset a volcano by installing a new bicycle path."

NEWSMAX

49,975 views • 2 years ago

[1/N]🚀New decoding paradigm drop!🚀 Introducing Lookahead Reasoning(LR): step-level speculation that stacks with Speculative Decoding(SD). It has been accepted to #NeurIPS2025 🎉 📖 Blog: 💻 Code: 📄 Paper:
0:22

[1/N]🚀New decoding paradigm drop!🚀 Introducing Lookahead Reasoning(LR): step-level speculation that stacks with Speculative Decoding(SD). It has been accepted to #NeurIPS2025 🎉 📖 Blog: 💻 Code: 📄 Paper:

Hao AI Lab

43,162 views • 9 months ago

Multimodal reasoning with Phi-4-reasoning-vision, new work on scaling LLM inference, benchmarking AI agents in network operations, cinematic video generation, adaptive evaluation for LLMs, and using AI to improve individual and population health.
2:00

Multimodal reasoning with Phi-4-reasoning-vision, new work on scaling LLM inference, benchmarking AI agents in network operations, cinematic video generation, adaptive evaluation for LLMs, and using AI to improve individual and population health.

Microsoft Research

11,672 views • 3 months ago