Excited to share our NeurIPS 2024 Oral, Convolutional Differentiable... Logic Gate Networks, leading to a range of inference efficiency records, including inference in only 4 nanoseconds 🏎️. We reduce model sizes by factors of 29x-61x over the SOTA. Paper:show more

Today we introduce Liquid Labs, our advanced research unit,... with the goal of understanding and building efficient and adaptive intelligence systems. Liquid Labs consolidates our existing research efforts at Liquid across architecture of foundation models, multimodality, training, data, and inference. The lab also will be home to new frontier research work across the broad range of foundation model build-up stack. Read the full announcement: We are hiring: Also find us at NeurIPS 2025 exhibition hall! 🚀show more

In flow matching, a coupling determines how noise and... data samples are paired during training. The choice of coupling is important because it influences the geometry of trajectories at inference time. The simplest choice is the independent coupling, where noise and data points are paired arbitrarily. This can lead to curved trajectories as the model averages over many conflicting pairings. However, if we use optimal transport on batches of pairs, this leads to fewer ambiguous intersections that the model must resolve, leading to straighter trajectories at inference time.show more

We are excited to share our paper in Journal... of Clinical Investigation in which we analyze transcriptomes of invading human pancreatic cancer organoids to interrogate the molecular programs that drive invasion - led by Yea Ji Jeong @FatemeShojaeian and Hildur Knuttsdotir:show more

Today, we’re excited to announce a partnership with Mind... Network. Both Nesa and Mind Network specialize in decentralized security, and we share a mission to bring this tech to crypto AI. Together we will explore a close technological collaboration, sharing components of our stacks with one another. Mind Network will also be using Nesa for its AI inference. Mind Network is the first FHE Restaking Layer for AI, focused on enhancing security at the consensus and validator levels of AI networks. Nesa is the Layer-1 blockchain for AI, specializing in private inference and building infrastructure to make it easy for any application, protocol, and smart contract to fuse with AI. Look out for our AMA together and other activations soon.show more

⭐The Year of Inference is here. Featherless is now... an official inference provider on Hugging Face, unlocking 6,700+ LLMs for anyone to run, eval, and deploy instantly. It all starts with accessibility. From DeepSeek to Mistral, LLaMA to Qwen — powerful LLMs are one click away. We believe the future of AI is shaped by the long tail: personalized, specialized models tuned to real people’s needs. To get there, inference must be open, affordable, and usable by all. Whether you're fine-tuning, prototyping, or scaling a product, this moment is for you. 🫱🏻‍🫲🏻Let’s make inference the easiest part of building with AI. 📢 Share this so more builders know what’s now possible. Excited to be partnering with clem 🤗 Julien Chaumond Vaibhav (VB) Srivastav Simon Brandeis & Hugging Face team to take this to the next level!show more

Finally getting to share one of my favorite projects.... ICLR Oral! 🏆 It’s so strange how rigid video tokenization is. Think about it: why should a still landscape cost the same amount of tokens as a busy street? We built InfoTok. We went back to basics with Shannon’s information theory to make tokens "adaptive" in a principled way. Its 2.3x better compression and 11x faster inference demonstrates the magic of the old-school theory ✨ Check it out:show more

🚀Introducing The LLM Inference Provider Leaderboard - a live-updated,... unbiased eval of API Inference products. Featuring: Abacus.AI, Anyscale, DeepInfra, Decart, Fireworks, Lepton AI, Together AI, Perplexity, Replicate, as well as OpenAI and Anthropic models For each provider's Mixtral-8x7B and Llama-2-70B-Chat public endpoint, we benchmark cost, rate limit, P50 & P90 of throughput & TTFT, and average daily collections overtime for long term tracking. At Martian, we route each API request to the best LLM to reduce cost, reduce latency, and get the best performance. So finding the best providers is an important problem for us. We found that there's a > 5x cost difference, > 6x throughput variation, and even larger rate limit discrepancies among providers! Choosing between different LLMs is only part of the equation -- the selection of different inference endpoints is also crucial to get the best performance for your use case. See highlights of provider performance in🧵👇show more

1/ Gemini 2.5 is here, and it’s our most... intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on Arena by a significant margin. With a model this intelligent, we wanted to get it to people as quickly as possible. Find it on Google AI Studio and in the Google Gemini for Gemini Advanced users now – and in Vertex in the coming weeks. This is the start of a new era of thinking models – and we can’t wait to see where things go from here.show more

Depth Any Video with Scalable Synthetic Data AI physicists... and chemists continue to make strides in depth estimation from video. Check out this new paper featuring some impressive examples. See the thread for more details (unfortunately no code yet). Abstract: Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse game environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates 0 - even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.show more

⚠️ huge redebut model spoilers ⚠️ I'm just too... excited to not share a WIP sneak peek of my new model in Warudo @ Hakuya Labs's warudo with StretchSense 🫶's finger tracking gloves ✌️🏻lookit them go!! model concepted and 3d modeled by the one and only ☽ Vezonia ☾, of course.show more

Someone is excited to have to some Shakshuka. Some... of this morning activity while the Israeli warplanes and drones continue to fly over Gaza. We are sick of these sounds that bring only death, fear and destruction in our cities. We miss having a somewhat of a normal life, because life in Gaza was never normal. End the siege. Ceasefire nowshow more

Ladies and Gentlemen, we will make our first appearance... in 8 years on Fri 30th August, returning to MothClub in Hackney for a 4 hour DJ set, our only show of 2024. 🎫 We are now down to the final 40 tickets, see you there. erol alkan @MrRichardNorrisshow more

we sped up distributed inference by up to 5x... with decentralized speculative decoding. many don't realize that AI models normally generate text one single word at a time, waiting for the network after every word. speculative decoding changes this by using a "guess & confirm" system, similar to autocomplete. how it's done: 1. draft locally (the guess) instead of waiting for the network, a tiny, fast model on your device guesses the next few words instantly, without waiting for the network. 2. confirm remotely (the check) the massive remote model doesn't generate from scratch; it just checks the draft. it looks at the guesses in a batch and says "yes, yes, no." you get multiple words in the time it usually takes to get one. 3. adaptive logic dsd is smart. if the topic is creative, it lets the draft flow loose. if the topic is math or code, it checks more strictly. it balances speed and precision automatically so your inference almost feel instant. find out more: paper: blog:show more

We are excited to introduce Stable Fast 3D, Stability... AI’s latest breakthrough in 3D asset generation technology. This innovative model transforms a single input image into a detailed 3D asset in just 0.5 seconds, setting a new standard for speed and quality in the field of 3D reconstruction! Alongside this release, we’ve also published a technical report that highlights how we achieve fast inference speeds with reduced baked illumination and material parameters. 👾You can learn more and access the report here:show more

Welcome to your new home, Seize the Grey! 🌟... Our Preakness Champion was welcomed to his new home and second career Gainesway where he will be a stallion in 2025! We couldn't be more proud of our Arrogate colt and all he has accomplished: 🏇 $2,425,938 in career earnings 🏇 5 wins 🏇 3 graded stakes, including the 2024 Preakness Stakes Thank you to all of his owners for their support, the entire team at the D. Wayne Lukas barn, and his jockey Jaime A. Torres. We'll miss seeing our boy in the starting gate but are so excited to see his foals hit the ground in a few years. On to the next chapter!show more

🌟 Day 1 Recap at WEBX 2024 in Japan!... We’re thrilled to share the highlights from Asia's leading Web3 event, where Atleta took center stage! 🏆 Our booth was the talk of the event, drawing the largest crowd and capturing everyone's attention! 🎤 Andrey Didovskiy 🪻 delivered a powerful talk on Web3 sports, showcasing Atleta’s progress, including our testnet surpassing 11M transactions. ⚽️ We were honored to have our ambassador, the legendary Edmílson, World Cup Champion with Brazil in 2002!show more

Disappointed with your ICLR paper being rejected? Ten years... ago today, Sergey and I finished training some of the first end-to-end neutral nets for robot control 🤖 We submitted the paper to RSS on January 23, 2015. It was rejected for being "incremental" and "unlikely to have much impact" Our resubmission to NeurIPS was also rejected It now has >4,000 citations (and more importantly, end-to-end training is widely accepted!) It's also cool to think about what's changed and what's the same -- - The network was 92k parameters and trained on ~15 minutes of data - The code was a combination of matlab, caffe, ROS, a custom CUDA kernel for speed, and a low-level 20 Hz controller in C++, all talking to each other. ROS+matlab was as bad as it sounds. - We pre-trained the encoder and did inference off-board on a workstation with a larger GPU. - We were paranoid about varying lighting messing up the network, so we did all the experiments after sunset (so long nights running experiments on the robot past 3 am) Now, we have manipulation policies that are far more dextrous, far more generalizable, and maybe on the cusp of breaking into the real world. :) (the paper:show more

The human brain is truly a marvel of nature.... If you horribly reductive, and boiled it down to a language model, you'd be looking at roughly 100 trillon parameters running as a sparse MoE architecture Only about 1-5% of neurons fire at any given moment, meaning the brain "activates" maybe 1-5 trillion parameters per inference step. For context, the largest AI models we've built probably top out around 5 trillion parameters. The brain is roughly 100x larger. Even its active params at any given moment are larger than almost every model in existence today. Here's what melts my brain (pun intnended) though Your brain does all of this on about 20 watts of power, less than a dim light bulb. Training a frontier AI model consumes enough electricity to power small cities for months. Running inference across data centers pulls megawatts. Your brain runs 24/7 for 80+ years on the equivalent of a phone charger. We haven't come close to matching the brain's scale. And we're not even in the same universe when it comes to efficiency. Evolution spent 500 million yrs optimizing the most energy-efficient intelligence architecture ever known. we're trying to brute force our way there with compute and electricity. Nature is still the best engineer in the room.show more

NEWS: Waymo has just officially announced that they have... raised $16 billion at a $126 billion post-money valuation. "Across 127 million miles of fully autonomous operation—the equivalent of going to the moon and back over 260 times—we have achieved a 90% reduction in serious injury crashes. This is the direct result of a driver that is never affected by the leading causes of road tragedy, including distraction, impairment, and fatigue. This infusion of capital will ensure we are positioned to move forward with unprecedented velocity, while maintaining our industry-leading safety standards. Our focus is now on global scale, bringing the safety and magic of the Waymo Driver to even more cities this year across the United States and internationally. From our recent launch in Miami to the new markets ahead, we are expanding our fleet and our world-class team to meet an exploding global demand for autonomous mobility."show more