Model merging is tricky when model weights aren’t aligned... Introducing KnOTS 🪢: a gradient-free framework to merge LoRA models. KnOTS is plug-and-play, boosting SoTA merging methods by up to 4.3%🚀 📜: 💻:show more

Introducing screengrasp - The new SOTA agent click position... model - beating Anthropic Computer Use, OmniParser and Molmo by a wide margin. - Simplified API access to the best click models on the market. 🔁Retweet and DM for free API credits. More details 👇show more

1/ Introducing Glider - the smallest model to beat... GPT-4o-mini on eval tasks ⚡🚀 - Open source, open weights, open code - Explainable evaluations by nature - Trained on 183 criteria and 685 domains Try it out for free at 🔥show more

Reasoning models often waste tokens self-doubting. Dynasor saves you... up to 81% tokens to arrive at the correct answer! 🧠✂️ - Probe the model halfway to get the certainty - Use Certainty to stop reasoning - 100% Training-Free, Plug-and-play 🎮Demo:show more

This also shows up in the representations learned by... the model. We plot the model’s representations of human and robot images. As pre-training is scaled up, the representation of humans and robots become more aligned: to a scaled-up model, human videos "look" like robot demos.show more

Protein–ligand cofolding models are getting incredibly powerful… but do... they have to be so slow? 🧬🐢💊 Our new preprint introduces a new flow-map framework called DeCAF for fast few-step cofolding — up to 5× faster while preserving sample quality on the SOTA Pearl model and 20x faster than Boltz 1x. ⚡🧵 📜 Blog: 🔗arXiv: Code (coming soon):show more

Introducing 𝗦𝘂𝗽𝗲𝗿 𝗝𝗦𝗢𝗡 𝗠𝗼𝗱𝗲, a framework for low latency... structured output generation from LLMs. Generate JSON up to 𝟮𝟬𝘅 𝗳𝗮𝘀𝘁𝗲𝗿 from OpenAI and open source models. ❌ No need to threaten the model, tip the AI, etc ❌ Built with Alex Derhacobian 🔧 🧵👇show more

Most image stacks bet on one giant, closed model.... We don’t. We route each image gen request on Syntax to the best open-source model/LoRA for the job. Quality rises, iteration speeds up, costs stay sane, and creators aren’t locked into one model’s quirks. The future is orchestration, not monoliths.show more

Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation paper page:... Large text-to-image diffusion models have exhibited impressive proficiency in generating high-quality images. However, when applying these models to video domain, ensuring temporal consistency across video frames remains a formidable challenge. This paper proposes a novel zero-shot text-guided video-to-video translation framework to adapt image models to videos. The framework includes two parts: key frame translation and full video translation. The first part uses an adapted diffusion model to generate key frames, with hierarchical cross-frame constraints applied to enforce coherence in shapes, textures and colors. The second part propagates the key frames to other frames with temporal-aware patch matching and frame blending. Our framework achieves global style and local texture temporal consistency at a low cost (without re-training or optimization). The adaptation is compatible with existing image diffusion techniques, allowing our framework to take advantage of them, such as customizing a specific subject with LoRA, and introducing extra spatial guidance with ControlNet. Extensive experimental results demonstrate the effectiveness of our proposed framework over existing methods in rendering high-quality and temporally-coherent videos.show more

my favorite of the new LTX 2.3 LoRAs ✨... Remember when a year ago we need a full on model like VACE to do that? and now an IC LoRA is even bettershow more

The King is coming back. Free to play for... everyone. Learn the model. Probe the edges. Level up. Test Stormrae and get ready for the next releases. Free prompts, more shards.show more

Introducing ✨Aya Expanse ✨ – an open-weights state-of-art family... of models to help close the language gap with AI. Aya Expanse is both global and local. Driven by a multi-year commitment to multilingual research.show more

Canter 2B is a photography-oriented text-to-image model being trained... on just a single GPU by data-archetype 🐎 are we entering the indie ai models era? still training, the v0002 checkpoint is available, more to come ▶️ play on spacesshow more

FLUX.2 is live on Runware! D0 drop! 🔥 Built... by Black Forest Labs, FLUX.2 is the new SOTA model that brings better control over structure, text, and references in image generation. This is a huge step forward for image gen & image editing. And we’re here to offer you the best prices on D0. This model comes in three versions. Details below.show more

NEW SECRET MYSTERY AI VIDEO MODEL ARENA CODE NAME:... BOUNCYBOHR Unlike Artificial Analysis, on Arena. AI you can submit your own prompts and this prompt is designed to try and unmask who created the model. Models powered by an LLM (like Seedance 2.0 and Omni) are smart and can see what you are doing. As far as thoughts? Eh? While another screenshot looked like Omni, this does look pretty Seedance to me. Judging by the result, this looks like the rumored new "improved" FAST model and not upgraded full 2.1 model that is supposed to be 25% better. Text To Video close-up cinematic scene from a film, professionally directed, focused, ultrafine details a woman laughs as she whiteboard writes out what model made this videoshow more

free access to 8+ top AI models 😳 APInex... is offering free models with 1M context - Gemini 3.8 Flash - Muse Spark 1.3 - GLM 5.3 Flash - Gemini 3.1 Pro - DeepSeek V4 Pro - GPT-5.6 Luna - Qwen 3.8 MAX - DeepSeek V4 Flash getting started: 1. go to 2. sign up with Gmail 3. create your API key 4. base url 5. choose a free model and start using free models, one API setup 👀show more

Microsoft made 100B parameter models run on a single... CPU. bitnet.cpp: The official inference framework for 1-bit LLMs. The math behind 1-bit LLMs is what makes them revolutionary. Traditional LLMs use 16-bit floating point weights. Every parameter is a number like 0.0023847 or -1.4729. When you run inference, you multiply these floats together. Billions of times. That's why you need GPUs, they're optimized for floating point matrix multiplication. BitNet b1.58 uses ternary weights: {-1, 0, 1}. That's not a simplification. That's a fundamental change in the math. When your weights are only -1, 0, or 1: → Multiply by 1 = keep the value → Multiply by -1 = flip the sign → Multiply by 0 = skip entirely Matrix multiplication becomes addition and subtraction. No floating point operations. No GPU required. This is why bitnet.cpp achieves: → 2.37x to 6.17x speedup on x86 CPUs → 1.37x to 5.07x speedup on ARM CPUs → 71.9% to 82.2% energy reduction on x86 → 55.4% to 70.0% energy reduction on ARM The speedups scale with model size. Larger models see bigger gains because there are more operations to simplify. A 100B parameter model running at human reading speed (5-7 tokens/second) on a single CPU. That's not optimization. That's a different paradigm. Why 1.58 bits? Because log₂(3) ≈ 1.58. Three possible values = 1.58 bits of information per weight. The key insight: These models aren't quantized after training. They're trained from scratch with ternary weights. The model learns to work within the constraint. No precision loss. No quality tradeoff.show more

🚨 FREE AI CODING MODEL ALERT! Tencent Hy's latest... model, HY3, is now FREE in Kilo Code for a limited time. Here are the one-shot results when we prompted Opus, Fable, and HY3 to "Create a 3D HTML visualizer of Earth spinning in space" in Kilo's Agent Manager:show more

This is the Canadian model and it has been... consistently cranking out a solid snow for Kentucky by Sunday morning. *IF* this ends up close to the final outcome it will be one of the greatest wins versus other models. This needs to be monitored!!!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