
GAASH Lab's QTrack Tracks Any Video Subject Using Plain English Descriptions
QTrack turns multi-object tracking into a language-conditioned reasoning task, hitting state-of-the-art on a new RMOT26 benchmark with just 3B parameters.
A focused feed of models, agents, research and open-source releases for people building with AI.

QTrack turns multi-object tracking into a language-conditioned reasoning task, hitting state-of-the-art on a new RMOT26 benchmark with just 3B parameters.

A training-free token compression method keeps Video LLMs accurate even when 99% of visual tokens are thrown away, with a 12.5x prefill speedup.

Pika's image, video, and sound tools now live inside ChatGPT as a plugin extension with a sidebar panel, timeline editor, and shared library.

An open-source desktop canvas lets creators chain prompts, images, and video models into reusable AI storyboarding workflows, with assets stored locally.

Black Forest Labs slashed FLUX 3 Video's 2K and 4K pricing in half and doubled generation speed, challenging Kling at the premium tier.

Runway is opening up its Gen-4.5 and Aleph 2.0 video models for private enterprise deployment on Baseten with fine-tuning and reserved GPUs.

A new family of video models skips autoregressive text generation to score time spans and answer options directly, hitting over 100x QA speedups.

A new open-source pipeline takes a single-person video and spits out a Mixamo-rigged GLB you can drop straight into Blender or Unity.

A community-maintained repackaging of Alibaba's Wan 2.1 video model lets 6GB consumer GPUs generate 480p clips through the WanGP toolbox.

A new sparse-view 3D asset pipeline fuses reconstruction and generation in a shared coordinate space, with code and weights now public.
Google DeepMind's TAPNet repository bundles every generation of their point tracker, from TAP-Net to TAPNext++, in one open-source hub.

A Chinese open-source infinite canvas workbench stitches scripts, characters, storyboards, and multimodal generation into a single node-based workflow for AI film production.

HiDream's new omnimodal video model lands at #6 on the Artificial Analysis I2V with Audio leaderboard, generating 1080p clips with synchronized audio at $5.80 per minute.

Tencent's 5B omni-modal parser handles documents, charts, geometry, audio and video into one structured JSON schema, rivaling Gemini-3-Pro.

xAI's distilled video model lands at #17 on the Artificial Analysis leaderboard, beating Veo 3.1 while costing roughly a third as much.

A community Windows app wraps NVIDIA's DLSS 5 neural rendering pipeline into a local Gradio UI for upscaling images and video.

Odyssey-3 is a real-time foundation world model that generates interactive 3D environments from prompts and tops the Physics-IQ benchmark at 66.1.

A new world model skips the tedious atom-by-atom replay in materials simulations, hitting speedups of 1,000x to 10,000x across five systems.

vLLM-Omni extends the popular inference engine with a stage-based orchestrator, cutting job completion time by up to 91.4% on Qwen3-Omni serving.

Artificial Analysis now flags video models that were post-trained from another base model, with a toggle to filter them out of the leaderboard.

Shengshu's new flagship jumps 16 spots on the Artificial Analysis image-to-video leaderboard while costing 25 percent less per minute than Vidu Q3 Pro.

Black Forest Labs' new multimodal model tops Google DeepMind's physics benchmark for video generation, beating Sora 2, Veo 3.1 and Cosmos 3.

Manus added a multi-track Video Editor to its agent, letting you generate, assemble, and hand-edit full videos from a prompt or raw footage.

A hierarchical JEPA trained end-to-end lifts Visual AntMaze planning success from 18% to 73% while using less planner compute.
No stories match these filters.