Your curated collection of saved posts and media
π Best Resource Paper Award at #ACL2026 @aclmeeting πThrilled to share that our deep research benchmark paper "HSCodeComp: A Realistic and Expert-level Agent Benchmark for Hierarchical Rule Application" reveived a Best Resource Paper Award #ACL2026! π― Hoping this sparks more focus on reliable AI Agents in the real world. https://t.co/ToFSPPaYb3
How to approach an unknown language in the ocean? Hereβs one of the first cases of AI interpretability leading to a scientific discovery -- in whales. We built an artificial baby model that learns language directly from raw sound and trained it to imitate whale speech. Then we looked inside. Our interpretability method recovered the properties biologists already thought were meaningful and pointed out those that had not been considered before. This was the initial clue that eventually led to the discovery of vowels in sperm whales. Understanding AI and reframing language as informative imagitation can help us step outside our human biases and discover new realities about the natural world. Published in Royal Society Open Science.
This is what faster-than-real-time video generation looks like.
A line in AI video was crossed, in my experiments with just the web interface, H3 Max can now create reasonably high quality AI video in less time than it takes you to watch it. This is realtime from the moment I pushed the "generate" button (and also includes prompt enhancement)
FastAPI Conf speaker news! π’ @jxnlco, creator of Instructor, the person that convinced AI Labs to provide structured output with Pydantic (automatic compatibility with FastAPI). He's bringing us some insights directly from the Codex team at @OpenAI π€ https://t.co/ioc3vjSHvX https://t.co/C1zlrff3aX
This paper does a good job of showing the promise and gaps of autonomous AI scientists. Big question is how much more advanced models close those gaps.
Today, we're excited to share early progress on using Gemini to accelerate scientific discovery in the real-world. We present an extension of Co-Scientist which we use to collaborate with scientists across materials science, biology, and computer science. https://t.co/jwDF5aSK28
π€ Debug Your Scripts in VS Code with GitHub Copilot Tired of remembering all the syntax for a launch.json file? In this quick tip, learn how to use GitHub Copilot to analyze your package.json, generate the right debug configurations, and launch your scripts directly with the built-in VS Code debugger.
Video world models shouldn't just render plausible pixels, they should understand "how the world evolves". π€ Introducing Latent Dynamics Reasoning (LDR). Instead of predicting future frames directly, LDR maps past frames into structured latent states, then rolls those states forward through kinematic integration. It learns only the higher-order motion residuals that drive the rollout. π To our knowledge, LDR is the first video world model to extrapolate learned dynamics beyond its training distribution. πͺ Paper / code / models / data are now public, check them out! π₯³ - Paper: https://t.co/Mnh1sD9jLf - Code: https://t.co/uJhu28darp - Model: https://t.co/1fJLmwFwTL - Data: https://t.co/Pxl0eirIgo
One of the trickiest problems you run into with voice AI in the real world is that people often call in messy environments. There might be other voices in the background, or the person might be talking to other people at the same time. Super cool work from Decagon Labs on how we've tackled this problem!
Conversational voice agents need to know when a different person is speaking, but not every background voice should count. We combined speaker embeddings with a post-trained audio-language model to determine when a speaker change matters. https://t.co/Cg5HKtyaUf
Introducing CUA-Lite 𧡠β an open platform for computer-use agents. Training and benchmarking CUAs (Computer-Use Agents) requires four core pieces: 1οΈβ£ Agents β the models and the scaffolding that drives them 2οΈβ£ Environments β runtime/sandboxes for agents to interact with, tasks & verifiers/graders 3οΈβ£ Traces β records of agent trajectories 4οΈβ£ Frameworks β to evaluate, SFT & RL-train agents Today, all four are fragmented. Every agent ships with its own implementation, often in a separate repo β there is no unified way to run them all. Every environment exposes its own interface and action space, often requiring an expensive VM sandbox for each verifiable task. Traces come in incompatible formats. And without common standards across the stack, every project ends up rebuilding its own tooling/framework for eval, SFT, and RL. CUA-Lite unifies the stack: β One standardized interface & action space for agents and environments β One standardized format for agent traces β One framework for evaluation, SFT & RL β Across desktop, browser & mobile And open resources plug straight in, creating the largest open collection of CUA agents, environments and traces, all in a unified format: π€ 10+ CUAs, including GPT, Claude, Gemini, Qwen, Muse-Glimmer, UI-TARS π 15+ benchmarks, including OSWorld, WebArena & AndroidWorld β‘ Optional VM-free sandboxes with 30K+ verifiable tasks for training π 10+ trace datasets, freely available on Hugging Face, including public datasets converted into the standardized format and fresh rollouts from frontier open-weight CUAs Led by @BerkeleyRDI , our goal is for CUA-Lite to become a community-driven, open-source ecosystem for computer-use agents. Join the community and contribute today: bring an environment (runtime/sandbox + tasks + verifier), traces, or an agent, and plug it into CUA-Lite!
Breeze TTS 2 by @BreezeBlueX dropped on Hugging Face as the #1 open weights TTS model on @ArtificialAnlys It does π¨ Voice Design (prompt a voice) ποΈ Voice Reference (upload a voice) ποΈ Voice Direction (upload & prompt a voice) vibe it on Spaces βΆοΈ https://t.co/MCKL1l4y6R https://t.co/QTgLO50JtD
Breeze TTS 2 is now the leading Open Weights TTS model in the Artificial Analysis Provider Voices Speech Arena, surpassing Fish Audio S2 Pro by 90 Elo points Breeze TTS 2 is the latest TTS model from @BreezeBlueX, supporting 50 languages, voice generation from text prompts, and
