2026-10-25

This paper shows that JEPA-style latent world models (LWMs) can learn across diverse domains and data sources by adopting the language-conditioned interface of video generation models. We establish this approach as an effective and efficient basis for planning with imagination and downstream policy fine-tuning. To this end, we introduce LaLa-World, a Language-conditioned Latent World model that learns from simulation and robot trajectories together with broader image and video data. Two designs

🤖LaLa-World is a language-conditioned latent world model that jointly learns from diverse simulation, robot, and video data to enable efficient model-predictive planning and policy initialization.

World Action Models (WAMs) have emerged as a promising approach to learning generalist robot policies using rich spatiotemporal priors from pre-trained video diffusion models. A recent line of WAMs improves inference efficiency by conditioning a separate action decoder on intermediate future video representations extracted from a single denoising step, avoiding costly iterative denoising required for video generation. This design makes action prediction depend directly on the quality of these fu

🤖FRED improves single-step future video representations in world action models through self-distillation and temporal conditioning, boosting robot policy performance on long-horizon and unseen tasks.

Complex camera motion is central to visual storytelling, yet translating cinematographic intent into controllable, executable camera trajectories remains challenging. We introduce FilmFlow, an agentic framework that converts natural-language instructions or reference videos into explicit camera trajectories for dynamic 3D environments. To generate these trajectories, a Director agent constructs executable camera plans by composing high-level motions from concurrent atomic operations that jointly

🤖FilmFlow is an agentic framework that translates natural-language or video instructions into executable camera trajectories for 3D scenes using specialized director, interpreter, scout, and critic agents, evaluated on the CinemaBench dataset.

As model parameters scale up, sparsely activated Mixture-of-Experts (MoE) approaches have become essential for model scaling. However, mainstream models currently adopt hierarchical architectures, where experts in different layers, although topologically independent, exhibit substantial similarity and redundancy in their stored content. Compared to the hierarchically arranged Local Expert in existing mainstream models, we hypothesize that inter-layer shared Meta Expert hold greater potential. To

🤖Shared meta-experts across layers reduce redundancy and improve efficiency compared to layer-specific local experts in mixture-of-experts models.

Code-based video generation offers fine-grained control, targeted editing, and component reuse compared with direct video generation. This approach requires multimodal large language models (MLLMs) to translate visual and temporal requirements into executable programs that produce complete videos. However, existing code-based benchmarks primarily target specialized tasks, leaving complete video creation across diverse creative categories and input modalities insufficiently evaluated. We introduc

🤖Code2Video-Compass is a benchmark evaluating multimodal language models on code-based video generation across text, image, and video inputs, revealing significant challenges in complex dynamic and state-dependent tasks.

Hey everyone, Inspired by Herdr, I've built an agent multiplexer that I've been using as my daily driver for a few weeks now. I think I improved on the concept in a few ways, focusing on the ergonomics I always wished I had: I show you what the agents are up to, along with a running feed of their activity. There's also a simple shortcut (F1) to go to the next unread agent. I use multiple accounts, so I've added unified launcher for Codex/Claude Code/Pi. Theres some careful ergonomics there: fast

A new study found Grok's AI overwhelmingly recommends Republican candidates while OpenAI's GPT favors Democrats, with the two AI models disagreeing in more than 90% of nearly 500 election races.

We created a list of the most notable AI agents that can live in your text messages, from general assistants to agents designed for families, travel, and work.

Article URL: Comments URL: Points: 50 # Comments: 17

On Thursday, Pennsylvania Governor Josh Shapiro signed the Artificial Intelligence Deceptive Advertising Act into law, requiring disclosures on AI-generated ads. The law requires any ad - whether it's a still image, video, audio, or text - that "has been significantly modified or generated by artificial intelligence" to include a label in the same format as […]