Large language models are increasingly deployed as agents that plan over long horizons and act through external tools. M…

In this work, we present Gander, an end-to-end model that unifies omni perception, realtime interaction, and agentic cap…

We present Miles v0.1, a full-stack, production-ready system for frontier post-training. Building upon the clean design …

Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and …

Large Language Models demonstrate remarkable proficiency in static reasoning, yet training them as autonomous agents thr…

Autoregressive (AR) video diffusion models have shown great potential in real-time video generation. Recent methods dist…

We study the problem of navigating cluttered indoor environments with a humanoid robot. Unlike conventional methods that…

Weak-to-strong generalization asks whether stronger models can learn from weaker supervisors and surpass them. This ques…

We introduce AuK, an open-source foundational model that unifies speech generation and editing through a common interfac…

Transferring human hand demonstrations to robotic grippers has recently emerged as a cost-effective solution for robot l…

Linear attention is increasingly used in frontier language models for efficient long-context inference and constant-memo…

Speculative decoding accelerates rollout generation, which dominates the cost of reinforcement learning (RL) post-traini…

Model misalignment, prompt injection, or operator misuse could lead AI agents operating frontier-lab accounts to exfiltr…

Visual generation is evolving from generative models used through a single invocation into agentic control processes tha…

Video foundation models increasingly rely on large-scale pretraining data, yet the end-to-end data pipelines behind them…

Latent visual reasoning aims to perform multimodal reasoning through hidden-state computation rather than explicit textu…

Diffusion-based models enable monocular geometry estimation, yet their pixel-space precision is limited by a shared, und…

Generating long-form multi-shot videos requires coherent within-shot motion and visually consistent narratives across sh…

As large language models (LLMs) are increasingly deployed in alignment-sensitive contexts, activation steering has emerg…

Most end-to-end autonomous-driving systems learn by imitating human driving logs, leaving their learned behavior constra…

Large language models (LLMs) are increasingly used to formulate optimization models from natural-language problem descri…

World-action models (WAM) predict future states to guide robot actions, enabling learning from both action-free video an…

Reasoning in large language models unfolds through diverse functional operations, such as problem formulation, goal deco…

We study the problem of generating a compositional 3D representation of a cluttered scene containing hundreds of objects…

Recent advances in automatic rigging now deliver animation-ready 3D assets at scale, yet generating the motion to drive …

Diverse and simulation-ready indoor scenes are essential for interactive entertainment and embodied AI, yet their scalab…

Layer dropout (a.k.a. stochastic depth) has been shown to enable faster training, higher accuracy, and robustness to zer…

LLM agents are rapidly becoming production software, deployed to handle customer service, adjudicate disputes, and opera…

Large Reasoning Models (LRMs) achieve superior problem-solving through extended Chain-of-Thought (CoT) generation, but t…

Vision-language models (VLMs) are expected to respond helpfully to appropriate requests while withholding compliance wit…

We present a continuous, population-scale measurement record of autonomous language-model trading agents operating in pr…

Striking a balance between helpfulness and safety remains a fundamental challenge in aligning large language models. To …

On-policy distillation (OPD) provides dense, per-token supervision for language model post-training, but its effectivene…

Online 3D reconstruction models perform poorly on long videos. This happens because regressing poses relative to a fixed…

We present Iris-mini and Iris-pro, two search agents trained at the 35B-A3B and 397B-A17B scales, together with the data…

Reinforcement Learning from Verifiable Rewards works well when a task has a programmatic checker, but most long-horizon …

Quantization is widely used to reduce the computational and memory demands of neural-network inference. In recurrent net…

A reasoning model can improve from its own on-policy experience, but this inner loop is fragile: terminal verifiers prov…

Audio-video diffusion models rely on cross-modal attention to coordinate text, sound, and visual content, yet this same …

Large language models (LLMs) are increasingly used to edit existing code, but correctness alone is not enough: useful re…

The ambition of the 2025 PNPL competition (Landau et al., 2025) was to launch a multi-year curriculum for non-invasive s…

Long-video language models cannot look at every frame: an hour sampled once per second is 3,600 images, and a system kee…

Despite the remarkable prowess of Vision-Language Models (VLMs) in general multimodal tasks, they remain fundamentally `…

For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and evaluation methods that…

Benchmarks for the side effects an agent causes on the way to a goal already exist, but HarvestBench is the first to put…

Many recurring text functions are easy to describe but difficult to implement with rules, while calling a large remote m…

Designing and authoring high-performance custom kernels for accelerators is a complex task that requires deep hardware-l…

Video editing spans diverse editing paradigms, yet achieving high-quality instruction-guided and subject-guided editing …

We present ENEAS, a unified, text-promptable method for instance tracking and semantic discovery. Text-promptable segmen…

Visual Place Recognition (VPR) localizes a query image by retrieving database images of the same or nearby place, yet it…