Benchmark researchers and developers of large language models (LLMs) and other AI systems need to find relevant evaluati…

A research idea may be novel, coherent, and scientifically plausible, yet its proposed method may remain insufficiently …

Recent advances in wearable sensing enable continuous monitoring of physiological and behavioral signals, yet existing b…

Paper2Agent, published in Nature, converts papers into validated MCP tools, scoring 91.2% on 300 questions across 74 pap…

World-action models (WAMs) jointly model future observations and actions, typically predicting the future as RGB images.…

Interactive control for video generation is moving from coarse prompts toward fine-grained, physically meaningful manipu…

Traditional multimodal representation learning and generation are two stages: a contrastive or self-supervised visual en…

As AI agents move from bounded tasks to persistent deployments, failures can propagate through memory, tools, other agen…

Foundation models, alongside advances in learned game-world models, are reshaping AI across the game lifecycle. Beyond p…

We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving sc…

Language model-generated rubrics are increasingly used as reward signals for rubric-based reinforcement learning, LLM-as…

Safety guardrails in open-weight language models can be readily bypassed using Refusal Feature Ablation (RFA), a techniq…

Digital agents must often adapt to new environments whose interfaces, tools, and failure modes are not fully captured by…

We present PhysBrain 1.5, a unified model for understanding physical environments, generating actions, and predicting fu…

Training prompts in online reinforcement learning (RL) differ substantially in how informative they are for the current …

Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enab…

Orthrus is a hybrid autoregressive-diffusion architecture that accelerates autoregressive language-model inference by ge…

Native 3D generators turn one image into a single mesh. TRELLIS.2 and its peers deliver high-fidelity non-watertight geo…

Multimodal agents can create complex videos in software such as Blender by coding without relying on diffusion models. Y…

Skills extend an LLM agent beyond its parametric knowledge, and the gain they promise rests on picking the right one. De…

Transformer representations evolve through learned additive transformations that either preserve their current direction…

Foundation models have progressed from learning and reasoning over existing knowledge, to increasingly learning through …

Backdoor poisoning attacks add poisoned examples to otherwise-clean finetuning data, pairing a trigger with a target beh…

A radiology report can already answer a clinical question, so it is hard to tell whether a vision-language model also us…

Vibe design agents turn natural-language briefs into rendered interfaces and frontend code. Yet a useful design agent sh…

Large language model (LLM) agents allocate test-time compute adaptively as they revise solutions, use tools, explore alt…

As language models become more capable, long-term collaboration in learning, reasoning, and decision-making calls for a …

Video diffusion models are stochastic and hard to control: precise content often requires repeated sampling without guar…

Recursive self-improvement is becoming increasingly vital for autonomous AI agents, where progress hinges on discovering…

Embodied navigation requires agents to interpret visual observations, accumulate spatial knowledge, and execute actions …

Computer-use agents increasingly interact with browsers, terminals, file systems, and external services, introducing saf…

Streaming omni-modal models must decide what and when to answer from the video chunks and synchronized audio observed so…

As AI agents become participants in the development of their successors, they reshape both the production of intelligenc…

Interactive video world models must maintain broad scene context under camera motion while producing high-fidelity obser…

This paper reports experiments across six frontier model types from OpenAI, Anthropic, xAI, and Google DeepMind. Ten ind…

A core goal of efficient reasoning is to improve the accuracy-efficiency frontier. However, jointly improving reasoning …

Unified multimodal large language models (MLLMs) and multi-agent systems have advanced visual generation. However, three…

Can financial vision-language models (VLMs) turn chart evidence into reliable action recommendations? Existing hallucina…

A central tenet of human cognition is systematicity, the principle that understanding one concept is inherently tied to …

Specialist distillation effectively transfers domain expertise to student models via teacher-generated reasoning traject…

Realtime spoken interaction demands deep reasoning, prompt responses, and fluid turn-taking. We present StepAudio 3 Real…

Fine-tuning instruct models often improves target performance while inducing behavioral drift from the reference model, …

Few-shot in-context learning (ICL), the capacity of a model to infer abstract patterns from input-output examples provid…

Visual goal and dynamics prediction can provide language-conditioned robot policies with both a target outcome and a rep…

We introduce StepAudio 3 Music, a large-scale, long-form music generation model that supports explicit musical planning …

When we speak of recursive self-improvement (RSI), are we speaking of a phenomenon, a mechanism, or a prospect? Towards …

Robot foundation models achieve strong in-distribution performance but often degrade under visual distribution shifts. W…

Reinforcement learning (RL) has become central to post-training of large language models. Recent advances in RL for Mixt…

In this work, we present ZGCM-1, a fully open 7B dense foundation model trained from scratch with extreme data, system, …

We introduce StepAudio 3 Gen, a general-purpose audio generation model that supports zero-shot text-to-speech (TTS), voi…