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…

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 …

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…

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…

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…

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…

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 …

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

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…

The increasing deployment of AI agents in long-horizon tasks yields massive execution logs. Diagnosing failures within t…

Reinforcement learning with verifiable rewards is typically performed on-policy, keeping training data close to the curr…

Post-training attention sparsification reduces the quadratic cumulative attention cost of pretrained Transformers by sel…

We demonstrate that a general-purpose agent can directly drive a physical robot throughout task execution without any ta…

We report a multi-month engineering program to build Sophea, a production bilingual Greek-English automatic speech recog…

Part-aware 3D asset generation enables applications such as editing, articulation, simulation, and fabrication, yet exis…

Code world models represent worlds as executable programs, but this representation alone does not determine how to const…

We present our submission to the EgoProactive track of the ECCV 2026 Wearable AI Challenge, which ranked first in the la…

We present Vidu S2, which comprises Vidu S2-Avatar, a real-time interactive digital-character model, and Vidu S2-Editing…

We describe our entry to the EgoLongQA track of the Wearable-AI Challenge in ECCV 2026, which placed first in the

3D point-cloud observations are inherently ambiguous in complex, cluttered manipulation scenes, where target objects may…

Optical flow methods typically rely on task-specific inductive biases, such as correlation volumes, feature warping, and…

Large language model (LLM) agents can benefit from reusable skills distilled from prior task experience, yet existing sk…

Objects in post-fire environments often undergo irreversible physical transformations that change their geometry, materi…

Iterative reference-conditioned image editing can introduce grid-like and granular textures, commonly described as digit…

In hybrid forecasting, a language model is often one of several available signals. A system may already have a market, c…

Multi-Agent Reinforcement Learning (MARL) has emerged as a pivotal paradigm for complex decision-making in autonomous sy…

Reducing audio-encoder depth lowers the inference cost of speech large language models, but removing complete blocks per…

Neurosymbolic systems rely on mathematical solvers to guarantee reasoning correctness, yet solvers are fundamentally bli…

In this technical report, we propose Pelican-Sim 1.0, a general world model simulator for embodied intelligence that pre…

Mainstream robotic policies often adopt a Markovian formulation, but many complex real-world manipulation tasks are inhe…

Autoregressive video world models enable interactive, long-horizon exploration, but flexible control remains challenging…

On-Policy Self-Distillation (OPSD) has emerged as a popular paradigm for large language model (LLM) self-improvement, al…