Recovering an editable design file from a raster image is a common and costly bottleneck in modern design workflows, yet remains challenging since editability depends on recovering...
Learning deployable manipulation policies is bottlenecked by the scarcity of data that is both high-fidelity and scalable. Real-robot teleoperation is accurate but costly to scale;...
In the age of foundation models, a model is only as good as its prompt. For this reason, prompt engineering has become an essential technique for improving language model performan...
Emerging Omni-modal Large Language Models (OmniLLMs) enable unified understanding of text, audio, and video, but their long audio-video token sequences introduce substantial memory...
We present Wonder, a general-purpose video world model for real-time, camera-controllable world exploration. Given an image or a conditional video, Wonder constructs a playable wor...
We introduce Shieldstral, a 3B-parameter policy-adaptive multimodal safety classifier that matches or outperforms models nearly 7times its size on text safety benchmarks and sets a...
While data curation for Vision Language Models (VLMs) is increasingly active, public practice for constructing pretraining mixtures remains largely heuristic: practitioners stack d...
Agentic search enables large language models to solve knowledge-intensive tasks by interleaving multi-step reasoning with retrieval, yet optimizing this with outcome-based reinforc...
Multimodal large language models (MLLMs) hold immense potential to revolutionize clinical practice, yet deploying them in the medical domain is fundamentally a vision-centric chall...
Multimodal foundation models learned to see and to speak by consuming the whole internet. Embodied agents admit no such shortcut, since they require data that couple observations w...
Many recent robot policies pursue stronger control by using large pretrained vision-language models (VLMs) as the action backbone. We introduce WorldDiT, a unified diffusion transf...
On-policy distillation (OPD) adapts diffusion models by querying a teacher along trajectories generated by the current student, but how it should behave under classifier-free guida...
Diffusion transformers are essential for high-fidelity video generation, but long token sequences make attention a dominant inference bottleneck. Training-free dynamic sparse atten...
Progress in video generation keeps narrowing the visual gap between AI-generated and professionally produced footage, yet most benchmarks still draw prompts from web sources or LLM...
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is ...
Standard vision-language models (VLMs) suffer from Moravec's paradox: they excel at complex offline visual reasoning but struggle with simple streaming perception tasks and process...
Relevance is a query-dependent estimate of whether a document or excerpt contains useful evidence. Existing retrieval agents use relevance to select top-k content, but document rel...
We introduce PerceptionBench, a benchmark specifically designed to evaluate the atomic visual perception capabilities of Multimodal Large Language Models (MLLMs). Existing benchmar...
Long-term memory systems store what a user says in an external store and retrieve it when a related query arrives. This interface rests on an assumption so natural that it is rarel...
The alignment of Small Language Models (SLMs) in the 70--500M parameter range using reinforcement learning is often considered unstable, though the underlying failure mechanisms ha...
Multi-turn long-horizon planning is critical for foundation model agents, yet how to fundamentally improve it remains unclear. Existing models are trained on uncontrollable and opa...
Reliable visual document understanding requires a model to attribute each answer to the evidence regions that support it. Recent benchmarks and systems express this step through a ...
The rapid evolution of generative models has unlocked new potentials in protein binder design, a pivotal task in structural biology, by facilitating end-to-end generation via joint...
Recent generative models are moving beyond silent video or standalone audio synthesis toward the joint generation of synchronized audio and video. Despite this progress, jointly ge...