When an LLM group's discussion is compressed into a short memory for a final decision maker, what should the memory keep? Two natural heuristics keep the rarest claims or the claim...
Diffusion video models produce striking clips, but they cannot reliably render an exact formula, a correct chart, a rule-consistent game or narration synchronized to on-screen even...
Learning controllable world dynamics from heterogeneous interaction videos is challenging because robot embodiments use incompatible action spaces, while human videos lack native c...
Vision--Language--Action (VLA) models generate robot actions from visual observations and language instructions, but their understanding of physical dynamics remains limited. Video...
Existing multi-agent collaboration (MAC) methods have primarily explored a group thinking collaboration topology, where agents independently generate solutions and aggregate their ...
Diffusion vision-language models (DVLMs) process their entire input at every denoising step. Since visual tokens make up 89-97% of this input on the benchmarks we study, most of th...
We present EmbeddingGemma 2, an open multimodal embedding model which natively represents text, images, audio, video, and combinations thereof in a unified space. Our approach intr...
Metis is a bet that better data, better training methods and new architectures can buy what a bigger parameter count cannot, at a fraction of the cost. Metis-1.6 is its latest step...
Large language models (LLMs) have shown increasing promise in research-level problem solving, yet a comprehensive collection of such problems is still missing, and evaluating them ...
Low-cost arms such as the SO-101 have become the most common entry point to robot learning, yet no released policy performs spatially constrained, language-conditioned tasks on the...
Classification accuracy and true-positive and false-positive rates alone do not determine whether restarting an AI agent improves success. Using an exact alarm-to-action identity f...
AI research agents can propose, execute, and improve programs that solve machine learning tasks. However, executing each candidate program requires training and evaluating ML model...
Large Language Models (LLMs) are increasingly used in multi-turn agentic workloads that require sustained interaction with complex environments. Existing reflective prompt optimize...
Agentic services alternate between model inference on clustered GPUs and external tools on distributed CPUs. In this scenario, existing systems (1) overlook tool-return readiness i...
Fine-tuning Large Language Models (LLMs) on instruction data can quietly erode their safety, even when no training example looks harmful. Because this safety-degrading data looks b...
Unified conditional image generation requires a single model to preserve different aspects of a visual input while producing a target image that follows textual guidance. Pretraine...
Real-world forgery is inherently heterogeneous: it manifests not only as digital manipulation but also as physical spoofing, and is carried not only by images but also by videos. D...
Language model agents are post-trained and deployed through a harness, the prompts, tools, and control logic that present a task to the model and execute its outputs. Harnesses are...
Interactive world generation requires models to follow successive commands while preserving relevant history and action consequences. We present Hy-Nomas, a video world model with ...
Scientific discovery often begins with an unexpected observation that prompts a new research question. In a world with altered physical laws, can large language models (LLMs) notic...
We propose Nemotron-Labs-Diffusion-Uni (NLD-Uni), a unified discrete diffusion large language model (DLLM) for visual understanding and generation tasks. Compared with prior unifie...
Video stylization typically transforms entire scenes, while local artistic editing requires precise region--style association, spatial control, and temporal consistency. We introdu...
Discrete visual tokens represent vision in a discrete form analogous to language, offering a native interface for multimodal modeling under a shared next-token prediction objective...
Reasoning language models generate thousands of tokens per answer, and generation speed is limited by memory bandwidth, so storing weights in two bits instead of bfloat16 can poten...