Search Results for "act"

...The motivation is to move beyond “text in, text out” and enable direct, live, multi-turn exchange involving language, gesture, gaze, vision, and modality switching without user friction. The system architecture includes a real-time multimodal signal pipeline for audio, video, and sensor data, a dialog manager that can decide when to act (speak, gesture, point) or query, and a cross-modal reasoning layer that fuses perception with semantic context. The research prototype includes components for visual grounding (understanding when a user references something in view), gesture recognition and synthesis, and turn-taking mechanisms that mirror human conversational timing. ...

Sapiens is a research framework from Meta AI focused on embodied intelligence and human-like multimodal learning, aiming to train agents that can perceive, reason, and act in complex environments. It integrates sensory inputs such as vision, audio, and proprioception into a unified learning architecture that allows agents to understand and adapt to their surroundings dynamically. The project emphasizes long-horizon reasoning and cross-modal grounding—connecting language, perception, and action into a single agentic model capable of following abstract goals. ...

...Unlike many vision-language models that treat images and text separately or require intermediate conversions, GLM-4.6V allows inputs such as images, screenshots or document pages directly as part of its reasoning pipeline — and can output or act via tools seamlessly, bridging perception and execution. Its architecture supports a very large context window (on the order of 128K tokens during training), which lets it handle complex multimodal inputs like long documents, multi-page reports, or video transcripts, while maintaining coherence across extended content. In benchmarks and internal evaluations, GLM-4.6V achieves state-of-the-art (SoTA) performance among models of comparable parameter scale on multimodal reasoning.

DeepResearch (Tongyi DeepResearch) is an open-source “deep research agent” developed by Alibaba’s Tongyi Lab designed for long-horizon, information-seeking tasks. It’s built to act like a research agent: synthesizing, reasoning, retrieving information via the web and documents, and backing its outputs with evidence. The model is about 30.5 billion parameters in size, though at any given token only ~3.3B parameters are active. It uses a mix of synthetic data generation, fine-tuning and reinforcement learning; supports benchmarks like web search, document understanding, question answering, “agentic” tasks; provides inference tools, evaluation scripts, and “web agent” style interfaces. ...

The Video PreTraining (VPT) repository provides code and model artifacts for a project where agents learn to act by watching human gameplay videos—specifically, gameplay of Minecraft—using behavioral cloning. The idea is to learn general priors of control from large-scale, unlabeled video data, and then optionally fine-tune those priors for more goal-directed behavior via environment interaction. The repository contains demonstration models of different widths, fine-tuned variants (e.g. for building houses or early-game tasks), and inference scripts that instantiate agents from pretrained weights. ...