#01
Gemini Omni 1.1 Flash lets you build with more control
推荐理由Gemini 是模型能力或接入方式上的更新。
Pai 的 AI 雷达
今天：Gemini Omni 1.1，Agentic Game Development（Agent 原型）。并行还有 TTPO、What Makes Good、Training Agents to。
A common strategy for scaling world models is to train on more crawled video with more compute. We argue that this strategy is inefficient: scaling world models also requires a recursive data engine that offers grounded
Recent prominent post-training methods, such as Reinforcement Learning (RL) and On-Policy Self-Distillation (OPSD), have driven rapid progress in mathematical reasoning for large language models, yet their reliance on gr
LLM agents increasingly rely on generated interaction data to learn how to interact with external environments. Agentic data generation must maintain consistency among environments, tasks, interactions, and success signa
AI-powered digital avatar streamers must answer product questions, engage viewers, and execute marketing strategies in real time, demanding low latency, frequent strategy updates, and accurate yet effective responses. Ev
Modern video games combine first-person perception, rapid visual changes, persistent world state, and heterogeneous native controls. Existing game agents map visual and task context directly to actions but lack explicit
Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent experience, which enables agents to progressi
Native 3D generators now recover impressive mesh geometry from a single image. However, a dense mesh stays soft where a machined object should be sharp, it carries no part decomposition, and it exposes no parameter a use
While generative AI has significantly advanced video editing, existing methods primarily focus on single-shot or short video clips. Editing long videos with multiple instructions remains a formidable challenge. Naive chu
Recent video generation models are increasingly framed as world models. Many physical processes can unfold in more than one valid way. Therefore, a world model should reproduce not only a plausible trajectory, but also t
Multimodal large language models (MLLMs) can interpret a street view, but urban agency depends on whether such local evidence remains useful after the agent starts to move. In this paper, we investigate how far current M
On-policy distillation (OPD), which leverages a pre-trained, specialized teacher model to provide dense supervisory signals, has achieved significant success in Large Language Models (LLMs) and has recently been adapted
Long-horizon agent runs generate experience that can improve both the current run and future work. Most self-improvement methods process this experience only after execution ends, so they cannot redirect the active run o
Zero-shot cross-task generalization, where a policy must execute manipulation tasks never seen during training, remains a central challenge in robot learning. In large language models, a novel task can be performed simpl
Evolution Strategies (ES) have recently emerged as a memory-efficient post-training paradigm for LLM reasoning. However, the optimization behavior of ES remains understudied, making it hard to define its advantage scope
High-fidelity image-to-3D generation requires a 3D representation that captures both geometry and appearance. To support relighting and integration into standard rendering pipelines, the representation should include phy
Recent advances in inference-time scaling have significantly improved the reasoning performance of large language models (LLMs). However, these methods typically rely on repeated generation or external verification. To a
Modern game development relies heavily on conventional graphics pipelines. High-quality visual content requires modeling, material authoring, animation, lighting, effects, and runtime optimization, making asset productio
Large-scale vision-language models (VLMs) have demonstrated remarkable versatility across a wide range of multimodal tasks. However, understanding humor remains challenging because humorous content often depends on subtl
Contact-rich manipulation requires adapting to contact states that can evolve substantially within an action horizon. However, chunk-based vision-language-action models predict complete action chunks from observations co
Explicit visual intermediates can help multimodal large language models (MLLMs) externalize spatial evidence and updated visual states, but their utility depends on whether an image editor can faithfully realize the requ
Reusable skill libraries allow large language model (LLM) agents to reuse procedural knowledge across tasks, but they also turn memory access into a challenging retrieval problem. Full-library prompting preserves coverag
Conventional video editing primarily focuses on scene-level content, whereas live streaming places greater emphasis on the human subject. However, directly applying existing video-editing methods to human-centric live st