AI各社の公式発表を1画面に。各社のページを個別に開かなくても最新の動きが追えます。
WM-VLM：ビジュアル・テキスト推論用の内部世界モデルの探査
Humans often solve spatial problems by mentally simulating visual transformations. In contrast, conventional vision-language models (VLMs) reason primarily through language. We investigate whether VLMs can solve spatial problems by reasoning with both text and generated visual states. To this end, w…
PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs
Physical trajectories contain more than snapshots of a system: they also reveal how its states evolve under governing conditions. However, representation learning for parametric partial differential equations (PDEs) has largely relied on reconstruction-based objectives that emphasize recovering obse…
RL環境がハブに登場
Persona Dosing: 段階的な特性制御のための校正活性化ステアリング
An activation-steering coefficient sets intervention strength, but requesting a particular degree of persona expression requires a behavioral scale. We study persona dosing: controlling a language model through a trait description and a requested mean intensity. PersonaDose specializes a shared, des…
オンポリシーか、オフポリシーか: 蒸留ダイナミクスの体系的研究
On-policy learning has been argued to reduce catastrophic forgetting, produce sparser parameter updates, and improve generalisation. However, existing comparisons between supervised fine-tuning and reinforcement learning vary many factors simultaneously, making the contribution of rollout policy dif…
エージェント事前知識を活用したポリシー学習
Robots that learn from a few demonstrations often require two forms of generalization. Compositional generalization recombines skills to solve new tasks, and skill generalization lets the learned policy behind each skill work in new situations. The two depend on each other, yet information is lost b…
潜在視覚推論の再考: 視覚証拠に基づいた潜在推論の基礎づけ
Latent visual reasoning (LVR) enables multimodal large language models (MLLMs) to perform intermediate computation in continuous latent tokens rather than expressing every reasoning step in words. However, unlike textual CoT, latent reasoning is not directly observable, making it difficult to superv…
周期的な弱点：チャンク化 KV キャッシュ圧縮からのフェーズ感度
Chunked KV-cache compression reduces the memory and attention costs of long-context inference by compressing windows of consecutive tokens into fewer cache entries at a fixed stride. Such compression also introduces a new positional coordinate: a token's phase, or its position relative to compressio…
LEGO-Anything：3Dシーン再構成用コーディングエージェント
A 3D scene reconstructed from a single image is most useful when represented not as a rendering or a fixed 3D output, but as an explicit scene program whose execution yields a scene that can be inspected, edited, and queried. We present LEGO-Anything, an Image-to-Code framework in which a coding age…
LLMは汎用非同期エージェント
Modern LLMs are increasingly capable as autonomous agents, but they follow sequential interaction cycles: read, think, reply or call tools, repeat. Many real-world use cases are not sequential: voice assistants, embodied agents, and monitoring systems receive new inputs while they think or perform a…
LongCat-DeepResearch技術報告書
We present LongCat-DeepResearch, a deep research system that combines an enhanced LongCat model with a multi-agent workflow for producing comprehensive, evidence-grounded reports. The workflow separates global planning from detailed investigation and coordinates revision at the section level. Multip…
PanoVLN：効果的なパノラマビジョン・言語ナビゲーションへ向けて
Recent vision-language models (VLMs) have advanced vision-and-language navigation (VLN), enabling models to predict navigation actions from visual observations and language instructions. In this work, we explore VLN with panoramic observations and introduce PanoVLN. The motivation is straightforward…
SentZero：胸部X線画像の多タスク少数ショット分析向け強化型文中心ビジョン言語事前学習
Vision-language (VL) pretraining using paired chest X-ray (CXR) images and radiology reports has shown strong potential for medical image understanding. However, existing methods often remain dependent on task-specific finetuning because radiology reports are lengthy, clinically dense, and difficult…
WorldPlay2：制御とホライズンにおける実時間インタラクティブワールドモデルの拡張
Interactive world models require responding in real time to versatile controls and maintaining long-horizon consistency. However, modeling heterogeneous controls remains difficult, while explosive contexts and unstable distillation impede achieving both long-horizon consistency and real-time respons…
思考が十分でない時を知る：小規模推論モデルにパラメトリック知識を超えた推論を教える
Scaling test-time computation is a powerful way to improve language-model reasoning, and is particularly appealing for small reasoning models (sRMs) that are cheap to serve. However, is additional thinking always the right operation? By intervening at intermediate reasoning states across two model f…
インターリーブ強化学習による統一モデル内での原生的反射学習
Unified multimodal models can both look at and render images, so in principle they can repair their own generations: diagnose what an image gets wrong, revise it, observe the result, and diagnose again. Whether a revision helps is known only after it is rendered, so the reflection text and the image…
ビジュアルエンコーダ除去はどこまで可能か：エンコーダフリーマルチモーダル事前訓練のスケーリング則
Most modern multimodal large language models (MLLMs) build on a pretrained visual encoder that provides a strong visual prior. Encoder-free MLLMs instead learn visual representations directly from raw pixels, offering a simple and unified architecture, but their scaling behavior has not been systema…
教師割り当てを超えて：領域正規化マルチ教師オンポリシー蒸留
Reinforcement learning can turn one language model into several specialists, each excellent at a single skill such as mathematics, coding or following instructions, but users need one model with all of these skills. Multi-teacher on-policy distillation (MOPD) merges them by letting the specialists t…
BasisがGPT-6 Astraで税務ワークブック作成を2倍高速化
GPT-6 Astra completed a 50-tab tax workbook twice as fast as GPT-5.6 Sol, and its stronger understanding of user intent gives Basis more confidence in real-world use.
あなたはCodex Originalですか？
We’re collecting real stories of builders, tinkerers, researchers, and creators who are using Codex to do incredible things. If you want to be a part of the next chapter of the Codex Originals program, tell us more about your story and project below.
SAIL: インコンテキスト模倣学習のスケーリング
関連性は適用可能性を示さない: パーソナルGUIエージェント向け経験活性化
Personal Graphical User Interface (GUI) agents rely on interaction history to infer what a user wants from ambiguous instructions and to anticipate recurring routines. Existing approaches retrieve task-relevant history and append it to the policy's context, implicitly assuming that experience releva…
状態の解き明かし: マスク付き拡散言語モデルで状態適応がいつ重要か
Masked diffusion language models (MDMs) admit flexible generation orders, making the unmasking strategy an inference decision. Existing methods vary in how they prioritize positions, control parallelism, restrict selection regions, revise predictions, or plan future denoising, yet it remains unclear…
ロボット操作のためのエージェント間再帰的ハーネス蒸留
A central goal in robotics is to enable manipulation across changing tasks and environments. Vision-language-action (VLA) models provide broad manipulation capabilities but can struggle when execution requires diagnosing failures and adapting behavior. Strong agents can discover effective interventi…
VisionHOPE：自己修正学習システムとしてのビジュアルバックボーン
Visual backbones have evolved from Convolutional Neural Networks (CNNs) with local aggregation to Vision Transformers (ViTs) with global interactions, State-Space Models (SSMs) with input-dependent state transitions, and Test-Time Training (TTT) layers that adapt an inner learner while processing an…
WideSWE：コーディングエージェントは複数リポジトリ間での変更を統括できるか
Coding-agent evaluation has progressed from resolving individual issues to carrying out long-horizon development, yet task completion is still largely assessed within a single codebase. In software ecosystems, many features and bug fixes require coordinated changes across multiple repositories. We i…
QwenGyre：超長期タスク実行エージェント向け弾性強化学習フレームワーク
Large language model (LLM) agents increasingly undertake extreme-long (xlong) horizon tasks, where a single execution can span hours, hundreds of model--environment interactions, and nearly 1M tokens per rollout. Applying online reinforcement learning (RL) to such executions poses two fundamental ch…
X-Tree——再利用可能な経験をトークン化し、エージェントの汎化を効率化
Multi-step agents are trained on flat action streams: SFT and RLVR weight every token uniformly and ignore the sub-procedures that recur across tasks, the hierarchy that lets humans plan top-down from reusable routines. This structure sits unused, and flat training uses each scarce trajectory less f…
LANTERN: 言語モデルに隠された数学知識の可視化
Language models can now prove theorems, but people still decide which problems to pursue. We ask whether a model's internal representations can help identify promising mathematical connections. We develop LANTERN, a fast, cost-efficient pipeline that uses a classifier over pretrained-model activatio…
同一ファミリー方策蒸留のスケーリング特性
*Reinforcement learning (RL)* can induce substantial reasoning capabilities in large language models (LLMs), but how much of this capability transfers across model scales, and how quickly, remains unclear. We study the scaling properties of *on-policy distillation (OPD)* across *weak-to-strong*, *sa…
二者間メモリを超えて：多者間音声会話向けインタラクション認識マルチモーダルメモリと適応型エージェント検索
Long-term memory enables agents to accumulate information and reason across sessions, yet existing research primarily focuses on dyadic text or image-text conversations, leaving long-term memory for multi-party spoken conversations underexplored. This setting requires preserving conversational conte…
VoxMem：大規模音声言語モデルのマルチモーダルメモリベンチマーク
Spoken conversational systems must recover information from prior interactions (i.e., memory), yet relevant information in speech extends beyond what was said to who said it, how it was spoken, and what was audible, information that exists only in the audio signal and cannot be recovered from a tran…
クリーンアンカー付きイン・フライトKVキャッシュによる高速自己回帰ビデオ拡散
Few-step autoregressive video diffusion generates a long video by splitting the video into temporal chunks and generating chunk-by-chunk, each through a short sequence of denoising stages. To memorize chunks that are already generated, previous methods reconstruct a clean or less-noisy key--value (K…
コードエージェントRL用グループワイズエージェント採点と優位性再配分
Reinforcement learning (RL) for code agents often uses executable tests to provide binary rewards. With these rewards, Group Relative Policy Optimization (GRPO) assigns identical advantages to test-passing trajectories within each rollout group, overlooking differences in implementation quality and…
DepthBench：残差接続が計算深度を有効にするメカニズムの測定
Depth is a natural way to increase the computational capacity in Transformers, yet the contribution of deeper layers can diminish as depth grows larger. Recent approaches enhance normalization (e.g., LayerNorm Scaling) or residual connections (e.g., mHC, AttnRes) to enable better information flow an…
Codexで売上60%増、75時間以上を削減したProaction
With Codex, GPT-Live-1, and GPT-6 Astra, Proaction builds, operates, and sells modern fleet management faster.
Loweが OpenAI を活用して数百万件の住宅改善の質問に回答
Lowe’s uses OpenAI models to power Mylow and Mylow Companion, helping customers and associates answer 25M+ questions and move home improvement projects forward.
WayfairがOpenAIでカタログ精度とサポート速度向上
Wayfair uses OpenAI models to improve ecommerce support and product catalog accuracy, automating ticket triage and enhancing millions of product attributes at scale.
分散型Master-Mind：マルチエージェント経路探索における反復的インテント除去を通じた共同アクション改善
Decentralized multi-agent path finding (MAPF) with communication requires agents to reach individual goals without collisions under partial observability. Learnable policies trained on expert data provide an effective approach to this problem. However, when several coordinated joint actions are vali…
Omni-IOスキル：エージェントOmni-Nativeを活かす
General-purpose agents can plan, reason, and act over long horizons, yet their production capabilities remain fragmented across text, images, audio, video, documents, 3D assets, and code. Extending a foundation model to additional modalities ties capability growth to costly model updates, while asse…
Duplex-MPE：全二重対話における多者インタラクションのベンチマーク
Real-time full-duplex speech models can listen while speaking, enabling natural interaction without rigid turn boundaries. Existing benchmarks evaluate turn-taking, interruption handling and multi-round dialogue, but largely centre on a designated user rather than an assistant participating in a sha…
対数線形複雑性を持つブロック疎行列注意機構
Scaling language models to long contexts is limited by the quadratic cost of self-attention. Block sparse attention offers an efficient alternative, but selecting the retained blocks remains a bottleneck. Conventional block selection requires scoring all query-block pairs and therefore remains quadr…
InternW0-Δ: 予測ダイナミクスと行動を橋渡しする世界行動モデル、2万時間以上のオープンデータを活用
World Action Models (WAMs) jointly model visual dynamics and action generation for generalist robot manipulation. A central challenge is to integrate priors from large-scale pretrained models---including visual dynamics, scene semantics, geometry, and motion---into a unified framework for robot acti…
FuseReg: 層融合の正則化が表現オートエンコーダーの再構成生成ギャップを緩和
Representation autoencoders (RAEs) reuse features from a pretrained visual encoder as reconstruction and diffusion latents, integrating strong visual representations into image generation. However, RAEs still need to decide which encoder layers form the shared latent space for the generator and pixe…
OpenAI API Changelog 2026-09-25
Fix gpt-6-sol gpt-6-luna Fixed a bug in image encoding that degraded image understanding in GPT-6 Sol and GPT-6 Luna . This update improves results on visual tasks in the API and Codex, including computer use. If your use cases involve image inputs, we recommend rerunning your evaluations and retryi…
拡張されたモデル選択肢、音声エージェント、継続的最適化によりエージェントを高速デプロイ
The best model for your business will keep changing. Adopting it should move your business forward, not send your team back to rebuild the architecture around it. The post Ship agents faster with expanded model choice, voice agents, and continuous optimization appeared first on Microsoft Azure Blog…
Gemini 3.8 Liveとライブアバター機能を発表
an image with the phrase "Gemini 3.8 Live with Live Avatar"
LFM2.5-VL-DSpark でビジョン言語モデルを高速化
事後訓練は無関連な判断に行動的影を残す
We find that language models can transfer capabilities through task-unrelated text. Post-training typically improves language models using task-specific data. Prior work on subliminal learning shows that information about these updates can pass through unrelated generations, but has largely focused…