Lens

Big on quality. Light on compute. Meet MAI‑Image‑2‑Efficient, our production model built for rapid iteration—delivering 4× the efficiency of MAI‑Image‑2. Learn more here: https://t.co/d3SF9gAmqG https

Big on quality. Light on compute. Meet MAI‑Image‑2‑Efficient, our production model built for rapid iteration—delivering 4× the efficiency of MAI‑Image‑2. Learn more here: https://t.co/d3SF9gAmqG https://t.co/vGH1wotBuh

The most accurate model across 25 languages, faster transcription speeds, and stronger performance in real‑world noise. MAI‑Transcribe‑1 sets a new bar for speech recognition. Learn more + try it toda

The most accurate model across 25 languages, faster transcription speeds, and stronger performance in real‑world noise. MAI‑Transcribe‑1 sets a new bar for speech recognition. Learn more + try it today: https://t.co/zBY6ZuqWMN https://t.co/yC3o4slXiW

MAI‑Transcribe‑1 makes speech‑to‑text clearer, faster, and more reliable even in noisy audio. Ranked #1 on the industry-standard FLEURS word error rate benchmark. Now in public preview. Learn more: ht

MAI‑Transcribe‑1 makes speech‑to‑text clearer, faster, and more reliable even in noisy audio. Ranked #1 on the industry-standard FLEURS word error rate benchmark. Now in public preview. Learn more: https://t.co/Gr4Q8jgCwL https://t.co/L6hndn3D34

Meet MAI‑Image‑2. Built with creatives, for real creative work. Ranked #5 on @arena’s text‑to‑image leaderboard. Available now: https://t.co/qT5nArWDm6 https://t.co/fWoDgxlCf5

RT Mustafa Suleyman: It's a big day. Our Superintelligence team will be the first to use Maia 200 as we develop our frontier AI models.

RT Mustafa Suleyman: All of today's @Copilot announcements boil down to one core idea: we're betting on humanist AI. An AI that always puts humans fir...

SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation

Multimodal Large Language Models (MLLMs) have made rapid progress in spatial intelligence, yet existing spatial reasoning benchmarks largely assume pristine visual inputs and overlook the degradations that commonly occur in real-world deployment, such as motion blur, low light, adverse weather, lens distortion, and compression artifacts. This raises a fundamental question: how robust is the spatial intelligence of current MLLMs when visual observations are imperfect? To answer this question, we introduce SpaceDG, the first large-scale dataset for degradation-aware spatial understanding. It is constructed with a physically grounded degradation synthesis engine that embeds degradation formation process into 3D Gaussian Splatting (3DGS) rendering, enabling realistic simulation of nine degradation types. The resulting dataset contains approximately 1M QA pairs from nearly 1,000 indoor scenes. We further introduce SpaceDG-Bench, an human-verified benchmark with 1,102 questions spanning 11 reasoning categories and 9 visual degradation types, yielding over 10K VQA instances. Evaluating 25 open- and closed-source MLLMs reveals that visual degradations consistently and substantially impair spatial reasoning, exposing a critical robustness gap. Finally, we show that finetuning on SpaceDG markedly improves degradation robustness and can even surpass human performance under degraded conditions without any performance drop on clean images, highlighting the promise of degradation-aware training for robust spatial intelligence.

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models

We introduce Lens, a 3.8B-parameter T2I model that achieves performance competitive with, and in several cases surpassing, state-of-the-art models with more than 6B parameters across various benchmarks, while requiring significantly less training compute. For example, Lens requires only about 19.3% of the training compute used by Z-Image. The training efficiency of Lens stems from two key strategies beyond its compact model size. First, we maximize data information density per training batch by (i) training on Lens-800M, a dataset of 800M densely captioned image-text pairs whose captions are generated by GPT-4.1 and contain approximately 109 words on average, providing richer semantic supervision than conventional short captions, and (ii) constructing each batch from images with multiple resolutions and diverse aspect ratios, thereby enlarging the effective visual coverage of each optimization step. Second, we improve convergence speed through careful architectural choices, including adopting a semantic VAE that provides better latent representations and employing a strong language encoder that accelerates optimization while enabling multilingual generalization from English-only training data. After pre-training, we apply RL with taxonomy-driven prompts (Lens-RL-8K) and structured reward rubrics to suppress artifacts and improve visual quality, a reasoner module with training-free system prompt search to better align user requests with the model, and distillation-based acceleration for 4-step inference. Through efficient training and systematic optimization, Lens generalizes to arbitrary aspect ratios from 1:2 to 2:1 and resolutions up to 1440^2, and supports prompts in several commonly used languages. Thanks to its compact size, Lens generates a 1024^2 image in 3.15 seconds on a single NVIDIA H100 GPU, while its distilled turbo version performs 4-step generation in 0.84 seconds.

Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning

Scaling test-time compute by iteratively updating a latent state has emerged as a powerful paradigm for reasoning. Yet the internal mechanisms that enable these iterative models to generalize beyond memorized patterns remain unclear. We hypothesize that generalizable reasoning arises from learning task-conditioned attractors: latent dynamical systems whose stable fixed points correspond to valid solutions. We formalize this process through Equilibrium Reasoners (EqR), which enable test-time scaling without external verifiers or task-specific priors. EqR scales internal dynamics along two axes: depth, by running more iterations, and breadth, by aggregating stochastic trajectories from multiple initializations. Empirically, gains from test-time scaling are tightly coupled with stronger convergence toward solution-aligned attractors. This attractor perspective allows neural networks to adaptively allocate test-time compute based on task difficulty. While simple cases converge within 1 to 5 iteration steps, harder cases benefit from massive test-time scaling. By unrolling up to the equivalent of 40,000 layers, scalable latent reasoning boosts accuracy from 2.6% for feedforward models to over 99% on Sudoku-Extreme. These results suggest that learned attractor landscapes provide a useful mechanistic lens for understanding scalable reasoning in iterative latent models.

AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation

Evaluation of software engineering (SWE) agents is dominated by a binary signal: whether the final patch passes the tests. This outcome-only view treats a principled solution and a chaotic trial-and-error process as equivalent. We show that this equivalence is empirically false. We evaluate 2,614 OpenHands trajectories from eight model backends on 60 SWE-bench Verified tasks. Of these, 47 have enough passing trajectories to construct task-level process references, yielding a 1,815-trajectory evaluation subset. Among passing trajectories in this subset, 10.7% exhibit behavior we call a Lucky Pass: regression cycles, blind retries, missing verification, or temporally disordered exploration, implementation, and verification. We introduce AgentLens, a framework for process-level assessment of SWE-agent trajectories, and release AgentLens-Bench, a dataset of 1,815 trajectories annotated with quality scores, waste signals, divergence points, and 47 task-level Prefix Tree Acceptor (PTA) references. AgentLens builds PTA references by merging multiple passing solutions for the same task, and uses a context-sensitive intent labeler to assign actions to Exploration, Implementation, Verification, or Orchestration based on trajectory history rather than tool identity alone. On AgentLens-Bench, the quality score separates passing trajectories into Lucky, Solid, and Ideal tiers and further decomposes Lucky Passes into five recurring mechanisms. Across the eight model backends, Lucky rates range from 0.5% to 23.2%, and some models move by as many as five rank positions when ranked by quality score instead of pass rate. We release the anonymized project repository, including the AgentLens-Bench dataset and AgentLens SDK, at https://github.com/microsoft/code-agent-state-trajectories/.

A Practical Algorithm for Feature-Rich, Non-Stationary Bandit Problems

Contextual bandits are incredibly useful in many practical problems. We go one step further by devising a more realistic problem that combines: (1) contextual bandits with dense arm features, (2) non-linear reward functions, and (3) a generalization of correlated bandits where reward distributions change over time but the degree of correlation maintains. This formulation lends itself to a wider set of applications such as recommendation tasks. To solve this problem, we introduce conditionally coupled contextual C3 Thompson sampling for Bernoulli bandits. It combines an improved Nadaraya-Watson estimator on an embedding space with Thompson sampling that allows online learning without retraining. Empirical results show that C3 outperforms the next best algorithm by 5.7% lower average cumulative regret on four OpenML tabular datasets as well as demonstrating a 12.4% click lift on Microsoft News Dataset (MIND) compared to other algorithms.