HistoFusionNet: Histogram-Guided Fusion and Frequency-Adaptive Refinement for Nighttime Image Dehazing

Nighttime image dehazing remains a challenging low-level vision problem due to the joint presence of haze, glow, non-uniform illumination, color distortion, and sensor noise, which often invalidate assumptions commonly used in daytime dehazing. To address these challenges, we propose HistoFusionNet, a transformer-enhanced architecture tailored for nighttime image dehazing by combining histogram-guided representation learning with frequency-adaptive feature refinement. Built upon a multi-scale encoder-decoder backbone, our method introduces histogram transformer blocks that model long-range dependencies by grouping features according to their dynamic-range characteristics, enabling more effective aggregation of similarly degraded regions under complex nighttime lighting. To further improve restoration fidelity, we incorporate a frequency-aware refinement branch that adaptively exploits complementary low- and high-frequency cues, helping recover scene structures, suppress artifacts, and enhance local details. This design yields a unified framework that is particularly well suited to the heterogeneous degradations encountered in real nighttime hazy scenes. Extensive experiments and highly competitive performance of our method on the NTIRE 2026 Nighttime Image Dehazing Challenge benchmark demonstrate the effectiveness of the proposed method. Our team ranked 1st among 22 participating teams, highlighting the robustness and competitive performance of HistoFusionNet. The code is available at: https://github.com/heydarimo/Night-Time-Dehazing

Voxtral TTS

We introduce Voxtral TTS, an expressive multilingual text-to-speech model that generates natural speech from as little as 3 seconds of reference audio. Voxtral TTS adopts a hybrid architecture that combines auto-regressive generation of semantic speech tokens with flow-matching for acoustic tokens. These tokens are encoded and decoded with Voxtral Codec, a speech tokenizer trained from scratch with a hybrid VQ-FSQ quantization scheme. In human evaluations conducted by native speakers, Voxtral TTS is preferred for multilingual voice cloning due to its naturalness and expressivity, achieving a 68.4\% win rate over ElevenLabs Flash v2.5. We release the model weights under a CC BY-NC license.

Deep Learning-Driven Black-Box Doherty Power Amplifier with Pixelated Output Combiner and Extended Efficiency Range

This article presents a deep learning-driven inverse design methodology for Doherty power amplifiers (PA) with multi-port pixelated output combiner networks. A deep convolutional neural network (CNN) is developed and trained as an electromagnetic (EM) surrogate model to accurately and rapidly predict the S-parameters of pixelated passive networks. By leveraging the CNN-based surrogate model within a blackbox Doherty framework and a genetic algorithm (GA)-based optimizer, we effectively synthesize complex Doherty combiners that enable an extended back-off efficiency range using fully symmetrical devices. As a proof of concept, we designed and fabricated two Doherty PA prototypes incorporating three-port pixelated combiners, implemented with GaN HEMT transistors. In measurements, both prototypes demonstrate a maximum drain efficiency exceeding 74% and deliver an output power surpassing 44.1 dBm at 2.75 GHz. Furthermore, a measured drain efficiency above 52% is maintained at the 9-dB back-off power level for both prototypes at the same frequency. To evaluate linearity and efficiency under realistic signal conditions, both prototypes are tested using a 20-MHz 5G new radio (NR)-like waveform exhibiting a peak-to-average power ratio (PAPR) of 9.0 dB. After applying digital predistortion (DPD), each design achieves an average power added efficiency (PAE) above 51%, while maintaining an adjacent channel leakage ratio (ACLR) better than -60.8 dBc.

Voxtral Realtime

We introduce Voxtral Realtime, a natively streaming automatic speech recognition model that matches offline transcription quality at sub-second latency. Unlike approaches that adapt offline models through chunking or sliding windows, Voxtral Realtime is trained end-to-end for streaming, with explicit alignment between audio and text streams. Our architecture builds on the Delayed Streams Modeling framework, introducing a new causal audio encoder and Ada RMS-Norm for improved delay conditioning. We scale pretraining to a large-scale dataset spanning 13 languages. At a delay of 480ms, Voxtral Realtime achieves performance on par with Whisper, the most widely deployed offline transcription system. We release the model weights under the Apache 2.0 license.

HLGFA: High-Low Resolution Guided Feature Alignment for Unsupervised Anomaly Detection

Unsupervised industrial anomaly detection (UAD) is essential for modern manufacturing inspection, where defect samples are scarce and reliable detection is required. In this paper, we propose HLGFA, a high-low resolution guided feature alignment framework that learns normality by modeling cross-resolution feature consistency between high-resolution and low-resolution representations of normal samples, instead of relying on pixel-level reconstruction. Dual-resolution inputs are processed by a shared frozen backbone to extract multi-level features, and high-resolution representations are decomposed into structure and detail priors to guide the refinement of low-resolution features through conditional modulation and gated residual correction. During inference, anomalies are naturally identified as regions where cross-resolution alignment breaks down. In addition, a noise-aware data augmentation strategy is introduced to suppress nuisance-induced responses commonly observed in industrial environments. Extensive experiments on standard benchmarks demonstrate the effectiveness of HLGFA, achieving 97.9% pixel-level AUROC and 97.5% image-level AUROC on the MVTec AD dataset, outperforming representative reconstruction-based and feature-based methods.

ERNIE 5.0 Technical Report

In this report, we introduce ERNIE 5.0, a natively autoregressive foundation model desinged for unified multimodal understanding and generation across text, image, video, and audio. All modalities are trained from scratch under a unified next-group-of-tokens prediction objective, based on an ultra-sparse mixture-of-experts (MoE) architecture with modality-agnostic expert routing. To address practical challenges in large-scale deployment under diverse resource constraints, ERNIE 5.0 adopts a novel elastic training paradigm. Within a single pre-training run, the model learns a family of sub-models with varying depths, expert capacities, and routing sparsity, enabling flexible trade-offs among performance, model size, and inference latency in memory- or time-constrained scenarios. Moreover, we systematically address the challenges of scaling reinforcement learning to unified foundation models, thereby guaranteeing efficient and stable post-training under ultra-sparse MoE architectures and diverse multimodal settings. Extensive experiments demonstrate that ERNIE 5.0 achieves strong and balanced performance across multiple modalities. To the best of our knowledge, among publicly disclosed models, ERNIE 5.0 represents the first production-scale realization of a trillion-parameter unified autoregressive model that supports both multimodal understanding and generation. To facilitate further research, we present detailed visualizations of modality-agnostic expert routing in the unified model, alongside comprehensive empirical analysis of elastic training, aiming to offer profound insights to the community.

Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning

Vision-Language Models have excelled at textual reasoning, but they often struggle with fine-grained spatial understanding and continuous action planning, failing to simulate the dynamics required for complex visual reasoning. In this work, we formulate visual reasoning by means of video generation models, positing that generated frames can act as intermediate reasoning steps between initial states and solutions. We evaluate their capacity in two distinct regimes: Maze Navigation for sequential discrete planning with low visual change and Tangram Puzzle for continuous manipulation with high visual change. Our experiments reveal three critical insights: (1) Robust Zero-Shot Generalization: In both tasks, the model demonstrates strong performance on unseen data distributions without specific finetuning. (2) Visual Context: The model effectively uses visual context as explicit control, such as agent icons and tangram shapes, enabling it to maintain high visual consistency and adapt its planning capability robustly to unseen patterns. (3) Visual Test-Time Scaling: We observe a test-time scaling law in sequential planning; increasing the generated video length (visual inference budget) empowers better zero-shot generalization to spatially and temporally complex paths. These findings suggest that video generation is not merely a media tool, but a scalable, generalizable paradigm for visual reasoning.

Learning Longitudinal Health Representations from EHR and Wearable Data

Foundation models trained on electronic health records show strong performance on many clinical prediction tasks but are limited by sparse and irregular documentation. Wearable devices provide dense continuous physiological signals but lack semantic grounding. Existing methods usually model these data sources separately or combine them through late fusion. We propose a multimodal foundation model that jointly represents electronic health records and wearable data as a continuous time latent process. The model uses modality specific encoders and a shared temporal backbone pretrained with self supervised and cross modal objectives. This design produces representations that are temporally coherent and clinically grounded. Across forecasting physiological and risk modeling tasks the model outperforms strong electronic health record only and wearable only baselines especially at long horizons and under missing data. These results show that joint electronic health record and wearable pretraining yields more faithful representations of longitudinal health.

STEP3-VL-10B Technical Report

We present STEP3-VL-10B, a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence. STEP3-VL-10B is realized through two strategic shifts: first, a unified, fully unfrozen pre-training strategy on 1.2T multimodal tokens that integrates a language-aligned Perception Encoder with a Qwen3-8B decoder to establish intrinsic vision-language synergy; and second, a scaled post-training pipeline featuring over 1k iterations of reinforcement learning. Crucially, we implement Parallel Coordinated Reasoning (PaCoRe) to scale test-time compute, allocating resources to scalable perceptual reasoning that explores and synthesizes diverse visual hypotheses. Consequently, despite its compact 10B footprint, STEP3-VL-10B rivals or surpasses models 10$\times$-20$\times$ larger (e.g., GLM-4.6V-106B, Qwen3-VL-235B) and top-tier proprietary flagships like Gemini 2.5 Pro and Seed-1.5-VL. Delivering best-in-class performance, it records 92.2% on MMBench and 80.11% on MMMU, while excelling in complex reasoning with 94.43% on AIME2025 and 75.95% on MathVision. We release the full model suite to provide the community with a powerful, efficient, and reproducible baseline.

From Human Hands to Robot Arms: Manipulation Skills Transfer via Trajectory Alignment

Learning diverse manipulation skills for real-world robots is severely bottlenecked by the reliance on costly and hard-to-scale teleoperated demonstrations. While human videos offer a scalable alternative, effectively transferring manipulation knowledge is fundamentally hindered by the significant morphological gap between human and robotic embodiments. To address this challenge and facilitate skill transfer from human to robot, we introduce Traj2Action,a novel framework that bridges this embodiment gap by using the 3D trajectory of the operational endpoint as a unified intermediate representation, and then transfers the manipulation knowledge embedded in this trajectory to the robot's actions. Our policy first learns to generate a coarse trajectory, which forms an high-level motion plan by leveraging both human and robot data. This plan then conditions the synthesis of precise, robot-specific actions (e.g., orientation and gripper state) within a co-denoising framework. Extensive real-world experiments on a Franka robot demonstrate that Traj2Action boosts the performance by up to 27% and 22.25% over $\pi_0$ baseline on short- and long-horizon real-world tasks, and achieves significant gains as human data scales in robot policy learning. Our project website, featuring code and video demonstrations, is available at https://anonymous.4open.science/w/Traj2Action-4A45/.