Emu3.5: Native Multimodal Models are World Learners

We introduce Emu3.5, a large-scale multimodal world model that natively predicts the next state across vision and language. Emu3.5 is pre-trained end-to-end with a unified next-token prediction objective on a corpus of vision-language interleaved data containing over 10 trillion tokens, primarily derived from sequential frames and transcripts of internet videos. The model naturally accepts interleaved vision-language inputs and generates interleaved vision-language outputs. Emu3.5 is further post-trained with large-scale reinforcement learning to enhance multimodal reasoning and generation. To improve inference efficiency, we propose Discrete Diffusion Adaptation (DiDA), which converts token-by-token decoding into bidirectional parallel prediction, accelerating per-image inference by about 20x without sacrificing performance. Emu3.5 exhibits strong native multimodal capabilities, including long-horizon vision-language generation, any-to-image (X2I) generation, and complex text-rich image generation. It also exhibits generalizable world-modeling abilities, enabling spatiotemporally consistent world exploration and open-world embodied manipulation across diverse scenarios and tasks. For comparison, Emu3.5 achieves performance comparable to Gemini 2.5 Flash Image (Nano Banana) on image generation and editing tasks and demonstrates superior results on a suite of interleaved generation tasks. We open-source Emu3.5 at https://github.com/baaivision/Emu3.5 to support community research.

$π_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models

Vision-Language-Action (VLA) models enable robots to understand and perform complex tasks from multimodal input. Although recent work explores using reinforcement learning (RL) to automate the laborious data collection process in scaling supervised fine-tuning (SFT), applying large-scale RL to flow-based VLAs (e.g., $\pi_0$, $\pi_{0.5}$) remains challenging due to intractable action log-likelihoods from iterative denoising. We address this challenge with $\pi_{\text{RL}}$, an open-source framework for training flow-based VLAs in parallel simulation. $\pi_{\text{RL}}$ implements two RL algorithms: (1) {Flow-Noise} models the denoising process as a discrete-time MDP with a learnable noise network for exact log-likelihood computation. (2) {Flow-SDE} integrates denoising with agent-environment interaction, formulating a two-layer MDP that employs ODE-to-SDE conversion for efficient RL exploration. We evaluate $\pi_{\text{RL}}$ on LIBERO and ManiSkill benchmarks. On LIBERO, $\pi_{\text{RL}}$ boosts few-shot SFT models $\pi_0$ and $\pi_{0.5}$ from 57.6% to 97.6% and from 77.1% to 98.3%, respectively. In ManiSkill, we train $\pi_{\text{RL}}$ in 320 parallel environments, improving $\pi_0$ from 41.6% to 85.7% and $\pi_{0.5}$ from 40.0% to 84.8% across 4352 pick-and-place tasks, demonstrating scalable multitask RL under heterogeneous simulation. Overall, $\pi_{\text{RL}}$ achieves significant performance gains and stronger generalization over SFT-models, validating the effectiveness of online RL for flow-based VLAs.

RoboBrain 2.0 Technical Report

We introduce RoboBrain 2.0, our latest generation of embodied vision-language foundation models, designed to unify perception, reasoning, and planning for complex embodied tasks in physical environments. It comes in two variants: a lightweight 7B model and a full-scale 32B model, featuring a heterogeneous architecture with a vision encoder and a language model. Despite its compact size, RoboBrain 2.0 achieves strong performance across a wide spectrum of embodied reasoning tasks. On both spatial and temporal benchmarks, the 32B variant achieves leading results, surpassing prior open-source and proprietary models. In particular, it supports key real-world embodied AI capabilities, including spatial understanding (e.g., affordance prediction, spatial referring, trajectory forecasting) and temporal decision-making (e.g., closed-loop interaction, multi-agent long-horizon planning, and scene graph updating). This report details the model architecture, data construction, multi-stage training strategies, infrastructure and practical applications. We hope RoboBrain 2.0 advances embodied AI research and serves as a practical step toward building generalist embodied agents. The code, checkpoint and benchmark are available at https://superrobobrain.github.io.

OmniGen2: Exploration to Advanced Multimodal Generation

In this work, we introduce OmniGen2, a versatile and open-source generative model designed to provide a unified solution for diverse generation tasks, including text-to-image, image editing, and in-context generation. Unlike OmniGen v1, OmniGen2 features two distinct decoding pathways for text and image modalities, utilizing unshared parameters and a decoupled image tokenizer. This design enables OmniGen2 to build upon existing multimodal understanding models without the need to re-adapt VAE inputs, thereby preserving the original text generation capabilities. To facilitate the training of OmniGen2, we developed comprehensive data construction pipelines, encompassing image editing and in-context generation data. Additionally, we introduce a reflection mechanism tailored for image generation tasks and curate a dedicated reflection dataset based on OmniGen2. Despite its relatively modest parameter size, OmniGen2 achieves competitive results on multiple task benchmarks, including text-to-image and image editing. To further evaluate in-context generation, also referred to as subject-driven tasks, we introduce a new benchmark named OmniContext. OmniGen2 achieves state-of-the-art performance among open-source models in terms of consistency. We will release our models, training code, datasets, and data construction pipeline to support future research in this field. Project Page: https://vectorspacelab.github.io/OmniGen2; GitHub Link: https://github.com/VectorSpaceLab/OmniGen2

SpikePingpong: High-Frequency Spike Vision-based Robot Learning for Precise Striking in Table Tennis Game

Learning to control high-speed objects in the real world remains a challenging frontier in robotics. Table tennis serves as an ideal testbed for this problem, demanding both rapid interception of fast-moving balls and precise adjustment of their trajectories. This task presents two fundamental challenges: it requires a high-precision vision system capable of accurately predicting ball trajectories, and it necessitates intelligent strategic planning to ensure precise ball placement to target regions. The dynamic nature of table tennis, coupled with its real-time response requirements, makes it particularly well-suited for advancing robotic control capabilities in fast-paced, precision-critical domains. In this paper, we present SpikePingpong, a novel system that integrates spike-based vision with imitation learning for high-precision robotic table tennis. Our approach introduces two key attempts that directly address the aforementioned challenges: SONIC, a spike camera-based module that achieves millimeter-level precision in ball-racket contact prediction by compensating for real-world uncertainties such as air resistance and friction; and IMPACT, a strategic planning module that enables accurate ball placement to targeted table regions. The system harnesses a 20 kHz spike camera for high-temporal resolution ball tracking, combined with efficient neural network models for real-time trajectory correction and stroke planning. Experimental results demonstrate that SpikePingpong achieves a remarkable 91% success rate for 30 cm accuracy target area and 71% in the more challenging 20 cm accuracy task, surpassing previous state-of-the-art approaches by 38% and 37% respectively. These significant performance improvements enable the robust implementation of sophisticated tactical gameplay strategies, providing a new research perspective for robotic control in high-speed dynamic tasks.

RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics

Spatial referring is a fundamental capability of embodied robots to interact with the 3D physical world. However, even with the powerful pretrained vision language models (VLMs), recent approaches are still not qualified to accurately understand the complex 3D scenes and dynamically reason about the instruction-indicated locations for interaction. To this end, we propose RoboRefer, a 3D-aware VLM that can first achieve precise spatial understanding by integrating a disentangled but dedicated depth encoder via supervised fine-tuning (SFT). Moreover, RoboRefer advances generalized multi-step spatial reasoning via reinforcement fine-tuning (RFT), with metric-sensitive process reward functions tailored for spatial referring tasks. To support SFT and RFT training, we introduce RefSpatial, a large-scale dataset of 20M QA pairs (2x prior), covering 31 spatial relations (vs. 15 prior) and supporting complex reasoning processes (up to 5 steps). In addition, we introduce RefSpatial-Bench, a challenging benchmark filling the gap in evaluating spatial referring with multi-step reasoning. Experiments show that SFT-trained RoboRefer achieves state-of-the-art spatial understanding, with an average success rate of 89.6%. RFT-trained RoboRefer further outperforms all other baselines by a large margin, even surpassing Gemini-2.5-Pro by 17.4% in average accuracy on RefSpatial-Bench. Notably, RoboRefer can be integrated with various control policies to execute long-horizon, dynamic tasks across diverse robots (e,g., UR5, G1 humanoid) in cluttered real-world scenes.

SpikeStereoNet: A Brain-Inspired Framework for Stereo Depth Estimation from Spike Streams

Conventional frame-based cameras often struggle with stereo depth estimation in rapidly changing scenes. In contrast, bio-inspired spike cameras emit asynchronous events at microsecond-level resolution, providing an alternative sensing modality. However, existing methods lack specialized stereo algorithms and benchmarks tailored to the spike data. To address this gap, we propose SpikeStereoNet, a brain-inspired framework and the first to estimate stereo depth directly from raw spike streams. The model fuses raw spike streams from two viewpoints and iteratively refines depth estimation through a recurrent spiking neural network (RSNN) update module. To benchmark our approach, we introduce a large-scale synthetic spike stream dataset and a real-world stereo spike dataset with dense depth annotations. SpikeStereoNet outperforms existing methods on both datasets by leveraging spike streams' ability to capture subtle edges and intensity shifts in challenging regions such as textureless surfaces and extreme lighting conditions. Furthermore, our framework exhibits strong data efficiency, maintaining high accuracy even with substantially reduced training data. The source code and datasets will be publicly available.

SpikeGen: Generative Framework for Visual Spike Stream Processing

Neuromorphic Visual Systems, such as spike cameras, have attracted considerable attention due to their ability to capture clear textures under dynamic conditions. This capability effectively mitigates issues related to motion and aperture blur. However, in contrast to conventional RGB modalities that provide dense spatial information, these systems generate binary, spatially sparse frames as a trade-off for temporally rich visual streams. In this context, generative models emerge as a promising solution to address the inherent limitations of sparse data. These models not only facilitate the conditional fusion of existing information from both spike and RGB modalities but also enable the conditional generation based on latent priors. In this study, we introduce a robust generative processing framework named SpikeGen, designed for visual spike streams captured by spike cameras. We evaluate this framework across multiple tasks involving mixed spike-RGB modalities, including conditional image/video deblurring, dense frame reconstruction from spike streams, and high-speed scene novel-view synthesis. Supported by comprehensive experimental results, we demonstrate that leveraging the latent space operation abilities of generative models allows us to effectively address the sparsity of spatial information while fully exploiting the temporal richness of spike streams, thereby promoting a synergistic enhancement of different visual modalities.

SPKLIP: Aligning Spike Video Streams with Natural Language

Spike cameras offer unique sensing capabilities but their sparse, asynchronous output challenges semantic understanding, especially for Spike Video-Language Alignment (Spike-VLA) where models like CLIP underperform due to modality mismatch. We introduce SPKLIP, the first architecture specifically for Spike-VLA. SPKLIP employs a hierarchical spike feature extractor that adaptively models multi-scale temporal dynamics in event streams, and uses spike-text contrastive learning to directly align spike video with language, enabling effective few-shot learning. A full-spiking visual encoder variant, integrating SNN components into our pipeline, demonstrates enhanced energy efficiency. Experiments show state-of-the-art performance on benchmark spike datasets and strong few-shot generalization on a newly contributed real-world dataset. SPKLIP's energy efficiency highlights its potential for neuromorphic deployment, advancing event-based multimodal research. The source code and dataset are available at [link removed for anonymity].

SOTA: Spike-Navigated Optimal TrAnsport Saliency Region Detection in Composite-bias Videos

Existing saliency detection methods struggle in real-world scenarios due to motion blur and occlusions. In contrast, spike cameras, with their high temporal resolution, significantly enhance visual saliency maps. However, the composite noise inherent to spike camera imaging introduces discontinuities in saliency detection. Low-quality samples further distort model predictions, leading to saliency bias. To address these challenges, we propose Spike-navigated Optimal TrAnsport Saliency Region Detection (SOTA), a framework that leverages the strengths of spike cameras while mitigating biases in both spatial and temporal dimensions. Our method introduces Spike-based Micro-debias (SM) to capture subtle frame-to-frame variations and preserve critical details, even under minimal scene or lighting changes. Additionally, Spike-based Global-debias (SG) refines predictions by reducing inconsistencies across diverse conditions. Extensive experiments on real and synthetic datasets demonstrate that SOTA outperforms existing methods by eliminating composite noise bias. Our code and dataset will be released at https://github.com/lwxfight/sota.