Yixuan Huang

Yixuan Huang, Jialin Yuan, Chanho Kim et al. · nvidia

Robots need to have a memory of previously observed, but currently occluded objects to work reliably in realistic environments. We investigate the problem of encoding object-oriented memory into a multi-object manipulation reasoning and planning framework. We propose DOOM and LOOM, which leverage transformer relational dynamics to encode the history of trajectories given partial-view point clouds and an object discovery and tracking engine. Our approaches can perform multiple challenging tasks including reasoning with occluded objects, novel objects appearance, and object reappearance. Throughout our extensive simulation and real-world experiments, we find that our approaches perform well in terms of different numbers of objects and different numbers of distractor actions. Furthermore, we show our approaches outperform an implicit memory baseline.

Wenhao Li, Yixuan Huang, Shengxin Zhu

This paper revisits the error analysis of the Stochastic Lanczos Quadrature (SLQ) method for approximating the trace of matrix functions, with a specific focus on asymmetric Lanczos quadrature rules. We reexplain an existing theoretical discrepancy regarding the necessity of a scaling factor when applying an affine transformation from the reference interval to the physical spectral interval. Furthermore, we introduce an optimized error reallocation technique for log-determinant estimation. Rather than evenly splitting the error tolerance between the Hutchinson trace estimator and the Lanczos quadrature, we formulate an optimization problem to strategically distribute the error budget. This approach minimizes the total number of matrix-vector multiplications (MVMs) required to reach a target accuracy for both Rademacher and Gaussian queries. Numerical experiments validate that this reallocation yields tighter theoretical bounds and provides a concrete rule-of-thumb for parameter configuration: to achieve a target accuracy efficiently, more computational resources should be allocated to the Lanczos process (larger m) rather than Monte Carlo sampling (smaller N).

Zijie Li, Yichun Shi, Jingxiang Sun et al.

We present MMCORE, a unified framework designed for multimodal image generation and editing. MMCORE leverages a pre-trained Vision-Language Model (VLM) to predict semantic visual embeddings via learnable query tokens, which subsequently serve as conditioning signals for a diffusion model. This streamlined design effectively transfers the rich understanding and reasoning capabilities of VLMs into the visual generation process. By obviating the need for deep fusion between autoregressive and diffusion models or training from scratch, MMCORE significantly reduces computational overhead while maintaining high-fidelity synthesis. MMCORE seamlessly integrates text-to-image synthesis with interleaved image generation, demonstrating robust multimodal comprehension in complex scenarios such as spatial reasoning and visual grounding. Comprehensive evaluations indicate that MMCORE consistently outperforms state-of-the-art baselines across a broad spectrum of text-to-image and single/multi-image editing benchmarks.

Yixuan Huang, Bowen Li, Vaibhav Saxena et al.

Robotic systems that interact with the physical world must reason about kinematic and dynamic constraints imposed by their own embodiment, their environment, and the task at hand. We introduce KinDER, a benchmark for Kinematic and Dynamic Embodied Reasoning that targets physical reasoning challenges arising in robot learning and planning. KinDER comprises 25 procedurally generated environments, a Gymnasium-compatible Python library with parameterized skills and demonstrations, and a standardized evaluation suite with 13 implemented baselines spanning task and motion planning, imitation learning, reinforcement learning, and foundation-model-based approaches. The environments are designed to isolate five core physical reasoning challenges: basic spatial relations, nonprehensile multi-object manipulation, tool use, combinatorial geometric constraints, and dynamic constraints, disentangled from perception, language understanding, and application-specific complexity. Empirical evaluation shows that existing methods struggle to solve many of the environments, indicating substantial gaps in current approaches to physical reasoning. We additionally include real-to-sim-to-real experiments on a mobile manipulator to assess the correspondence between simulation and real-world physical interaction. KinDER is fully open-sourced and intended to enable systematic comparison across diverse paradigms for advancing physical reasoning in robotics. Website and code: https://prpl-group.com/kinder-site/

Lihan Zha, Asher J. Hancock, Mingtong Zhang et al.

A long-standing goal in robotics is a generalist policy that can be deployed zero-shot on new robot embodiments without per-embodiment adaptation. Despite large-scale multi-embodiment pre-training, existing Vision-Language-Action models (VLAs) remain tightly coupled to their training embodiments and typically require costly fine-tuning. We introduce Language-Action Pre-training (LAP), a simple recipe that represents low-level robot actions directly in natural language, aligning action supervision with the pre-trained vision-language model's input-output distribution. LAP requires no learned tokenizer, no costly annotation, and no embodiment-specific architectural design. Based on LAP, we present LAP-3B, which to the best of our knowledge is the first VLA to achieve substantial zero-shot transfer to previously unseen robot embodiments without any embodiment-specific fine-tuning. Across multiple novel robots and manipulation tasks, LAP-3B attains over 50% average zero-shot success, delivering roughly a 2x improvement over the strongest prior VLAs. We further show that LAP enables efficient adaptation and favorable scaling, while unifying action prediction and VQA in a shared language-action format that yields additional gains through co-training.

Bingchen Zhao, Qiushan Guo, Ye Wang et al.

We introduce CompTok, a training framework for learning visual tokenizers whose tokens are enhanced for compositionality. CompTok uses a token-conditioned diffusion decoder. By employing an InfoGAN-style objective, where we train a recognition model to predict the tokens used to condition the diffusion decoder using the decoded images, we enforce the decoder to not ignore any of the tokens. To promote compositional control, besides the original images, CompTok also trains on tokens formed by swapping token subsets between images, enabling more compositional control of the token over the decoder. As the swapped tokens between images do not have ground truth image targets, we apply a manifold constraint via an adversarial flow regularizer to keep unpaired swap generations on the natural-image distribution. The resulting tokenizer not only achieves state-of-the-art performance on image class-conditioned generation, but also demonstrates properties such as swapping tokens between images to achieve high level semantic editing of an image. Additionally, we propose two metrics that measures the landscape of the token space that can be useful to describe not only the compositionality of the tokens, but also how easy to learn the landscape is for a generator to be trained on this space. We show in experiments that CompTok can improve on both of the metrics as well as supporting state-of-the-art generators for class conditioned generation.

Ziqi Chen, Yi Ren, Yixuan Huang et al.

Integrating AI into the physical layer is a cornerstone of 6G networks. However, current data-driven approaches struggle to generalize across dynamic environments because they lack an intrinsic understanding of electromagnetic wave propagation. We introduce the Wireless World Model (WWM), a multi-modal foundation framework predicting the spatiotemporal evolution of wireless channels by internalizing the causal relationship between 3D geometry and signal dynamics. Pre-trained on a massive ray-traced multi-modal dataset, WWM overcomes the data authenticity gap, further validated under real-world measurement data. Using a joint-embedding predictive architecture with a multi-modal mixture-of-experts Transformer, WWM fuses channel state information, 3D point clouds, and user trajectories into a unified representation. Across the five key downstream tasks supported by WWM, it achieves remarkable performance in seen environments, unseen generalization scenarios, and real-world measurements, consistently outperforming SOTA uni-modal foundation models and task-specific models. This paves the way for physics-aware 6G intelligence that adapts to the physical world.

Chang Liu, Mengting Chen, Yixuan Huang et al.

The field of image-to-video generation has made remarkable progress. However, challenges such as human limb twisting and facial distortion persist, especially when generating long videos or modeling intensive motions. Existing human image animation works address these issues by incorporating human-specific semantic representations, e.g., dense poses or ID embeddings, as additional conditions. However, conditioning on these representations could decrease the generation flexibility. Moreover, their reliance on RGB pixel supervision also lacks emphasis on learning necessary 3D geometric relationships and temporal coherence. In contrast, we introduce a novel approach named SemanticREPA that leverages these semantic representations as supervision signals through representation alignment. Specifically, we begin by training a structure alignment module that aligns the structure representations obtained from video latents with video depth estimation features. We then fix the pretrained module, and utilize it to provide additional supervision on the structure representations of the diffusion models, achieving structure rectification to generate coherent and stable human structures. Simultaneously, we develop an ID alignment module to align the ID representations of the generated videos to face recognition features. We further propose to use the predicted structure representations to refine identity restoration in relevant regions. With structure and ID alignment, our method demonstrates superior quality on extended character motions and enhanced character consistency.

Yixuan Huang, Jiawei Chen, Shengfan Zhang et al.

Collaborative filtering (CF) recommendation has been significantly advanced by integrating Graph Neural Networks (GNNs) and Graph Contrastive Learning (GCL). However, (i) random edge perturbations often distort critical structural signals and degrade semantic consistency across augmented views, and (ii) data sparsity hampers the propagation of collaborative signals, limiting generalization. To tackle these challenges, we propose RaDAR (Relation-aware Diffusion-Asymmetric Graph Contrastive Learning Framework for Recommendation Systems), a novel framework that combines two complementary view generation mechanisms: a graph generative model to capture global structure and a relation-aware denoising model to refine noisy edges. RaDAR introduces three key innovations: (1) asymmetric contrastive learning with global negative sampling to maintain semantic alignment while suppressing noise; (2) diffusion-guided augmentation, which employs progressive noise injection and denoising for enhanced robustness; and (3) relation-aware edge refinement, dynamically adjusting edge weights based on latent node semantics. Extensive experiments on three public benchmarks demonstrate that RaDAR consistently outperforms state-of-the-art methods, particularly under noisy and sparse conditions.

Adnan Labib, Qiao Wang, Yixuan Huang et al.

Automated assistants for Grammatical Error Correction are now embedded in educational platforms serving millions of learners, yet three critical gaps remain in this domain: (1) latest-generation Large Language Models (LLMs) lack comprehensive evaluation on grammar correction tasks; (2) whether combining these LLMs improves correction quality is unexplored; and (3) the extent to which reference-based metrics underestimate GEC system performance has not been adequately quantified. In this study, first, we evaluate latest-generation LLMs on edit precision, fluency preservation, and meaning retention, showing fine-tuned GPT-4o achieves state-of-the-art performance across all three dimensions. Second, through grammatical error type analysis we demonstrate that individual LLMs exhibit highly similar error correction patterns ($ρ=0.947$). Third, we show that reference-based metrics underestimate GEC performance with 73.76% of GPT-4o corrections different from gold standards being equally valid or even superior. These GEC evaluation findings equip educators with guidance for selecting GEC assistants that enhance rather than constrain student linguistic development. We make our data, code, and models publicly available.

Team Seedream, Yunpeng Chen, Yu Gao et al.

We introduce Seedream 4.0, an efficient and high-performance multimodal image generation system that unifies text-to-image (T2I) synthesis, image editing, and multi-image composition within a single framework. We develop a highly efficient diffusion transformer with a powerful VAE which also can reduce the number of image tokens considerably. This allows for efficient training of our model, and enables it to fast generate native high-resolution images (e.g., 1K-4K). Seedream 4.0 is pretrained on billions of text-image pairs spanning diverse taxonomies and knowledge-centric concepts. Comprehensive data collection across hundreds of vertical scenarios, coupled with optimized strategies, ensures stable and large-scale training, with strong generalization. By incorporating a carefully fine-tuned VLM model, we perform multi-modal post-training for training both T2I and image editing tasks jointly. For inference acceleration, we integrate adversarial distillation, distribution matching, and quantization, as well as speculative decoding. It achieves an inference time of up to 1.8 seconds for generating a 2K image (without a LLM/VLM as PE model). Comprehensive evaluations reveal that Seedream 4.0 can achieve state-of-the-art results on both T2I and multimodal image editing. In particular, it demonstrates exceptional multimodal capabilities in complex tasks, including precise image editing and in-context reasoning, and also allows for multi-image reference, and can generate multiple output images. This extends traditional T2I systems into an more interactive and multidimensional creative tool, pushing the boundary of generative AI for both creativity and professional applications. Seedream 4.0 is now accessible on https://www.volcengine.com/experience/ark?launch=seedream.

Haicheng Wang, Chen Ju, Weixiong Lin et al.

In rapidly evolving field of vision-language models (VLMs), contrastive language-image pre-training (CLIP) has made significant strides, becoming foundation for various downstream tasks. However, relying on one-to-one (image, text) contrastive paradigm to learn alignment from large-scale messy web data, CLIP faces a serious myopic dilemma, resulting in biases towards monotonous short texts and shallow visual expressivity. To overcome these issues, this paper advances CLIP into one novel holistic paradigm, by updating both diverse data and alignment optimization. To obtain colorful data with low cost, we use image-to-text captioning to generate multi-texts for each image, from multiple perspectives, granularities, and hierarchies. Two gadgets are proposed to encourage textual diversity. To match such (image, multi-texts) pairs, we modify the CLIP image encoder into multi-branch, and propose multi-to-multi contrastive optimization for image-text part-to-part matching. As a result, diverse visual embeddings are learned for each image, bringing good interpretability and generalization. Extensive experiments and ablations across over ten benchmarks indicate that our holistic CLIP significantly outperforms existing myopic CLIP, including image-text retrieval, open-vocabulary classification, and dense visual tasks.

Zihan Ling, Zhiyao Guo, Yixuan Huang et al.

Recent advancements in large language models (LLMs) and multi-modal LLMs have been remarkable. However, these models still rely solely on their parametric knowledge, which limits their ability to generate up-to-date information and increases the risk of producing erroneous content. Retrieval-Augmented Generation (RAG) partially mitigates these challenges by incorporating external data sources, yet the reliance on databases and retrieval systems can introduce irrelevant or inaccurate documents, ultimately undermining both performance and reasoning quality. In this paper, we propose Multi-Modal Knowledge-Based Retrieval-Augmented Generation (MMKB-RAG), a novel multi-modal RAG framework that leverages the inherent knowledge boundaries of models to dynamically generate semantic tags for the retrieval process. This strategy enables the joint filtering of retrieved documents, retaining only the most relevant and accurate references. Extensive experiments on knowledge-based visual question-answering tasks demonstrate the efficacy of our approach: on the E-VQA dataset, our method improves performance by +4.2% on the Single-Hop subset and +0.4% on the full dataset, while on the InfoSeek dataset, it achieves gains of +7.8% on the Unseen-Q subset, +8.2% on the Unseen-E subset, and +8.1% on the full dataset. These results highlight significant enhancements in both accuracy and robustness over the current state-of-the-art MLLM and RAG frameworks.

Zengyu Zou, Jingyuan Wang, Yixuan Huang et al.

This paper addresses the cooperative Multi-Vehicle Dynamic Pickup and Delivery Problem with Stochastic Requests (MVDPDPSR) and proposes an end-to-end centralized decision-making framework based on sequence-to-sequence, named Multi-Agent Pointer Transformer (MAPT). MVDPDPSR is an extension of the vehicle routing problem and a spatio-temporal system optimization problem, widely applied in scenarios such as on-demand delivery. Classical operations research methods face bottlenecks in computational complexity and time efficiency when handling large-scale dynamic problems. Although existing reinforcement learning methods have achieved some progress, they still encounter several challenges: 1) Independent decoding across multiple vehicles fails to model joint action distributions; 2) The feature extraction network struggles to capture inter-entity relationships; 3) The joint action space is exponentially large. To address these issues, we designed the MAPT framework, which employs a Transformer Encoder to extract entity representations, combines a Transformer Decoder with a Pointer Network to generate joint action sequences in an AutoRegressive manner, and introduces a Relation-Aware Attention module to capture inter-entity relationships. Additionally, we guide the model's decision-making using informative priors to facilitate effective exploration. Experiments on 8 datasets demonstrate that MAPT significantly outperforms existing baseline methods in terms of performance and exhibits substantial computational time advantages compared to classical operations research methods.

Mingen Li, Houjian Yu, Yixuan Huang et al.

Long-horizon routing tasks of deformable linear objects (DLOs), such as cables and ropes, are common in industrial assembly lines and everyday life. These tasks are particularly challenging because they require robots to manipulate DLO with long-horizon planning and reliable skill execution. Successfully completing such tasks demands adapting to their nonlinear dynamics, decomposing abstract routing goals, and generating multi-step plans composed of multiple skills, all of which require accurate high-level reasoning during execution. In this paper, we propose a fully autonomous hierarchical framework for solving challenging DLO routing tasks. Given an implicit or explicit routing goal expressed in language, our framework leverages vision-language models~(VLMs) for in-context high-level reasoning to synthesize feasible plans, which are then executed by low-level skills trained via reinforcement learning. To improve robustness in long horizons, we further introduce a failure recovery mechanism that reorients the DLO into insertion-feasible states. Our approach generalizes to diverse scenes involving object attributes, spatial descriptions, as well as implicit language commands. It outperforms the next best baseline method by nearly 50% and achieves an overall success rate of 92.5% across long-horizon routing scenarios.

Ruihao Zhang, Mao chen, Fei Ye et al.

T cell receptor (TCR) repertoires encode critical immunological signatures for autoimmune diseases, yet their clinical application remains limited by sequence sparsity and low witness rates. We developed EAMil, a multi-instance deep learning framework that leverages TCR sequencing data to diagnose systemic lupus erythematosus (SLE) and rheumatoid arthritis (RA) with exceptional accuracy. By integrating PrimeSeq feature extraction with ESMonehot encoding and enhanced gate attention mechanisms, our model achieved state-of-the-art performance with AUCs of 98.95% for SLE and 97.76% for RA. EAMil successfully identified disease-associated genes with over 90% concordance with established differential analyses and effectively distinguished disease-specific TCR genes. The model demonstrated robustness in classifying multiple disease categories, utilizing the SLEDAI score to stratify SLE patients by disease severity as well as to diagnose the site of damage in SLE patients, and effectively controlling for confounding factors such as age and gender. This interpretable framework for immune receptor analysis provides new insights for autoimmune disease detection and classification with broad potential clinical applications across immune-mediated conditions.

Yixuan Huang, Michael Bentley, Tucker Hermans et al.

Tendon-driven robots, a type of continuum robot, have the potential to reduce the invasiveness of surgery by enabling access to difficult-to-reach anatomical targets. In the future, the automation of surgical tasks for these robots may help reduce surgeon strain in the face of a rapidly growing population. However, directly encoding surgical tasks and their associated context for these robots is infeasible. In this work we take steps toward a system that is able to learn to successfully perform context-dependent surgical tasks by learning directly from a set of expert demonstrations. We present three models trained on the demonstrations conditioned on a vector encoding the context of the demonstration. We then use these models to plan and execute motions for the tendon-driven robot similar to the demonstrations for novel context not seen in the training set. We demonstrate the efficacy of our method on three surgery-inspired tasks.