arXiv subjects

Eric Li

Publications and source records attributed to Eric Li.

At least 37 records · Page 2Linked to original sources

arXiv2025

PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusion

Generating a complete and explorable 360-degree visual world enables a wide range of downstream applications. While prior works have advanced the field, they remain constrained by either narrow field-of-view limitations, which hinder the synthesis of continuous and holistic scenes, or insufficient camera controllability that restricts free exploration by users or autonomous agents. To address this, we propose PanoWorld-X, a novel framework for high-fidelity and controllable panoramic video generation with diverse camera trajectories. Specifically, we first construct a large-scale dataset of panoramic video-exploration route pairs by simulating camera trajectories in virtual 3D environments via Unreal Engine. As the spherical geometry of panoramic data misaligns with the inductive priors from conventional video diffusion, we then introduce a Sphere-Aware Diffusion Transformer architecture that reprojects equirectangular features onto the spherical surface to model geometric adjacency in latent space, significantly enhancing visual fidelity and spatiotemporal continuity. Extensive experiments demonstrate that our PanoWorld-X achieves superior performance in various aspects, including motion range, control precision, and visual quality, underscoring its potential for real-world applications.

cs.CV↗

arXiv2025

PanoLora: Bridging Perspective and Panoramic Video Generation with LoRA Adaptation

Generating high-quality 360° panoramic videos remains a significant challenge due to the fundamental differences between panoramic and traditional perspective-view projections. While perspective videos rely on a single viewpoint with a limited field of view, panoramic content requires rendering the full surrounding environment, making it difficult for standard video generation models to adapt. Existing solutions often introduce complex architectures or large-scale training, leading to inefficiency and suboptimal results. Motivated by the success of Low-Rank Adaptation (LoRA) in style transfer tasks, we propose treating panoramic video generation as an adaptation problem from perspective views. Through theoretical analysis, we demonstrate that LoRA can effectively model the transformation between these projections when its rank exceeds the degrees of freedom in the task. Our approach efficiently fine-tunes a pretrained video diffusion model using only approximately 1,000 videos while achieving high-quality panoramic generation. Experimental results demonstrate that our method maintains proper projection geometry and surpasses previous state-of-the-art approaches in visual quality, left-right consistency, and motion diversity.

cs.CV↗

arXiv2025

Efficient Probabilistic Visualization of Local Divergence of 2D Vector Fields with Independent Gaussian Uncertainty

This work focuses on visualizing uncertainty of local divergence of two-dimensional vector fields. Divergence is one of the fundamental attributes of fluid flows, as it can help domain scientists analyze potential positions of sources (positive divergence) and sinks (negative divergence) in the flow. However, uncertainty inherent in vector field data can lead to erroneous divergence computations, adversely impacting downstream analysis. While Monte Carlo (MC) sampling is a classical approach for estimating divergence uncertainty, it suffers from slow convergence and poor scalability with increasing data size and sample counts. Thus, we present a two-fold contribution that tackles the challenges of slow convergence and limited scalability of the MC approach. (1) We derive a closed-form approach for highly efficient and accurate uncertainty visualization of local divergence, assuming independently Gaussian-distributed vector uncertainties. (2) We further integrate our approach into Viskores, a platform-portable parallel library, to accelerate uncertainty visualization. In our results, we demonstrate significantly enhanced efficiency and accuracy of our serial analytical (speed-up up to 1946X) and parallel Viskores (speed-up up to 19698X) algorithms over the classical serial MC approach. We also demonstrate qualitative improvements of our probabilistic divergence visualizations over traditional mean-field visualization, which disregards uncertainty. We validate the accuracy and efficiency of our methods on wind forecast and ocean simulation datasets.

stat.CO↗

arXiv2025

Matrix-3D: Omnidirectional Explorable 3D World Generation

Explorable 3D world generation from a single image or text prompt forms a cornerstone of spatial intelligence. Recent works utilize video model to achieve wide-scope and generalizable 3D world generation. However, existing approaches often suffer from a limited scope in the generated scenes. In this work, we propose Matrix-3D, a framework that utilize panoramic representation for wide-coverage omnidirectional explorable 3D world generation that combines conditional video generation and panoramic 3D reconstruction. We first train a trajectory-guided panoramic video diffusion model that employs scene mesh renders as condition, to enable high-quality and geometrically consistent scene video generation. To lift the panorama scene video to 3D world, we propose two separate methods: (1) a feed-forward large panorama reconstruction model for rapid 3D scene reconstruction and (2) an optimization-based pipeline for accurate and detailed 3D scene reconstruction. To facilitate effective training, we also introduce the Matrix-Pano dataset, the first large-scale synthetic collection comprising 116K high-quality static panoramic video sequences with depth and trajectory annotations. Extensive experiments demonstrate that our proposed framework achieves state-of-the-art performance in panoramic video generation and 3D world generation. See more in https://matrix-3d.github.io.

cs.CV↗

arXiv2025

Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation

We introduce Skywork UniPic, a 1.5 billion-parameter autoregressive model that unifies image understanding, text-to-image generation, and image editing within a single architecture-eliminating the need for task-specific adapters or inter-module connectors-and demonstrate that compact multimodal systems can achieve state-of-the-art performance on commodity hardware. Skywork UniPic achieves a GenEval score of 0.86, surpassing most existing unified models; sets a new DPG-Bench complex-generation record of 85.5; attains 5.83 on GEditBench-EN and 3.49 on ImgEdit-Bench for image editing; and generates 1024 x 1024 images with under 15 GB of GPU memory (e.g., RTX 4090). (1) a decoupled encoding strategy that leverages a masked autoregressive encoder for synthesis and a SigLIP2 encoder for understanding, all feeding a shared autoregressive decoder; (2) a progressive, resolution-aware training schedule scaling from 256 x 256 to 1024 x 1024 while dynamically unfreezing parameters to balance capacity and stability; and (3) meticulously curated, 100 million-scale datasets augmented with task-specific reward models to refine generation and editing objectives. By demonstrating that high-fidelity multimodal integration need not incur prohibitive resource demands, Skywork UniPic establishes a practical paradigm for deployable, high-fidelity multimodal AI. Code and weights are publicly available at https://huggingface.co/Skywork/Skywork-UniPic-1.5B.

cs.CV↗

arXiv2025

Matrix-Game: Interactive World Foundation Model

We introduce Matrix-Game, an interactive world foundation model for controllable game world generation. Matrix-Game is trained using a two-stage pipeline that first performs large-scale unlabeled pretraining for environment understanding, followed by action-labeled training for interactive video generation. To support this, we curate Matrix-Game-MC, a comprehensive Minecraft dataset comprising over 2,700 hours of unlabeled gameplay video clips and over 1,000 hours of high-quality labeled clips with fine-grained keyboard and mouse action annotations. Our model adopts a controllable image-to-world generation paradigm, conditioned on a reference image, motion context, and user actions. With over 17 billion parameters, Matrix-Game enables precise control over character actions and camera movements, while maintaining high visual quality and temporal coherence. To evaluate performance, we develop GameWorld Score, a unified benchmark measuring visual quality, temporal quality, action controllability, and physical rule understanding for Minecraft world generation. Extensive experiments show that Matrix-Game consistently outperforms prior open-source Minecraft world models (including Oasis and MineWorld) across all metrics, with particularly strong gains in controllability and physical consistency. Double-blind human evaluations further confirm the superiority of Matrix-Game, highlighting its ability to generate perceptually realistic and precisely controllable videos across diverse game scenarios. To facilitate future research on interactive image-to-world generation, we will open-source the Matrix-Game model weights and the GameWorld Score benchmark at https://github.com/SkyworkAI/Matrix-Game.

cs.CV↗

arXiv2025

Flow-based Domain Randomization for Learning and Sequencing Robotic Skills

Domain randomization in reinforcement learning is an established technique for increasing the robustness of control policies trained in simulation. By randomizing environment properties during training, the learned policy can become robust to uncertainties along the randomized dimensions. While the environment distribution is typically specified by hand, in this paper we investigate automatically discovering a sampling distribution via entropy-regularized reward maximization of a normalizing-flow-based neural sampling distribution. We show that this architecture is more flexible and provides greater robustness than existing approaches that learn simpler, parameterized sampling distributions, as demonstrated in six simulated and one real-world robotics domain. Lastly, we explore how these learned sampling distributions, combined with a privileged value function, can be used for out-of-distribution detection in an uncertainty-aware multi-step manipulation planner.

cs.RO↗

arXiv2025

Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insights

We examine the reasoning and planning capabilities of large language models (LLMs) in solving complex tasks. Recent advances in inference-time techniques demonstrate the potential to enhance LLM reasoning without additional training by exploring intermediate steps during inference. Notably, OpenAI's o1 model shows promising performance through its novel use of multi-step reasoning and verification. Here, we explore how scaling inference-time techniques can improve reasoning and planning, focusing on understanding the tradeoff between computational cost and performance. To this end, we construct a comprehensive benchmark, known as Sys2Bench, and perform extensive experiments evaluating existing inference-time techniques on eleven diverse tasks across five categories, including arithmetic reasoning, logical reasoning, common sense reasoning, algorithmic reasoning, and planning. Our findings indicate that simply scaling inference-time computation has limitations, as no single inference-time technique consistently performs well across all reasoning and planning tasks.

cs.AI↗

arXiv2024

Observation of Interface Piezoelectricity in Superconducting Devices on Silicon

The evolution of superconducting quantum processors is driven by the need to reduce errors and scale for fault-tolerant computation. Reducing physical qubit error rates requires further advances in the microscopic modeling and control of decoherence mechanisms in superconducting qubits. Piezoelectric interactions contribute to decoherence by mediating energy exchange between microwave photons and acoustic phonons. Centrosymmetric materials like silicon and sapphire do not display piezoelectricity and are the preferred substrates for superconducting qubits. However, the broken centrosymmetry at material interfaces may lead to piezoelectric losses in qubits. While this loss mechanism was predicted two decades ago, interface piezoelectricity has not been experimentally observed in superconducting devices. Here, we report the observation of interface piezoelectricity at an aluminum-silicon junction and show that it constitutes an important loss channel for superconducting devices. We fabricate aluminum interdigital surface acoustic wave transducers on silicon and demonstrate piezoelectric transduction from room temperature to millikelvin temperatures. We find an effective electromechanical coupling factor of $K^2\approx 2 \times 10^{-5}\%$ comparable to weakly piezoelectric substrates. We model the impact of the measured interface piezoelectric response on superconducting qubits and find that the piezoelectric surface loss channel limits qubit quality factors to $Q\sim10^4-10^8$ for designs with different surface participation ratios and electromechanical mode matching. These results identify electromechanical surface losses as a significant dissipation channel for superconducting qubits, and show the need for heterostructure and phononic engineering to minimize errors in next-generation superconducting qubits.

quant-ph↗

arXiv2024

WebSuite: Systematically Evaluating Why Web Agents Fail

We describe WebSuite, the first diagnostic benchmark for generalist web agents, designed to systematically evaluate why agents fail. Advances in AI have led to the rise of numerous web agents that autonomously operate a browser to complete tasks. However, most existing benchmarks focus on strictly measuring whether an agent can or cannot complete a task, without giving insight on why. In this paper, we 1) develop a taxonomy of web actions to facilitate identifying common failure patterns, and 2) create an extensible benchmark suite to assess agents' performance on our taxonomized actions. This benchmark suite consists of both individual tasks, such as clicking a button, and end-to-end tasks, such as adding an item to a cart, and is designed such that any failure of a task can be attributed directly to a failure of a specific web action. We evaluate two popular generalist web agents, one text-based and one multimodal, and identify unique weaknesses for each agent. Because WebSuite can disaggregate task failures into specific action failures, this enables granular identification of which UX flows an individual agent has trouble with and immediately highlights promising avenues for improvement. These findings highlight the need for more focused benchmarking on where web agents go wrong to effectively improve agents beyond their weaker performance today.

cs.SE↗

arXiv2023

Bayes3D: fast learning and inference in structured generative models of 3D objects and scenes

Robots cannot yet match humans' ability to rapidly learn the shapes of novel 3D objects and recognize them robustly despite clutter and occlusion. We present Bayes3D, an uncertainty-aware perception system for structured 3D scenes, that reports accurate posterior uncertainty over 3D object shape, pose, and scene composition in the presence of clutter and occlusion. Bayes3D delivers these capabilities via a novel hierarchical Bayesian model for 3D scenes and a GPU-accelerated coarse-to-fine sequential Monte Carlo algorithm. Quantitative experiments show that Bayes3D can learn 3D models of novel objects from just a handful of views, recognizing them more robustly and with orders of magnitude less training data than neural baselines, and tracking 3D objects faster than real time on a single GPU. We also demonstrate that Bayes3D learns complex 3D object models and accurately infers 3D scene composition when used on a Panda robot in a tabletop scenario.

cs.RO↗

arXiv2023

Non-Markovian dynamics of a superconducting qubit in a phononic bandgap

The overhead to construct a logical qubit from physical qubits rapidly increases with the decoherence rate. Current superconducting qubits reduce dissipation due to two-level systems (TLSs) by using large device footprints. However, this approach provides partial protection, and results in a trade-off between qubit footprint and dissipation. This work introduces a new platform using phononics to engineer superconducting qubit-TLS interactions. We realize a superconducting qubit on a phononic bandgap metamaterial that suppresses TLS-mediated phonon emission. We use the qubit to probe its thermalization dynamics with the phonon-engineered TLS bath. Inside the phononic bandgap, we observe the emergence of non-Markovian qubit dynamics due to the Purcell-engineered TLS lifetime of 34 $μs$. We discuss the implications of these observations for extending qubit relaxation times through simultaneous phonon protection and miniaturization.

quant-ph↗

arXiv2023

PaLM 2 Technical Report

We introduce PaLM 2, a new state-of-the-art language model that has better multilingual and reasoning capabilities and is more compute-efficient than its predecessor PaLM. PaLM 2 is a Transformer-based model trained using a mixture of objectives. Through extensive evaluations on English and multilingual language, and reasoning tasks, we demonstrate that PaLM 2 has significantly improved quality on downstream tasks across different model sizes, while simultaneously exhibiting faster and more efficient inference compared to PaLM. This improved efficiency enables broader deployment while also allowing the model to respond faster, for a more natural pace of interaction. PaLM 2 demonstrates robust reasoning capabilities exemplified by large improvements over PaLM on BIG-Bench and other reasoning tasks. PaLM 2 exhibits stable performance on a suite of responsible AI evaluations, and enables inference-time control over toxicity without additional overhead or impact on other capabilities. Overall, PaLM 2 achieves state-of-the-art performance across a diverse set of tasks and capabilities. When discussing the PaLM 2 family, it is important to distinguish between pre-trained models (of various sizes), fine-tuned variants of these models, and the user-facing products that use these models. In particular, user-facing products typically include additional pre- and post-processing steps. Additionally, the underlying models may evolve over time. Therefore, one should not expect the performance of user-facing products to exactly match the results reported in this report.

cs.CL↗

arXiv2021

Exceeding the limits of algorithmic self-calibration in super-resolution imaging

Fourier ptychographic microscopy is a computational imaging technique that provides quantitative phase information and high resolution over a large field-of-view. Although the technique presents numerous advantages over conventional microscopy, model mismatch due to unknown optical aberrations can significantly limit reconstruction quality. Many attempts to address this issue rely on embedding pupil recovery into the reconstruction algorithm. In this paper we demonstrate the limitations of a purely algorithmic approach and evaluate the merits of implementing a simple, dedicated calibration procedure. In simulations, we find that for a target sample reconstruction error, we can image without any aberration corrections up to a maximum aberration magnitude of $λ$/40. When we use algorithmic self-calibration, we can increase the aberration magnitude up to $λ$/10, and with our in situ speckle calibration technique, this working range is extended further to a maximum aberration magnitude of $λ$/3. Hence, one can trade-off complexity for accuracy by using a separate calibration process, which is particularly useful for larger aberrations.

physics.optics↗

arXiv2020

AGenT Zero: Zero-shot Automatic Multiple-Choice Question Generation for Skill Assessments

Multiple-choice questions (MCQs) offer the most promising avenue for skill evaluation in the era of virtual education and job recruiting, where traditional performance-based alternatives such as projects and essays have become less viable, and grading resources are constrained. The automated generation of MCQs would allow assessment creation at scale. Recent advances in natural language processing have given rise to many complex question generation methods. However, the few methods that produce deployable results in specific domains require a large amount of domain-specific training data that can be very costly to acquire. Our work provides an initial foray into MCQ generation under high data-acquisition cost scenarios by strategically emphasizing paraphrasing the question context (compared to the task). In addition to maintaining semantic similarity between the question-answer pairs, our pipeline, which we call AGenT Zero, consists of only pre-trained models and requires no fine-tuning, minimizing data acquisition costs for question generation. AGenT Zero successfully outperforms other pre-trained methods in fluency and semantic similarity. Additionally, with some small changes, our assessment pipeline can be generalized to a broader question and answer space, including short answer or fill in the blank questions.

cs.CY↗

arXiv2019

Robust concurrent topology optimization of structure and its composite material considering uncertainty with imprecise probability

This paper studied a robust concurrent topology optimization (RCTO) approach to design the structure and its composite materials simultaneously. For the first time, the material uncertainty with imprecise probability is integrated into the multi-scale concurrent topology optimization (CTO) framework. To describe the imprecise probabilistic uncertainty efficiently, the type I hybrid interval random model is adopted. An improved hybrid perturbation analysis (IHPA) method is formulated to estimate the expectation and stand variance of the objective function in the worst case. Combined with the bi-directional evolutionary structural optimization (BESO) framework, the robust designs of the structure and its composite material are carried out. Several 2D and 3D numerical examples are presented to illustrate the effectiveness of the proposed method. The results show that the proposed method has high efficiency and low precision loss. In addition, the proposed RCTO approach remains efficient in both of linear static and dynamic structures, which shows its extensive adaptability.

cs.CE↗

arXiv2019

ALZA: An Efficient Hybrid Decentralized Payment System

The efficiency of decentralized book systems like Bitcoin and Ethereum has always been a challenge. It is usually measured by three major factors: scalability, throughput, and latency. Scalability refers to how the system capacity is increased by adding more physical resources. Throughput measures the volume of transactions for a given period of time, where most current solutions attempt to improve such as NEO, EOS, etc. Latency measures the processing time of any single transaction. In current blockchain based systems, the block generation rate is the main latency bottleneck. Off-chain processes such as state channels are the most recent work that can integrate partial inbound transactions, reducing latency. Unfortunately, the state channel introduces more issues at the same time, such as cross-channel synchronization, which makes the state channel unavailable for full adoption of current blockchain solutions. In order to solve the efficiency problem, we proposed an end-to-end solution called ALZA, which links the dedicated high-throughput blockchain with self-organizing payment fields. This mechanism allows arbitrary set of users to create payment fields that process extremely low latency transactions within each field. Therefore, users can make transactions almost immediately. Since all transactions are conducted within fields, transaction costs will be reduced by several orders of magnitude. In addition, ALZA distributes main ledger to each client through an innovative replication mechanism. Therefore, the system will be significantly more robust to blockchain system failures. In theory, ALZA can complete millions of transactions in one second, which naturally supports high-frequency trading.

cs.DC↗

arXiv2001

Optical Cooper Pair Breaking Spectroscopy of Cuprate Superconductors

The photon energy dependence of optical Cooper pair breaking rate (CPBR) is studied for compressibly strained La1.85Sr0.15CuO4 (LSCO) films and YBa2Cu2.92Zn0.08O7-delta (YBCZO) thin films, and compared to that in YBa2Cu3O7-delta (YBCO). Unlike in the case of YBCO, the CPBR for LSCO does not show obvious photon energy dependence. In YBCZO the CPBR shows strong photon energy dependence similar to YBCO, but with a red shift in the peak position. Analysis of these results strongly favours a physical picture based on electronic phase separation in high Tc superconductivity.

cond-mat.supr-con↗