Publications (99)
MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence
Lianmin Zheng, Jiacheng Yang, Han Cai +3
We introduce MAgent, a platform to support research and development of many-agent reinforcement learning. Unlike previous research platforms on single or multi-agent reinforcement…
Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
Shuo Yang, Haocheng Xi, Yilong Zhao +10
Diffusion Transformers (DiTs) are essential for video generation but suffer from significant latency due to the quadratic complexity of attention. By computing only critical tokens…
MDS Generalized Convertible Code
Songping Ge, Han Cai, Xiaohu Tang
In this paper, we consider the convertible codes with the maximum distance separable (MDS) property, which can adjust the code rate according to the failure rates of devices. We fi…
Measuring Zak phase in room-temperature atoms
Ruosong Mao, Xingqi Xu, Jiefei Wang +5
Cold atoms provide a flexible platform for synthesizing and characterizing topolog-ical matter, where geometric phases play a central role. However, cold atoms are intrinsically pr…
Robust Multi-Sensor Multi-Target Tracking Using Possibility Labeled Multi-Bernoulli Filter
Han Cai, Chenbao Xue, Jeremie Houssineau +1
With the increasing complexity of multiple target tracking scenes, a single sensor may not be able to effectively monitor a large number of targets. Therefore, it is imperative to…
Nanoscale High Transition Temperature Superconducting Quantum Interference Device Transimpedance Amplifier
Hao Li, Ethan Y. Cho, Han Cai +1
As the quantum generation of electronics takes the stage, a cast of important support electronics is needed to connect these novel devices to our classical worlds. In the case of s…
COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training
Haocheng Xi, Han Cai, Ligeng Zhu +4
FP8 training has emerged as a promising method for improving training efficiency. Existing frameworks accelerate training by applying FP8 computation to linear layers while leaving…
A Construction of Maximally Recoverable Codes with Order-Optimal Field Size
Han Cai, Ying Miao, Moshe Schwartz +1
We construct maximally recoverable codes (corresponding to partial MDS codes) which are based on linearized Reed-Solomon codes. The new codes have a smaller field size requirement…
Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter
Qinghao Hu, Shang Yang, Junxian Guo +7
The emergence of Large Language Models (LLMs) with strong reasoning capabilities marks a significant milestone, unlocking new frontiers in complex problem-solving. However, trainin…
Accelerate High-Quality Diffusion Models with Inner Loop Feedback
Matthew Gwilliam, Han Cai, Di Wu +2
We propose Inner Loop Feedback (ILF), a novel approach to accelerate diffusion models' inference. ILF trains a lightweight module to predict future features in the denoising proces…
Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
Junyu Chen, Han Cai, Junsong Chen +6
We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models for accelerating high-resolution diffusion models. Existing autoencoder models have demonstrated…
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
Enze Xie, Junsong Chen, Yuyang Zhao +11
This paper presents SANA-1.5, a linear Diffusion Transformer for efficient scaling in text-to-image generation. Building upon SANA-1.0, we introduce three key innovations: (1) Effi…
Realization of all-band-flat photonic lattices
Jing Yang, Yuanzhen Li, Yumeng Yang +6
Flatbands play an important role in correlated quantum matter and have novel applications in photonic lattices. Synthetic magnetic fields and destructive interference in lattices a…
Multiqubit Greenberger-Horne-Zeilinger state generated by synthetic magnetic field in circuit QED
Wei Feng, Da-Wei Wang, Han Cai +1
We propose a scheme to generate Greenberger-Horne-Zeilinger (GHZ) state for N superconducting qubits in a circuit QED system. By sinusoidally modulating the qubit-qubit coupling, a…
Construction of Locally Repairable Array Codes with Optimal Repair Bandwidth under the Rack-Aware Storage Model
Yumeng Yang, Han Cai, Xiaohu Tang
In this paper, we discuss codes for distributed storage systems with hierarchical repair properties. Specifically, we devote attention to the repair problem of the rack-aware stora…
On Optimal Locally Repairable Codes and Generalized Sector-Disk Codes
Han Cai, Moshe Schwartz
Optimal locally repairable codes with information locality are considered. Optimal codes are constructed, whose length is also order-optimal with respect to a new bound on the code…
DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space
Junyu Chen, Dongyun Zou, Wenkun He +4
We present DC-AE 1.5, a new family of deep compression autoencoders for high-resolution diffusion models. Increasing the autoencoder's latent channel number is a highly effective a…
Wavelength-tunable high-fidelity entangled photon sources enabled by dual Stark effects
Chen Chen, Jun-Yong Yan, Hans-Georg Babin +16
The construction of a large-scale quantum internet requires quantum repeaters containing multiple entangled photon sources with identical wavelengths. Semiconductor quantum dots ca…
Once-for-All: Train One Network and Specialize it for Efficient Deployment
Han Cai, Chuang Gan, Tianzhe Wang +2
We address the challenging problem of efficient inference across many devices and resource constraints, especially on edge devices. Conventional approaches either manually design o…
Unification of valley and anomalous Hall effects in a strained lattice
Jiale Yuan, Han Cai, Congjun Wu +3
Two dimensional lattices are an important stage for studying many aspects of quantum physics, in particular the topological phases. The valley Hall and anomalous Hall effects are t…
Path-Level Network Transformation for Efficient Architecture Search
Han Cai, Jiacheng Yang, Weinan Zhang +2
We introduce a new function-preserving transformation for efficient neural architecture search. This network transformation allows reusing previously trained networks and existing…
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
Han Cai, Ligeng Zhu, Song Han
Neural architecture search (NAS) has a great impact by automatically designing effective neural network architectures. However, the prohibitive computational demand of conventional…
From photon momentum transfer to acceleration sensing
Jianyu Yang, Nan Li, Yuyao Pan +8
As a typical application of photon momentum transfer, optical levitation systems are known for their ideal isolation from mechanical dissipation and thermal noise. These characters…
Direct and mediated dipole-dipole interactions in a reconfigurable array of optical traps
Mian Wu, Nan Li, Han Cai +2
Optically levitated nanoparticles in vacuum experience both electrostatic and light-induced dipole-dipole interactions, offering a versatile platform to explore mesoscopic entangle…
Velocity Scanning Tomography for Room-Temperature Quantum Simulation
Jiefei Wang, Ruosong Mao, Xingqi Xu +9
Quantum simulation offers an analog approach for exploring exotic quantum phenomena using controllable platforms, typically necessitating ultracold temperatures to maintain the qua…
Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE
Haozhan Tang, Zerui Wang, Yuxian Gu +2
Modern LLMs are increasingly deployed in long-context applications such as retrieval-augmented generation, repository-level coding, and agentic workflows whose accumulated reasonin…
On Optimal Locally Repairable Codes with Super-Linear Length
Han Cai, Ying Miao, Moshe Schwartz +1
Locally repairable codes which are optimal with respect to the bound presented by Prakash et al. are considered. New upper bounds on the length of such optimal codes are derived. T…
Layout Design for Intelligent Warehouse by Evolution with Fitness Approximation
Haifeng Zhang, Zilong Guo, Han Cai +5
With the rapid growth of the express industry, intelligent warehouses that employ autonomous robots for carrying parcels have been widely used to handle the vast express volume. Fo…
DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Muyang Li, Tianle Cai, Jiaxin Cao +7
Diffusion models have achieved great success in synthesizing high-quality images. However, generating high-resolution images with diffusion models is still challenging due to the e…
Realizing the Haldane Model in Thermal Atoms
Jiefei Wang, Jianhao Dai, Ruosong Mao +7
Topological materials hold great promise for developing next-generation devices with transport properties that remain resilient in the presence of local imperfections. However, the…
Floquet superradiance lattices in thermal atoms
Xingqi Xu, Jiefei Wang, Jianhao Dai +4
Floquet modulation has been widely used in optical lattices for coherent control of quantum gases, in particular for synthesizing artificial gauge fields and simulating topological…
Electromagnetically Induced Transparency with Superradiant and Subradiant states
Wei Feng, Da-Wei Wang, Han Cai +2
We construct the electromagnetically induced transparency (EIT) by dynamically coupling a superradiant state with a subradiant state. The superradiant and subradiant states with en…
APQ: Joint Search for Network Architecture, Pruning and Quantization Policy
Tianzhe Wang, Kuan Wang, Han Cai +3
We present APQ for efficient deep learning inference on resource-constrained hardware. Unlike previous methods that separately search the neural architecture, pruning policy, and q…
Network Augmentation for Tiny Deep Learning
Han Cai, Chuang Gan, Ji Lin +1
We introduce Network Augmentation (NetAug), a new training method for improving the performance of tiny neural networks. Existing regularization techniques (e.g., data augmentation…
Topological phase transitions in superradiance lattices
Da-Wei Wang, Han Cai, Luqi Yuan +2
Topological phases of matters are of fundamental interest and have promising applications. Fascinating topological properties of light have been unveiled in classical optical mater…
Decentralised possibilistic inference with applications to target tracking
Jeremie Houssineau, Han Cai, Murat Uney +1
Fusing and sharing information from multiple sensors over a network is a challenging task, partly due to the absence of a foundational rule for fusing probability distributions tha…
Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
Haocheng Xi, Shuo Yang, Yilong Zhao +11
Diffusion Transformers (DiTs) dominate video generation but their high computational cost severely limits real-world applicability, usually requiring tens of minutes to generate a…
A Cooperative Repair Scheme for Zigzag MSR Codes in Distributed Storage Systems
Yajuan Liu, Han Cai, Xiaohu Tang
In this paper, we propose a novel cooperative repair scheme for Zigzag MSR codes with optimal repair bandwidth, enabling the repair of any h failed nodes. To the best of our knowle…
Efficient Architecture Search by Network Transformation
Han Cai, Tianyao Chen, Weinan Zhang +2
Techniques for automatically designing deep neural network architectures such as reinforcement learning based approaches have recently shown promising results. However, their succe…
Mesoscopic Superposition States Generated by Synthetic Spin-orbit Interaction in Fock-state Lattices
Da-Wei Wang, Han Cai, Ren-Bao Liu +1
Mesoscopic superposition states of photons can be prepared in three cavities interacting with the same two-level atom. By periodically modulating the three cavity frequencies aroun…
EfficientViT-SAM: Accelerated Segment Anything Model Without Accuracy Loss
Zhuoyang Zhang, Han Cai, Song Han
We present EfficientViT-SAM, a new family of accelerated segment anything models. We retain SAM's lightweight prompt encoder and mask decoder while replacing the heavy image encode…
MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning
Ji Lin, Wei-Ming Chen, Han Cai +2
Tiny deep learning on microcontroller units (MCUs) is challenging due to the limited memory size. We find that the memory bottleneck is due to the imbalanced memory distribution in…
Optimal Locally Repairable Codes: An Improved Bound and Constructions
Han Cai, Cuiling Fan, Ying Miao +2
We study the Singleton-type bound that provides an upper limit on the minimum distance of locally repairable codes. We present an improved bound by carefully analyzing the combinat…
Cosmos 3: Omnimodal World Models for Physical AI
NVIDIA, :, Aditi +293
We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-t…
A Transformation of Repairing Reed-Solomon Codes from Rack-Aware Storage Model to Homogeneous Storage Model
Yumeng Yang, Han Cai, Xiaohu Tang
In this paper, we address the node repair problem of Reed-Solomon (RS) coded distributed storage systems. Specifically, to overcome the challenges of multiple-node failures of RS c…
Topological phases of quantized light
Han Cai, Da-Wei Wang
Topological photonics is an emerging research area that focuses on the topological states of classical light. Here we reveal the topological phases that are intrinsic to the partic…
Repairing Schemes for Tamo-Barg Codes
Han Cai, Ying Miao, Moshe Schwartz +1
In this paper, the repair problem for erasures beyond locality in locally repairable codes is explored under a practical system setting, where a rack-aware storage system consists…
Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation
Yihan Wang, Muyang Li, Han Cai +2
Pose estimation plays a critical role in human-centered vision applications. However, it is difficult to deploy state-of-the-art HRNet-based pose estimation models on resource-cons…
Large-scale Interactive Recommendation with Tree-structured Policy Gradient
Haokun Chen, Xinyi Dai, Han Cai +5
Reinforcement learning (RL) has recently been introduced to interactive recommender systems (IRS) because of its nature of learning from dynamic interactions and planning for long-…
Product-based Neural Networks for User Response Prediction
Yanru Qu, Han Cai, Kan Ren +4
Predicting user responses, such as clicks and conversions, is of great importance and has found its usage in many Web applications including recommender systems, web search and onl…
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
Haocheng Xi, Shuo Yang, Yilong Zhao +13
Despite rapid progress in autoregressive video diffusion, an emerging system algorithm bottleneck limits both deployability and generation capability: KV cache memory. In autoregre…
TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learning
Han Cai, Chuang Gan, Ligeng Zhu +1
On-device learning enables edge devices to continually adapt the AI models to new data, which requires a small memory footprint to fit the tight memory constraint of edge devices.…
Optically Levitated Nanoparticles as Receiving Antennas for Low Frequency Wireless Communication
Zhenhai Fu, Jinsheng Xu, Shaochong Zhu +13
Low-frequency (LF) wireless communications play a crucial role in ensuring anti-interference, long-range, and efficient communication across various environments. However, in conve…
DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
Wenkun He, Yuchao Gu, Junyu Chen +11
Existing text-to-image diffusion models excel at generating high-quality images, but face significant efficiency challenges when scaled to high resolutions, like 4K image generatio…
SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
Junsong Chen, Shuchen Xue, Yuyang Zhao +6
This paper presents SANA-Sprint, an efficient diffusion model for ultra-fast text-to-image (T2I) generation. SANA-Sprint is built on a pre-trained foundation model and augmented wi…
Long Text Generation via Adversarial Training with Leaked Information
Jiaxian Guo, Sidi Lu, Han Cai +3
Automatically generating coherent and semantically meaningful text has many applications in machine translation, dialogue systems, image captioning, etc. Recently, by combining wit…
Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search
Yuxian Gu, Qinghao Hu, Shang Yang +4
We present Jet-Nemotron, a new family of hybrid-architecture language models, which matches or exceeds the accuracy of leading full-attention models while significantly improving g…
Convertible Codes: MSR-to-MSR Conversion with Optimal Access and Bandwidth
Yumeng Yang, Han Cai, Xianfu Lei +1
In this paper, we study convertible codes in the merge regime and focus on the minimum storage regenerating (MSR) setting, where both the initial codes and the final code admit opt…
Design Automation for Efficient Deep Learning Computing
Song Han, Han Cai, Ligeng Zhu +4
Efficient deep learning computing requires algorithm and hardware co-design to enable specialization: we usually need to change the algorithm to reduce memory footprint and improve…
Observation of momentum-space chiral edge currents in room-temperature atoms
Han Cai, Jinhong Liu, Jinze Wu +4
Chiral edge currents play an important role in characterizing topological matter. In atoms, they have been observed at such a low temperature that the atomic motion can be measured…
Hide to Guide: Learning via Semantic Masking
Ruitao Liu, Qinghao Hu, Alex Hu +6
Reinforcement learning with verifiable rewards (RLVR) has become a powerful paradigm for improving language models on reasoning-intensive tasks, but its effectiveness is often limi…
Locally Repairable Convertible Codes: Improved Lower Bound and General Construction
Songping Ge, Han Cai, Xiaohu Tang
In this paper, we consider the convertible code with locally repairable property. We present an improved lower bound on access cost associated with . Then, we provide a gen…
Many-body chiral edge currents and sliding phases of atomic spinwaves in momentum-space lattice
Yongqiang Li, Han Cai, Da-wei Wang +3
Collective excitations (spinwaves) of long-lived atomic hyperfine states can be synthesized into a Bose-Hubbard model in momentum space. We explore many-body ground states and dyna…
Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow
Haocheng Xi, Charlie Ruan, Peiyuan Liao +7
Reinforcement learning (RL) is essential for enhancing the complex reasoning capabilities of large language models (LLMs). However, existing RL training pipelines are computational…
Detection of low-energy fluxons from engineered long Josephson junctions for efficient computing
Han Cai, Liuqi Yu, Waltraut Wustmann +2
Single-Flux Quantum (SFQ) digital logic is typically energy efficient and fast, and logic that uses ballistic and reversible principles provides a new platform to improve efficienc…
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers
Enze Xie, Junsong Chen, Junyu Chen +8
We introduce Sana, a text-to-image framework that can efficiently generate images up to 40964096 resolution. Sana can synthesize high-resolution, high-quality images with s…
Zak Phase Induced Topological Nonreciprocity
Xiao Liu, Jiefei Wang, Ruosong Mao +5
Topological physics provides novel insights for designing functional photonic devices, such as magnetic-free optical diodes, which are important in optical engineering and quantum…
Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs
Hao Kang, Qingru Zhang, Han Cai +4
Large language models (LLMs) have shown remarkable performance across diverse reasoning and generation tasks, and are increasingly deployed as agents in dynamic environments such a…
Activation Maximization Generative Adversarial Nets
Zhiming Zhou, Han Cai, Shu Rong +5
Class labels have been empirically shown useful in improving the sample quality of generative adversarial nets (GANs). In this paper, we mathematically study the properties of the…
DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder
Junyu Chen, Wenkun He, Yuchao Gu +12
We introduce DC-VideoGen, a post-training acceleration framework for efficient video generation. DC-VideoGen can be applied to any pre-trained video diffusion model, improving effi…
Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models
Yecheng Wu, Song Han, Han Cai
The paper proposes Lightning OPD 2.0, a method that reduces style‑related bias when using on‑policy distillation across different teacher models, improving performance on mathemati…
Real-Time Bidding by Reinforcement Learning in Display Advertising
Han Cai, Kan Ren, Weinan Zhang +4
The majority of online display ads are served through real-time bidding (RTB) --- each ad display impression is auctioned off in real-time when it is just being generated from a us…
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
Yuchao Gu, Guian Fang, Yuxin Jiang +4
Few-step video generation has been significantly advanced by consistency distillation. However, the performance of consistency-distilled models often degrades as more sampling step…
Optimal Locally Repairable Systematic Codes Based on Packings
Han Cai, Minquan Cheng, Cuiling Fan +1
Locally repairable codes are desirable for distributed storage systems to improve the repair efficiency. In this paper, we first build a bridge between locally repairable code and…
Scaling Vision Pre-Training to 4K Resolution
Baifeng Shi, Boyi Li, Han Cai +8
High-resolution perception of visual details is crucial for daily tasks. Current vision pre-training, however, is still limited to low resolutions (e.g., 378 x 378 pixels) due to t…
Quantum Squeezing Enhanced Photothermal Microscopy
Pengcheng Fu, Xiao Liu, Siming Wang +10
Label-free optical microscopy through absorption or scattering spectroscopy provides fundamental insights across biology and materials science, yet its sensitivity remains fundamen…
JetViT: Efficient High-Resolution Vision Transformer with Post-Training Attention Search
Dongyun Zou, Zhuoyang Zhang, Junyu Chen +8
We introduce JetViT, a novel family of hybrid-architecture Vision Transformer (ViT) models that match the accuracy of state-of-the-art full-attention vision foundation models while…
A Bound on the Minimal Field Size of LRCs, and Cyclic MR Codes That Attain It
Han Cai, Moshe Schwartz
We prove a new lower bound on the field size of locally repairable codes (LRCs). Additionally, we construct maximally recoverable (MR) codes which are cyclic. While a known constru…
High-Temperature Superconductor Quantum Flux Parametron for Energy-Efficient Logic
Han Cai, Jay C. LeFebvre, Hao Li +3
As we rapidly advance through the information age, the power consumed by computers, data centers, and networks grows exponentially. This has inspired a race to develop alternative…
A New Cooperative Repair Scheme with k + 1 Helper Nodes for (n, k) Hadamard MSR codes with Small Sub-packetization
Yajuan Liu, Han Cai, Xiaohu Tang
Cooperative repair model is an available technology to deal with multiple node failures in distributed storage systems. Recently, explicit constructions of cooperative MSR codes we…
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
Haotian Tang, Yecheng Wu, Shang Yang +7
We introduce Hybrid Autoregressive Transformer (HART), an autoregressive (AR) visual generation model capable of directly generating 1024x1024 images, rivaling diffusion models in…
Network-Coding Solutions for Minimal Combination Networks and Their Sub-networks
Han Cai, Johan Chrisnata, Tuvi Etzion +2
Minimal multicast networks are fascinating and efficient combinatorial objects, where the removal of a single link makes it impossible for all receivers to obtain all messages. We…
Experimental observation of one-dimensional superradiance lattices in ultracold atoms
Liangchao Chen, Pengjun Wang, Zengming Meng +5
We measure the superradiant emission in a one-dimensional (1D) superradiance lattice (SL) in ultracold atoms. Resonantly excited to a superradiant state, the atoms are further coup…
Synthesis of antisymmetric spin exchange interaction and entanglement generation with chiral spin states in a superconducting circuit
Da-Wei Wang, Chao Song, Wei Feng +8
We have synthesized the anti-symmetric spin exchange interaction (ASI), which is also called the Dzyaloshinskii-Moriya interaction, in a superconducting circuit containing five sup…
Ideal flat and resolved SU(3) Landau levels in three dimensions
Mian Peng, Qiang Wei, Jiale Yuan +4
Landau levels (LLs) are of great importance for understanding the quantum Hall effect and associated many-body physics. Recently, their three-dimensional (3D) counterparts, i.e., d…
Condition-Aware Neural Network for Controlled Image Generation
Han Cai, Muyang Li, Zhuoyang Zhang +3
We present Condition-Aware Neural Network (CAN), a new method for adding control to image generative models. In parallel to prior conditional control methods, CAN controls the imag…
Coherent control of quantum topological states of light in Fock-state lattices
Jinfeng Deng, Hang Dong, Chuanyu Zhang +11
Topological photonics provides a novel platform to explore topological physics beyond traditional electronic materials and stimulates promising applications in topologically protec…
Symmetry protected single photon subradiance
Han Cai, Da-Wei Wang, Anatoly A. Svidzinsky +2
We study the protection of subradiant states by the symmetry of the atomic distributions in the Dicke limit, in which collective Lamb shifts cannot be neglected. We find that anti-…
Flash-KMeans: Fast and Memory-Efficient Exact K-Means
Shuo Yang, Haocheng Xi, Yilong Zhao +10
-means has historically been positioned primarily as an offline processing primitive, typically used for dataset organization or embedding preprocessing rather than as a first-c…
EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction
Han Cai, Junyan Li, Muyan Hu +2
High-resolution dense prediction enables many appealing real-world applications, such as computational photography, autonomous driving, etc. However, the vast computational cost ma…
ActionMap: Robot Policy Learning via Voxel Action Heatmap
Pei Yang, Hai Ci, Yanzhe Chen +3
Vision-language-action (VLA) models have advanced rapidly across backbones, training recipes, and data scale, yet the action decoder, which converts the backbone's hidden state int…
A Class of Minimum Storage Cooperative Regenerating Codes with Low Access Property
Xing Lin, Han Cai, Xiaohu Tang
In this paper, a new repair scheme for a modified construction of MDS codes is studied. The obtained repair scheme has optimal bandwidth for multiple failed nodes under the coopera…
Quantum coherence between cavity and artificial atom in a superconducting circuit QED ladder system
Qichun Liu, Han Cai, Yingshan Zhang +2
We have created a quantum three-level ladder system with the cavity dispersive energy level in a superconducting circuit quantum electrodynamics system consisting of a transmon qub…
DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer
Yecheng Wu, Junyu Chen, Zhuoyang Zhang +7
We introduce DC-AR, a novel masked autoregressive (AR) text-to-image generation framework that delivers superior image generation quality with exceptional computational efficiency.…
Flat-band localization in Creutz superradiance lattices
Yanyan He, Ruosong Mao, Han Cai +5
Flat bands play an important role in diffraction-free photonics and attract fundamental interest in many-body physics. Here we report the engineering of flat-band localization of c…
Entanglement generation and manipulation in the Hong-Ou-Mandel experiment: A hidden scenario beyond two-photon interference
Li-Kai Yang, Han Cai, Tao Peng +1
Hong-Ou-Mandel (HOM) effect was long believed to be a two-photon interference phenomenon. It describes the fact that two indistinguishable photons mixed at a beam splitter will bun…
SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
Junsong Chen, Yuyang Zhao, Jincheng Yu +17
We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720x1280 resolution and minute-length duration. SANA-Video synthesizes high-resolution,…
Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications
Han Cai, Ji Lin, Yujun Lin +5
Deep neural networks (DNNs) have achieved unprecedented success in the field of artificial intelligence (AI), including computer vision, natural language processing and speech reco…
HAT: Hardware-Aware Transformers for Efficient Natural Language Processing
Hanrui Wang, Zhanghao Wu, Zhijian Liu +4
Transformers are ubiquitous in Natural Language Processing (NLP) tasks, but they are difficult to be deployed on hardware due to the intensive computation. To enable low-latency in…