arXiv subjects

Liming Liu

Publications and source records attributed to Liming Liu.

At least 37 records · Page 2Linked to original sources

arXiv2026

R-Meshfusion: Reinforcement Learning Powered Sparse-View Mesh Reconstruction with Diffusion Priors

Mesh reconstruction from multi-view images is a fundamental problem in computer vision, but its performance degrades significantly under sparse-view conditions, especially in unseen regions where no ground-truth observations are available. While recent advances in diffusion models have demonstrated strong capabilities in synthesizing novel views from limited inputs, their outputs often suffer from visual artifacts and lack 3D consistency, posing challenges for reliable mesh optimization. In this paper, we propose a novel framework that leverages diffusion models to enhance sparse-view mesh reconstruction in a principled and reliable manner. To address the instability of diffusion outputs, we propose a Consensus Diffusion Module that filters unreliable generations via interquartile range (IQR) analysis and performs variance-aware image fusion to produce robust pseudo-supervision. Building on this, we design an online reinforcement learning strategy based on the Upper Confidence Bound (UCB) to adaptively select the most informative viewpoints for enhancement, guided by diffusion loss. Finally, the fused images are used to jointly supervise a NeRF-based model alongside sparse-view ground truth, ensuring consistency across both geometry and appearance. Extensive experiments demonstrate that our method achieves significant improvements in both geometric quality and rendering quality.

cs.CV↗

arXiv2025

SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models

Vision-Language-Action (VLA) models excel in robotic manipulation but are constrained by their heavy reliance on expert demonstrations, leading to demonstration bias and limiting performance. Reinforcement learning (RL) is a vital post-training strategy to overcome these limits, yet current VLA-RL methods, including group-based optimization approaches, are crippled by severe reward sparsity. Relying on binary success indicators wastes valuable information in failed trajectories, resulting in low training efficiency. To solve this, we propose Self-Referential Policy Optimization (SRPO), a novel VLA-RL framework. SRPO eliminates the need for external demonstrations or manual reward engineering by leveraging the model's own successful trajectories, generated within the current training batch, as a self-reference. This allows us to assign a progress-wise reward to failed attempts. A core innovation is the use of latent world representations to measure behavioral progress robustly. Instead of relying on raw pixels or requiring domain-specific fine-tuning, we utilize the compressed, transferable encodings from a world model's latent space. These representations naturally capture progress patterns across environments, enabling accurate, generalized trajectory comparison. Empirical evaluations on the LIBERO benchmark demonstrate SRPO's efficiency and effectiveness. Starting from a supervised baseline with 48.9% success, SRPO achieves a new state-of-the-art success rate of 99.2% in just 200 RL steps, representing a 103% relative improvement without any extra supervision. Furthermore, SRPO shows substantial robustness, achieving a 167% performance improvement on the LIBERO-Plus benchmark.

cs.RO↗

arXiv2025

Chat with AI: The Surprising Turn of Real-time Video Communication from Human to AI

AI Video Chat emerges as a new paradigm for Real-time Communication (RTC), where one peer is not a human, but a Multimodal Large Language Model (MLLM). This makes interaction between humans and AI more intuitive, as if chatting face-to-face with a real person. However, this poses significant challenges to latency, because the MLLM inference takes up most of the response time, leaving very little time for video streaming. Due to network uncertainty, transmission latency becomes a critical bottleneck preventing AI from being like a real person. To address this, we call for AI-oriented RTC research, exploring the network requirement shift from "humans watching video" to "AI understanding video". We begin by recognizing the main differences between AI Video Chat and traditional RTC. Then, through prototype measurements, we identify that ultra-low bitrate is a key factor for low latency. To reduce bitrate dramatically while maintaining MLLM accuracy, we propose Context-Aware Video Streaming that recognizes the importance of each video region for chat and allocates bitrate almost exclusively to chat-important regions. To evaluate the impact of video streaming quality on MLLM accuracy, we build the first benchmark, named Degraded Video Understanding Benchmark (DeViBench). Finally, we discuss some open questions and ongoing solutions for AI Video Chat. DeViBench is open-sourced at: https://github.com/pku-netvideo/DeViBench.

cs.NI↗

arXiv2025

COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs

Large Language Models (LLMs) have demonstrated remarkable success across various domains, yet their optimization remains a significant challenge due to the complex and high-dimensional loss landscapes they inhabit. While adaptive optimizers such as AdamW are widely used, they suffer from critical limitations, including an inability to capture interdependencies between coordinates and high memory consumption. Subsequent research, exemplified by SOAP, attempts to better capture coordinate interdependence but incurs greater memory overhead, limiting scalability for massive LLMs. An alternative approach aims to reduce memory consumption through low-dimensional projection, but this leads to substantial approximation errors, resulting in less effective optimization (e.g., in terms of per-token efficiency). In this paper, we propose COSMOS, a novel hybrid optimizer that leverages the varying importance of eigensubspaces in the gradient matrix to achieve memory efficiency without compromising optimization performance. The design of COSMOS is motivated by our empirical insights and practical considerations. Specifically, COSMOS applies SOAP to the leading eigensubspace, which captures the primary optimization dynamics, and MUON to the remaining eigensubspace, which is less critical but computationally expensive to handle with SOAP. This hybrid strategy significantly reduces memory consumption while maintaining robust optimization performance, making it particularly suitable for massive LLMs. Numerical experiments on various datasets and transformer architectures are provided to demonstrate the effectiveness of COSMOS. Our code is available at https://github.com/lliu606/COSMOS.

cs.LG↗

arXiv2025

Learning to Mitigate Post-Outage Load Surges: A Data-Driven Framework for Electrifying and Decarbonizing Grids

Electrification and decarbonization are transforming power system demand and recovery dynamics, yet their implications for post-outage load surges remain poorly understood. Here we analyze a metropolitan-scale heterogeneous dataset for Indianapolis comprising 30,046 feeder-level outages between 2020 and 2024, linked to smart meters and submetering, to quantify the causal impact of electric vehicles (EVs), heat pumps (HPs) and distributed energy resources (DERs) on restoration surges. Statistical analysis and causal forest inference demonstrate that rising penetrations of all three assets significantly increase surge ratios, with effects strongly modulated by restoration timing, outage duration and weather conditions. We develop a component-aware multi-task Transformer estimator that disaggregates EV, HP and DER contributions, and apply it to project historical outages under counterfactual 2035 adoption pathways. In a policy-aligned pathway, evening restorations emerge as the binding reliability constraint, with exceedance probabilities of 0.057 when 30\% of system load is restored within the first 15 minutes. Mitigation measures, probabilistic EV restarts, short thermostat offsets and accelerated DER reconnection, reduce exceedance to 0.019 and eliminate it entirely when 20\% or less of system load is restored. These results demonstrate that transition-era surges are asset-driven and causally linked to electrification and decarbonization, but can be effectively managed through integrated operational strategies.

eess.SY↗

arXiv2025

NorMuon: Making Muon more efficient and scalable

The choice of optimizer significantly impacts the training efficiency and computational costs of large language models (LLMs). Recently, the Muon optimizer has demonstrated promising results by orthogonalizing parameter updates, improving optimization geometry through better conditioning. Despite Muon's emergence as a candidate successor to Adam, the potential for jointly leveraging their strengths has not been systematically explored. In this work, we bridge this gap by proposing NorMuon (Neuron-wise Normalized Muon), an optimizer that synergistically combines orthogonalization with neuron-level adaptive learning rates. Our analysis reveals that while Muon effectively reduces condition numbers, the resulting updates exhibit highly non-uniform neuron norms, causing certain neurons to dominate the optimization process. NorMuon addresses this imbalance by maintaining second-order momentum statistics for each neuron and applying row-wise normalization after orthogonalization, ensuring balanced parameter utilization while preserving Muon's conditioning benefits. To enable practical deployment at scale, we develop an efficient distributed implementation under the FSDP2 framework that strategically distributes orthogonalization computations across devices. Experiments across multiple model scales demonstrate that NorMuon consistently outperforms both Adam and Muon, achieving 21.74% better training efficiency than Adam and 11.31% improvement over Muon on 1.1 B pretraining setting, while maintaining a comparable memory footprint to Muon. Our findings suggest that orthogonalization and adaptive learning rates are complementary rather than competing approaches, opening new avenues for optimizer design in large-scale deep learning.

cs.LG↗

arXiv2025

LIMI: Less is More for Agency

We define Agency as the emergent capacity of AI systems to function as autonomous agents actively discovering problems, formulating hypotheses, and executing solutions through self-directed engagement with environments and tools. This fundamental capability marks the dawn of the Age of AI Agency, driven by a critical industry shift: the urgent need for AI systems that don't just think, but work. While current AI excels at reasoning and generating responses, industries demand autonomous agents that can execute tasks, operate tools, and drive real-world outcomes. As agentic intelligence becomes the defining characteristic separating cognitive systems from productive workers, efficiently cultivating machine autonomy becomes paramount. Current approaches assume that more data yields better agency, following traditional scaling laws from language modeling. We fundamentally challenge this paradigm. LIMI (Less Is More for Intelligent Agency) demonstrates that agency follows radically different development principles. Through strategic focus on collaborative software development and scientific research workflows, we show that sophisticated agentic intelligence can emerge from minimal but strategically curated demonstrations of autonomous behavior. Using only 78 carefully designed training samples, LIMI achieves 73.5% on comprehensive agency benchmarks, dramatically outperforming state-of-the-art models: Kimi-K2-Instruct (24.1%), DeepSeek-V3.1 (11.9%), Qwen3-235B-A22B-Instruct (27.5%), and GLM-4.5 (45.1%). Most strikingly, LIMI demonstrates 53.7% improvement over models trained on 10,000 samples-achieving superior agentic intelligence with 128 times fewer samples. Our findings establish the Agency Efficiency Principle: machine autonomy emerges not from data abundance but from strategic curation of high-quality agentic demonstrations.

cs.AI↗

arXiv2025

FlowletFormer: Network Behavioral Semantic Aware Pre-training Model for Traffic Classification

Network traffic classification using pre-training models has shown promising results, but existing methods struggle to capture packet structural characteristics, flow-level behaviors, hierarchical protocol semantics, and inter-packet contextual relationships. To address these challenges, we propose FlowletFormer, a BERT-based pre-training model specifically designed for network traffic analysis. FlowletFormer introduces a Coherent Behavior-Aware Traffic Representation Model for segmenting traffic into semantically meaningful units, a Protocol Stack Alignment-Based Embedding Layer to capture multilayer protocol semantics, and Field-Specific and Context-Aware Pretraining Tasks to enhance both inter-packet and inter-flow learning. Experimental results demonstrate that FlowletFormer significantly outperforms existing methods in the effectiveness of traffic representation, classification accuracy, and few-shot learning capability. Moreover, by effectively integrating domain-specific network knowledge, FlowletFormer shows better comprehension of the principles of network transmission (e.g., stateful connections of TCP), providing a more robust and trustworthy framework for traffic analysis.

cs.LG↗

arXiv2025

Data-driven quantification and visualization of resilience metrics of power distribution system

This paper presents a data-driven approach for quantifying the resilience of distribution power grids to extreme weather events using two key metrics: (a) the number of outages and (b) restoration time. The method leverages historical outage records maintained by power utilities and weather measurements collected by the National Oceanic and Atmospheric Administration (NOAA) to evaluate resilience across a utility's service territory. The proposed framework consists of three stages. First, outage events are systematically extracted from the outage records by temporally and spatially aggregating coincident component outages. In the second stage, weather zones across the service territory are delineated using a Voronoi polygon approach, based on the locations of NOAA weather sensors. Finally, data-driven models for outage fragility and restoration time are developed for each weather zone. These models enable the quantification and visualization of resilience metrics under varying intensities of extreme weather events. The proposed method is demonstrated using real-world data from a US distribution utility, located in Indianapolis, focused on wind- and precipitation-related events. The dataset spans two decades and includes over 160,000 outage records.

eess.SY↗

arXiv2025

Subspecialty-Specific Foundation Model for Intelligent Gastrointestinal Pathology

Gastrointestinal (GI) diseases represent a clinically significant burden, necessitating precise diagnostic approaches to optimize patient outcomes. Conventional histopathological diagnosis suffers from limited reproducibility and diagnostic variability. To overcome these limitations, we develop Digepath, a specialized foundation model for GI pathology. Our framework introduces a dual-phase iterative optimization strategy combining pretraining with fine-screening, specifically designed to address the detection of sparsely distributed lesion areas in whole-slide images. Digepath is pretrained on over 353 million multi-scale images from 210,043 H&E-stained slides of GI diseases. It attains state-of-the-art performance on 33 out of 34 tasks related to GI pathology, including pathological diagnosis, protein expression status prediction, gene mutation prediction, and prognosis evaluation. We further translate the intelligent screening module for early GI cancer and achieve near-perfect 99.70% sensitivity across nine independent medical institutions. This work not only advances AI-driven precision pathology for GI diseases but also bridge critical gaps in histopathological practice.

eess.IV↗

arXiv2025

Promptus: Can Prompts Streaming Replace Video Streaming with Stable Diffusion

With the exponential growth of video traffic, traditional video streaming systems are approaching their limits in compression efficiency and communication capacity. To further reduce bitrate while maintaining quality, we propose Promptus, a disruptive semantic communication system that streaming prompts instead of video content, which represents real-world video frames with a series of "prompts" for delivery and employs Stable Diffusion to generate videos at the receiver. To ensure that the generated video is pixel-aligned with the original video, a gradient descent-based prompt fitting framework is proposed. Further, a low-rank decomposition-based bitrate control algorithm is introduced to achieve adaptive bitrate. For inter-frame compression, an interpolation-aware fitting algorithm is proposed. Evaluations across various video genres demonstrate that, compared to H.265, Promptus can achieve more than a 4x bandwidth reduction while preserving the same perceptual quality. On the other hand, at extremely low bitrates, Promptus can enhance the perceptual quality by 0.139 and 0.118 (in LPIPS) compared to VAE and H.265, respectively, and decreases the ratio of severely distorted frames by 89.3% and 91.7%. Our work opens up a new paradigm for efficient video communication. Promptus is open-sourced at: https://github.com/JiangkaiWu/Promptus.

cs.NI↗

arXiv2025

PromptMobile: Efficient Promptus for Low Bandwidth Mobile Video Streaming

Traditional video compression algorithms exhibit significant quality degradation at extremely low bitrates. Promptus emerges as a new paradigm for video streaming, substantially cutting down the bandwidth essential for video streaming. However, Promptus is computationally intensive and can not run in real-time on mobile devices. This paper presents PromptMobile, an efficient acceleration framework tailored for on-device Promptus. Specifically, we propose (1) a two-stage efficient generation framework to reduce computational cost by 8.1x, (2) a fine-grained inter-frame caching to reduce redundant computations by 16.6%, (3) system-level optimizations to further enhance efficiency. The evaluations demonstrate that compared with the original Promptus, PromptMobile achieves a 13.6x increase in image generation speed. Compared with other streaming methods, PromptMobile achives an average LPIPS improvement of 0.016 (compared with H.265), reducing 60% of severely distorted frames (compared to VQGAN).

cs.NI↗

arXiv2025

MCBlock: Boosting Neural Radiance Field Training Speed by MCTS-based Dynamic-Resolution Ray Sampling

Neural Radiance Field (NeRF) is widely known for high-fidelity novel view synthesis. However, even the state-of-the-art NeRF model, Gaussian Splatting, requires minutes for training, far from the real-time performance required by multimedia scenarios like telemedicine. One of the obstacles is its inefficient sampling, which is only partially addressed by existing works. Existing point-sampling algorithms uniformly sample simple-texture regions (easy to fit) and complex-texture regions (hard to fit), while existing ray-sampling algorithms sample these regions all in the finest granularity (i.e. the pixel level), both wasting GPU training resources. Actually, regions with different texture intensities require different sampling granularities. To this end, we propose a novel dynamic-resolution ray-sampling algorithm, MCBlock, which employs Monte Carlo Tree Search (MCTS) to partition each training image into pixel blocks with different sizes for active block-wise training. Specifically, the trees are initialized according to the texture of training images to boost the initialization speed, and an expansion/pruning module dynamically optimizes the block partition. MCBlock is implemented in Nerfstudio, an open-source toolset, and achieves a training acceleration of up to 2.33x, surpassing other ray-sampling algorithms. We believe MCBlock can apply to any cone-tracing NeRF model and contribute to the multimedia community.

cs.CV↗

arXiv2025

A Minimalist Example of Edge-of-Stability and Progressive Sharpening

Recent advances in deep learning optimization have unveiled two intriguing phenomena under large learning rates: Edge of Stability (EoS) and Progressive Sharpening (PS), challenging classical Gradient Descent (GD) analyses. Current research approaches, using either generalist frameworks or minimalist examples, face significant limitations in explaining these phenomena. This paper advances the minimalist approach by introducing a two-layer network with a two-dimensional input, where one dimension is relevant to the response and the other is irrelevant. Through this model, we rigorously prove the existence of progressive sharpening and self-stabilization under large learning rates, and establish non-asymptotic analysis of the training dynamics and sharpness along the entire GD trajectory. Besides, we connect our minimalist example to existing works by reconciling the existence of a well-behaved ``stable set" between minimalist and generalist analyses, and extending the analysis of Gradient Flow Solution sharpness to our two-dimensional input scenario. These findings provide new insights into the EoS phenomenon from both parameter and input data distribution perspectives, potentially informing more effective optimization strategies in deep learning practice.

cs.LG↗

arXiv2022

Data-Driven Affinely Adjustable Robust Volt/VAr Control

This paper proposes a data-driven affinely adjustable robust Volt/VAr control (AARVVC) scheme, which modulates the smart inverter reactive power in an affine function of its active power, based on the voltage sensitivities with respect to real/reactive power injections. To achieve a fast and accurate estimation of voltage sensitivities, we propose a data-driven method based on deep neural network (DNN), together with a rule-based bus-selection process using the bidirectional search method. Our method only uses the operating statuses of selected buses as inputs to DNN, thus significantly improving the training efficiency and reducing information redundancy. Finally, a distributed consensus-based solution, based on the alternating direction method of multipliers (ADMM), for the AARVVC is applied to decide the inverter reactive power adjustment rule with respect to its active power. Only limited information exchange is required between each local agent and the central agent to obtain the slope of the reactive power adjustment rule, and there is no need for the central agent to solve any (sub)optimization problems. Numerical results on the modified IEEE-123 bus system validate the effectiveness and superiority of the proposed data-driven AARVVC method.

eess.SY↗

arXiv2016

Dynamic Terahertz Beam Steering Based on Graphene Metasurfaces

A full (2$π$) phase modulation is critical for efficient wavefront manipulation. In this article, a metasurface based on graphene long/short-strip resonators is used to implement a dynamic 2$π$ phase modulation by applying different voltages to different graphene resonators. The configuration is found to have high reflection efficiency (minimum 56%) and has a full phase modulation in a wide frequency range. Terahertz (THz) beam steering as large as 120 degrees ($\pm60^\circ$) is demonstrated in a broad frequency range (1.2 to 1.9 THz) by changing the Fermi levels of different graphene resonators accordingly. This metasurface can provide a new platform for effectively manipulating THz waves.

physics.optics↗

arXiv2005

Evolving Networks and Birth-and-Death Processes

Using a simple model with link removals as well as link additions, we show that an evolving network is scale free with a degree exponent in the range of (2, 4]. We then establish a relation between the network evolution and a set of non-homogeneous birth-and-death processes, and, with which, we capture the process by which the network connectivity evolves. We develop an effective algorithm to compute the network degree distribution accurately. Comparing analytical and numerical results with simulation, we identify some interesting network properties and verify the effectiveness of our method.

math-ph↗

arXiv2004

A Markov Chain-Based Numerical Method for Calculating Network Degree Distributions

This paper establishes a relation between scale-free networks and Markov chains, and proposes a computation framework for degree distributions of scale-free networks. We first find that, under the BA model, the degree evolution of individual nodes in a scale-free network follows some non-homogeneous Markov chains. Exploring the special structure of these Markov chains, we are able to develop an efficient algorithm to compute the degree distribution numerically. The complexity of our algorithm is O(t^2), where $t$ is the number of time steps for adding new nodes. We use three examples to demonstrate the computation procedure and compare the results with those from the existing methods.

math-ph↗