arXiv subjects

Xuelong Li

Publications and source records attributed to Xuelong Li.

At least 271 records · Page 15Linked to original sources

arXiv2025

LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Rendering and Control

This paper scales object-level reconstruction to complex scenes, advancing interactive scene reconstruction. We introduce two datasets, OmniSim and InterReal, featuring 28 scenes with multiple interactive objects. To tackle the challenge of inaccurate interactive motion recovery in complex scenes, we propose LiveScene, a scene-level language-embedded interactive radiance field that efficiently reconstructs and controls multiple objects. By decomposing the interactive scene into local deformable fields, LiveScene enables separate reconstruction of individual object motions, reducing memory consumption. Additionally, our interaction-aware language embedding localizes individual interactive objects, allowing for arbitrary control using natural language. Our approach demonstrates significant superiority in novel view synthesis, interactive scene control, and language grounding performance through extensive experiments. Project page: https://livescenes.github.io.

cs.CV↗

arXiv2025

Large model enhanced computational ghost imaging

Ghost imaging (GI) achieves 2D image reconstruction through high-order correlation of 1D bucket signals and 2D light field information, particularly demonstrating enhanced detection sensitivity and high-quality image reconstruction via efficient photon collection in scattering media. Recent investigations have established that deep learning (DL) can substantially enhance the ghost imaging reconstruction quality. Furthermore, with the emergence of large models like SDXL, GPT-4, etc., the constraints of conventional DL in parameters and architecture have been transcended, enabling models to comprehensively explore relationships among all distinct positions within feature sequences. This paradigm shift has significantly advanced the capability of DL in restoring severely degraded and low-resolution imagery, making it particularly advantageous for noise-robust image reconstruction in GI applications. In this paper, we propose the first large imaging model with 1.4 billion parameters that incorporates the physical principles of GI (GILM). The proposed GILM implements a skip connection mechanism to mitigate gradient explosion challenges inherent in deep architectures, ensuring sufficient parametric capacity to capture intricate correlations among object single-pixel measurements. Moreover, GILM leverages multi-head attention mechanism to learn spatial dependencies across pixel points during image reconstruction, facilitating the extraction of comprehensive object information for subsequent reconstruction. We validated the effectiveness of GILM through a series of experiments, including simulated object imaging, imaging objects in free space, and imaging object located 52 meters away in underwater environment. The experimental results show that GILM effectively analyzes the fluctuation trends of the collected signals, thereby optimizing the recovery of the object's image from the acquired data.

eess.IV↗

arXiv2025

From Captions to Rewards (CAREVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models

Aligning large vision-language models (LVLMs) with human preferences is challenging due to the scarcity of fine-grained, high-quality, and multimodal preference data without human annotations. Existing methods relying on direct distillation often struggle with low-confidence data, leading to suboptimal performance. To address this, we propose CAREVL, a novel method for preference reward modeling by reliably using both high- and low-confidence data. First, a cluster of auxiliary expert models (textual reward models) innovatively leverages image captions as weak supervision signals to filter high-confidence data. The high-confidence data are then used to fine-tune the LVLM. Second, low-confidence data are used to generate diverse preference samples using the fine-tuned LVLM. These samples are then scored and selected to construct reliable chosen-rejected pairs for further training. CAREVL achieves performance improvements over traditional distillation-based methods on VL-RewardBench and MLLM-as-a-Judge benchmark, demonstrating its effectiveness. The code will be released soon.

cs.CV↗

arXiv2025

Underlying Semantic Diffusion for Effective and Efficient In-Context Learning

Diffusion models has emerged as a powerful framework for tasks like image controllable generation and dense prediction. However, existing models often struggle to capture underlying semantics (e.g., edges, textures, shapes) and effectively utilize in-context learning, limiting their contextual understanding and image generation quality. Additionally, high computational costs and slow inference speeds hinder their real-time applicability. To address these challenges, we propose Underlying Semantic Diffusion (US-Diffusion), an enhanced diffusion model that boosts underlying semantics learning, computational efficiency, and in-context learning capabilities on multi-task scenarios. We introduce Separate & Gather Adapter (SGA), which decouples input conditions for different tasks while sharing the architecture, enabling better in-context learning and generalization across diverse visual domains. We also present a Feedback-Aided Learning (FAL) framework, which leverages feedback signals to guide the model in capturing semantic details and dynamically adapting to task-specific contextual cues. Furthermore, we propose a plug-and-play Efficient Sampling Strategy (ESS) for dense sampling at time steps with high-noise levels, which aims at optimizing training and inference efficiency while maintaining strong in-context learning performance. Experimental results demonstrate that US-Diffusion outperforms the state-of-the-art method, achieving an average reduction of 7.47 in FID on Map2Image tasks and an average reduction of 0.026 in RMSE on Image2Map tasks, while achieving approximately 9.45 times faster inference speed. Our method also demonstrates superior training efficiency and in-context learning capabilities, excelling in new datasets and tasks, highlighting its robustness and adaptability across diverse visual domains.

cs.CV↗

arXiv2025

Preference Aligned Diffusion Planner for Quadrupedal Locomotion Control

Diffusion models demonstrate superior performance in capturing complex distributions from large-scale datasets, providing a promising solution for quadrupedal locomotion control. However, the robustness of the diffusion planner is inherently dependent on the diversity of the pre-collected datasets. To mitigate this issue, we propose a two-stage learning framework to enhance the capability of the diffusion planner under limited dataset (reward-agnostic). Through the offline stage, the diffusion planner learns the joint distribution of state-action sequences from expert datasets without using reward labels. Subsequently, we perform the online interaction in the simulation environment based on the trained offline planner, which significantly diversified the original behavior and thus improves the robustness. Specifically, we propose a novel weak preference labeling method without the ground-truth reward or human preferences. The proposed method exhibits superior stability and velocity tracking accuracy in pacing, trotting, and bounding gait under different speeds and can perform a zero-shot transfer to the real Unitree Go1 robots. The project website for this paper is at https://shangjaven.github.io/preference-aligned-diffusion-legged.

cs.RO↗

arXiv2025

Humanoid Whole-Body Locomotion on Narrow Terrain via Dynamic Balance and Reinforcement Learning

Humans possess delicate dynamic balance mechanisms that enable them to maintain stability across diverse terrains and under extreme conditions. However, despite significant advances recently, existing locomotion algorithms for humanoid robots are still struggle to traverse extreme environments, especially in cases that lack external perception (e.g., vision or LiDAR). This is because current methods often rely on gait-based or perception-condition rewards, lacking effective mechanisms to handle unobservable obstacles and sudden balance loss. To address this challenge, we propose a novel whole-body locomotion algorithm based on dynamic balance and Reinforcement Learning (RL) that enables humanoid robots to traverse extreme terrains, particularly narrow pathways and unexpected obstacles, using only proprioception. Specifically, we introduce a dynamic balance mechanism by leveraging an extended measure of Zero-Moment Point (ZMP)-driven rewards and task-driven rewards in a whole-body actor-critic framework, aiming to achieve coordinated actions of the upper and lower limbs for robust locomotion. Experiments conducted on a full-sized Unitree H1-2 robot verify the ability of our method to maintain balance on extremely narrow terrains and under external disturbances, demonstrating its effectiveness in enhancing the robot's adaptability to complex environments. The videos are given at https://whole-body-loco.github.io.

cs.RO↗

arXiv2025

Leader and Follower: Interactive Motion Generation under Trajectory Constraints

With the rapid advancement of game and film production, generating interactive motion from texts has garnered significant attention due to its potential to revolutionize content creation processes. In many practical applications, there is a need to impose strict constraints on the motion range or trajectory of virtual characters. However, existing methods that rely solely on textual input face substantial challenges in accurately capturing the user's intent, particularly in specifying the desired trajectory. As a result, the generated motions often lack plausibility and accuracy. Moreover, existing trajectory - based methods for customized motion generation rely on retraining for single - actor scenarios, which limits flexibility and adaptability to different datasets, as well as interactivity in two-actor motions. To generate interactive motion following specified trajectories, this paper decouples complex motion into a Leader - Follower dynamic, inspired by role allocation in partner dancing. Based on this framework, this paper explores the motion range refinement process in interactive motion generation and proposes a training-free approach, integrating a Pace Controller and a Kinematic Synchronization Adapter. The framework enhances the ability of existing models to generate motion that adheres to trajectory by controlling the leader's movement and correcting the follower's motion to align with the leader. Experimental results show that the proposed approach, by better leveraging trajectory information, outperforms existing methods in both realism and accuracy.

cs.RO↗

arXiv2025

AudioSpa: Spatializing Sound Events with Text

Text-to-audio (TTA) systems have recently demonstrated strong performance in synthesizing monaural audio from text. However, the task of generating binaural spatial audio from text, which provides a more immersive auditory experience by incorporating the sense of spatiality, have not been explored yet. In this work, we introduce text-guided binaural audio generation. As an early effort, we focus on the scenario where a monaural reference audio is given additionally. The core problem is to associate specific sound events with their directions, thereby creating binaural spatial audio. The challenge lies in the complexity of textual descriptions and the limited availability of single-source sound event datasets. To address this, we propose AudioSpa, an end-to-end model that applies large language models to process both acoustic and textual information. We employ fusion multi-head attention (FMHA) to integrate text tokens, which enhances the generation capability of the multimodal learning. Additionally, we propose a binaural source localization model to assess the quality of the generated audio. Finally, we design a data augmentation strategy to generate diverse datasets, which enables the model to spatialize sound events across various spatial positions. Experimental results demonstrate that our model is able to put sounds at the specified locations accurately. It achieves competitive performance in both localization accuracy and signal distortion. Our demonstrations are available at https://linfeng-feng.github.io/AudioSpa-demo.

eess.AS↗

arXiv2025

AI Flow at the Network Edge

Recent advancements in large language models (LLMs) and their multimodal variants have led to remarkable progress across various domains, demonstrating impressive capabilities and unprecedented potential. In the era of ubiquitous connectivity, leveraging communication networks to distribute intelligence is a transformative concept, envisioning AI-powered services accessible at the network edge. However, pushing large models from the cloud to resource-constrained environments faces critical challenges. Model inference on low-end devices leads to excessive latency and performance bottlenecks, while raw data transmission over limited bandwidth networks causes high communication overhead. This article presents AI Flow, a framework that streamlines the inference process by jointly leveraging the heterogeneous resources available across devices, edge nodes, and cloud servers, making intelligence flow across networks. To facilitate cooperation among multiple computational nodes, the proposed framework explores a paradigm shift in the design of communication network systems from transmitting information flow to intelligence flow, where the goal of communications is task-oriented and folded into the inference process. Experimental results demonstrate the effectiveness of the proposed framework through an image captioning use case, showcasing the ability to reduce response latency while maintaining high-quality captions. This article serves as a position paper for identifying the motivation, challenges, and principles of AI Flow.

eess.SP↗

arXiv2025

Online Preference Alignment for Language Models via Count-based Exploration

Reinforcement Learning from Human Feedback (RLHF) has shown great potential in fine-tuning Large Language Models (LLMs) to align with human preferences. Existing methods perform preference alignment from a fixed dataset, which can be limited in data coverage, and the resulting reward model is hard to generalize in out-of-distribution responses. Thus, online RLHF is more desirable to empower the LLM to explore outside the support of the initial dataset by iteratively collecting the prompt-response pairs. In this paper, we study the fundamental problem in online RLHF, i.e. \emph{how to explore} for LLM. We give a theoretical motivation in linear reward assumption to show that an optimistic reward with an upper confidence bound (UCB) term leads to a provably efficient RLHF policy. Then, we reformulate our objective to direct preference optimization with an exploration term, where the UCB-term can be converted to a count-based exploration bonus. We further propose a practical algorithm, named \emph{Count-based Online Preference Optimization (COPO)}, which leverages a simple coin-flip counting module to estimate the pseudo-count of a prompt-response pair in previously collected data. COPO encourages LLMs to balance exploration and preference optimization in an iterative manner, which enlarges the exploration space and the entire data coverage of iterative LLM policies. We conduct online RLHF experiments on Zephyr and Llama-3 models. The results on instruction-following and standard academic benchmarks show that COPO significantly increases performance.

cs.LG↗

arXiv2025

LEAF: Unveiling Two Sides of the Same Coin in Semi-supervised Facial Expression Recognition

Semi-supervised learning has emerged as a promising approach to tackle the challenge of label scarcity in facial expression recognition (FER) task. However, current state-of-the-art methods primarily focus on one side of the coin, i.e., generating high-quality pseudo-labels, while overlooking the other side: enhancing expression-relevant representations. In this paper, we unveil both sides of the coin by proposing a unified framework termed hierarchicaL dEcoupling And Fusing (LEAF) to coordinate expression-relevant representations and pseudo-labels for semi-supervised FER. LEAF introduces a hierarchical expression-aware aggregation strategy that operates at three levels: semantic, instance, and category. (1) At the semantic and instance levels, LEAF decouples representations into expression-agnostic and expression-relevant components, and adaptively fuses them using learnable gating weights. (2) At the category level, LEAF assigns ambiguous pseudo-labels by decoupling predictions into positive and negative parts, and employs a consistency loss to ensure agreement between two augmented views of the same image. Extensive experiments on benchmark datasets demonstrate that by unveiling and harmonizing both sides of the coin, LEAF outperforms state-of-the-art semi-supervised FER methods, effectively leveraging both labeled and unlabeled data. Moreover, the proposed expression-aware aggregation strategy can be seamlessly integrated into existing semi-supervised frameworks, leading to significant performance gains. Our code is available at \url{https://github.com/zfkarl/LEAF}.

cs.CV↗

arXiv2025

FastUMI: A Scalable and Hardware-Independent Universal Manipulation Interface with Dataset

Real-world manipulation data involving robotic arms is crucial for developing generalist action policies, yet such data remains scarce since existing data collection methods are hindered by high costs, hardware dependencies, and complex setup requirements. In this work, we introduce FastUMI, a substantial redesign of the Universal Manipulation Interface (UMI) system that addresses these challenges by enabling rapid deployment, simplifying hardware-software integration, and delivering robust performance in real-world data acquisition. Compared with UMI, FastUMI has several advantages: 1) It adopts a decoupled hardware design and incorporates extensive mechanical modifications, removing dependencies on specialized robotic components while preserving consistent observation perspectives. 2) It also refines the algorithmic pipeline by replacing complex Visual-Inertial Odometry (VIO) implementations with an off-the-shelf tracking module, significantly reducing deployment complexity while maintaining accuracy. 3) FastUMI includes an ecosystem for data collection, verification, and integration with both established and newly developed imitation learning algorithms, accelerating policy learning advancement. Additionally, we have open-sourced a high-quality dataset of over 10,000 real-world demonstration trajectories spanning 22 everyday tasks, forming one of the most diverse UMI-like datasets to date. Experimental results confirm that FastUMI facilitates rapid deployment, reduces operational costs and labor demands, and maintains robust performance across diverse manipulation scenarios, thereby advancing scalable data-driven robotic learning.

cs.RO↗

arXiv2025

Why Does Dropping Edges Usually Outperform Adding Edges in Graph Contrastive Learning?

Graph contrastive learning (GCL) has been widely used as an effective self-supervised learning method for graph representation learning. However, how to apply adequate and stable graph augmentation to generating proper views for contrastive learning remains an essential problem. Dropping edges is a primary augmentation in GCL while adding edges is not a common method due to its unstable performance. To our best knowledge, there is no theoretical analysis to study why dropping edges usually outperforms adding edges. To answer this question, we introduce a new metric, namely Error Passing Rate (EPR), to quantify how a graph fits the network. Inspired by the theoretical conclusions and the idea of positive-incentive noise, we propose a novel GCL algorithm, Error-PAssing-based Graph Contrastive Learning (EPAGCL), which uses both edge adding and edge dropping as its augmentations. To be specific, we generate views by adding and dropping edges based on the weights derived from EPR. Extensive experiments on various real-world datasets are conducted to validate the correctness of our theoretical analysis and the effectiveness of our proposed algorithm. Our code is available at: https://github.com/hyzhang98/EPAGCL.

cs.LG↗

arXiv2025

FGAseg: Fine-Grained Pixel-Text Alignment for Open-Vocabulary Semantic Segmentation

Open-vocabulary segmentation aims to identify and segment specific regions and objects based on text-based descriptions. A common solution is to leverage powerful vision-language models (VLMs), such as CLIP, to bridge the gap between vision and text information. However, VLMs are typically pretrained for image-level vision-text alignment, focusing on global semantic features. In contrast, segmentation tasks require fine-grained pixel-level alignment and detailed category boundary information, which VLMs alone cannot provide. As a result, information extracted directly from VLMs can't meet the requirements of segmentation tasks. To address this limitation, we propose FGAseg, a model designed for fine-grained pixel-text alignment and category boundary supplementation. The core of FGAseg is a Pixel-Level Alignment module that employs a cross-modal attention mechanism and a text-pixel alignment loss to refine the coarse-grained alignment from CLIP, achieving finer-grained pixel-text semantic alignment. Additionally, to enrich category boundary information, we introduce the alignment matrices as optimizable pseudo-masks during forward propagation and propose Category Information Supplementation module. These pseudo-masks, derived from cosine and convolutional similarity, provide essential global and local boundary information between different categories. By combining these two strategies, FGAseg effectively enhances pixel-level alignment and category boundary information, addressing key challenges in open-vocabulary segmentation. Extensive experiments demonstrate that FGAseg outperforms existing methods on open-vocabulary semantic segmentation benchmarks.

cs.CV↗

arXiv2024

A Greedy Strategy for Graph Cut

We propose a Greedy strategy to solve the problem of Graph Cut, called GGC. It starts from the state where each data sample is regarded as a cluster and dynamically merges the two clusters which reduces the value of the global objective function the most until the required number of clusters is obtained, and the monotonicity of the sequence of objective function values is proved. To reduce the computational complexity of GGC, only mergers between clusters and their neighbors are considered. Therefore, GGC has a nearly linear computational complexity with respect to the number of samples. Also, unlike other algorithms, due to the greedy strategy, the solution of the proposed algorithm is unique. In other words, its performance is not affected by randomness. We apply the proposed method to solve the problem of normalized cut which is a widely concerned graph cut problem. Extensive experiments show that better solutions can often be achieved compared to the traditional two-stage optimization algorithm (eigendecomposition + k-means), on the normalized cut problem. In addition, the performance of GGC also has advantages compared to several state-of-the-art clustering algorithms.

cs.LG↗

arXiv2024

VAST 1.0: A Unified Framework for Controllable and Consistent Video Generation

Generating high-quality videos from textual descriptions poses challenges in maintaining temporal coherence and control over subject motion. We propose VAST (Video As Storyboard from Text), a two-stage framework to address these challenges and enable high-quality video generation. In the first stage, StoryForge transforms textual descriptions into detailed storyboards, capturing human poses and object layouts to represent the structural essence of the scene. In the second stage, VisionForge generates videos from these storyboards, producing high-quality videos with smooth motion, temporal consistency, and spatial coherence. By decoupling text understanding from video generation, VAST enables precise control over subject dynamics and scene composition. Experiments on the VBench benchmark demonstrate that VAST outperforms existing methods in both visual quality and semantic expression, setting a new standard for dynamic and coherent video generation.

cs.CV↗

arXiv2024

Enhance Vision-Language Alignment with Noise

With the advancement of pre-trained vision-language (VL) models, enhancing the alignment between visual and linguistic modalities in downstream tasks has emerged as a critical challenge. Different from existing fine-tuning methods that add extra modules to these two modalities, we investigate whether the frozen model can be fine-tuned by customized noise. Our approach is motivated by the scientific study of beneficial noise, namely Positive-incentive Noise (Pi-noise or $π$-noise) , which quantitatively analyzes the impact of noise. It therefore implies a new scheme to learn beneficial noise distribution that can be employed to fine-tune VL models. Focusing on few-shot classification tasks based on CLIP, we reformulate the inference process of CLIP and apply variational inference, demonstrating how to generate $π$-noise towards visual and linguistic modalities. Then, we propose Positive-incentive Noise Injector (PiNI), which can fine-tune CLIP via injecting noise into both visual and text encoders. Since the proposed method can learn the distribution of beneficial noise, we can obtain more diverse embeddings of vision and language to better align these two modalities for specific downstream tasks within limited computational resources. We evaluate different noise incorporation approaches and network architectures of PiNI. The evaluation across 11 datasets demonstrates its effectiveness.

cs.CV↗

arXiv2024

Cross-Scan Mamba with Masked Training for Robust Spectral Imaging

Snapshot Compressive Imaging (SCI) enables fast spectral imaging but requires effective decoding algorithms for hyperspectral image (HSI) reconstruction from compressed measurements. Current CNN-based methods are limited in modeling long-range dependencies, while Transformer-based models face high computational complexity. Although recent Mamba models outperform CNNs and Transformers in RGB tasks concerning computational efficiency or accuracy, they are not specifically optimized to fully leverage the local spatial and spectral correlations inherent in HSIs. To address this, we propose the Cross-Scanning Mamba, named CS-Mamba, that employs a Spatial-Spectral SSM for global-local balanced context encoding and cross-channel interaction promotion. Besides, while current reconstruction algorithms perform increasingly well in simulation scenarios, they exhibit suboptimal performance on real data due to limited generalization capability. During the training process, the model may not capture the inherent features of the images but rather learn the parameters to mitigate specific noise and loss, which may lead to a decline in reconstruction quality when faced with real scenes. To overcome this challenge, we propose a masked training method to enhance the generalization ability of models. Experiment results show that our CS-Mamba achieves state-of-the-art performance and the masked training method can better reconstruct smooth features to improve the visual quality.

cs.CV↗