arXiv subjects

Lixiang Liu

Publications and source records attributed to Lixiang Liu.

8 recordsLinked to original sources

arXiv2026

Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference

The performance of large language model (LLM)-based multi-agent systems (MAS) largely depends on effective communication topologies. Existing topology generation methods, however, typically learn communication topologies through black-box optimization driven solely by task-level rewards. While effective, such optimization provides little insight into why particular communication edges are selected, making it difficult to identify the critical communication subgraphs responsible for successful collaboration. To address this limitation, we propose E2-Explainer, a model-agnostic framework for providing interpretable explanations of communication topologies produced by arbitrary topology generators. Specifically, we formulate topology explanation as a causal attribution problem that identifies compact communication subgraphs supported by edge-level evidence of task preservation. We obtain this evidence with a Granger-style objective that measures how masking each communication channel changes the task outcome and the stability of the final response. The resulting budgeted subgraphs are then distilled into an amortized explainer, enabling efficient post-hoc explanation without repeated edge-level evaluations at deployment. Extensive experiments on multiple reasoning and coding benchmarks demonstrate that E2-Explainer identifies critical communication subgraphs that preserve successful collaboration. These subgraphs can also be executed directly to prune redundant communication edges, substantially reducing communication costs while maintaining competitive task performance.

cs.MA↗

arXiv2026

Generalizing Graph Foundation Models via Hyperbolic Retrieval-Augmented Generation

Graph foundation models (GFMs) emerged as a dominant paradigm in graph representation learning by leveraging large-scale pre-training for cross-domain inference. However, the parameterized knowledge encoded within these models is insufficient to cope with distribution shifts, limiting their generalization ability. To mitigate this issue, retrieval-augmented generation (RAG) has been introduced to incorporate external knowledge at inference time. Nevertheless, existing RAG frameworks operating in Euclidean space suffer from a fundamental geometric limitation: the polynomial volume growth of Euclidean space is inherently mismatched with the tree-structured external knowledge bases. This mismatch leads to the loss of semantic granularity in retrieval and gives rise to the hubness phenomenon.To address this limitation, we propose a Hyperbolic Retrieval-Augmented Generation (HyRAG) framework designed to enhance the generalization capabilities of GFMs. Specifically, the introduced Hyperbolic Knowledge Indexing module retains the tree-like hierarchies of the external knowledge base by modeling them within hyperbolic space. The Multi-granularity Retrieval module then provides GFMs with the global semantic anchors and local semantic nuances through coarse-grained and fine-grained knowledge retrieval, respectively. Finally, the Dual-path Fusion module achieves effective knowledge integration for graph tasks at both the feature and structural levels. Experiments on multiple graph benchmarks demonstrate significant improvements in the zero-shot setting, highlighting the generalization of our method for robust GFMs inference.

cs.IR↗

arXiv2025

GRLoc: Geometric Representation Regression for Visual Localization

Absolute Pose Regression (APR) has emerged as a compelling paradigm for visual localization. However, APR models typically operate as black boxes, directly regressing a 6-DoF pose from a query image, which can lead to memorizing training views rather than understanding 3D scene geometry. In this work, we propose a geometrically-grounded alternative. Inspired by novel view synthesis, which renders images from intermediate geometric representations, we reformulate APR as its inverse that regresses the underlying 3D representations directly from the image, and we name this paradigm Geometric Representation Regression (GRR). Our model explicitly predicts two disentangled geometric representations in the world coordinate system: (1) a raymap's directions to estimate camera rotation, and (2) a corresponding pointmap to estimate camera translation. The final camera pose is then recovered from these geometric components using a differentiable deterministic solver. This disentangled approach, which separates the learned visual-to-geometry mapping from the final pose calculation, introduces a strong geometric prior into the network. We find that the explicit decoupling of rotation and translation predictions measurably boosts performance. We demonstrate state-of-the-art performance on 7-Scenes and Cambridge Landmarks datasets, validating that modeling the inverse rendering process is a more robust path toward generalizable absolute pose estimation.

cs.CV↗

arXiv2025

On the Design of Capacity-Achieving Distributions for Discrete-Time Poisson Channel with Low-Precision ADCs

This paper investigates the design of the capacity-achieving input distribution for the discrete-time Poisson channel (DTPC) under dark current effects with low-precision analog-to-digital converters (ADCs). This study introduces an efficient optimization algorithm that integrates the Newton-Raphson and Blahut-Arimoto (BA) methods to determine the capacity-achieving input distribution and the corresponding amplitudes of input mass points for the DTPC, subject to both peak and average power constraints. Additionally, the Karush-Kuhn-Tucker (KKT) conditions are established to provide necessary and sufficient conditions for the optimality of the obtained capacity-achieving distribution. Simulation results illustrate that the proposed algorithm attains $72\%$ and $83\%$ of the theoretical capacity at 5 dB for 1-bit and 2-bit quantized DTPC, respectively. Furthermore, for a finite-precision quantized DTPC (i.e., ${\log _2}K$ bits), the capacity can be achieved by a non-uniform discrete input distribution with support for $K$ mass points, under the given power constraints.

eess.SP↗

arXiv2024

Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspective

Foundational Vision-Language models such as CLIP have exhibited impressive generalization in downstream tasks. However, CLIP suffers from a two-level misalignment issue, i.e., task misalignment and data misalignment, when adapting to specific tasks. Soft prompt tuning has mitigated the task misalignment, yet the data misalignment remains a challenge. To analyze the impacts of the data misalignment, we revisit the pre-training and adaptation processes of CLIP and develop a structural causal model. We discover that while we expect to capture task-relevant information for downstream tasks accurately, the task-irrelevant knowledge impacts the prediction results and hampers the modeling of the true relationships between the images and the predicted classes. As task-irrelevant knowledge is unobservable, we leverage the front-door adjustment and propose Causality-Guided Semantic Decoupling and Classification (CDC) to mitigate the interference of task-irrelevant knowledge. Specifically, we decouple semantics contained in the data of downstream tasks and perform classification based on each semantic. Furthermore, we employ the Dempster-Shafer evidence theory to evaluate the uncertainty of each prediction generated by diverse semantics. Experiments conducted in multiple different settings have consistently demonstrated the effectiveness of CDC.

cs.CV↗

arXiv2023

Unsupervised Social Event Detection via Hybrid Graph Contrastive Learning and Reinforced Incremental Clustering

Detecting events from social media data streams is gradually attracting researchers. The innate challenge for detecting events is to extract discriminative information from social media data thereby assigning the data into different events. Due to the excessive diversity and high updating frequency of social data, using supervised approaches to detect events from social messages is hardly achieved. To this end, recent works explore learning discriminative information from social messages by leveraging graph contrastive learning (GCL) and embedding clustering in an unsupervised manner. However, two intrinsic issues exist in benchmark methods: conventional GCL can only roughly explore partial attributes, thereby insufficiently learning the discriminative information of social messages; for benchmark methods, the learned embeddings are clustered in the latent space by taking advantage of certain specific prior knowledge, which conflicts with the principle of unsupervised learning paradigm. In this paper, we propose a novel unsupervised social media event detection method via hybrid graph contrastive learning and reinforced incremental clustering (HCRC), which uses hybrid graph contrastive learning to comprehensively learn semantic and structural discriminative information from social messages and reinforced incremental clustering to perform efficient clustering in a solidly unsupervised manner. We conduct comprehensive experiments to evaluate HCRC on the Twitter and Maven datasets. The experimental results demonstrate that our approach yields consistent significant performance boosts. In traditional incremental setting, semi-supervised incremental setting and solidly unsupervised setting, the model performance has achieved maximum improvements of 53%, 45%, and 37%, respectively.

cs.SI↗

arXiv2022

Tailoring Terahertz Propagation by Phase and Amplitude Control in Metasurfaces

Using metasurfaces to control the wave propagation at will has been very successful over the broad electromagnetic spectrum in recent years. By encoding specially designed abrupt changes of electromagnetic parameters into metasurfaces, such as phase and amplitude, nearly arbitrary control over the output wavefronts could be realized. Constituted by a single- or fewlayer of planar structures, metasurfaces are straightforward in design and fabrication, thus promising many realistic applications. Moreover, such control concept can be further extended to the surface wave regime. In this review, we present our recent progress on metasurfaces capable of tailoring the propagation of both free-space and surface terahertz waves. Following an introduction of the basic concept and theory, a number of unique terahertz metasurfaces are presented, showing the ability in devising ultra-thin and compact functional terahertz components.

physics.optics↗

arXiv2017

Two-dimensional material based "field-effect CCD"

Charge-coupled device (CCD), along with the complementary metal-oxide-semiconductor (CMOS), is one of the major imaging technologies. Traditional CCDs rely on the charge transfer between potential wells, which gives them advantages of simple pixel structure, high sensitivity, and low noise. However, the serial transfer requires fabrication incompatible with CMOS, and leads to slower, more complex, and less flexible readout than random access. Here, we report a new-concept CCD called field-effect CCD (FE-CCD), which is based on the capacitive "coupling" between the semiconductor substrate and the 2D material. The strong field effect of the 2D material enables amplification, and non-destructive readout of the integrated charges in one pixel without transfer. We demonstrated the broadband response of our CCD (up to 1870 nm) and the successful integration of 2D hetero-structures for reducing the power consumption. The demonstrated FE-CCD provides a valuable strategy for versatile 2D materials to be monolithically integrated into the semiconductor imaging technology.

physics.app-ph↗