arXiv subjects

Feng Liu

Publications and source records attributed to Feng Liu.

At least 271 records · Page 15Linked to original sources

arXiv2025

Cavity-Quantum Electrodynamics with Moiré Flatband Photonic Crystals

Quantum emitters are a key component in photonic quantum technologies. Enhancing their single-photon emission by engineering the photonic environment using cavities can significantly improve the overall efficiency in quantum information processing. However, this enhancement is often constrained by the need for precise nanoscale control over the emitter's position within micro- or nano-cavities. Inspired by the fascinating physics of moiré patterns, we present an approach to strongly modify the spontaneous emission rate of a quantum emitter using a finely designed multilayer moiré photonic crystal with a robust isolated-flatband dispersion. Theoretical analysis reveals that, due to its nearly infinite photonic density of states, the moiré cavity can simultaneously achieve a high Purcell factor and exhibit large tolerance over the emitter's position. We experimentally demonstrate the coupling between this moiré cavity and a quantum dot through the cavity-determined polarization of the dot's emission. The radiative lifetime of the quantum dot can be tuned by a factor of 40, ranging from 42 ps to 1692 ps, which is attributed to strong Purcell enhancement and Purcell inhibition effects. Our findings pave the way for moiré flatband cavity-enhanced quantum light sources, quantum optical switches, and quantum nodes for quantum internet applications.

physics.optics↗

arXiv2025

GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs

Large language model (LLM) unlearning has demonstrated its essential role in removing privacy and copyright-related responses, crucial for their legal and safe applications. However, the pursuit of complete unlearning often comes with substantial costs due to its compromises in their general functionality, leading to a notorious trade-off between unlearning and retention. It motivates this paper to explore enhanced unlearning schemes that can mitigate this trade-off. Specifically, we propose Gradient Rectified Unlearning (GRU), an improved framework that regulates the directions of gradient updates during the unlearning procedure such that their side impacts on other, unrelated responses can be minimized. GRU is easy and general to implement, demonstrating practical effectiveness across a variety of well-established unlearning benchmarks.

cs.LG↗

arXiv2025

Understanding Model Reprogramming for CLIP via Decoupling Visual Prompts

Model reprogramming adapts pretrained models to downstream tasks by modifying only the input and output spaces. Visual reprogramming (VR) is one instance for vision tasks that adds a trainable noise pattern (i.e., a visual prompt) to input images to facilitate downstream classification. The existing VR approaches for CLIP train a single visual prompt using all descriptions of different downstream classes. However, the limited learning capacity may result in (1) a failure to capture diverse aspects of the descriptions (e.g., shape, color, and texture), and (2) a possible bias toward less informative attributes that do not help distinguish between classes. In this paper, we introduce a decoupling-and-reweighting framework. Our decoupled visual prompts (DVP) are optimized using descriptions grouped by explicit causes (DVP-cse) or unsupervised clusters (DVP-cls). Then, we integrate the outputs of these visual prompts with a probabilistic reweighting matrix (PRM) that measures their contributions to each downstream class. Theoretically, DVP lowers the empirical risk bound. Experimentally, DVP outperforms baselines on average across 11 downstream datasets. Notably, the DVP-PRM integration enables insights into how individual visual prompts influence classification decisions, providing a probabilistic framework for understanding reprogramming. Our code is available at https://github.com/tmlr-group/DecoupledVP.

cs.LG↗

arXiv2025

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse

Large language models (LLMs) are often used for infilling tasks, which involve predicting or generating missing information in a given text. These tasks typically require multiple interactions with similar context. To reduce the computation of repeated historical tokens, cross-request key-value (KV) cache reuse, a technique that stores and reuses intermediate computations, has become a crucial method in multi-round interactive services. However, in infilling tasks, the KV cache reuse is often hindered by the structure of the prompt format, which typically consists of a prefix and suffix relative to the insertion point. Specifically, the KV cache of the prefix or suffix part is frequently invalidated as the other part (suffix or prefix) is incrementally generated. To address the issue, we propose EFIM, a transformed prompt format of FIM to unleash the performance potential of KV cache reuse. Although the transformed prompt can solve the inefficiency, it exposes subtoken generation problems in current LLMs, where they have difficulty generating partial words accurately. Therefore, we introduce a fragment tokenization training method which splits text into multiple fragments before tokenization during data processing. Experiments on two representative LLMs show that LLM serving with EFIM can lower the latency by 52% and improve the throughput by 98% while maintaining the original infilling capability. EFIM's source code is publicly available at https://github.com/gty111/EFIM.

cs.CL↗

arXiv2025

Quantum-inspired Beamforming Optimization for Quantized Phase-only Massive MIMO Arrays

This paper introduces an innovative quantum-inspired method for beamforming (BF) optimization in multiple-input multiple-output (MIMO) arrays. The method leverages the simulated bifurcation (SB) algorithm to address the complex combinatorial optimization problem due to the quantized phase configuration. We propose novel encoding techniques for high-bit phase quantization, which are then mapped into Ising spins. This enables efficient construction of the Hamiltonians and subsequent optimization of BF patterns. The results clearly demonstrate that the SB optimizer surpasses traditional schemes such as digital BF, holographic algorithms and genetic algorithms, offering faster convergence and higher solution quality. The impressive capability of the SB optimizer to handle complex BF scenarios, including sidelobe suppression and multiple beams with nulls, is undoubtedly demonstrated through several application cases. These findings strongly suggest that quantum-inspired methods have great potential to advance MIMO techniques in next-generation wireless communication.

physics.app-ph↗

arXiv2025

Bridging the Gap: Self-Optimized Fine-Tuning for LLM-based Recommender Systems

Recent years have witnessed extensive exploration of Large Language Models (LLMs) on the field of Recommender Systems (RS). There are currently two commonly used strategies to enable LLMs to have recommendation capabilities: 1) The "Guidance-Only" strategy uses in-context learning to exploit and amplify the inherent semantic understanding and item recommendation capabilities of LLMs; 2) The "Tuning-Only" strategy uses supervised fine-tuning (SFT) to fine-tune LLMs with the aim of fitting them to real recommendation data. However, neither of these strategies can effectively bridge the gap between the knowledge space of LLMs and recommendation, and their performance do not meet our expectations. To better enable LLMs to learn recommendation knowledge, we combine the advantages of the above two strategies and proposed a novel "Guidance+Tuning" method called Self-Optimized Fine-Tuning (SOFT), which adopts the idea of curriculum learning. It first employs self-distillation to construct an auxiliary easy-to-learn but meaningful dataset from a fine-tuned LLM. Then it further utilizes a self-adaptive curriculum scheduler to enable LLMs to gradually learn from simpler data (self-distilled data) to more challenging data (real RS data). Extensive experiments demonstrate that SOFT significantly enhances the recommendation accuracy (37.59\% on average) of LLM-based methods. The code is available via https://anonymous.4open.science/r/Self-Optimized-Fine-Tuning-264E

cs.IR↗

arXiv2025

NeuroTree: Hierarchical Functional Brain Pathway Decoding for Mental Health Disorders

Mental disorders are among the most widespread diseases globally. Analyzing functional brain networks through functional magnetic resonance imaging (fMRI) is crucial for understanding mental disorder behaviors. Although existing fMRI-based graph neural networks (GNNs) have demonstrated significant potential in brain network feature extraction, they often fail to characterize complex relationships between brain regions and demographic information in mental disorders. To overcome these limitations, we propose a learnable NeuroTree framework that integrates a k-hop AGE-GCN with neural ordinary differential equations (ODEs) and contrastive masked functional connectivity (CMFC) to enhance similarities and dissimilarities of brain region distance. Furthermore, NeuroTree effectively decodes fMRI network features into tree structures, which improves the capture of high-order brain regional pathway features and enables the identification of hierarchical neural behavioral patterns essential for understanding disease-related brain subnetworks. Our empirical evaluations demonstrate that NeuroTree achieves state-of-the-art performance across two distinct mental disorder datasets. It provides valuable insights into age-related deterioration patterns, elucidating their underlying neural mechanisms.

cs.NE↗

arXiv2025

Flow Matching based Sequential Recommender Model

Generative models, particularly diffusion model, have emerged as powerful tools for sequential recommendation. However, accurately modeling user preferences remains challenging due to the noise perturbations inherent in the forward and reverse processes of diffusion-based methods. Towards this end, this study introduces FMRec, a Flow Matching based model that employs a straight flow trajectory and a modified loss tailored for the recommendation task. Additionally, from the diffusion-model perspective, we integrate a reconstruction loss to improve robustness against noise perturbations, thereby retaining user preferences during the forward process. In the reverse process, we employ a deterministic reverse sampler, specifically an ODE-based updating function, to eliminate unnecessary randomness, thereby ensuring that the generated recommendations closely align with user needs. Extensive evaluations on four benchmark datasets reveal that FMRec achieves an average improvement of 6.53% over state-of-the-art methods. The replication code is available at https://github.com/FengLiu-1/FMRec.

cs.IR↗

arXiv2025

Temporal and Spatial Feature Fusion Framework for Dynamic Micro Expression Recognition

When emotions are repressed, an individual's true feelings may be revealed through micro-expressions. Consequently, micro-expressions are regarded as a genuine source of insight into an individual's authentic emotions. However, the transient and highly localised nature of micro-expressions poses a significant challenge to their accurate recognition, with the accuracy rate of micro-expression recognition being as low as 50%, even for professionals. In order to address these challenges, it is necessary to explore the field of dynamic micro expression recognition (DMER) using multimodal fusion techniques, with special attention to the diverse fusion of temporal and spatial modal features. In this paper, we propose a novel Temporal and Spatial feature Fusion framework for DMER (TSFmicro). This framework integrates a Retention Network (RetNet) and a transformer-based DMER network, with the objective of efficient micro-expression recognition through the capture and fusion of temporal and spatial relations. Meanwhile, we propose a novel parallel time-space fusion method from the perspective of modal fusion, which fuses spatio-temporal information in high-dimensional feature space, resulting in complementary "where-how" relationships at the semantic level and providing richer semantic information for the model. The experimental results demonstrate the superior performance of the TSFmicro method in comparison to other contemporary state-of-the-art methods. This is evidenced by its effectiveness on three well-recognised micro-expression datasets.

cs.CV↗

arXiv2025

DUAL: Dynamic Uncertainty-Aware Learning

Deep learning models frequently encounter feature uncertainty in diverse learning scenarios, significantly impacting their performance and reliability. This challenge is particularly complex in multi-modal scenarios, where models must integrate information from different sources with inherent uncertainties. We propose Dynamic Uncertainty-Aware Learning (DUAL), a unified framework that effectively handles feature uncertainty in both single-modal and multi-modal scenarios. DUAL introduces three key innovations: Dynamic Feature Uncertainty Modeling, which continuously refines uncertainty estimates through joint consideration of feature characteristics and learning dynamics; Adaptive Distribution-Aware Modulation, which maintains balanced feature distributions through dynamic sample influence adjustment; and Uncertainty-aware Cross-Modal Relationship Learning, which explicitly models uncertainties in cross-modal interactions. Through extensive experiments, we demonstrate DUAL's effectiveness across multiple domains: in computer vision tasks, it achieves substantial improvements of 7.1% accuracy on CIFAR-10, 6.5% accuracy on CIFAR-100, and 2.3% accuracy on Tiny-ImageNet; in multi-modal learning, it demonstrates consistent gains of 4.1% accuracy on CMU-MOSEI and 2.8% accuracy on CMU-MOSI for sentiment analysis, while achieving 1.4% accuracy improvements on MISR. The code will be available on GitHub soon.

cs.LG↗

arXiv2025

Structure-Aware Corpus Construction and User-Perception-Aligned Metrics for Large-Language-Model Code Completion

Code completion technology based on large language model has significantly improved the development efficiency of programmers. However, in practical applications, there remains a gap between current commonly used code completion evaluation metrics and users' actual perception. To address this issue, we propose two evaluation metrics for code completion tasks--LCP and ROUGE-LCP, from the perspective of probabilistic modeling. Furthermore, to tackle the lack of effective structural semantic modeling and cross-module dependency information in LLMs for repository-level code completion scenarios, we propose a data processing method based on a Structure-Preserving and Semantically-Reordered Code Graph (SPSR-Graph). Through theoretical analysis and experimental validation, we demonstrate the superiority of the proposed evaluation metrics in terms of user perception consistency, as well as the effectiveness of the data processing method in enhancing model performance.

cs.SE↗

arXiv2025

Progressive Autoregressive Video Diffusion Models

Current frontier video diffusion models have demonstrated remarkable results at generating high-quality videos. However, they can only generate short video clips, normally around 10 seconds or 240 frames, due to computation limitations during training. Existing methods naively achieve autoregressive long video generation by directly placing the ending of the previous clip at the front of the attention window as conditioning, which leads to abrupt scene changes, unnatural motion, and error accumulation. In this work, we introduce a more natural formulation of autoregressive long video generation by revisiting the noise level assumption in video diffusion models. Our key idea is to 1. assign the frames with per-frame, progressively increasing noise levels rather than a single noise level and 2. denoise and shift the frames in small intervals rather than all at once. This allows for smoother attention correspondence among frames with adjacent noise levels, larger overlaps between the attention windows, and better propagation of information from the earlier to the later frames. Video diffusion models equipped with our progressive noise schedule can autoregressively generate long videos with much improved fidelity compared to the baselines and minimal quality degradation over time. We present the first results on text-conditioned 60-second (1440 frames) long video generation at a quality close to frontier models. Code and video results are available at https://desaixie.github.io/pa-vdm/.

cs.CV↗

arXiv2025

Evidence of competing ground states between fractional Chern insulator and antiferromagnetism in moiré MoTe2

Two-dimensional moire materials present unprecedented opportunities to explore quantum phases of matter arising from the interplay of band topology and strong correlations.One of the most striking examples is the recent observation of fractional quantum anomalous Hall (FQAH) effect in twisted bilayer MoTe$_2$ (tMoTe2) with relatively large twist angles(~3.7deg-3.9deg). The electronic ground states are usually expected to be sensitive to the twist angle, as the twist angle determines the electron bandwidth and correlation strength in the moire system. Here, we report the observation of unexpected competing magnetic ground states in tMoTe2 moire superlattice, on which balance can be tipped by both twist angle and electric field (E). Specifically, we observed anomalous antiferromagnetic (AFM) ground states with zero Hall resistance at both v_h=1 and 2/3, at intermediate twist angles ~3deg. The AFM orders are suppressed by applying vertical E, and emergent ferromagnetism accompanied by integer Chern insulator (ICI) or fractional Chern insulator (FCI) states are observed near the critical E (E_c) of moire superlattice symmetry transition. Our results demonstrate tMoTe2 as a fascinating platform for exploring unexpected correlated phases with nontrivial topology and fractional excitations and point to electric-field-controlled ultralow-power spin-valleytronic devices.

cond-mat.mes-hall↗

arXiv2025

ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models

Current diffusion-based text-to-video methods are limited to producing short video clips of a single shot and lack the capability to generate multi-shot videos with discrete transitions where the same character performs distinct activities across the same or different backgrounds. To address this limitation we propose a framework that includes a dataset collection pipeline and architectural extensions to video diffusion models to enable text-to-multi-shot video generation. Our approach enables generation of multi-shot videos as a single video with full attention across all frames of all shots, ensuring character and background consistency, and allows users to control the number, duration, and content of shots through shot-specific conditioning. This is achieved by incorporating a transition token into the text-to-video model to control at which frames a new shot begins and a local attention masking strategy which controls the transition token's effect and allows shot-specific prompting. To obtain training data we propose a novel data collection pipeline to construct a multi-shot video dataset from existing single-shot video datasets. Extensive experiments demonstrate that fine-tuning a pre-trained text-to-video model for a few thousand iterations is enough for the model to subsequently be able to generate multi-shot videos with shot-specific control, outperforming the baselines. You can find more details in https://shotadapter.github.io/

cs.CV↗

arXiv2025

TACFN: Transformer-based Adaptive Cross-modal Fusion Network for Multimodal Emotion Recognition

The fusion technique is the key to the multimodal emotion recognition task. Recently, cross-modal attention-based fusion methods have demonstrated high performance and strong robustness. However, cross-modal attention suffers from redundant features and does not capture complementary features well. We find that it is not necessary to use the entire information of one modality to reinforce the other during cross-modal interaction, and the features that can reinforce a modality may contain only a part of it. To this end, we design an innovative Transformer-based Adaptive Cross-modal Fusion Network (TACFN). Specifically, for the redundant features, we make one modality perform intra-modal feature selection through a self-attention mechanism, so that the selected features can adaptively and efficiently interact with another modality. To better capture the complementary information between the modalities, we obtain the fused weight vector by splicing and use the weight vector to achieve feature reinforcement of the modalities. We apply TCAFN to the RAVDESS and IEMOCAP datasets. For fair comparison, we use the same unimodal representations to validate the effectiveness of the proposed fusion method. The experimental results show that TACFN brings a significant performance improvement compared to other methods and reaches the state-of-the-art. All code and models could be accessed from https://github.com/shuzihuaiyu/TACFN.

cs.CV↗

arXiv2025

A Unified Data Representation Learning for Non-parametric Two-sample Testing

Learning effective data representations has been crucial in non-parametric two-sample testing. Common approaches will first split data into training and test sets and then learn data representations purely on the training set. However, recent theoretical studies have shown that, as long as the sample indexes are not used during the learning process, the whole data can be used to learn data representations, meanwhile ensuring control of Type-I errors. The above fact motivates us to use the test set (but without sample indexes) to facilitate the data representation learning in the testing. To this end, we propose a representation-learning two-sample testing (RL-TST) framework. RL-TST first performs purely self-supervised representation learning on the entire dataset to capture inherent representations (IRs) that reflect the underlying data manifold. A discriminative model is then trained on these IRs to learn discriminative representations (DRs), enabling the framework to leverage both the rich structural information from IRs and the discriminative power of DRs. Extensive experiments demonstrate that RL-TST outperforms representative approaches by simultaneously using data manifold information in the test set and enhancing test power via finding the DRs with the training set.

cs.LG↗

arXiv2025

Person Recognition at Altitude and Range: Fusion of Face, Body Shape and Gait

We address the problem of whole-body person recognition in unconstrained environments. This problem arises in surveillance scenarios such as those in the IARPA Biometric Recognition and Identification at Altitude and Range (BRIAR) program, where biometric data is captured at long standoff distances, elevated viewing angles, and under adverse atmospheric conditions (e.g., turbulence and high wind velocity). To this end, we propose FarSight, a unified end-to-end system for person recognition that integrates complementary biometric cues across face, gait, and body shape modalities. FarSight incorporates novel algorithms across four core modules: multi-subject detection and tracking, recognition-aware video restoration, modality-specific biometric feature encoding, and quality-guided multi-modal fusion. These components are designed to work cohesively under degraded image conditions, large pose and scale variations, and cross-domain gaps. Extensive experiments on the BRIAR dataset, one of the most comprehensive benchmarks for long-range, multi-modal biometric recognition, demonstrate the effectiveness of FarSight. Compared to our preliminary system, this system achieves a 34.1% absolute gain in 1:1 verification accuracy (TAR@0.1% FAR), a 17.8% increase in closed-set identification (Rank-20), and a 34.3% reduction in open-set identification errors (FNIR@1% FPIR). Furthermore, FarSight was evaluated in the 2025 NIST RTE Face in Video Evaluation (FIVE), which conducts standardized face recognition testing on the BRIAR dataset. These results establish FarSight as a state-of-the-art solution for operational biometric recognition in challenging real-world conditions.

cs.CV↗

arXiv2025

Interplay of quantum and real-space geometry in the anomalous Landau levels of singular flat bands

Quantum geometry of electronic state in momentum space, distinct from real-space structural geometry, has attracted increasing interest to shed light on understanding quantum phenomena. An interesting recent study [Nature 584, 59-63 (2020)] has numerically solved a 2-band effective Hamiltonian to show the anomalous Landau level (ALL) spreading $\mathitΔ$ of a singular flat band (SFB), such as hosted in a kagome lattice, in relation to the maximal quantum distance $d$ of the SFB, $\mathitΔ(d)$, which enables a direct measure of quantum geometry. Here, we investigate the ALLs of SFB by studying both the 2-band Hamiltonian and a diatomic kagome lattice hosting two SFBs mirrored by particle-hole symmetry. We derive an exact analytical solution of the 2-band Hamiltonian to show there are two branches of $\mathitΔ(d)$. Strikingly, for the diatomic kagome lattice, $\mathitΔ$ depends on not only $d$ but also $r$, the real-space diatomic distance. As $r$ increases, $\mathitΔ$ shrinks toward zero while $d$ remains intact, which can be intuitively understood from the magnetic-field-induced disruption of destructive interference of the SFB compact localized states. Based on semiclassical theory, we derive rigorously the dependence of $\mathitΔ$ on $r$ that originates from the tuning of the non-Abelian orbital moment of the two SFBs by real-space geometry.

cond-mat.mes-hall↗