Searcharxiv⌕ Search

arXiv subjects

Yunhao Liu

Publications and source records attributed to Yunhao Liu.

At least 19 recordsLinked to original sources

DecompJSCC: Joint Source-Channel Coding With Decoupled SNR and Rate Adaptation

Deep joint source-channel coding (DeepJSCC) for image transmission must adapt to changes in the signal-to-noise ratio (SNR) and available transmission resources. However, some existing joint-adaptive methods condition the encoder on the requested rate, while others apply static masks after encoding. The former couples latent formation to the rate request, whereas the latter cannot adapt channel selection to image content. To address these limitations, we propose DecompJSCC, which decomposes joint adaptation into SNR-conditioned latent formation and post-encoding rate control within a single model. The encoder applies SNR-conditioned block attention residuals across all stages, aggregating intra-stage and cross-stage semantic representations. At the receiver, an adapter performs SNR-conditioned affine correction. We introduce a post-encoding rate-adaptive channel semantic budgeting (RCSB) module whose shared gate selects channels of the formed latent by image content, adjusts their gains, and keeps exactly the requested count. This keeps the encoder output independent of the rate request for a fixed image and SNR. Experimental results show that DecompJSCC outperforms SwinJSCC and SA-RA-JSCC in peak signal-to-noise ratio (PSNR) across a range of SNR and rate settings, by 0.64 dB and 1.00 dB over SwinJSCC and by 0.97 dB and 0.96 dB over SA-RA-JSCC on Kodak and CLIC2021, while using only 7.5% of SwinJSCC's Adaptive ModNet parameters.

eess.IV↗

Taming Neural Fields with a Frequency-Lipschitz Curriculum for Sparse-View CT Reconstruction

Sparse-view computed tomography (SVCT) reduces radiation dose by acquiring fewer projection views, but the resulting under-determined inverse problem requires careful regularization to prevent reconstruction algorithms from fitting streak artifacts and hallucinated structures. Existing implicit neural representation (INR) methods rely on implicit spectral bias or iterative external denoising, yet they provide limited control over when high-frequency capacity is exposed during optimization. To address this limitation, we propose FLIC (Frequency-Lipschitz INR Curriculum), a capacity-controlled self-prior INR framework that makes the network's representational capacity explicit and schedulable. The core of our method is a joint frequency-Lipschitz curriculum that couples random Fourier feature encoding with spectrally normalized MLP decoding under non-uniform Lipschitz budgets, guiding reconstruction along a coarse-to-fine trajectory from stable global anatomy to fine details. The terminal capacity is automatically calibrated from FBP gradient statistics, enabling scan-adaptive regularization without per-scan manual tuning of the terminal Lipschitz budget. We further introduce a prior-guided adaptive ray sampling strategy that concentrates integration samples near high-gradient anatomical boundaries, improving forward-model fidelity. The entire framework operates in a single training stage without iterative denoising, enabling efficient per-image reconstruction. Extensive experiments on four public CT datasets under noise-free and low-dose settings show that our method achieves state-of-the-art unsupervised reconstruction quality with consistent performance across diverse anatomical structures.

cs.CV↗

Reaching Is Not Finding: Map-Anchored Visual Prompting for the Last Mile of Aerial Vision-Language Navigation

Aerial vision-language navigation (VLN) asks a drone to find an object described in natural language. The description usually locates the object relative to named landmarks, such as streets and buildings. We observe that current navigators often bring the drone close to the target and then stop at the wrong place: they reach the target without finding it. This gap is shared by navigators of very different designs, from imitation learners to a fine-tuned 7B vision-language model. A simple test reveals the cause. When we replace the target object in the instruction with another one next to the same landmarks, no navigator goes to it, and most stop where they did before. Navigators learn to reach the landmarks, not to identify the described object. We therefore propose MAP-VP, a plug-and-play module for the last step. After any navigator stops, MAP-VP draws the landmarks named in the instruction onto the drone's current view, using the landmark outlines that the benchmark provides on a map. A fine-tuned 4B vision-language model then locates the target relative to these landmarks. The training data are generated automatically from the benchmark annotations. Neither drawing the landmarks nor fine-tuning helps much alone, but together they are highly effective. Without retraining any navigator, MAP-VP significantly improves all six navigators we test on CityNav. It roughly doubles the success rate of the two strongest trained navigators, raising HETT from 25.9% to 54.6% and FlightGPT from 24.2% to 48.9%, whereas CityNav's official detector-based last step adds less than two points to HETT.

cs.CV↗

EgoKit: Towards Unified Low-Cost Egocentric Data Collection with Heterogeneous Devices

Egocentric video is increasingly used as a data source for robot learning, activity understanding, and embodied AI research, but collecting it at scale remains fragmented in practice: each candidate host device, such as an Android phone, iPhone, iPad, smart glasses, or extended reality (XR) headset, exposes a different SDK, a different policy on raw camera access, and different limitations on external USB cameras and on-device tracking. Synchronized ego-view and wrist-view capture is therefore typically obtained by either committing to a single proprietary platform or building one-off rigs that do not transfer across devices. To address this gap, we present EgoKit, a toolkit that exposes the same egocentric recording workflow across six heterogeneous host devices. Across all supported devices, EgoKit presents the same recording interaction and produces locally stored video with a uniform log format; on XR headsets, it additionally logs head pose and OpenXR-standard 26-joint hand tracking aligned to the video streams. The companion accessories, including two wrist cameras with mounts, a head strap, and a USB-C hub, add wrist-view capture to any supported host without custom hardware fabrication. To validate that EgoKit data can train robot policies, we replicated HumanEgo with 41 demonstrations recorded by EgoKit-PICO: in simulation, policies trained on 20 or 40 of them placed a cube on a tray in 60-74% of 100 unseen layouts, about as often as policies trained on Project Aria recordings of the same layouts. EgoKit is available at https://egokit.chuange.org/.

cs.CV↗

Topological Superradiant Universality Classes in Cavity-Mediated Spin Chains

Superradiant phase transitions are fundamental phenomena in light-matter coupled systems. Here, we uncover a novel class of superradiant criticality that is topologically distinct from previously known superradiant transitions. Using cavity-mediated cluster-Ising chains as an illustrative example, we numerically demonstrate that the critical line separating the superradiant phase from the cavity topological phase hosts robust symmetry-protected edge degeneracies, a feature absent in conventional superradiant transitions. Remarkably, although its local bulk critical properties are indistinguishable from those of the previously identified topologically trivial superradiant transition, the two criticalities cannot be smoothly connected without breaking the protecting symmetries or passing through a multicritical point. We further show that such topological superradiant criticality is generic, also occurring in cavity-mediated $\mathbb{Z}_{n}^{}$ cluster-qudit chains, as supported by complementary lattice simulations.

quant-ph↗

AdaptInfer: Adaptive Token Pruning for Vision-Language Model Inference via Dynamical Text Guidance

Vision-language models (VLMs) have achieved impressive performance on multimodal inference tasks, but the cost remains a significant challenge due to the large number of vision tokens processed during the prefill stage. Existing token pruning methods often rely on utilizing the static attention patterns directly, failing to exploit the dynamic internal signals within VLMs. To address the issue, we propose AdaptInfer, a novel plug-and-play framework for vision token pruning. First, we introduce a dynamic text-guided pruning mechanism that construct soft priors over text-token importance on each pruning layer, allowing more informed scoring of vision tokens at each stage. Second, we observe a highly consistent distribution of cross-modal attention shifts by architecture, which inspires us to introduce a efficient data-driven schedule which determines the pruning locations automatically. Experimental results have verified the effectiveness and generalization of the proposed method. Under the same token budget, AdaptInfer surpasses existing approaches in accuracy. For instance, AdaptInfer maintains averagely 99.4% accuracy on Qwen2-VL while 70% of the prefilling vision token overhead is reduced. The source code is available on: https://github.com/weiczh02/AdaptInfer-base.

cs.CV↗

PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation

Faithfully translating research papers into repository-level implementations remains challenging because papers often describe methods at a high level, leave implementation assumptions implicit, and require generated repositories to preserve method logic, evaluation protocols, and cross-file consistency. Despite recent advances in paper-to-code agents, their intermediate outputs are often presented as free-form plans or summaries that downstream coding agents may ignore, reinterpret, or compress, leading to algorithmic simplification and inconsistent repository structure. To address these challenges, we introduce PaperCompiler, a paper-to-code generation framework that compiles paper-grounded evidence into explicit repository-level implementation specifications. PaperCompiler grounds implementation-relevant evidence while preserving source provenance and distinguishing paper-supported, inferred, externally delegated, and unresolved information. The resulting specifications encode non-degradation requirements, ownership assignments, cross-file dependencies, and file-level constraints. Repository generation proceeds under these compiled specifications while retaining flexibility over local engineering choices not fixed by the paper. PaperCompiler outperforms strong baselines on Paper2CodeBench, achieving a 13.8% relative improvement in reference-based fidelity (from 3.64 to 4.15) and reducing high-severity evaluator critiques (from 13.2% to 6.1%).

cs.CL↗

Motion-as-Prompt: Enhancing Motion Reasoning in Multimodal Large Language Models via Motion-Guided Cross-Frame Visual Prompting

Motion-centric video reasoning is fundamental to interactive applications such as robotic manipulation and autonomous navigation. However, multimodal large language models (MLLMs) typically process videos through sparse uniform sampling to control visual-token and attention costs. This strategy may discard critical transitions between sampled frames, limiting reasoning about object movement, collisions, and causal interactions. To mitigate this issue, we propose Motion-as-Prompt (MaP), a track-guided cross-frame visual prompting framework. MaP recovers dense point trajectories, selects motion-informative frames, and marks the trajectories accumulated between consecutive sampled frames directly onto the visual inputs, making otherwise hidden displacement, direction changes, and interactions observable to frozen MLLMs. Experiments on CLEVRER and Something-Something-v2 show that MaP consistently improves average motion-reasoning accuracy, yielding gains of 4.2% and 8.9% for GPT-5.5, respectively. Notably, these improvements are obtained without degrading non-motion understanding, highlighting the robustness of MaP. These results demonstrate that MaP provides a simple and effective solution for enhancing motion-centric video reasoning without model training or architectural modification. Project page:https://github.com/SunVictor23/MaP.

cs.CV↗

HUGIN: Enhancing Vision-Language Planning for Autonomous Logistics Sorting

Autonomous logistics sorting systems (ALSS) are an important industrial application of embodied AI, which requires joint planning over spatially disjoint camera views. We formulate this setting as Joint Multi-Scene Understanding (JMSU). With open-world visual understanding and task-planning capabilities, vision-language models (VLMs) are promising candidates for JMSU. However, directly applying existing VLMs to JMSU is non-trivial due to scarce cross-scene supervision and attention dispersion caused by long visual context in JMSU. To address these challenges, we propose HUGIN, a training framework with two complementary components. Endogenous Data Augmentation recombines verified atomic facts under operating constraints, while Global Context Ranking aligns the instruction representation more strongly with the complete visual context than with a partial visual context. To support ongoing research, we construct a high-quality industrial sorting dataset and benchmark named SortingBench from four layouts of autonomous logistics sorting systems. Across five open VLMs, HUGIN consistently outperforms matched baselines; for example, the accuracy on SortingBench of Qwen3-VL-8B increases from 63.6% to 78.8%. Additional experiments verify the effectiveness of each component and JMSU's spillover benefits in embodied tasks. Deployment tests involving more than 15,000 packages support the practical viability of VLM-based planning for autonomous logistics sorting.

cs.AI↗

MCPGuard: Finding Conformance Gaps in MCP SDKs via Dual-Track Analysis and Dynamic Adjudication

The Model Context Protocol (MCP) connects large language model agents to external tools and services through official SDKs that implement message validation and session logic. Specification constraints omitted by these SDKs may propagate to downstream applications, highlighting the importance of SDK-level conformance testing. Yet existing MCP conformance tools mainly exercise running endpoints and reveal little about whether SDK models enforce specification requirements. We present MCPGuard, an automated LLM-based framework for detecting specification-to-SDK conformance gaps. Its structural track aligns JSON Schema constraints with normalized SDK models and produces constraint-specific evidence. Its behavioral track extracts normative prose rules, retrieves bounded function-level slices, and audits them with LLMs for candidate omissions. An evidence-aware dynamic adjudicator then inspects complete source context and builds PoCs to validate candidates. A shared kernel with language-specific adapters enables analysis across SDKs. On the official Python 1.26.0 and TypeScript 1.29.0 SDKs, MCPGuard confirms 13 and 19 findings, respectively, none of which are exposed by two black-box baselines. Tests on open MCP servers further show that these gaps can systematically propagate downstream. By making SDK conformance of specification constraints directly testable, MCPGuard complements conventional endpoint-oriented conformance suites.

cs.AI↗

Multi-Robot Open Adaptive Teaming Across Unseen Environments, Partners, and Scales

Deploying robot teams in the real world requires simultaneous adaptation to unseen environments, unknown partners, and varying team sizes, yet existing approaches often address these challenges in isolation under the closed-world assumption of fixed teammates. We formalize this as open adaptive multi-robot teaming and propose a hypergraphic-form game formulation that captures team-level cooperative relationships beyond pairwise interactions, providing a principled foundation for coordination structure inference when team composition changes dynamically within episodes. Unlike graph neural network architectures, this is a game-theoretic construct for modeling strategic interactions and payoff structures among agents. Building on this formulation, we develop the Hypergraphic Open-ended Learning Algorithm (HOLA), which progressively expands partner and environment diversity during training rather than optimizing for fixed configurations. Evaluated on cooperative pursuit with multi-drone and multi-quadruped platforms, HOLA outperforms all baselines across all three adaptability dimensions. Learned policies transfer directly to physical hardware without fine-tuning, with successful deployments on Crazyflie and Zsibot L1 platforms confirming robust real-world coordination in novel environments with unseen teammates.

cs.RO↗

SynSeg: Feature Synergy for Multi-Category Contrastive Learning in End-to-End Open-Vocabulary Semantic Segmentation

Semantic segmentation in open-vocabulary scenarios presents significant challenges due to the wide range and granularity of semantic categories. Existing weakly-supervised methods often rely on category-specific supervision and ill-suited feature construction methods for contrastive learning, leading to semantic misalignment and poor performance. In this work, we introduce a novel weakly-supervised approach, SynSeg, to address the challenges. SynSeg performs Multi-Category Contrastive Learning (MCCL) as a stronger training signal which robustly injecting intra- and inter-category knowledge during training. We also propose a new feature reconstruction framework named Feature Synergy Structure (FSS). FSS reconstructs discriminative features for contrastive learning through prior fusion and semantic-activation-map enhancement, effectively avoiding the foreground bias introduced by the visual encoder. Furthermore, SynSeg is a lightweight end-to-end solution capable for real-time inference. In general, SynSeg effectively improves the abilities in semantic localization and discrimination under weak supervision in an efficient manner. Extensive experiments on benchmarks demonstrate that our method outperforms state-of-the-art (SOTA) performance, with mIoU score gains ranging from 0.6% up to 8.9% across all reported benchmarks.

cs.CV↗

EventRadar: Long-Range Visual UAV Discovery through Spatiotemporal Event Sensing

Unauthorized unmanned aerial vehicle (UAV) activity around airports, public venues, and other sensitive sites has made protected-airspace monitoring increasingly important. A practical sensing system must search a wide angular region, find small long-range targets, and return both bearing support and UAV-specific evidence before a restricted perimeter is breached. Existing UAV detection paths often rely on spatially organized evidence, such as body extent, silhouette, or track continuity. At long range, however, these cues become difficult to preserve and verify as the target footprint weakens and its image-plane support shrinks. EventRadar follows a complementary cue: propeller-induced temporal periodicity, which recent event-camera sensing studies have shown can reveal UAV-specific motion after appearance becomes weak. We extend this cue to kilometer-scale active sensing with an event-camera prototype. Scene-Anchored Geometry Evidence (SAGE) fuses scanning events with IMU pose to maintain a bearing-indexed scene memory, separating transient candidate support from persistent background clutter. Comb-guided Harmonic-Group Learned Iterative Shrinkage and Thresholding Algorithm (CHG) then treats each candidate as a weak high-rate timing signal and recovers phase-insensitive harmonic evidence with fixed compute. Compared with related event-camera baselines on 700-1500 m UAV event recordings, EventRadar achieves 0.990 mAP$_{.3}$ and 0.949 F1$_{.3}$, reduces FN$_{.3}$ to 0.009, and shows real-time feasibility in prototype profiling.

cs.CV↗

A DMFT approach to evaluate electronic frictional effects near solid surfaces of strongly correlated systems

Electronic friction-Langevin dynamics (EF-LD) provides an efficient framework for capturing nonadiabatic effects at solid surfaces, with particular relevance to electrochemistry and molecular electronics. In this work, we investigate electronic friction in the two-dimensional Hubbard-Holstein model employing dynamical mean-field theory (DMFT), where the full density-matrix numerical renormalization group (FDM-NRG) serves as the impurity solver. Our results are benchmarked against mean-field theory (MFT). DMFT yields two distinct peaks in the electronic friction, arising from electron attachment/detachment resonances with the solid Fermi level, whereas MFT is unable to capture this Fermi resonance. We further examine the dynamics of electronic friction via EF-LD simulations. Our simulations uncover significant discrepancies mainly in the electronic population evolution predicted by MFT versus DMFT, indicating that MFT is inadequate for describing nonadiabatic dynamics in strongly correlated systems. Thanks to its flexibility and computational efficiency, the proposed DMFT-based approach can be readily extended to a broad range of applications.

physics.chem-ph↗

Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding

Proactive streaming video understanding requires Video-LLMs to decide when to respond as a video unfolds, a task where existing methods often fall short due to their implicit, query-agnostic modeling of visual evidence. We introduce Response-G1, a novel framework that establishes explicit, structured alignment between the accumulated video evidence and the query's expected response conditions via scene graphs. The framework operates in three fine-tuning-free stages: (1) online query-guided scene graph generation from streaming clips; (2) memory-based retrieval of the most semantically relevant historical scene graphs; and (3) retrieval-augmented trigger prompting for per-frame "silence/response" decisions. By grounding both evidence and conditions in a shared graph representation, Response-G1 achieves more interpretable and accurate response timing decisions. Experimental results on established benchmarks demonstrate the superiority of our method in both proactive and reactive tasks, validating the advantage of explicit scene graph modeling and retrieval in streaming video understanding.

cs.CV↗

HCInfer: An Efficient Inference System via Error Compensation for Resource-Constrained Devices

LLMs often struggle with memory-constrained deployment on consumer-grade hardware due to their massive parameter sizes. While existing solutions such as model compression and offloading improve deployment feasibility, they often suffer from substantial accuracy degradation or severe throughput bottlenecks. Recent error compensation methods recover accuracy through auxiliary LoRA-style branches, and we observe that these branches are inherently amenable to offloading: they require substantial parameter storage but access only a small subset of compensation parameters during each inference step. Motivated by this opportunity, we propose HCInfer, a heterogeneous inference system that offloads residual compensation to the CPU while executing the compressed backbone on the GPU, and further introduces an asynchronous compensation pipeline and sensitivity-aware dynamic rank allocation to hide compensation overhead and maximize accuracy recovery. Experimental results show that HCInfer achieves a maximum accuracy improvement of 5.2% on downstream tasks compared to compression model and sustaining a maximum speedup of 10.4x compared to full-precision model.

cs.LG↗

Copula-enhanced Vision Transformer for high myopia diagnosis through OU UWF fundus images

The advancement of AI-assisted myopia screening necessitates the joint diagnosis of both-eye (OU) high myopia (HM) status and the prediction of axial length (AL). This clinical requirement introduces a complex mixed-type (binary-continuous) multitask learning task with bi-domain (OU) image covariates, giving rise to two key challenges: i) capture the inter-ocular asymmetry of OU images within a cutting-edge foundation model; ii) model and estimate the conditional dependence structure among mixed-type multivariate responses given image covariates. We address the challenges by: i) imposing residual adapters on the Vision Transformer foundation model to capture the OU similarity and heterogeneity simultaneously; ii) developing a four-dimensional copula loss that is implementable in PyTorch based on a latent variable expression for the Gaussian copula likelihood, and proposing a computationally efficient fast Monte Carlo Expectation Maximization (fMCEM) algorithm to estimate copula parameters. We further formulate a specific overfitting problem called stronger covariance phenomenon in multitask learning. We reveal the disturbance of the phenomenon to estimation of copula parameters and theoretically demonstrate the numerical stability of the proposed fMCEM algorithm against the disturbance. The application to our annotated OU ultra-widefield fundus image dataset and simulation on synthetic data demonstrate that our method stably enhances the predictive capabilities on both classification and regression tasks.

cs.CV↗

Rethinking Soft Compression in Retrieval-Augmented Generation: A Query-Conditioned Selector Perspective

Retrieval-Augmented Generation (RAG) effectively grounds Large Language Models (LLMs) with external knowledge and is widely applied to Web-related tasks. However, its scalability is hindered by excessive context length and redundant retrievals. Recent research on soft context compression aims to address this by encoding long documents into compact embeddings, yet they often underperform non-compressed RAG due to their reliance on auto-encoder-like full-compression that forces the encoder to compress all document information regardless of relevance to the input query. In this work, we conduct an analysis on this paradigm and reveal two fundamental limitations: (I) Infeasibility, full-compression conflicts with the LLM's downstream generation behavior; and (II) Non-necessity: full-compression is unnecessary and dilutes task-relevant information density. Motivated by these insights, we introduce SeleCom, a selector-based soft compression framework for RAG that redefines the encoder's role as query-conditioned information selector. The selector is decoder-only and is trained with a massive, diverse and difficulty-graded synthetic QA dataset with curriculum learning. Extensive experiments show that SeleCom significantly outperforms existing soft compression approaches and achieves competitive or superior performance to non-compression baselines, while reducing computation and latency by 33.8%~84.6%.

cs.CL↗