Searcharxiv⌕ Search

arXiv subjects

Lin Zhang

Publications and source records attributed to Lin Zhang.

At least 73 records · Page 4Linked to original sources
arXiv2026

Within the MDT Room: Situated in Multidisciplinary Team-Grounded Agent Debate for Clinical Diagnosis

Rare disease diagnosis is inherently challenging due to heterogeneous symptoms, limited clinical familiarity, and fragmented evidence across specialties. Recent large language model (LLM)-based agentic systems have shown promise by simulating multidisciplinary team discussions to generate and evaluate diagnostic hypotheses. However, fully automated diagnosis remains unrealistic, and existing human-in-the-loop approaches provide limited support for effective clinician-agent collaboration. In practice, clinicians are often presented with final diagnostic outputs and lengthy, unstructured agent discussion logs, making it difficult to inspect reasoning, intervene in a timely manner, or guide agent deliberation effectively. To address these challenges, we developed MDTRoom, an interactive system that transforms multi-agent discussions from linear transcripts into a structured, inspectable workspace. The system externalizes patient data, evidence provenance, hypothesis evolution, and inter-agent conflicts as interconnected visual objects, enabling clinicians to efficiently examine, intervene in, and guide agent reasoning. Our evaluation demonstrates the effectiveness of MDTRoom in supporting clinician-agent collaboration.

cs.HC↗
arXiv2026

GS3LAM: Gaussian Semantic Splatting SLAM

Recently, the multi-modal fusion of RGB, depth, and semantics has shown great potential in dense Simultaneous Localization and Mapping (SLAM). However, a prerequisite for generating consistent semantic maps is the availability of dense, efficient, and scalable scene representations. Existing semantic SLAM systems based on explicit representations are often limited by resolution and an inability to predict unknown areas. Conversely, implicit representations typically rely on time-consuming ray tracing, failing to meet real-time requirements. Fortunately, 3D Gaussian Splatting (3DGS) has emerged as a promising representation that combines the efficiency of point-based methods with the continuity of geometric structures. To this end, we propose GS3LAM, a Gaussian Semantic Splatting SLAM framework that processes multimodal data to render consistent, dense semantic maps in real-time. GS3LAM models the scene as a Semantic Gaussian Field (SG-Field) and jointly optimizes camera poses and the field via multimodal error constraints. Furthermore, a Depth-adaptive Scale Regularization (DSR) scheme is introduced to resolve misalignments between scale-invariant Gaussians and geometric surfaces. To mitigate catastrophic forgetting, we propose a Random Sampling-based Keyframe Mapping (RSKM) strategy, which demonstrates superior performance over common local covisibility optimization methods. Extensive experiments on benchmark datasets show that GS3LAM achieves increased tracking robustness, superior rendering quality, and enhanced semantic precision compared to state-of-the-art methods. Source code is available at https://github.com/lif314/GS3LAM.

cs.CV↗
arXiv2026

Integrated Spoofing-Robust Automatic Speaker Verification via a Three-Class Formulation and LLR

Spoofing-robust automatic speaker verification (SASV) aims to integrate automatic speaker verification (ASV) and countermeasure (CM). A popular solution is fusion of independent ASV and CM scores. To better modeling SASV, some frameworks integrate ASV and CM within a single network. However, these solutions are typically bi-encoder based, offer limited interpretability, and cannot be readily adapted to new evaluation parameters without retraining. Based on this, we propose a unified end-to-end framework via a three-class formulation that enables log-likelihood ratio (LLR) inference from class logits for a more interpretable decision pipeline. Experiments show comparable performance to existing methods on ASVSpoof5 and better results on SpoofCeleb. The visualization and analysis also prove that the three-class reformulation provides more interpretability.

eess.AS↗
arXiv2026

daVinci-Env: Open SWE Environment Synthesis at Scale

Training capable software engineering (SWE) agents demands large-scale, executable, and verifiable environments that provide dynamic feedback loops for iterative code editing, test execution, and solution refinement. However, existing open-source datasets remain limited in scale and repository diversity, while industrial solutions are opaque with unreleased infrastructure, creating a prohibitive barrier for most academic research groups. We present OpenSWE, the largest fully transparent framework for SWE agent training in Python, comprising 45,320 executable Docker environments spanning over 12.8k repositories, with all Dockerfiles, evaluation scripts, and infrastructure fully open-sourced for reproducibility. OpenSWE is built through a multi-agent synthesis pipeline deployed across a 64-node distributed cluster, automating repository exploration, Dockerfile construction, evaluation script generation, and iterative test analysis. Beyond scale, we propose a quality-centric filtering pipeline that characterizes the inherent difficulty of each environment, filtering out instances that are either unsolvable or insufficiently challenging and retaining only those that maximize learning efficiency. With $891K spent on environment construction and an additional $576K on trajectory sampling and difficulty-aware curation, the entire project represents a total investment of approximately $1.47 million, yielding about 13,000 curated trajectories from roughly 9,000 quality guaranteed environments. Extensive experiments validate OpenSWE's effectiveness: OpenSWE-32B and OpenSWE-72B achieve 62.4% and 66.0% on SWE-bench Verified, establishing SOTA among Qwen2.5 series. Moreover, SWE-focused training yields substantial out-of-domain improvements, including up to 12 points on mathematical reasoning and 5 points on science benchmarks, without degrading factual recall.

cs.SE↗
arXiv2026

RealVLG-R1: A Large-Scale Real-World Visual-Language Grounding Benchmark for Robotic Perception and Manipulation

Visual-language grounding aims to establish semantic correspondences between natural language and visual entities, enabling models to accurately identify and localize target objects based on textual instructions. Existing VLG approaches focus on coarse-grained, object-level localization, while traditional robotic grasping methods rely predominantly on geometric cues and lack language guidance, which limits their applicability in language-driven manipulation scenarios. To address these limitations, we propose the RealVLG framework, which integrates the RealVLG-11B dataset and the RealVLG-R1 model to unify real-world visual-language grounding and grasping tasks. RealVLG-11B dataset provides multi-granularity annotations including bounding boxes, segmentation masks, grasp poses, contact points, and human-verified fine-grained language descriptions, covering approximately 165,000 images, over 800 object instances, 1.3 million segmentation, detection, and language annotations, and roughly 11 billion grasping examples. Building on this dataset, RealVLG-R1 employs Reinforcement Fine-tuning on pretrained large-scale vision-language models to predict bounding boxes, segmentation masks, grasp poses, and contact points in a unified manner given natural language instructions. Experimental results demonstrate that RealVLG supports zero-shot perception and manipulation in real-world unseen environments, establishing a unified semantic-visual multimodal benchmark that provides a comprehensive data and evaluation platform for language-driven robotic perception and grasping policy learning. All data and code are publicly available at https://github.com/lif314/RealVLG-R1.

cs.CV↗
arXiv2026

AGCD: Agent-Guided Cross-Modal Decoding for Weather Forecasting

Accurate weather forecasting is more than grid-wise regression: it must preserve coherent synoptic structures and physical consistency of meteorological fields, especially under autoregressive rollouts where small one-step errors can amplify into structural bias. Existing physics-priors approaches typically impose global, once-for-all constraints via architectures, regularization, or NWP coupling, offering limited state-adaptive and sample-specific controllability at deployment. To bridge this gap, we propose Agent-Guided Cross-modal Decoding (AGCD), a plug-and-play decoding-time prior-injection paradigm that derives state-conditioned physics-priors from the current multivariate atmosphere and injects them into forecasters in a controllable and reusable way. Specifically, We design a multi-agent meteorological narration pipeline to generate state-conditioned physics-priors, utilizing MLLMs to extract various meteorological elements effectively. To effectively apply the priors, AGCD further introduce cross-modal region interaction decoding that performs region-aware multi-scale tokenization and efficient physics-priors injection to refine visual features without changing the backbone interface. Experiments on WeatherBench demonstrate consistent gains for 6-hour forecasting across two resolutions (5.625 degree and 1.40625 degree) and diverse backbones (generic and weather-specialized), including strictly causal 48-hour autoregressive rollouts that reduce early-stage error accumulation and improve long-horizon stability.

cs.AI↗
arXiv2026

One application of Duistermaat-Heckman measure in quantum information theory

While the exact separability probability of 8/33 for two-qubit states under the Hilbert-Schmidt measure has been reported by Huong and Khoi [\href{https://doi.org/10.1088/1751-8121/ad8493}{J.Phys.A:Math.Theor.{\bf57}, 445304(2024)}], detailed derivations remain inaccessible for general audiences. This paper provides a comprehensive, self-contained derivation of this result, elucidating the underlying geometric and probabilistic structures. We achieve this by developing a framework centered on the computation of Hilbert-Schmidt volumes for key components: the quantum state space, relevant flag manifolds, and regular (co)adjoint orbits. Crucially, we establish and leverage the connection between these Hilbert-Schmidt volumes and the symplectic volumes of the corresponding regular co-adjoint orbits, formalized through the Duistermaat-Heckman measure. By meticulously synthesizing these volume computations -- specifically, the ratios defining the relevant probability measures -- we reconstruct and rigorously verify the 8/33 separability probability. Our approach offers a transparent pathway to this fundamental constant, detailing the interplay between symplectic geometry, representation theory, and quantum probability.

quant-ph↗
arXiv2026

Can LLMs Help Localize Fake Words in Partially Fake Speech?

Large language models (LLMs), trained on large-scale text, have recently attracted significant attention for their strong performance across many tasks. Motivated by this, we investigate whether a text-trained LLM can help localize fake words in partially fake speech, where only specific words within a speech are edited. We build a speech LLM to perform fake word localization via next token prediction. Experiments and analyses on AV-Deepfake1M and PartialEdit indicates that the model frequently leverages editing-style pattern learned from the training data, particularly word-level polarity substitutions for those two databases we discussed, as cues for localizing fake words. Although such particular patterns provide useful information in an in-domain scenario, how to avoid over-reliance on such particular pattern and improve generalization to unseen editing styles remains an open question.

eess.AS↗
arXiv2026

Holographic QCD equation of state constrained by lattice QCD: neural-ODE for probe-limit and a back-reaction test

We study the equation of state (EoS) of QCD matter in a bottom-up holographic setup that combines an Einstein-Maxwell-dilaton (EMD) sector with an improved Karch-Katz-Son-Stephanov (KKSS) flavor action. In the probe approximation, we perform an inverse reconstruction of the model functions by parameterizing them with neural networks and solving the EMD equations via a differentiable ODE solver (a neural ODE framework), calibrating the model to a $(2+1)$-flavor lattice-QCD EoS at finite temperature and finite baryon chemical potential. The reconstructed model functions are then parametrized and kept fixed across thermodynamic states. Next, viewing the EMD sector as an effective description of pure Yang--Mills theory, we fix its parameters by fitting the $μ_B=0$ lattice pure-glue EoS using a hybrid optimization strategy. Finally, we go beyond the probe limit and solve the coupled EMD$+$KKSS equations with back-reaction, using the pure-glue-calibrated EMD sector as a fixed input and varying the KKSS couplings to compare with the $μ_B=0$ two-flavor lattice EoS. We find a visible mismatch and a high-temperature behavior in which the back-reacted dimensionless ratios approach a nearly $β_1$-insensitive plateau close to the pure-glue baseline, providing a simple structural diagnostic for the present flavor-sector truncation.

hep-ph↗
arXiv2026

ARport: An Augmented Reality System for Markerless Image-Guided Port Placement in Robotic Surgery

Purpose: Precise port placement is a critical step in robot-assisted surgery, where port configuration influences both visual access to the operative field and instrument maneuverability. To bridge the gap between preoperative planning and intraoperative execution, we present ARport, an augmented reality (AR) system that automatically maps pre-planned trocar layouts onto the patient's body surface, providing intuitive spatial guidance during surgical preparation. Methods: ARport, implemented on an optical see-through head-mounted display (OST-HMD), operates without any external sensors or markers, simplifying setup and enhancing workflow integration. It reconstructs the operative scene from RGB, depth, and pose data captured by the OST-HMD, extracts the patient's body surface using a foundation model, and performs surface-based markerless registration to align preoperative anatomical models to the extracted patient's body surface, enabling in-situ visualization of planned trocar layouts. A demonstration video illustrating the overall workflow is available online. Results: In full-scale human-phantom experiments, ARport accurately overlaid pre-planned trocar sites onto the physical phantom, achieving consistent spatial correspondence between virtual plans and real anatomy. Conclusion: ARport provides a fully marker-free and hardware-minimal solution for visualizing preoperative trocar plans directly on the patient's body surface. The system facilitates efficient intraoperative setup and demonstrates potential for seamless integration into routine clinical workflows.

cs.CV↗
arXiv2026

ESDD2: Environment-Aware Speech and Sound Deepfake Detection Challenge Evaluation Plan

Audio recorded in real-world environments often contains a mixture of foreground speech and background environmental sounds. With rapid advances in text-to-speech, voice conversion, and other generation models, either component can now be modified independently. Such component-level manipulations are harder to detect, as the remaining unaltered component can mislead the systems designed for whole deepfake audio, and they often sound more natural to human listeners. To address this gap, we have proposed CompSpoofV2 dataset and a separation-enhanced joint learning framework. CompSpoofV2 is a large-scale curated dataset designed for component-level audio anti-spoofing, which contains over 250k audio samples, with a total duration of approximately 283 hours. Based on the CompSpoofV2 and the separation-enhanced joint learning framework, we launch the Environment-Aware Speech and Sound Deepfake Detection Challenge (ESDD2), focusing on component-level spoofing, where both speech and environmental sounds may be manipulated or synthesized, creating a more challenging and realistic detection scenario. The challenge will be held in conjunction with the IEEE International Conference on Multimedia and Expo 2026 (ICME 2026).

cs.SD↗
arXiv2026

FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding

Transitioning Multimodal Large Language Models (MLLMs) from offline to online streaming video understanding is essential for continuous perception. However, existing methods lack flexible adaptivity, leading to irreversible detail loss and context fragmentation. To resolve this, we propose FreshMem, a Frequency-Space Hybrid Memory network inspired by the brain's logarithmic perception and memory consolidation. FreshMem reconciles short-term fidelity with long-term coherence through two synergistic modules: Multi-scale Frequency Memory (MFM), which projects overflowing frames into representative frequency coefficients, complemented by residual details to reconstruct a global historical "gist"; and Space Thumbnail Memory (STM), which discretizes the continuous stream into episodic clusters by employing an adaptive compression strategy to distill them into high-density space thumbnails. Extensive experiments show that FreshMem significantly boosts the Qwen2-VL baseline, yielding gains of 5.20%, 4.52%, and 2.34% on StreamingBench, OV-Bench, and OVO-Bench, respectively. As a training-free solution, FreshMem outperforms several fully fine-tuned methods, offering a highly efficient paradigm for long-horizon streaming video understanding.

cs.CV↗
arXiv2026

ES-MemEval: Benchmarking Conversational Agents on Personalized Long-Term Emotional Support

Large Language Models (LLMs) have shown strong potential as conversational agents. Yet, their effectiveness remains limited by deficiencies in robust long-term memory, particularly in complex, long-term web-based services such as online emotional support. However, existing long-term dialogue benchmarks primarily focus on static and explicit fact retrieval, failing to evaluate agents in critical scenarios where user information is dispersed, implicit, and continuously evolving. To address this gap, we introduce ES-MemEval, a comprehensive benchmark that systematically evaluates five core memory capabilities: information extraction, temporal reasoning, conflict detection, abstention, and user modeling, in long-term emotional support settings, covering question answering, summarization, and dialogue generation tasks. To support the benchmark, we also propose EvoEmo, a multi-session dataset for personalized long-term emotional support that captures fragmented, implicit user disclosures and evolving user states. Extensive experiments on open-source long-context, commercial, and retrieval-augmented (RAG) LLMs show that explicit long-term memory is essential for reducing hallucinations and enabling effective personalization. At the same time, RAG improves factual consistency but struggles with temporal dynamics and evolving user states. These findings highlight both the potential and limitations of current paradigms and motivate more robust integration of memory and retrieval for long-term personalized dialogue systems.

cs.CL↗
arXiv2026

HyLRA: Hybrid Layer Reuse Attention for Efficient Long-Context Inference

Long-context inference in Large Language Models (LLMs) is bottlenecked by the quadratic computation complexity of attention and the substantial memory footprint of Key-Value (KV) caches. While existing sparse attention mechanisms attempt to mitigate this by exploiting inherent sparsity, they often rely on rigid patterns or aggressive pruning, failing to achieve an optimal balance between efficiency and accuracy. In this paper, we introduce {\bf HyLRA} ({\bf Hy}brid {\bf L}ayer {\bf R}euse {\bf A}ttention), a novel framework driven by layer-wise sparsity profiling. Our empirical analysis uncovers a dual characteristic in attention mechanics: \textit{intra-layer sensitivity}, where specific layers necessitate full attention to prevent feature distortion, and \textit{inter-layer similarity}, where consecutive layers share substantial critical tokens. Based on these observations, HyLRA employs an offline dynamic programming approach to derive an optimal layer-wise policy. This hybrid strategy retains full attention for sensitive layers to ensure robustness, while enabling tolerant layers to bypass quadratic calculations by directly reusing top-$k$ indices from preceding layers. This approach allows LLMs to restrict computation to the most critical tokens, effectively overcoming the quadratic bottleneck of dense attention. Extensive evaluations demonstrate that HyLRA improves inference throughput by 6\%--46\% while maintaining comparable performance (with $<1\%$ accuracy degradation), consistently outperforming state-of-the-art sparse attention methods. HyLRA is open source at \href{https://anonymous.4open.science/r/unified-cache-management-CF80/}{\texttt{/r/unified-cache-management-CF80/}}

cs.CL↗
arXiv2026

Movable Antenna Empowered Covert Dual-Functional Radar-Communication

Movable antenna (MA) has emerged as a promising technology to flexibly reconfigure wireless channels by adjusting antenna placement. In this paper, we study a secured dual-functional radar-communication (DFRC) system aided by movable antennas. To enhance the communication security, we aim to maximize the achievable sum rate by jointly optimizing the transmitter beamforming vectors, receiving filter, and antenna placement, subject to radar signal-to-noise ratio (SINR) and transmission covertness constraints. We consider multiple Willies operating in both non-colluding and colluding modes. For noncolluding Willies, we first employ a Lagrangian dual transformation procedure to reformulate the challenging optimization problem into a more tractable form. Subsequently, we develop an efficient block coordinate descent (BCD) algorithm that integrates semidefinite relaxation (SDR), projected gradient descent (PGD), Dinkelbach transformation, and successive convex approximation (SCA) techniques to tackle the resulting problem. For colluding Willies, we first derive the minimum detection error probability (DEP) by characterizing the optimal detection statistic, which is proven to follow the generalized Erlang distribution. Then, we develop a minimum mean square error (MMSE)-based algorithm to address the colluding detection problem. We further provide a comprehensive complexity analysis on the unified design framework. Simulation results demonstrate that the proposed method can significantly improve the covert sum rate, and achieve a superior balance between communication and radar performance compared with existing benchmark schemes.

eess.SP↗
arXiv2026

MiLDEdit: Reasoning-Based Multi-Layer Design Document Editing

Real-world design documents (e.g., posters) are inherently multi-layered, combining decoration, text, and images. Editing them from natural-language instructions requires fine-grained, layer-aware reasoning to identify relevant layers and coordinate modifications. Prior work largely overlooks multi-layer design document editing, focusing instead on single-layer image editing or multi-layer generation, which assume a flat canvas and lack the reasoning needed to determine what and where to modify. To address this gap, we introduce the Multi-Layer Document Editing Agent (MiLDEAgent), a reasoning-based framework that combines an RL-trained multimodal reasoner for layer-wise understanding with an image editor for targeted modifications. To systematically benchmark this setting, we introduce the MiLDEBench, a human-in-the-loop corpus of over 20K design documents paired with diverse editing instructions. The benchmark is complemented by a task-specific evaluation protocol, MiLDEEval, which spans four dimensions including instruction following, layout consistency, aesthetics, and text rendering. Extensive experiments on 14 open-source and 2 closed-source models reveal that existing approaches fail to generalize: open-source models often cannot complete multi-layer document editing tasks, while closed-source models suffer from format violations. In contrast, MiLDEAgent achieves strong layer-aware reasoning and precise editing, significantly outperforming all open-source baselines and attaining performance comparable to closed-source models, thereby establishing the first strong baseline for multi-layer document editing.

cs.CV↗
arXiv2026

Circulant quantum channels and its applications

This note introduces a family of circulant quantum channels -- a subclass of the mixed-permutation channels -- and investigates its key structural and operational properties. We show that the image of the circulant quantum channel is precisely the set of circulant matrices. This characterization facilitates the analysis of arbitrary $n$-th order Bargmann invariants. Furthermore, we prove that the channel is entanglement-breaking, implying a substantially reduced resource cost for erasing quantum correlations compared to a general mixed-permutation channel. Applications of this channel are also discussed, including the derivation of tighter lower bounds for $\ell_p$-norm coherence and a characterization of its action in bipartite systems.

quant-ph↗
arXiv2026

WeDefense: A Toolkit to Defend Against Fake Audio

The advances in generative AI have enabled the creation of synthetic audio which is perceptually indistinguishable from real, genuine audio. Although this stellar progress enables many positive applications, it also raises risks of misuse, such as for impersonation, disinformation and fraud. Despite a growing number of open-source fake audio detection codes released through numerous challenges and initiatives, most are tailored to specific competitions, datasets or models. A standardized and unified toolkit that supports the fair benchmarking and comparison of competing solutions with not just common databases, protocols, metrics, but also a shared codebase, is missing. To address this, we propose WeDefense, the first open-source toolkit to support both fake audio detection and localization. Beyond model training, WeDefense emphasizes critical yet often overlooked components: flexible input and augmentation, calibration, score fusion, standardized evaluation metrics, and analysis tools for deeper understanding and interpretation. The toolkit is publicly available at https://github.com/zlin0/wedefense with interactive demos for fake audio detection and localization.

cs.SD↗