arXiv subjects

Xinyu Zhang

Publications and source records attributed to Xinyu Zhang.

At least 145 records · Page 8Linked to original sources

arXiv2025

MAction-SocialNav: Multi-Action Socially Compliant Navigation via Reasoning-enhanced Prompt Tuning

Socially compliant navigation requires robots to move safely and appropriately in human-centered environments by respecting social norms. However, social norms are often ambiguous, and in a single scenario, multiple actions may be equally acceptable. Most existing methods simplify this problem by assuming a single correct action, which limits their ability to handle real-world social uncertainty. In this work, we propose MAction-SocialNav, an efficient vision language model for socially compliant navigation that explicitly addresses action ambiguity, enabling generating multiple plausible actions within one scenario. To enhance the model's reasoning capability, we introduce a novel meta-cognitive prompt (MCP) method. Furthermore, to evaluate the proposed method, we curate a multi-action socially compliant navigation dataset that accounts for diverse conditions, including crowd density, indoor and outdoor environments, and dual human annotations. The dataset contains 789 samples, each with three-turn conversation, split into 710 training samples and 79 test samples through random selection. We also design five evaluation metrics to assess high-level decision precision, safety, and diversity. Extensive experiments demonstrate that the proposed MAction-SocialNav achieves strong social reasoning performance while maintaining high efficiency, highlighting its potential for real-world human robot navigation. Compared with zero-shot GPT-4o and Claude, our model achieves substantially higher decision quality (APG: 0.595 vs. 0.000/0.025) and safety alignment (ER: 0.264 vs. 0.642/0.668), while maintaining real-time efficiency (1.524 FPS, over 3x faster).

cs.RO↗

arXiv2025

Continual Learning on CLIP via Incremental Prompt Tuning with Intrinsic Textual Anchors

Continual learning (CL) enables deep networks to acquire new knowledge while avoiding catastrophic forgetting. The powerful generalization ability of pre-trained models (PTMs), such as the Contrastive Language-Image Pre-training (CLIP) model, has inspired a range of CL methods targeting new and specialized tasks, providing rich multi-modal embeddings that support lightweight, incremental prompt tuning. Existing methods often rely on complex designs built upon specific assumptions, such as intricate regularization schemes for prompt pools, specialized routing mechanisms, or multi-stage incrementations, that introduce additional-and possibly unnecessary-complexity, underutilizing CLIP's intrinsic capabilities. In this paper, we propose a concise CL approach for CLIP based on incremental prompt tuning that fully exploits its multi-modal structure and the stability of textual representations. Our method, Textual Prototype-guided Prompt Tuning (TPPT), introduces textual prototypes not merely as static classifiers, as in existing methods, but as stable anchors to guide the learning of visual prompts, thereby shaping the embedding space (i.e., TPPT-V). We show that our bidirectional supervision strategy enables more effective learning of new knowledge while reducing forgetting. To further close the vision-language gap during CL, we jointly optimizes visual and textual prompts (i.e., TPPT-VT). We also introduce a relational diversity regularization on the textual anchors to prevent embedding space collapse and mitigate correlated forgetting. Extensive experiments and analyses demonstrate the effectiveness of our proposed approach, highlighting the benefits of leveraging CLIP's intrinsic guidance for continual adaptation.

cs.CV↗

arXiv2025

SocialNav-MoE: A Mixture-of-Experts Vision Language Model for Socially Compliant Navigation with Reinforcement Fine-Tuning

For robots navigating in human-populated environments, safety and social compliance are equally critical, yet prior work has mostly emphasized safety. Socially compliant navigation that accounts for human comfort, social norms, and contextual appropriateness remains underexplored. Vision language models (VLMs) show promise for this task; however, large-scale models incur substantial computational overhead, leading to higher inference latency and energy consumption, which makes them unsuitable for real-time deployment on resource-constrained robotic platforms. To address this issue, we investigate the effectiveness of small VLM and propose SocialNav-MoE, an efficient Mixture-of-Experts vision language model for socially compliant navigation with reinforcement fine-tuning (RFT). We further introduce a semantic similarity reward (SSR) to effectively leverage RFT for enhancing the decision-making capabilities. Additionally, we study the effectiveness of different small language model types (Phi, Qwen, and StableLM), routing strategies, and vision encoders (CLIP vs. SigLIP, frozen vs. fine-tuned). Experiments on the SNEI dataset demonstrate that SocialNav-MoE achieves an excellent balance between navigation accuracy and efficiency. The proposed SSR function is more effective than hard-level and character-level rewards. Source code will be released upon acceptance.

cs.CV↗

arXiv2025

Seedream 4.0: Toward Next-generation Multimodal Image Generation

We introduce Seedream 4.0, an efficient and high-performance multimodal image generation system that unifies text-to-image (T2I) synthesis, image editing, and multi-image composition within a single framework. We develop a highly efficient diffusion transformer with a powerful VAE which also can reduce the number of image tokens considerably. This allows for efficient training of our model, and enables it to fast generate native high-resolution images (e.g., 1K-4K). Seedream 4.0 is pretrained on billions of text-image pairs spanning diverse taxonomies and knowledge-centric concepts. Comprehensive data collection across hundreds of vertical scenarios, coupled with optimized strategies, ensures stable and large-scale training, with strong generalization. By incorporating a carefully fine-tuned VLM model, we perform multi-modal post-training for training both T2I and image editing tasks jointly. For inference acceleration, we integrate adversarial distillation, distribution matching, and quantization, as well as speculative decoding. It achieves an inference time of up to 1.8 seconds for generating a 2K image (without a LLM/VLM as PE model). Comprehensive evaluations reveal that Seedream 4.0 can achieve state-of-the-art results on both T2I and multimodal image editing. In particular, it demonstrates exceptional multimodal capabilities in complex tasks, including precise image editing and in-context reasoning, and also allows for multi-image reference, and can generate multiple output images. This extends traditional T2I systems into an more interactive and multidimensional creative tool, pushing the boundary of generative AI for both creativity and professional applications. We further scale our model and data as Seedream 4.5. Seedream 4.0 and Seedream 4.5 are accessible on Volcano Engine https://www.volcengine.com/experience/ark?launch=seedream.

cs.CV↗

arXiv2025

NumeriKontrol: Adding Numeric Control to Diffusion Transformers for Instruction-based Image Editing

Instruction-based image editing enables intuitive manipulation through natural language commands. However, text instructions alone often lack the precision required for fine-grained control over edit intensity. We introduce NumeriKontrol, a framework that allows users to precisely adjust image attributes using continuous scalar values with common units. NumeriKontrol encodes numeric editing scales via an effective Numeric Adapter and injects them into diffusion models in a plug-and-play manner. Thanks to a task-separated design, our approach supports zero-shot multi-condition editing, allowing users to specify multiple instructions in any order. To provide high-quality supervision, we synthesize precise training data from reliable sources, including high-fidelity rendering engines and DSLR cameras. Our Common Attribute Transform (CAT) dataset covers diverse attribute manipulations with accurate ground-truth scales, enabling NumeriKontrol to function as a simple yet powerful interactive editing studio. Extensive experiments show that NumeriKontrol delivers accurate, continuous, and stable scale control across a wide range of attribute editing scenarios. These contributions advance instruction-based image editing by enabling precise, scalable, and user-controllable image manipulation.

cs.CV↗

arXiv2025

OralGPT-Omni: A Versatile Dental Multimodal Large Language Model

Multimodal Large Language Models (MLLMs) have exhibited immense potential across numerous medical specialties; yet, dentistry remains underexplored, in part due to limited domain-specific data, scarce dental expert annotations, insufficient modality-specific modeling, and challenges in reliability. In this paper, we present OralGPT-Omni, the first dental-specialized MLLM designed for comprehensive and trustworthy analysis across diverse dental imaging modalities and clinical tasks. To explicitly capture dentists' diagnostic reasoning, we construct TRACE-CoT, a clinically grounded chain-of-thought dataset that mirrors dental radiologists' decision-making processes. This reasoning supervision, combined with our proposed four-stage training paradigm, substantially strengthens the model's capacity for dental image understanding and analysis. In parallel, we introduce MMOral-Uni, the first unified multimodal benchmark for dental image analysis. It comprises 2,809 open-ended question-answer pairs spanning five modalities and five tasks, offering a comprehensive evaluation suite to date for MLLMs in digital dentistry. OralGPT-Omni achieves an overall score of 51.84 on the MMOral-Uni benchmark and 45.31 on the MMOral-OPG benchmark, dramatically outperforming the scores of GPT-5. Our work promotes intelligent dentistry and paves the way for future advances in dental image analysis. All code, benchmark, and models will be made publicly available.

cs.CV↗

arXiv2025

GEO-Detective: Unveiling Location Privacy Risks in Images with LLM Agents

Images shared on social media often expose geographic cues. While early geolocation methods required expert effort and lacked generalization, the rise of Large Vision Language Models (LVLMs) now enables accurate geolocation even for ordinary users. However, existing approaches are not optimized for this task. To explore the full potential and associated privacy risks, we present Geo-Detective, an agent that mimics human reasoning and tool use for image geolocation inference. It follows a procedure with four steps that adaptively selects strategies based on image difficulty and is equipped with specialized tools such as visual reverse search, which emulates how humans gather external geographic clues. Experimental results show that GEO-Detective outperforms baseline large vision language models (LVLMs) overall, particularly on images lacking visible geographic features. In country level geolocation tasks, it achieves an improvement of over 11.1% compared to baseline LLMs, and even at finer grained levels, it still provides around a 5.2% performance gain. Meanwhile, when equipped with external clues, GEO-Detective becomes more likely to produce accurate predictions, reducing the "unknown" prediction rate by more than 50.6%. We further explore multiple defense strategies and find that Geo-Detective exhibits stronger robustness, highlighting the need for more effective privacy safeguards.

cs.CR↗

arXiv2025

Portfolio Optimization via Transfer Learning

Recognizing that asset markets generally exhibit shared informational characteristics, we develop a portfolio strategy based on transfer learning that leverages cross-market information to enhance the investment performance in the market of interest by forward validation. Our strategy asymptotically identifies and utilizes the informative datasets, selectively incorporating valid information while discarding the misleading information. This enables our strategy to achieve the maximum Sharpe ratio asymptotically. The promising performance is demonstrated by numerical studies and case studies of two portfolios: one consisting of stocks dual-listed in A-shares and H-shares, and another comprising equities from various industries of the United States.

q-fin.PM↗

arXiv2025

Covert Waveform Design for Integrated Sensing and Communication System in Clutter Environment

This paper proposes an integrated sensing and communication (ISAC) system covert waveform design method for complex clutter environments, with the core objective of maximizing the signal-to-clutter-plus-noise ratio (SCNR). The design achieves efficient clutter suppression while meeting the covertness requirement through joint optimization of the transmit waveform and receive filter, enabling cooperative radar detection and wireless communication. This study presents key innovations that explicitly address target Doppler shift uncertainty, significantly enhancing system robustness against Doppler effects. To ensure communication reliability, the method incorporates phase difference constraints between communication signal elements in the waveform design, along with energy constraint, covert constraint, and peak-to-average power ratio (PAPR) constraint. The original non-convex optimization problem is transformed into a tractable convex optimization form through convex optimization technique. Simulation results demonstrate that the optimized waveform not only satisfies the covertness requirement in complex clutter environment, but also achieves superior target detection performance. It also ensures reliable communication and confirms the effectiveness of propose method.

eess.SP↗

arXiv2025

Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation

Dataset distillation compresses large-scale datasets into compact, highly informative synthetic data, significantly reducing storage and training costs. However, existing research primarily focuses on balanced datasets and struggles to perform under real-world long-tailed distributions. In this work, we emphasize the critical role of soft labels in long-tailed dataset distillation and uncover the underlying mechanisms contributing to performance degradation. Specifically, we derive an imbalance-aware generalization bound for model trained on distilled dataset. We then identify two primary sources of soft-label bias, which originate from the distillation model and the distilled images, through systematic perturbation of the data imbalance levels. To address this, we propose ADSA, an Adaptive Soft-label Alignment module that calibrates the entangled biases. This lightweight module integrates seamlessly into existing distillation pipelines and consistently improves performance. On ImageNet-1k-LT with EDC and IPC=50, ADSA improves tail-class accuracy by up to 11.8% and raises overall accuracy to 41.4%. Extensive experiments demonstrate that ADSA provides a robust and generalizable solution under limited label budgets and across a range of distillation techniques. Code is available at: https://github.com/j-cyoung/ADSA_DD.git.

cs.CV↗

arXiv2025

Think with Self-Decoupling and Self-Verification: Automated RTL Design with Backtrack-ToT

Large language models (LLMs) hold promise for automating integrated circuit (IC) engineering using register transfer level (RTL) hardware description languages (HDLs) like Verilog. However, challenges remain in ensuring the quality of Verilog generation. Complex designs often fail in a single generation due to the lack of targeted decoupling strategies, and evaluating the correctness of decoupled sub-tasks remains difficult. While the chain-of-thought (CoT) method is commonly used to improve LLM reasoning, it has been largely ineffective in automating IC design workflows, requiring manual intervention. The key issue is controlling CoT reasoning direction and step granularity, which do not align with expert RTL design knowledge. This paper introduces VeriBToT, a specialized LLM reasoning paradigm for automated Verilog generation. By integrating Top-down and design-for-verification (DFV) approaches, VeriBToT achieves self-decoupling and self-verification of intermediate steps, constructing a Backtrack Tree of Thought with formal operators. Compared to traditional CoT paradigms, our approach enhances Verilog generation while optimizing token costs through flexible modularity, hierarchy, and reusability.

cs.AR↗

arXiv2025

Direct observation of room-temperature exciton condensation

Exciton condensation--an interaction-driven, macroscopically coherent paired-fermion state--offers the prospect for dissipationless energy transport in solids, akin to that in superconductivity. Although their light effective mass and strong Coulomb binding favour high transition temperatures, convincing demonstrations of pure-exciton condensation have hitherto been limited to cryogenic conditions. Here, we report the direct observation of quasi-equilibrium condensation of dark excitons in monolayer tungsten diselenide at 300 K and ambient pressure. We achieve this by creating nanoscale spacing-graded Stark traps to confine free excitons, setting the finite-size scale, non-resonant off-axis optical injection to control the local density-temperature trajectory, and employing surface plasmon polariton-enhanced microsphere-assisted microscopy to boost dark-exciton emission and directly image first-order spatial coherence with sub-diffraction resolution. We observe a sharp degeneracy threshold and a clear phase transition, evidenced by extended first-order spatial coherence with algebraic decay and a critical exponent consistent with the universal Berezinskii-Kosterlitz-Thouless criterion. Identical condensation signatures are observed in over 30 independent samples. Our work establishes a room-temperature excitonic platform for exploring strongly correlated many-body physics and advancing near-dissipationless, coherent quantum technologies.

physics.optics↗

arXiv2025

An LLM-based Framework for Human-Swarm Teaming Cognition in Disaster Search and Rescue

Large-scale disaster Search And Rescue (SAR) operations are persistently challenged by complex terrain and disrupted communications. While Unmanned Aerial Vehicle (UAV) swarms offer a promising solution for tasks like wide-area search and supply delivery, yet their effective coordination places a significant cognitive burden on human operators. The core human-machine collaboration bottleneck lies in the ``intention-to-action gap'', which is an error-prone process of translating a high-level rescue objective into a low-level swarm command under high intensity and pressure. To bridge this gap, this study proposes a novel LLM-CRF system that leverages Large Language Models (LLMs) to model and augment human-swarm teaming cognition. The proposed framework initially captures the operator's intention through natural and multi-modal interactions with the device via voice or graphical annotations. It then employs the LLM as a cognitive engine to perform intention comprehension, hierarchical task decomposition, and mission planning for the UAV swarm. This closed-loop framework enables the swarm to act as a proactive partner, providing active feedback in real-time while reducing the need for manual monitoring and control, which considerably advances the efficacy of the SAR task. We evaluate the proposed framework in a simulated SAR scenario. Experimental results demonstrate that, compared to traditional order and command-based interfaces, the proposed LLM-driven approach reduced task completion time by approximately $64.2\%$ and improved task success rate by $7\%$. It also leads to a considerable reduction in subjective cognitive workload, with NASA-TLX scores dropping by $42.9\%$. This work establishes the potential of LLMs to create more intuitive and effective human-swarm collaborations in high-stakes scenarios.

cs.RO↗

arXiv2025

Co-MTP: A Cooperative Trajectory Prediction Framework with Multi-Temporal Fusion for Autonomous Driving

Vehicle-to-everything technologies (V2X) have become an ideal paradigm to extend the perception range and see through the occlusion. Exiting efforts focus on single-frame cooperative perception, however, how to capture the temporal cue between frames with V2X to facilitate the prediction task even the planning task is still underexplored. In this paper, we introduce the Co-MTP, a general cooperative trajectory prediction framework with multi-temporal fusion for autonomous driving, which leverages the V2X system to fully capture the interaction among agents in both history and future domains to benefit the planning. In the history domain, V2X can complement the incomplete history trajectory in single-vehicle perception, and we design a heterogeneous graph transformer to learn the fusion of the history feature from multiple agents and capture the history interaction. Moreover, the goal of prediction is to support future planning. Thus, in the future domain, V2X can provide the prediction results of surrounding objects, and we further extend the graph transformer to capture the future interaction among the ego planning and the other vehicles' intentions and obtain the final future scenario state under a certain planning action. We evaluate the Co-MTP framework on the real-world dataset V2X-Seq, and the results show that Co-MTP achieves state-of-the-art performance and that both history and future fusion can greatly benefit prediction.

cs.LG↗

arXiv2025

VRP-SAM: SAM with Visual Reference Prompt

In this paper, we propose a novel Visual Reference Prompt (VRP) encoder that empowers the Segment Anything Model (SAM) to utilize annotated reference images as prompts for segmentation, creating the VRP-SAM model. In essence, VRP-SAM can utilize annotated reference images to comprehend specific objects and perform segmentation of specific objects in target image. It is note that the VRP encoder can support a variety of annotation formats for reference images, including \textbf{point}, \textbf{box}, \textbf{scribble}, and \textbf{mask}. VRP-SAM achieves a breakthrough within the SAM framework by extending its versatility and applicability while preserving SAM's inherent strengths, thus enhancing user-friendliness. To enhance the generalization ability of VRP-SAM, the VRP encoder adopts a meta-learning strategy. To validate the effectiveness of VRP-SAM, we conducted extensive empirical studies on the Pascal and COCO datasets. Remarkably, VRP-SAM achieved state-of-the-art performance in visual reference segmentation with minimal learnable parameters. Furthermore, VRP-SAM demonstrates strong generalization capabilities, allowing it to perform segmentation of unseen objects and enabling cross-domain segmentation. The source code and models will be available at https://github.com/syp2ysy/VRP-SAM

cs.CV↗

arXiv2025

FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts

In this paper, we introduce FedMGP, a new paradigm for personalized federated prompt learning in vision-language models. FedMGP equips each client with multiple groups of paired textual and visual prompts, enabling the model to capture diverse, fine-grained semantic and instance-level cues. A diversity loss is introduced to drive each prompt group to specialize in distinct and complementary semantic aspects, ensuring that the groups collectively cover a broader range of local characteristics. During communication, FedMGP employs a dynamic prompt aggregation strategy based on similarity-guided probabilistic sampling: each client computes the cosine similarity between its prompt groups and the global prompts from the previous round, then samples s groups via a softmax-weighted distribution. This soft selection mechanism preferentially aggregates semantically aligned knowledge while still enabling exploration of underrepresented patterns effectively balancing the preservation of common knowledge with client-specific features. Notably, FedMGP maintains parameter efficiency by redistributing a fixed prompt capacity across multiple groups, achieving state-of-the-art performance with the lowest communication parameters among all federated prompt learning methods. Theoretical analysis shows that our dynamic aggregation strategy promotes robust global representation learning by reinforcing shared semantics while suppressing client-specific noise. Extensive experiments demonstrate that FedMGP consistently outperforms prior approaches in both personalization and domain generalization across diverse federated vision-language benchmarks. The code will be released on https://github.com/weihao-bo/FedMGP.git.

cs.CV↗

arXiv2025

Scaling Diffusion Transformers Efficiently via $μ$P

Diffusion Transformers have emerged as the foundation for vision generative models, but their scalability is limited by the high cost of hyperparameter (HP) tuning at large scales. Recently, Maximal Update Parametrization ($μ$P) was proposed for vanilla Transformers, which enables stable HP transfer from small to large language models, and dramatically reduces tuning costs. However, it remains unclear whether $μ$P of vanilla Transformers extends to diffusion Transformers, which differ architecturally and objectively. In this work, we generalize standard $μ$P to diffusion Transformers and validate its effectiveness through large-scale experiments. First, we rigorously prove that $μ$P of mainstream diffusion Transformers, including U-ViT, DiT, PixArt-$α$, and MMDiT, aligns with that of the vanilla Transformer, enabling the direct application of existing $μ$P methodologies. Leveraging this result, we systematically demonstrate that DiT-$μ$P enjoys robust HP transferability. Notably, DiT-XL-2-$μ$P with transferred learning rate achieves 2.9 times faster convergence than the original DiT-XL-2. Finally, we validate the effectiveness of $μ$P on text-to-image generation by scaling PixArt-$α$ from 0.04B to 0.61B and MMDiT from 0.18B to 18B. In both cases, models under $μ$P outperform their respective baselines while requiring small tuning cost, only 5.5% of one training run for PixArt-$α$ and 3% of consumption by human experts for MMDiT-18B. These results establish $μ$P as a principled and efficient framework for scaling diffusion Transformers.

cs.LG↗

arXiv2025

Symmetry-Driven Asynchronous Forwarding for Reliable Distributed Coordination in Toroidal Networks

The proliferation of large-scale distributed systems, such as satellite constellations and high-performance computing clusters, demands robust communication primitives that maintain coordination under unreliable links. The torus topology, with its inherent rotational and reflection symmetries, is a prevalent architecture in these domains. However, conventional routing schemes suffer from substantial packet loss during control-plane synchronization after link failures. This paper introduces a symmetry-driven asynchronous forwarding mechanism that leverages the torus's geometric properties to achieve reliable packet delivery without control-plane coordination. We model packet flow using a topological potential gradient and demonstrate that symmetry-breaking failures naturally induce a reverse flow, which we harness for fault circumvention. We propose two local forwarding strategies, Reverse Flow with Counter-facing Priority (RF-CF) and Lateral-facing Priority (RF-LF), that guarantee reachability to the destination via forward-flow phase transition points, without protocol modifications or additional in-packet overhead. Through percolation analysis and packet-level simulations on a 16 x 16 torus, we show that our mechanism reduces packet loss by up to 17.5% under a 1% link failure rate, with the RF-LF strategy contributing to 28% of successfully delivered packets. This work establishes a foundational link between topological symmetry and communication resilience, providing a lightweight, protocol-agnostic substrate for enhancing distributed systems.

cs.NI↗