arXiv subjects

Ye Wang

Publications and source records attributed to Ye Wang.

At least 109 records · Page 6Linked to original sources

arXiv2025

AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent

To address the enormous size of Large Language Models (LLMs), model compression methods, such as quantization and pruning, are often deployed, especially on edge devices. In this work, we focus on layer-wise post-training quantization and pruning. Drawing connections between activation-aware weight pruning and sparse approximation problems, and motivated by the success of Iterative Hard Thresholding (IHT), we propose a unified method for Activation-aware Weight pruning and quantization via Projected gradient descent (AWP). Our experiments demonstrate that AWP outperforms state-of-the-art LLM pruning and quantization methods. Theoretical convergence guarantees of the proposed method for pruning are also provided.

cs.LG↗

arXiv2025

PairHuman: A High-Fidelity Photographic Dataset for Customized Dual-Person Generation

Personalized dual-person portrait customization has considerable potential applications, such as preserving emotional memories and facilitating wedding photography planning. However, the absence of a benchmark dataset hinders the pursuit of high-quality customization in dual-person portrait generation. In this paper, we propose the PairHuman dataset, which is the first large-scale benchmark dataset specifically designed for generating dual-person portraits that meet high photographic standards. The PairHuman dataset contains more than 100K images that capture a variety of scenes, attire, and dual-person interactions, along with rich metadata, including detailed image descriptions, person localization, human keypoints, and attribute tags. We also introduce DHumanDiff, which is a baseline specifically crafted for dual-person portrait generation that features enhanced facial consistency and simultaneously balances in personalized person generation and semantic-driven scene creation. Finally, the experimental results demonstrate that our dataset and method produce highly customized portraits with superior visual quality that are tailored to human preferences. Our dataset is publicly available at https://github.com/annaoooo/PairHuman.

cs.CV↗

arXiv2025

Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models

Large Language Models (LLMs) exhibit impressive capabilities, but remain susceptible to a growing spectrum of safety risks, including jailbreaks, toxic content, hallucinations, and bias. Existing defenses often address only a single threat type or resort to rigid outright rejection, sacrificing user experience and failing to generalize across diverse and novel attacks. This paper introduces Adversarial Scenario Extrapolation (ASE), a novel inference-time computation framework that leverages Chain-of-Thought (CoT) reasoning to simultaneously enhance LLM robustness and seamlessness. ASE guides the LLM through a self-generative process of contemplating potential adversarial scenarios and formulating defensive strategies before generating a response to the user query. Comprehensive evaluation on four adversarial benchmarks with four latest LLMs shows that ASE achieves near-zero jailbreak attack success rates and minimal toxicity, while slashing outright rejections to <4%. ASE outperforms six state-of-the-art defenses in robustness-seamlessness trade-offs, with 92-99% accuracy on adversarial Q&A and 4-10x lower bias scores. By transforming adversarial perception into an intrinsic cognitive process, ASE sets a new paradigm for secure and natural human-AI interaction.

cs.CL↗

arXiv2025

FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction

Controlling the spatial and semantic structure of diffusion-generated images remains a challenge. Existing methods like ControlNet rely on handcrafted condition maps and retraining, limiting flexibility and generalization. Inversion-based approaches offer stronger alignment but incur high inference cost due to dual-path denoising. We present FreeControl, a training-free framework for semantic structural control in diffusion models. Unlike prior methods that extract attention across multiple timesteps, FreeControl performs one-step attention extraction from a single, optimally chosen key timestep and reuses it throughout denoising. This enables efficient structural guidance without inversion or retraining. To further improve quality and stability, we introduce Latent-Condition Decoupling (LCD): a principled separation of the key timestep and the noised latent used in attention extraction. LCD provides finer control over attention quality and eliminates structural artifacts. FreeControl also supports compositional control via reference images assembled from multiple sources - enabling intuitive scene layout design and stronger prompt alignment. FreeControl introduces a new paradigm for test-time control, enabling structurally and semantically aligned, visually coherent generation directly from raw images, with the flexibility for intuitive compositional design and compatibility with modern diffusion models at approximately 5 percent additional cost.

cs.CV↗

arXiv2025

Iterative Foundation Model Fine-Tuning on Multiple Rewards

Fine-tuning foundation models has emerged as a powerful approach for generating objects with specific desired properties. Reinforcement learning (RL) provides an effective framework for this purpose, enabling models to generate outputs that maximize a given reward function. However, in many applications such as text generation and drug discovery, it can be suboptimal to optimize using a single reward signal, as multiple evaluation criteria are often necessary. This paper proposes a novel reinforcement learning-based method for fine-tuning foundation models using multiple reward signals. By employing an iterative fine-tuning strategy across these rewards, our approach generalizes state-of-the-art RL-based methods. We further provide a theoretical analysis that offers insights into the performance of multi-reward RL fine-tuning. Experimental results across diverse domains including text, biological sequence, and small molecule generation, demonstrate the effectiveness of the proposed algorithm compared to state-of-the-art baselines.

cs.LG↗

arXiv2025

A Scenario-Based Approach for Stochastic Economic Model Predictive Control with an Expected Shortfall Constraint

This paper presents a novel approach to stochastic economic model predictive control (SEMPC) that minimizes average economic cost while satisfying an empirical expected shortfall (EES) constraint to manage risk. A new scenario-based problem formulation ensuring controlled risk with high confidence while minimizing the average cost is introduced. The probabilistic guarantees is dependent on the number of support elements over the entire input domain, which is difficult to find for high-dimensional systems. A heuristic algorithm is proposed to find the number of support elements. Finally, an efficient method is presented to reduce the computational complexity of the SEMPC problem with an EES constraint. The approach is validated on a water distribution network, showing its effectiveness in balancing performance and risk.

eess.SY↗

arXiv2025

PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMs

Existing LLM-based role-playing methods often rely on superficial textual descriptions or simplistic metrics, inadequately modeling both intrinsic and extrinsic character dimensions. Additionally, they typically simulate character memory with implicit model knowledge or basic retrieval augment generation without explicit memory alignment, compromising memory consistency. The two issues weaken reliability of role-playing LLMs in several applications, such as trustworthy social simulation. To address these limitations, we propose PsyMem, a novel framework integrating fine-grained psychological attributes and explicit memory control for role-playing. PsyMem supplements textual descriptions with 26 psychological indicators to detailed model character. Additionally, PsyMem implements memory alignment training, explicitly trains the model to align character's response with memory, thereby enabling dynamic memory-controlled responding during inference. By training Qwen2.5-7B-Instruct on our specially designed dataset (including 5,414 characters and 38,962 dialogues extracted from novels), the resulting model, termed as PsyMem-Qwen, outperforms baseline models in role-playing, achieving the best performance in human-likeness and character fidelity.

cs.CL↗

arXiv2025

LouisKV: Efficient KV Cache Retrieval for Long Input-Output Sequences

While Key-Value (KV) cache succeeds in reducing redundant computations in auto-regressive models, it introduces significant memory overhead, limiting its practical deployment in long-sequence scenarios. Existing KV retrieval methods mitigate this by dynamically retaining only a subset of KV entries on the GPU. However, they still suffer from notable efficiency and accuracy bottlenecks due to per-token retrieval and coarse-grained page-level KV management, especially in long-output reasoning scenarios. With the emergence of large reasoning models, efficiently handling such scenarios has become increasingly important. To address this issue, we present two key observations: (1) critical KVs exhibit strong temporal locality during decoding, and (2) these KVs exhibit distinct distribution patterns across the input prompt and generated output. Building on these observations, we propose LouisKV, an efficient KV cache retrieval framework designed for various long-sequence scenarios. Specifically, LouisKV introduces a semantic-aware retrieval strategy leveraging temporal locality to trigger retrieval only at semantic boundaries, drastically reducing computation and data transfer overhead. LouisKV also designs a decoupled, fine-grained management scheme that tailors differentiated strategies for input and output sequences to create retrieval units that better match the model's attention patterns, enabling precise identification of critical KVs. Furthermore, to boost efficiency, LouisKV incorporates several kernel-level optimizations, including custom Triton and CUDA kernels to accelerate the KV clustering and retrieval. Evaluations show that LouisKV achieves up to 4.7$\times$ speedup over state-of-the-art KV retrieval methods while maintaining near-lossless accuracy across diverse long-sequence tasks, including long-input short-output, short-input long-output, and long-input long-output scenarios.

cs.LG↗

arXiv2025

Peransformer: Improving Low-informed Expressive Performance Rendering with Score-aware Discriminator

Highly-informed Expressive Performance Rendering (EPR) systems transform music scores with rich musical annotations into human-like expressive performance MIDI files. While these systems have achieved promising results, the availability of detailed music scores is limited compared to MIDI files and are less flexible to work with using a digital audio workstation (DAW). Recent advancements in low-informed EPR systems offer a more accessible alternative by directly utilizing score-derived MIDI as input, but these systems often exhibit suboptimal performance. Meanwhile, existing works are evaluated with diverse automatic metrics and data formats, hindering direct objective comparisons between EPR systems. In this study, we introduce Peransformer, a transformer-based low-informed EPR system designed to bridge the gap between low-informed and highly-informed EPR systems. Our approach incorporates a score-aware discriminator that leverages the underlying score-derived MIDI files and is trained on a score-to-performance paired, note-to-note aligned MIDI dataset. Experimental results demonstrate that Peransformer achieves state-of-the-art performance among low-informed systems, as validated by subjective evaluations. Furthermore, we extend existing automatic evaluation metrics for EPR systems and introduce generalized EPR metrics (GEM), enabling more direct, accurate, and reliable comparisons across EPR systems.

cs.SD↗

arXiv2025

OWL: Overcoming Window Length-Dependence in Speculative Decoding for Long-Context Inputs

Speculative decoding promises faster inference for large language models (LLMs), yet existing methods fail to generalize to real-world settings. Benchmarks typically assume short contexts (e.g., 2K tokens), whereas practical workloads involve long contexts. We find current approaches degrade severely with long contexts; for instance, EAGLE3 even slows down the generation speed by 0.81x. We address these limitations by releasing a new long-context benchmark (LongSpecBench) and introducing a novel model (OWL). OWL achieves about 5x higher acceptance length than EAGLE3 on long-context inputs through three innovations: (1) an LSTM-based drafter conditioned only on the last-token state, making it generalize to various lengths, (2) a special token [SPEC] in the verifier that produces richer representation for drafter, and (3) a hybrid algorithm combining both tree and non-tree decoding methods. We release all code and datasets to advance future research.

cs.CL↗

arXiv2025

Disentangling Score Content and Performance Style for Joint Piano Rendering and Transcription

Expressive performance rendering (EPR) and automatic piano transcription (APT) are fundamental yet inverse tasks in music information retrieval: EPR generates expressive performances from symbolic scores, while APT recovers scores from performances. Despite their dual nature, prior work has addressed them independently. In this paper we propose a unified framework that jointly models EPR and APT by disentangling note-level score content and global performance style representations from both paired and unpaired data. Our framework is built on a transformer-based sequence-to-sequence architecture and is trained using only sequence-aligned data, without requiring fine-grained note-level alignment. To automate the rendering process while ensuring stylistic compatibility with the score, we introduce an independent diffusion-based performance style recommendation module that generates style embeddings directly from score content. This modular component supports both style transfer and flexible rendering across a range of expressive styles. Experimental results from both objective and subjective evaluations demonstrate that our framework achieves competitive performance on EPR and APT tasks, while enabling effective content-style disentanglement, reliable style transfer, and stylistically appropriate rendering. Demos are available at https://jointpianist.github.io/epr-apt/

cs.SD↗

arXiv2025

DemoGrasp: Universal Dexterous Grasping from a Single Demonstration

Universal grasping with multi-fingered dexterous hands is a fundamental challenge in robotic manipulation. While recent approaches successfully learn closed-loop grasping policies using reinforcement learning (RL), the inherent difficulty of high-dimensional, long-horizon exploration necessitates complex reward and curriculum design, often resulting in suboptimal solutions across diverse objects. We propose DemoGrasp, a simple yet effective method for learning universal dexterous grasping. We start from a single successful demonstration trajectory of grasping a specific object and adapt to novel objects and poses by editing the robot actions in this trajectory: changing the wrist pose determines where to grasp, and changing the hand joint angles determines how to grasp. We formulate this trajectory editing as a single-step Markov Decision Process (MDP) and use RL to optimize a universal policy across hundreds of objects in parallel in simulation, with a simple reward consisting of a binary success term and a robot-table collision penalty. In simulation, DemoGrasp achieves a 95% success rate on DexGraspNet objects using the Shadow Hand, outperforming previous state-of-the-art methods. It also shows strong transferability, achieving an average success rate of 84.6% across diverse dexterous hand embodiments on six unseen object datasets, while being trained on only 175 objects. Through vision-based imitation learning, our policy successfully grasps 110 unseen real-world objects, including small, thin items. It generalizes to spatial, background, and lighting changes, supports both RGB and depth inputs, and extends to language-guided grasping in cluttered scenes.

cs.RO↗

arXiv2025

TS-P$^2$CL: Plug-and-Play Dual Contrastive Learning for Vision-Guided Medical Time Series Classification

Medical time series (MedTS) classification is pivotal for intelligent healthcare, yet its efficacy is severely limited by poor cross-subject generation due to the profound cross-individual heterogeneity. Despite advances in architectural innovations and transfer learning techniques, current methods remain constrained by modality-specific inductive biases that limit their ability to learn universally invariant representations. To overcome this, we propose TS-P$^2$CL, a novel plug-and-play framework that leverages the universal pattern recognition capabilities of pre-trained vision models. We introduce a vision-guided paradigm that transforms 1D physiological signals into 2D pseudo-images, establishing a bridge to the visual domain. This transformation enables implicit access to rich semantic priors learned from natural images. Within this unified space, we employ a dual-contrastive learning strategy: intra-modal consistency enforces temporal coherence, while cross-modal alignment aligns time-series dynamics with visual semantics, thereby mitigating individual-specific biases and learning robust, domain-invariant features. Extensive experiments on six MedTS datasets demonstrate that TS-P$^2$CL consistently outperforms fourteen methods in both subject-dependent and subject-independent settings.

cs.CV↗

arXiv2025

MindRef: Mimicking Human Memory for Hierarchical Reference Retrieval with Fine-Grained Location Awareness

When completing knowledge-intensive tasks, humans sometimes need an answer and a corresponding reference passage for auxiliary reading. Previous methods required obtaining pre-segmented article chunks through additional retrieval models. This paper explores leveraging the parameterized knowledge stored during the pre-training phase of large language models (LLMs) to recall reference passage from any starting position independently. We propose a two-stage framework that simulates the scenario of humans recalling easily forgotten references. Initially, the LLM is prompted to recall document title identifiers to obtain a coarse-grained document set. Then, based on the acquired coarse-grained document set, it recalls fine-grained passage. In the two-stage recall process, we use constrained decoding to ensure that content outside of the stored documents is not generated. To increase speed, we only recall a short prefix in the second stage, and then locate its position to retrieve a complete passage. Experiments on KILT knowledge-sensitive tasks have verified that LLMs can independently recall reference passage locations in various task forms, and the obtained reference significantly assists downstream tasks.

cs.CL↗

arXiv2025

Task-Agnostic Learnable Weighted-Knowledge Base Scheme for Robust Semantic Communications

With the emergence of diverse and massive data in the upcoming sixth-generation (6G) networks, the task-agnostic semantic communication system is regarded to provide robust intelligent services. In this paper, we propose a task-agnostic learnable weighted-knowledge base semantic communication (TALSC) framework for robust image transmission to address the real-world heterogeneous data bias in KB, including label flipping noise and class imbalance. The TALSC framework incorporates a sample confidence module (SCM) as meta-learner and the semantic coding networks as learners. The learners are updated based on the empirical knowledge provided by the learnable weighted-KB (LW-KB). Meanwhile, the meta-learner evaluates the significance of samples according to the task loss feedback, and adjusts the update strategy of learners to enhance the robustness in semantic recovery for unknown tasks. To strike a balance between SCM parameters and precision of significance evaluation, we design an SCM-grid extension (SCM-GE) approach by embedding the Kolmogorov-Arnold networks (KAN) within SCM, which leverages the concept of spline refinement in KAN and enables scalable SCM with customizable granularity without retraining. Simulations demonstrate that the TALSC framework effectively mitigates the effects of flipping noise and class imbalance in task-agnostic image semantic communication, achieving at least 12% higher semantic recovery accuracy (SRA) and multi-scale structural similarity (MS-SSIM) compared to state-of-the-art methods.

cs.IT↗

arXiv2025

Causal Inference in Longitudinal Data under Unknown Interference

In longitudinal studies where units are embedded in space or a social network, interference may arise, meaning that a unit's outcome can depend on treatment histories of others. The presence of interference poses significant challenges for causal inference, particularly when the interference structure -- how a unit's outcome responds to others' influences -- is complex, heterogeneous, and unknown to researchers. This paper develops a general framework for identifying and estimating both direct and spillover effects of treatment histories under minimal assumptions about the interference structure. We introduce a class of causal estimands that capture the effects of treatment histories at any specified proximity level and show that they can be represented by a modified marginal structural model. Under sequential exchangeability, these estimands are identifiable and can be estimated using inverse probability weighting. We derive conditions for consistency and asymptotic normality of the estimators and provide procedures for constructing asymptotically conservative confidence intervals. The method's utility is demonstrated through applications in both social science and biomedical settings.

stat.ME↗

arXiv2025

Simple o3: Towards Interleaved Vision-Language Reasoning

Multimodal Large Language Models (MLLMs) have shown impressive performance on vision-language tasks, but their long Chain-of-Thought (CoT) capabilities in multimodal scenarios remain underexplored. Inspired by OpenAI's o3 model, which emulates human-like ''thinking with image'' through iterative visual transformations and linguistic reasoning, we propose Simple o3, an end-to-end framework that integrates dynamic tool interactions (e.g., cropping, zooming, and reusing) into interleaved vision-language reasoning via supervised fine-tuning (SFT). Our approach features a scalable data synthesis pipeline that generates high-quality interleaved vision-language reasoning chains via an ''observe-reason-act'' cycle, complete with executable visual operations and rigorous verification, yielding the open-source TWI-Tools-146K dataset. Experimental results demonstrate Simple o3's superior performance on diverse benchmarks, outperforming existing approaches. By combining enhanced reasoning capabilities, Simple o3 establishes a powerful yet computationally affordable paradigm for advancing multimodal reasoning. Remarkably, we provide the first in-depth analysis of different interleaved reasoning strategies, offering insights into their impact on model performance. We found that by introducing additional visual tokens for interleaved vision-language reasoning, reusing and magnifying the original image significantly improves the model's visual reasoning and fine-grained perception, while image cropping based on precise visual grounding allows the model to effectively focus on key entities or regions, further enhancing its capabilities.

cs.CV↗

arXiv2025

Multi-Class Stackelberg Games for the Co-Design of Networked Systems

We investigate a co-design problem, encompassing simultaneous design of system infrastructure and control, through a game-theoretical framework. To this end, we propose the co-design problem as a two-layer hierarchical strategic interaction. At the upper layer, a leader (or multiple leaders) determines system design parameters, while at the lower layer, a follower (or multiple followers) optimizes the control strategy. To capture this hierarchy, we propose four novel classes of Stackelberg games that integrate diverse strategic behaviors, including combinations of cooperative and non-cooperative interactions across two different layers. Notably, the leaders' interactions are represented using a normal-form game, whereas the followers' interactions are modeled by different games (dynamic games in discrete time). These distinct game structures result in a Stackelberg game that accommodates different game types per layer, and/or supports heterogeneous strategic behaviors involving cooperation and non-cooperation simultaneously. Learning algorithms using the best-response dynamics are used to solve the game problems when considering a discrete strategic space for the leaders. The efficacy of the proposed approach is demonstrated through an application to the co-design of the Barcelona drinking water network.

eess.SY↗