arXiv subjects

Yang Liu

Publications and source records attributed to Yang Liu.

At least 955 records · Page 53Linked to original sources

arXiv2025

InteractMove: Text-Controlled Human-Object Interaction Generation in 3D Scenes with Movable Objects

We propose a novel task of text-controlled human object interaction generation in 3D scenes with movable objects. Existing human-scene interaction datasets suffer from insufficient interaction categories and typically only consider interactions with static objects (do not change object positions), and the collection of such datasets with movable objects is difficult and costly. To address this problem, we construct the InteractMove dataset for Movable Human-Object Interaction in 3D Scenes by aligning existing human object interaction data with scene contexts, featuring three key characteristics: 1) scenes containing multiple movable objects with text-controlled interaction specifications (including same-category distractors requiring spatial and 3D scene context understanding), 2) diverse object types and sizes with varied interaction patterns (one-hand, two-hand, etc.), and 3) physically plausible object manipulation trajectories. With the introduction of various movable objects, this task becomes more challenging, as the model needs to identify objects to be interacted with accurately, learn to interact with objects of different sizes and categories, and avoid collisions between movable objects and the scene. To tackle such challenges, we propose a novel pipeline solution. We first use 3D visual grounding models to identify the interaction object. Then, we propose a hand-object joint affordance learning to predict contact regions for different hand joints and object parts, enabling accurate grasping and manipulation of diverse objects. Finally, we optimize interactions with local-scene modeling and collision avoidance constraints, ensuring physically plausible motions and avoiding collisions between objects and the scene. Comprehensive experiments demonstrate our method's superiority in generating physically plausible, text-compliant interactions compared to existing approaches.

cs.CV↗

arXiv2025

Sparse-Up: Learnable Sparse Upsampling for 3D Generation with High-Fidelity Textures

The creation of high-fidelity 3D assets is often hindered by a 'pixel-level pain point': the loss of high-frequency details. Existing methods often trade off one aspect for another: either sacrificing cross-view consistency, resulting in torn or drifting textures, or remaining trapped by the resolution ceiling of explicit voxels, forfeiting fine texture detail. In this work, we propose Sparse-Up, a memory-efficient, high-fidelity texture modeling framework that effectively preserves high-frequency details. We use sparse voxels to guide texture reconstruction and ensure multi-view consistency, while leveraging surface anchoring and view-domain partitioning to break through resolution constraints. Surface anchoring employs a learnable upsampling strategy to constrain voxels to the mesh surface, eliminating over 70% of redundant voxels present in traditional voxel upsampling. View-domain partitioning introduces an image patch-guided voxel partitioning scheme, supervising and back-propagating gradients only on visible local patches. Through these two strategies, we can significantly reduce memory consumption during high-resolution voxel training without sacrificing geometric consistency, while preserving high-frequency details in textures.

cs.CV↗

arXiv2025

Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation

Vision-language model (VLM) based GUI agents show promise for automating complex desktop and mobile tasks, but face significant challenges in applying reinforcement learning (RL): (1) slow multi-turn interactions with GUI environments for policy rollout, and (2) insufficient high-quality agent-environment interactions for policy learning. To address these challenges, we propose DART, a Decoupled Agentic RL Training framework for GUI agents, which coordinates heterogeneous modules in a highly decoupled manner. DART separates the training system into four asynchronous modules: environment cluster, rollout service, data manager, and trainer. This design enables non-blocking communication, asynchronous training, rollout-wise trajectory sampling, and per-worker model synchronization, significantly improving the system efficiency: 1.6*GPU utilization for rollout, 1.9* training throughput, and 5.5* environment utilization. To facilitate effective learning from abundant samples, we introduce an adaptive data curation scheme: (1) pre-collecting successful trajectories for challenging tasks to supplement sparse success in online sampling; (2) dynamically adjusting rollout numbers and trajectory lengths based on task difficulty; (3) training selectively on high-entropy steps to prioritize critical decisions; (4) stabilizing learning via truncated importance sampling for policy mismatch between policy rollout and updating. On the OSWorld benchmark, DART-GUI-7B achieves a 42.13% task success rate, a 14.61% absolute gain over the base model, and 7.34% higher than open-source SOTA. We will fully open-source our training framework, data, and model checkpoints via computer-use-agents.github.io/dart-gui, which we believe is a timely contribution to the open-source community of agentic RL training.

cs.LG↗

arXiv2025

GeoDANO: Geometric VLM with Domain Agnostic Vision Encoder

We introduce GeoDANO, a geometric vision-language model (VLM) with a domain-agnostic vision encoder, for solving plane geometry problems. Although VLMs have been employed for solving geometry problems, their ability to recognize geometric features remains insufficiently analyzed. To address this gap, we propose a benchmark that evaluates the recognition of visual geometric features, including primitives such as dots and lines, and relations such as orthogonality. Our preliminary study shows that vision encoders often used in general-purpose VLMs, e.g., OpenCLIP, fail to detect these features and struggle to generalize across domains. To overcome the limitation, we develop GeoCLIP, a CLIP-based model trained on synthetic geometric diagram--caption pairs. Benchmark results show that GeoCLIP outperforms existing vision encoders in recognizing geometric features. We then propose our VLM, GeoDANO, which augments GeoCLIP with a domain adaptation strategy for unseen diagram styles. GeoDANO outperforms specialized methods for plane geometry problems and GPT-4o on MathVerse. The implementation is available at https://github.com/ml-postech/GeoDANO.

cs.CV↗

arXiv2025

MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) have demonstrated significant advances across numerous vision-language tasks. MLLMs have shown promising capability in aligning visual and textual modalities, allowing them to process image-text pairs with clear and explicit meanings. However, resolving the inherent ambiguities present in real-world language and visual contexts remains a challenge. Existing multimodal benchmarks typically overlook linguistic and visual ambiguities, relying mainly on unimodal context for disambiguation and thus failing to exploit the mutual clarification potential between modalities. To bridge this gap, we introduce MUCAR, a novel and challenging benchmark designed explicitly for evaluating multimodal ambiguity resolution across multilingual and cross-modal scenarios. MUCAR includes first a multilingual dataset where ambiguous textual expressions are uniquely resolved by corresponding visual contexts, and second a dual-ambiguity dataset that systematically pairs ambiguous images with ambiguous textual contexts, with each combination carefully constructed to yield a single, clear interpretation through mutual disambiguation. Extensive evaluations involving 19 state-of-the-art multimodal models--encompassing both open-source and proprietary architectures--reveal substantial gaps compared to human-level performance, highlighting the need for future research into more sophisticated cross-modal ambiguity comprehension methods, further pushing the boundaries of multimodal reasoning.

cs.CL↗

arXiv2025

Resource Consumption Red-Teaming for Large Vision-Language Models

Resource Consumption Attacks (RCAs) have emerged as a significant threat to the deployment of Large Language Models (LLMs). With the integration of vision modalities, additional attack vectors exacerbate the risk of RCAs in large vision-language models (LVLMs). However, existing red-teaming studies have mainly overlooked visual inputs as a potential attack surface, resulting in insufficient mitigation strategies against RCAs in LVLMs. To address this gap, we propose RECITE ($\textbf{Re}$source $\textbf{C}$onsumpt$\textbf{i}$on Red-$\textbf{Te}$aming for LVLMs), the first approach for exploiting visual modalities to trigger unbounded RCAs red-teaming. First, we present $\textit{Vision Guided Optimization}$, a fine-grained pixel-level optimization to obtain \textit{Output Recall Objective} adversarial perturbations, which can induce repeating output. Then, we inject the perturbations into visual inputs, triggering unbounded generations to achieve the goal of RCAs. Empirical results demonstrate that RECITE increases service response latency by over 26 $\uparrow$, resulting in an additional 20\% increase in GPU utilization and memory consumption. Our study reveals security vulnerabilities in LVLMs and establishes a red-teaming framework that can facilitate the development of future defenses against RCAs.

cs.CR↗

arXiv2025

Introducing Multimodal Paradigm for Learning Sleep Staging PSG via General-Purpose Model

Sleep staging is essential for diagnosing sleep disorders and assessing neurological health. Existing automatic methods typically extract features from complex polysomnography (PSG) signals and train domain-specific models, which often lack intuitiveness and require large, specialized datasets. To overcome these limitations, we introduce a new paradigm for sleep staging that leverages large multimodal general-purpose models to emulate clinical diagnostic practices. Specifically, we convert raw one-dimensional PSG time-series into intuitive two-dimensional waveform images and then fine-tune a multimodal large model to learn from these representations. Experiments on three public datasets (ISRUC, MASS, SHHS) demonstrate that our approach enables general-purpose models, without prior exposure to sleep data, to acquire robust staging capabilities. Moreover, explanation analysis reveals our model learned to mimic the visual diagnostic workflow of human experts for sleep staging by PSG images. The proposed method consistently outperforms state-of-the-art baselines in accuracy and robustness, highlighting its efficiency and practical value for medical applications. The code for the signal-to-image pipeline and the PSG image dataset will be released.

eess.SP↗

arXiv2025

LLM Assisted Alpha Fairness for 6 GHz WiFi and NR_U Coexistence: An Agentic Orchestrator for Throughput, Energy, and SLA

Unlicensed 6GHz is becoming a primary workhorse for high-capacity access, with Wi-Fi and 5G NR-U competing for the same channels under listen-before-talk (LBT) rules. Operating in this regime requires decisions that jointly trade throughput, energy, and service-level objectives while remaining safe and auditable. We present an agentic controller that separates {policy} from {execution}. At the start of each scheduling epoch the agent summarizes telemetry (per-channel busy and baseline LBT failure; per-user CQI, backlog, latency, battery, priority, and power mode) and invokes a large language model (LLM) to propose a small set of interpretable knobs: a fairness index α, per-channel duty-cycle caps for Wi-Fi/NR-U, and class weights. A deterministic optimizer then enforces feasibility and computes an α-fair allocation that internalizes LBT losses and energy cost; malformed or unsafe policies are clamped and fall back to a rule baseline. In a 6GHz simulator with two 160MHz channels and mixed Wi-Fi/NR-U users, LLM-assisted policies consistently improve energy efficiency while keeping throughput competitive with a strong rule baseline. One LLM lowers total energy by 35.3% at modest throughput loss, and another attains the best overall trade-off, finishing with higher total bits (+3.5%) and higher bits/J (+12.2%) than the baseline. We release code, per-epoch logs, and plotting utilities to reproduce all figures and numbers, illustrating how transparent, policy-level LLM guidance can safely improve wireless coexistence.

eess.SY↗

arXiv2025

Inference-Time Scaling for Generalist Reward Modeling

Reinforcement learning (RL) has been widely adopted in post-training for large language models (LLMs) at scale. Recently, the incentivization of reasoning capabilities in LLMs from RL indicates that $\textit{proper learning methods could enable effective inference-time scalability}$. A key challenge of RL is to obtain accurate reward signals for LLMs in various domains beyond verifiable questions or artificial rules. In this work, we investigate how to improve reward modeling (RM) with more inference compute for general queries, i.e. the $\textbf{inference-time scalability of generalist RM}$, and further, how to improve the effectiveness of performance-compute scaling with proper learning methods. For the RM approach, we adopt pointwise generative reward modeling (GRM) to enable flexibility for different input types and potential for inference-time scaling. For the learning method, we propose Self-Principled Critique Tuning (SPCT) to foster scalable reward generation behaviors in GRMs through online RL, to generate principles adaptively and critiques accurately, resulting in $\textbf{DeepSeek-GRM}$ models. Furthermore, for effective inference-time scaling, we use parallel sampling to expand compute usage, and introduce a meta RM to guide voting process for better scaling performance. Empirically, we show that SPCT significantly improves the quality and scalability of GRMs, outperforming existing methods and models in various RM benchmarks without severe biases, and could achieve better performance compared to training-time scaling. DeepSeek-GRM still meets challenges in some tasks, which we believe can be addressed by future efforts in generalist reward systems. The models are released at Hugging Face and ModelScope.

cs.CL↗

arXiv2025

Shaping Initial State Prevents Modality Competition in Multi-modal Fusion: A Two-stage Scheduling Framework via Fast Partial Information Decomposition

Multi-modal fusion often suffers from modality competition during joint training, where one modality dominates the learning process, leaving others under-optimized. Overlooking the critical impact of the model's initial state, most existing methods address this issue during the joint learning stage. In this study, we introduce a two-stage training framework to shape the initial states through unimodal training before the joint training. First, we propose the concept of Effective Competitive Strength (ECS) to quantify a modality's competitive strength. Our theoretical analysis further reveals that properly shaping the initial ECS by unimodal training achieves a provably tighter error bound. However, ECS is computationally intractable in deep neural networks. To bridge this gap, we develop a framework comprising two core components: a fine-grained computable diagnostic metric and an asynchronous training controller. For the metric, we first prove that mutual information(MI) is a principled proxy for ECS. Considering MI is induced by per-modality marginals and thus treats each modality in isolation, we further propose FastPID, a computationally efficient and differentiable solver for partial information decomposition, which decomposes the joint distribution's information into fine-grained measurements: modality-specific uniqueness, redundancy, and synergy. Guided by these measurements, our asynchronous controller dynamically balances modalities by monitoring uniqueness and locates the ideal initial state to start joint training by tracking peak synergy. Experiments on diverse benchmarks demonstrate that our method achieves state-of-the-art performance. Our work establishes that shaping the pre-fusion models' initial state is a powerful strategy that eases competition before it starts, reliably unlocking synergistic multi-modal fusion.

cs.LG↗

arXiv2025

Chiral Integrable Boundary States in the SU(4) Alternating Spin Chain

Previously identified integrable boundary states in ABJM theory are exclusively achiral. This paper presents the first chiral integrable boundary states in the $SU(4)$ alternating spin chain from the planar two-loop dilatation operator in the scalar sector. Utilizing a sufficient condition for the untwisted integrable condition, we identify specific two-site and four-site basis boundary states as chiral integrable states. Numerical evidence indicates that other basis states are unlikely to be chiral integrable. Furthermore, we compute the overlaps between these chiral integrable basis states and on-shell Bethe eigenstates.

hep-th↗

arXiv2025

MemOrb: A Plug-and-Play Verbal-Reinforcement Memory Layer for E-Commerce Customer Service

Large Language Model-based agents(LLM-based agents) are increasingly deployed in customer service, yet they often forget across sessions, repeat errors, and lack mechanisms for continual self-improvement. This makes them unreliable in dynamic settings where stability and consistency are critical. To better evaluate these properties, we emphasize two indicators: task success rate as a measure of overall effectiveness, and consistency metrics such as Pass$^k$ to capture reliability across multiple trials. To address the limitations of existing approaches, we propose MemOrb, a lightweight and plug-and-play verbal reinforcement memory layer that distills multi-turn interactions into compact strategy reflections. These reflections are stored in a shared memory bank and retrieved to guide decision-making, without requiring any fine-tuning. Experiments show that MemOrb significantly improves both success rate and stability, achieving up to a 63 percentage-point gain in multi-turn success rate and delivering more consistent performance across repeated trials. Our results demonstrate that structured reflection is a powerful mechanism for enhancing long-term reliability of frozen LLM agents in customer service scenarios.

cs.CL↗

arXiv2025

Large Language Models for Cyber Security: A Systematic Literature Review

The rapid advancement of Large Language Models (LLMs) has opened up new opportunities for leveraging artificial intelligence in a variety of application domains, including cybersecurity. As the volume and sophistication of cyber threats continue to grow, there is an increasing need for intelligent systems that can automatically detect vulnerabilities, analyze malware, and respond to attacks. In this survey, we conduct a comprehensive review of the literature on the application of LLMs in cybersecurity~(LLM4Security). By comprehensively collecting over 40K relevant papers and systematically analyzing 185 papers from top security and software engineering venues, we aim to provide a holistic view of how LLMs are being used to solve diverse problems across the cybersecurity domain. Through our analysis, we identify several key findings. First, we observe that LLMs are being applied to an expanding range of cybersecurity tasks, including vulnerability detection, malware analysis, and network intrusion detection. Second, we analyze application trends of different LLM architectures (such as encoder-only, encoder-decoder, and decoder-only) across security domains. Third, we identify increasingly sophisticated techniques for adapting LLMs to cybersecurity, such as advanced fine-tuning, prompt engineering, and external augmentation strategies. A significant emerging trend is the use of LLM-based autonomous agents, which represent a paradigm shift from single-task execution to orchestrating complex, multi-step security workflows.

cs.CR↗

arXiv2025

Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle

In recent years, training methods centered on Reinforcement Learning (RL) have markedly enhanced the reasoning and alignment performance of Large Language Models (LLMs), particularly in understanding human intents, following user instructions, and bolstering inferential strength. Although existing surveys offer overviews of RL augmented LLMs, their scope is often limited, failing to provide a comprehensive summary of how RL operates across the full lifecycle of LLMs. We systematically review the theoretical and practical advancements whereby RL empowers LLMs, especially Reinforcement Learning with Verifiable Rewards (RLVR). First, we briefly introduce the basic theory of RL. Second, we thoroughly detail application strategies for RL across various phases of the LLM lifecycle, including pre-training, alignment fine-tuning, and reinforced reasoning. In particular, we emphasize that RL methods in the reinforced reasoning phase serve as a pivotal driving force for advancing model reasoning to its limits. Next, we collate existing datasets and evaluation benchmarks currently used for RL fine-tuning, spanning human-annotated datasets, AI-assisted preference data, and program-verification-style corpora. Subsequently, we review the mainstream open-source tools and training frameworks available, providing clear practical references for subsequent research. Finally, we analyse the future challenges and trends in the field of RL-enhanced LLMs. This survey aims to present researchers and practitioners with the latest developments and frontier trends at the intersection of RL and LLMs, with the goal of fostering the evolution of LLMs that are more intelligent, generalizable, and secure.

cs.CL↗

arXiv2025

Probability density function for dispersion measure of fast radio burst from extragalactic medium

Fast Radio Bursts (FRBs) have emerged as powerful probes in cosmology. An optimized method was recently proposed to extract the cosmic baryon density from localized FRBs by maximizing the joint likelihood function of the extragalactic dispersion measure ($\mathrm{DM}_{\mathrm{ext}}$). In this paper, we identify a crucial factor that was omitted in the probability density function (PDF) for $\mathrm{DM}_{\mathrm{ext}}$ in that method. Using simulated FRB data, we demonstrate that neglecting this factor leads to a systematic bias in the inferred cosmic baryon density, with deviations exceeding the $1σ$ confidence level. This highlights the necessity of including the missing factor for reliable cosmological applications of FRBs. Furthermore, applying our corrected PDF to a sample of 88 real localized FRBs, we find that the baryon density inferred with the original PDF is inconsistent with the Planck 2018 CMB results, whereas our corrected PDF yields excellent agreement.

astro-ph.CO↗

arXiv2025

Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony

In this paper, we propose a novel framework, Combo, for harmonious co-speech holistic 3D human motion generation and efficient customizable adaption. In particular, we identify that one fundamental challenge as the multiple-input-multiple-output (MIMO) nature of the generative model of interest. More concretely, on the input end, the model typically consumes both speech signals and character guidance (e.g., identity and emotion), which not only poses challenge on learning capacity but also hinders further adaptation to varying guidance; on the output end, holistic human motions mainly consist of facial expressions and body movements, which are inherently correlated but non-trivial to coordinate in current data-driven generation process. In response to the above challenge, we propose tailored designs to both ends. For the former, we propose to pre-train on data regarding a fixed identity with neutral emotion, and defer the incorporation of customizable conditions (identity and emotion) to fine-tuning stage, which is boosted by our novel X-Adapter for parameter-efficient fine-tuning. For the latter, we propose a simple yet effective transformer design, DU-Trans, which first divides into two branches to learn individual features of face expression and body movements, and then unites those to learn a joint bi-directional distribution and directly predicts combined coefficients. Evaluated on BEAT2 and SHOW datasets, Combo is highly effective in generating high-quality motions but also efficient in transferring identity and emotion. Project website: \href{https://xc-csc101.github.io/combo/}{Combo}.

cs.CV↗

arXiv2025

Decentralized Estimation and Control for Leader-Follower Networked Systems with Asymmetric Information Structure

In this paper, the decentralized estimation and linear quadratic (LQ) control problem for a leader-follower networked system (LFNS) is studied from the perspective of asymmetric information. Specifically, for a leader-follower network, the follower agent will be affected by the leader agent, while the follower agent will not affect the leader agent. Hence, the information sets accessed by the control variables of the leader agent and the follower agent are asymmetric, which will bring essential difficulties in finding the optimal control strategy. To this end, the orthogonal decomposition method is adopted to achieve the main results. The main contributions of this paper can be summarized as follows: Firstly, the optimal iterative estimation is derived using the conditional independence property established in this paper. Secondly, the optimal decentralized control strategy is derived by decoupling the forward-backward stochastic difference equations (FBSDEs), based on the derived optimal iterative estimation. Thirdly, the necessary and sufficient conditions for the feedback stabilization of the LFNS in infinite-horizon are derived. Finally, the proposed theoretical results are applied to solve the decentralized control problem of a leader-follower autonomous underwater vehicle (LF-AUV) system. The optimal control inputs for the AUVs are provided, and simulation results verify the effectiveness of the obtained results.

math.OC↗

arXiv2025

Application of the Quantum Approximate Optimization Algorithm in Solving the Total Domination Problem

Recent advancements in quantum computing have spurred substantial research into the application of quantum algorithms to combinatorial optimization problems. Among these challenges, the Total Domination Problem (TDP) emerges as a classic and critical paradigm in the field. For a graph G(V, E), TDP entails finding a minimal subset D subset of V that contains no isolated vertices, where every vertex not in D has at least one neighbor in D. TDP finds extensive applications across domains such as computer networks, social networks, and communications. Since the latter half of the last century, research efforts have focused on establishing its NP-completeness and developing solution algorithms, which have become foundational to combinatorial mathematics. Despite this rich history, the application of quantum algorithms to TDP remains largely underexplored. In this study, we present a pioneering application of the Quantum Approximate Optimization Algorithm (QAOA) to tackle TDP, evaluating its efficacy across a diverse set of parameters. This paper proves that the upper bound on the number of qubits required to solve TDP is 2|V| + |V| log_2( (2|E|)/|V| - 1 ). Our experimental findings demonstrate that QAOA is effective in addressing TDP: under most parameter combinations, it successfully computes a valid total dominating set (TDS). However, the algorithm's performance in identifying the optimal TDS is contingent upon specific parameter choices, revealing a significant bias in the distribution of effective parameter points. This research contributes valuable insights into the potential of quantum algorithms for solving TDP and lays a solid groundwork for future investigations in this area.

quant-ph↗