Search arXiv⌕ Search

arXiv subjects

Qi Zhang

Publications and source records attributed to Qi Zhang.

At least 127 records · Page 7Linked to original sources
arXiv2026

DeepSAGE: Stage-Aware Reinforcement Learning for Structured CBT Counseling Dialogue

Large Language Model (LLM)-based counseling agents can generate fluent and supportive responses, but they often lack the structured, goal-directed progression required to conduct a coherent therapeutic session. We present DeepSAGE (Strategic AI Guidance Engine), a hybrid LLM--Deep Reinforcement Learning (DRL) framework for stage-aware counseling dialogue grounded in the first session of Cognitive Behavioral Therapy (CBT). DeepSAGE represents the session as eleven stages with explicit therapeutic objectives, with an external controller determines stage completion and the DRL model selects therapeutic intentions that guide LLM response generation. We evaluate DeepSAGE against six retrieval-, prompting-, stage-, and policy-based alternatives. DeepSAGE elicits higher simulated client engagement and openness and achieves the strongest balance of stage-goal completion and dialogue efficiency among stage-structured systems. Domain expert review further indicates that the generated conversations exhibit broadly plausible emotional trajectories and recognizable CBT processes. Because the evaluation relies primarily on simulated clients and model-based metrics, these findings demonstrate comparative dialogue-control improvements rather than clinical effectiveness. These results suggest that combining stage-structured dialogue with learned strategy selection is a promising approach for AI counseling, though clinical effectiveness, safety, and real-world utility require further human evaluation.

cs.AI↗
arXiv2026

Real Interference Alignment for Active IRS-Aided Systems: A Rate-Profile Learning-Based Approach

With additional spatial degrees of freedom provided by the active intelligent reflecting surface (IRS), interference alignment (IA) can be achieved at low cost. In this letter, we propose a real IA scheme for an active IRS-aided system. The proposed scheme only requires the IRS to know the instantaneous channel coefficients under the assumption of blocked direct links. To maximize the achievable sum rate subject to individual minimum rate requirements and transmission power constraints, we propose a rate-profile learning-based algorithm. The algorithm uses offline-trained achievable rate profiles to decouple the original problem into multiple feasibility subproblems, which are then solved by generalized eigenvalue decomposition. Simulation results demonstrate that our proposed algorithm outperforms the conventional weighted minimum mean square error algorithm, while requiring significantly less program execution time.

cs.IT↗
arXiv2026

Dual-Cache Latent Space Communication between Heterogeneous Language Models

Multi-agent LLM systems split work across models, so answering often requires knowledge that sits in another agent's context: a Sharer has encoded information that a Receiver needs to complete its task. They usually communicate by exchanging text, which puts autoregressive decoding on the critical path and reduces the exchange to a discrete message written without sight of the receiver's state. Recent latent protocols instead translate the sharer's key-value (KV) cache into the receiver's: C2C supports heterogeneous models but requires both to read the same input, while LCF-X removes this shared-context requirement through position-free sharer-cache pooling. Three restrictions remain: LCF-X compresses the sharer alone, supplies the same layer-local summary to every receiver position with no joint cross-layer memory to retrieve from, and assumes matched layer count and KV geometry. We introduce XKV, which lifts all three: learned-query attention pools both caches; self-attention over receiver-aligned layer tokens, with a learned layer map reconciling different depths, mixes the pooled summaries into a compact joint memory; and a shared position decoder lets every raw receiver cache position retrieve its own per-head-gated residual in the receiver's native KV geometry. Both models stay frozen and may differ in family, depth, KV-head count, head dimension, and tokenizer; only the translator is trained. Across 45 dataset-model-pair settings (six heterogeneous and three same-model ordered pairings, five datasets), XKV attains the highest macro score and best average rank, improving on LCF-X on every dataset (by 4.6 exact-match and 4.2 F1 points on ROPES) and surpassing text communication on four of the five, while training 76% fewer parameters and translating a cache pair 10.3x faster (5.8 vs. 59.9 ms); end to end, XKV is 26% faster than LCF-X and 6.8x faster than text communication.

cs.AI↗
arXiv2026

ReX-Shot: Single-Image Rephotography via Geometry- and Camera-Grounded Generation

Single-image rephotography aims to synthesize new shots of a scene from a single reference image with specified viewpoints, focal lengths, and photographic effects, which are intrinsically coupled in imaging. Existing methods typically treat these factors separately and struggle under joint control: novel-view synthesis may introduce geometric distortions under focal-length changes, while super-resolution and instruction-guided editing remain confined to 2D and cannot reliably extend detail restoration or appearance control to novel viewpoints. We attribute these limitations to imperfect single-image 3D reconstruction and the sampling limit of continuous focal-length enlargement. To reduce projection bias from geometric errors, we use implicitly transformed foundation-model features for robust target-view guidance. We further formulate focal-length enlargement as a geometry-guided super-resolution problem and exploit generative detail priors to recover details lost during sparse 3D resampling. Built on this 3D-aware generative backbone, we lift photographic-effect control from 2D filtering to 3D-aware appearance editing, preserving content consistency across viewpoints and focal lengths. These components form ReX-Shot, a geometry- and camera-grounded generative framework for single-image rephotography. To our knowledge, ReX-Shot is the first unified framework to jointly control viewpoint, focal length, and parameterized photographic effects from a single image. Experiments show that ReX-Shot outperforms representative baselines across all three controls while enabling near-real-time interactive rephotography.

cs.CV↗
arXiv2026

SocialCoach: Personalized Social Skill Learning with Agentic Tutoring and Practice

Social skills such as negotiation and leadership are crucial for personal and professional success in today's interconnected world. However, scalable and effective training remains a significant challenge due to the scarcity of expert coaching. In this work, we introduce SocialCoach, an LLM-powered agentic tutoring system for personalized social skill learning. SocialCoach constructs a theory-to-practice corpus of traceable strategies, cases, and practice scenarios, and uses this corpus for both scheduling and reflective tutoring. We formulate social practice personalization as cold-start, retrieval-constrained sequential practice scheduling. Given a learner profile, simulated proficiency state, and observed practice history, a policy produces structured prescriptions that are realized through corpus retrieval. To enhance scheduling effectiveness, we optimize complete pathways with trajectory-level GRPO using rubric-judge based pairwise preferences. Additionally, we instantiate the scheduling approach in a deployed platform with goal-driven practice and knowledge-grounded reflective tutoring. Finally, in the synthetic cold-start setting, experiment results show that SocialCoach achieves higher pathway-quality ratings than baselines in scheduling and tutoring quality. We also conduct human studies to demonstrate its usefulness for real-world social skill learning.

cs.HC↗
arXiv2026

Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning

We introduce Mobius-v0, an architecture that comprises a globally shared Memory (FFN) that stores knowledge vectors and multiple Reasoners (Self-Attn) that iteratively achieve compositional reasoning. Using hidden states as cache and carrier, reasoners repeatedly query memory for required knowledge-vectors, while the knowledge is transmitted back to reasoning operators. Through this knowledge-reasoning-separation architecture, Mobius achieves better knowledge compression and reasoning efficiency. Built upon Mobius-v0 architecture: 1) Our 7B model trained-from-scratch achieves similar downstream score as a 7B Transformer baseline with 62.6% of baseline's training data. 2) Our Intern-S2-Mobius, continually-pretrained from Qwen3.5-35B, achieves similar downstream score while delivering nearly 4x end-to-end inference speedup.

cs.AI↗
arXiv2026

HiCo-GS: Hierarchical Context Aggregation and Geometric Consistency for Octree Gaussian Splatting

Octree-based anchor Gaussian Splatting has emerged as a scalable representation for city-scale novel view synthesis, where multi-level anchors adaptively capture scene content from coarse building structures to fine architectural details. However, we identify a fundamental limitation in existing methods: cross-level feature isolation, where each level's anchor features are optimized independently with no inter-level communication, causing color drift on building facades and over-smoothing in textured regions. We present HiCo-GS, a high-fidelity reconstruction framework with two complementary modules. Cross-Level Context Aggregation (CLCA) enables bidirectional hierarchical prior injection by leveraging the octree's spatial containment structure to aggregate per-level context vectors into parent-self-child triplets, fused via a lightweight MLP with residual connection. Coarse-level structural priors flow down to inform fine-level anchors, while fine-level detail statistics feed back to prevent over-smoothing, at negligible computational overhead. Depth-Normal Geometric Consistency (DNGC) regularization enforces agreement between rendered normals and depth-derived normals through an alpha-weighted consistency loss, complemented by edge-aware smoothness losses with progressive warmup that exploit the strong planar priors ubiquitous in urban geometry to suppress floating artifacts. We further introduce the China-Pagoda dataset comprising 8 ancient Chinese pagodas with over 1,200 images each, featuring dense ornamental carvings, curved multi-layer eaves, and repetitive fine-grained textures. Extensive experiments on Mill19, UrbanScene3D, MatrixCity, and China-Pagoda demonstrate that HiCo-GS achieves state-of-the-art rendering quality and substantially cleaner geometry across real-world and synthetic urban benchmarks.Code: https://github.com/WZ-CS/HiCo-GS.

cs.CV↗
arXiv2026

SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information

Large language models (LLMs) are increasingly deployed as mobile assistants, where a key challenge is leveraging personal information scattered across multiple applications (apps) to complete user instructions. However, due to the lack of dedicated benchmarks, their capabilities remain poorly understood. To address this gap, we introduce SPIEval, a human-curated benchmark grounded in five cognitive capabilities (i.e., reasoning, disambiguation, integration, preference inference, and multi-intent decomposition). SPIEval comprises 250 tasks spanning 4,335 personal records distributed across 10 apps and supports multi-turn interaction through 21 tools. Analysis shows that the benchmark exhibits diverse scenarios, challenging tasks, scattered information, controllable environments, and verifiable outcomes. We evaluate nine representative LLMs and find substantial room for improvement. The best-performing model, GPT-5.5 (xhigh), achieves only 57.3% accuracy, while the weakest achieves just 16.4%. Further analysis reveals that 79% of failures stem from inaccurate information localization, as LLMs often commit to plausible but incorrect information instead of continuing retrieval for verification. We also find that fewer than 2% of retrieval actions employ advanced search methods and observe substantial variation in search efficiency across models. These findings expose fundamental limitations of current LLM-based mobile assistants and motivate future research in this direction. Data and code are available at https://huggingface.co/datasets/Junjie-Ye/SPIEval.

cs.CL↗
arXiv2026

Fluid Antenna System-Enabled Interference Alignment

Interference alignment is an efficient spectrum reuse scheme for multiuser wireless networks. In this letter, assuming no channel state information at the transmitters, we investigate a fluid antenna system (FAS)-enabled interference alignment scheme over a multiuser interference channel. In the proposed system, the additional spatial degrees of freedom provided by the FAS are exploited to nullify the real components of the effective combined interference such that those are reserved for interference-free desired signal detection. The interference alignment conditions and corresponding outage probabilities are theoretically derived. Simulations verify that the theoretically derived outage probabilities agree well with the numerical results. Furthermore, the proposed system is able to achieve a higher average sum rate than conventional single-user transmission schemes over non-interfering channels.

cs.IT↗
arXiv2026

A Computable Stochastic Riccati Equations Framework for Mean--Variance Portfolio Selection with Multifactor Stochastic Volatility Model

We investigate a computable and empirically implementable framework for continuous-time mean--variance optimal portfolio selection with random market coefficients. The market model is built on a tractable multifactor stochastic volatility structure, which captures state-dependent risk premia, stochastic volatility, and dynamic cross-asset dependence. The optimal control is characterized by stochastic Riccati equations. On the computational side, we design an iterative BSDE-based procedure to approximate the stochastic Riccati equation from above and below, where the initial upper and lower bounds are obtained by solving two linear BSDEs. We then apply a logarithmic transformation to remove the singularity in the SRE, and solve the resulting transformed equation using both Deep BSDE and DBDP methods. The linear BSDE bounds also provide effective initial-value estimates, improving the convergence speed and training stability of the Deep BSDE solver. Empirical experiments based on sector ETF data show that the proposed multifactor mean--variance strategy produces smooth target-return wealth dynamics, with improved drawdown control and downside-risk protection relative to benchmark strategies. These results demonstrate the practical potential of combining stochastic Riccati equations, neural BSDE solvers, and multifactor market modeling for dynamic asset allocation.

math.OC↗
arXiv2026

Stochastic Homogenization of Non-local Hamilton-Jacobi-Bellman equations

In this paper we apply the method of Kosygina, Rezakhanlou and Varadhan (CPAM 2006) to establish stochastic homogenization of Hamilton-Jacobi-Bellman (HJB) equation with a vanishing non-local integro-differential operator and a convex super-linearly growing Hamiltonian in stationary ergodic random medium. Their method, first designed for homogenization of HJB equations with vanishing Laplacian operator, relies on stochastic optimal control representation of the solution, a key construction of approximate super-correctors and the technique of linking diffusion process to abstract diffusion in random media. We show how the procedures can be carried out for HJB equations with jump-diffusion. In particular, for the construction of approximate super-correctors, we represent the non-local integro-differential operator as the divergence of a regular integral operator acting on the gradient.

math.AP↗
arXiv2026

Local Structure Dictates Ionic Transport and Mechanical Properties in Glassy Solid Electrolytes for Lithium Batteries

Electrolytes composed of sulfide and halide glasses are promising candidates for all-solid-state lithium batteries owing to their processability, lack of grain boundaries, and relatively high ionic conductivity. Nevertheless, their ionic conductivity and mechanical properties are still not satisfying for the real-world applications. Significant advances in solid electrolytes require a thorough understanding of their microstructures. Here, we reveal the connections among structure, ionic transport properties, and mechanical stability in a series of glassy solid electrolytes by employing molecular dynamics simulations based on a machine learning interatomic potential. Specifically, we explore how the interplay between B-S and P-S networks in glassy Li-S-P-B-I (LSPBI) governs ionic conductivity and deformation behavior. The introduction of P2S5 into a B2S3-based glass induces a critical structural transformation, through which both ionic conductivity and mechanical nano-ductility can be enhanced. For a moderate P2S5 content, incorporated PS4 units depolymerize the rigid boron framework, creating percolative diffusion pathways for fast ionic transport. Concurrently, the flexible P-S-P configurations enable energy dissipation through bond bending, leading to the brittle-to-ductile transition. However, excessive P2S5 increases the fraction of polyphosphates (e.g., P2S6 and P2S7), thereby polymerizing the structural network and ultimately impeding Li+ mobility. Our work thus provides atomistic principles for engineering glass electrolytes with balanced ionic conductivity and mechanical robustness.

cond-mat.mtrl-sci↗
arXiv2026

DRL-Based Secure Transmission for Rotatable Antenna-Enabled Low-Altitude ISAC Systems

The development of the low-altitude economy has driven innovation in intelligent antenna systems within ISAC systems. In this paper, we investigate a Rotatable Antenna (RA)-enabled low-altitude integrated sensing and communication (ISAC) system. In practical terms, the RA array can flexibly adjust the three-dimensional (3D) beam direction of each antenna to enhance array directional gain, thereby improving the communication security of legitimate mobile users against potential eavesdropping risks from the unmanned aerial vehicle (UAV). Our objective is to maximize the minimum secrecy rate (SR) by jointly optimizing transmit beamforming matrix, transmit and receive RAs' pointing matrices. To this end, an multi-agent proximal policy optimization with three improvement mechanisms (MAPPO-T) algorithm is proposed to cope with the issue of complex multi-agent collaborative decision-making problem. Simulation results show that the introduction of RAs can effectively improve SR performance compared to the traditional fixed orientation antenna (FOA)-based system. In addition, the proposed MAPPO-T algorithm validate the superiority compared to the standard MAPPO algorithm.

eess.SP↗
arXiv2026

Uncovering expert objectives in production planning via inverse optimization: An industrial case study

Production planning in the manufacturing industry often relies on the use of optimization models, but defining an appropriate objective function can be a challenge. In practice, planners must balance competing goals, manage uncertainty, and account for qualitative business preferences that are difficult to quantify. As a result, many optimization models fail to match expert behavior, limiting trust and adoption. In this work, we propose a data-driven inverse optimization framework to infer the objective function implicitly captured in expert planners' decisions. We formulate the production planning problem as a mixed-integer linear program, where the unknown objective function is represented as a weighted sum of hypothesized cost terms. A suboptimality-loss-based inverse optimization method is then applied to learn the objective weights from historical production plans. The proposed approach is applied to a real industrial case provided by Dow, where the inferred weights reveal that avoiding inventory shortages and maintaining consistent cycle lengths dominate the planners' decision-making. Time- and product-dependent extensions further improve predictive accuracy and uncover evolving priorities. Expert interviews confirm the practical validity of these insights. Overall, this study shows that inverse optimization can transform tacit human expertise into interpretable models, enabling more accurate and trusted decision-support tools for complex industrial systems.

math.OC↗
arXiv2026

Active View Selection for Scene-level Multi-view Crowd Counting and Localization with Limited Labeling Budget

Multi-view crowd counting and localization fuse the input multi-views for estimating the crowd number or locations on the ground. Existing methods mainly focus on accurately predicting on the crowd shown in the input views, which neglects the problem of choosing the `best' camera views to perceive all crowds well in the scene. Besides, existing view selection methods require massive labeled views and images, and lack the ability for cross-scene settings, reducing their application scenarios. Thus, in this paper, we study the view selection issue for better scene-level multi-view crowd counting and localization results with cross-scene ability and limited label demand, instead of input-view-level results. We first propose an independent view selection method (IVS) that considers view and scene geometries in the view selection strategy and conducts the view selection, labeling, and downstream tasks independently. Based on IVS, we also put forward an active view selection method (AVS) that jointly conducts the view selection, labeling, and downstream tasks. In AVS, we actively select the labeled views and consider both the view/scene geometries and the predictions of the downstream task models in the view selection process. Experiments on multi-view counting and localization tasks demonstrate the cross-scene and the limited label demand advantages of the proposed active view selection method (AVS), outperforming existing methods and with wider application scenarios.

cs.CV↗
arXiv2026

An inverse mixed-integer optimization framework for learning interpretable models of expert decision making

Understanding how experts make decisions and being able to transfer that knowledge is important, especially in complex engineering applications. It is highly valuable for training novices, improving the performance of human-machine systems, and potentially enabling fully autonomous systems that perform as well as human experts. However, an expert's decision-making strategy, developed through years of experience, is often not directly accessible, since the implicit preferences and decision rules involved can be difficult to specify explicitly. This has motivated the use of observed decisions made by the expert to learn an interpretable model that captures the expert's decision-making process. In this work, we develop an inverse optimization approach to jointly learn the decision-maker's preferences (or perceived costs) and the decision rules governing their choices. We demonstrate the general applicability of our approach using three case studies that consider a shift assignment problem, a production planning problem, and a real-world routing problem, respectively. Across these case studies, modeling both perceived costs and decision rules leads to better predictions, highlighting the value of the proposed framework and its greater flexibility in capturing and replicating expert decision making.

math.OC↗
arXiv2026

Belief-Contraction-Driven Active Inverse Source Localization and Characterization

Active inverse source localization and characterization (ISLC) in dynamic fields requires sequential decision making under partial observability, where a mobile sensor must infer latent source parameters from sparse, noisy readings. We introduce a belief-contraction-driven approach that unifies inference, stopping, and control. An attention-augmented particle filter stabilizes Bayesian belief updates through ESS-based resampling, feature-aware sparse attention smoothing, and Metropolis-Hastings rejuvenation that preserves the filtering posterior. Belief contraction (posterior dispersion) defines both a termination rule and a goal-aligned intrinsic reward, enabling reinforcement learning without distance-to-source shaping. Across seven field modalities, spatial out-of-distribution tests, and nonstationary source shifts, our agent (ATT-PFRL) achieves higher completion, faster convergence, and more accurate localization than planning and RL+Bayes baselines under similar computation. Fixed-trajectory studies also show improved ESS and lower RMSE, isolating the benefit of the inference layer.

cs.LG↗
arXiv2026

Mitigating Compounding Error via Video Representation Regularization

Video diffusion-based world models enable long autoregressive video generation for robotics, autonomous driving and simulation tasks, yet sliding-window autoregressive inference suffers from severe error accumulation that degrades frame quality over time. Although this phenomenon has been widely observed, the underlying mechanism of compounding error and how to achieve stable long-horizon generation remain largely unresolved. In this paper, we investigate the internal representation dynamics of video world models and discover that compounding error is tightly coupled with dimensional collapse of hidden representations. Specifically, the effective rank of model representations sharply decreases at the onset of generation drift, revealing a strong connection between representational degradation and long-term rollout instability. Furthermore, we find that pure training data scaling fails to boost model resistance to error drift, contradicting mainstream scaling paradigms. To address this problem, we propose video representation regularization, a lightweight training constraint that stabilizes latent representations and suppresses iterative error accumulation. Compared with Diffusion Forcing, our method achieves improvements from 38.65 to 55.56 and from 44.37 to 72.08 on the Aesthetic Quality and Imaging Quality metrics of VBench. Our work establishes the first connection between autoregressive video drifting and model internal representations, adopts erank as a quantitative metric for error accumulation, reveals counterintuitive scaling limitations for video world models, and presents a simple yet effective regularization strategy to improve long video generation robustness.

cs.CV↗