arXiv subjects

Zihan Chen

Publications and source records attributed to Zihan Chen.

At least 37 records · Page 2Linked to original sources

arXiv2026

Rethinking the Foundations of Two-Sided AI Models for 6G

For next-generation air interfaces, two-sided artificial intelligence (AI) models have received growing attention, with AI models deployed at both the transmitter and receiver for efficient channel feedback and data communication. However, their practical deployment is complicated by assumptions commonly made in existing studies, including isolation from legacy users, training under predefined channel conditions, and gradient-based fine-tuning requiring substantial cross-vendor communication. This article revisits these assumptions and presents practical alternatives. First, for legacy coexistence, we integrate two-sided model processing into the 5G New Radio (NR) protocol stack and validate its operation alongside conventional NR on a real-world testbed. Second, instead of training under a massive number of predefined channel conditions, we construct a compact model table by jointly optimizing two-sided models with trainable surrogate channels, and select the best model according to the current channel condition to enable channel adaptation with high task performance and low training/storage overhead. Finally, unlike existing fine-tuning that exchanges large gradient vectors containing potentially private model information, we present gradient-free zeroth-order fine-tuning that requires only scalar feedback, facilitating multi-vendor interoperability. Together, these approaches advance the practical deployment of two-sided AI models while highlighting key open challenges.

eess.SP↗

arXiv2026

UniMod: Enhancing Multi-Modal Medical Diagnosis through Cross-Modality and Within-Modality Alignment

Multi-modal learning combining medical images and clinical text is promising for disease diagnosis. However, standard multi-modal training leads to shortcut learning: models exploit the easier modality (e.g., diagnostic cues in text) while neglecting harder-to-learn features (e.g., subtle visual patterns). We propose UniMod, a framework that mitigates shortcut learning by requiring each modality to predict the diagnosis on its own. It supervises image-only, text-only, and multi-modal classification simultaneously, so each modality must extract diagnostic features. We add cross-modality alignment for knowledge transfer and within-modality supervised contrastive alignment over same-diagnosis patients. On Harvard-Glaucoma, UniMod reaches 0.850 AUC, outperforming OGM-GE and Gradient Blending by 1.6-1.8%; on CheXpert Plus, it reaches 0.966 AUC, surpassing them by over 5%. UniMod also extends to 5-class multi-label diagnosis without architectural change, improving mean AUC by 0.097 over CGGM.

cs.CV↗

arXiv2026

Loss-Resilient Wireless Video Token Communication over Block Fading Channels

Video token communication represents video content as discrete tokens that differ in their importance to reconstruction and exhibit temporal dependencies. When these tokens are packetized for wireless transmission, block fading can cause multiple important or correlated tokens to be lost together, severely degrading video reconstruction. To address this issue, we propose a loss-resilient wireless video token communication (WVTC) framework. WVTC evaluates token importance from the intrinsic predictive structure of video tokens, assigning high priority to structural I-tokens and measuring P-token importance by temporal neighborhood novelty. A shuffled mixed I/P-token packetization scheme disperses structural anchors and correlated temporal regions across packets. Using only current block channel state information, an online scheduler jointly considers packet importance density, MCS-dependent decoding reliability, block capacity, and importance concentration when allocating packets to fading blocks. At the receiver, a fine-tuned detokenizer reconstructs missing content from surviving tokens without retransmission. Numerical results demonstrate improved perceptual quality and more graceful degradation under increasing packet error rates.

cs.LG↗

arXiv2026

IDATA: Scalable Invertible Diffusion for Unrestricted Adversarial Transfer Attack

Unrestricted adversarial transfer attacks are important for evaluating the black-box robustness of deep visual models. Diffusion-based attacks have shown promising transferability and visual imperceptibility by optimizing adversarial perturbations along denoising trajectories in latent space. However, existing methods are limited by two challenges: memory-intensive multistep backpropagation and frequency-agnostic perturbation over intermediate latents. To address these issues, we propose IDATA, a memory-efficient diffusion framework for unrestricted adversarial transfer attack. IDATA consists of two key components: an Invertible Diffusion Module (IDM) and a Low-Frequency Constraint Module (LFCM). Specifically, IDM reformulates adversarial optimization over diffusion trajectories as an invertible process, enabling constant-memory backpropagation through on-demand reconstruction of intermediate states instead of storing the full denoising chain. Moreover, LFCM leverages Discrete Wavelet Transform (DWT) to decompose latent variables into low- and high-frequency components, restricting perturbations to semantically stable low-frequency subspaces, thereby improving transferability while preserving visual imperceptibility. Extensive experiments on multiple benchmarks and diverse model architectures demonstrate that IDATA consistently outperforms state-of-the-art baselines in attack success rate, memory efficiency, and visual imperceptibility. These results suggest that IDATA is a promising tool for black-box robustness evaluation of deep visual models. Code is available at https://github.com/colourful-pan/IDATA.

cs.CV↗

arXiv2026

Media Meets Communication in 6G: Fundamentals, Key Technologies, and Applications

The rapid advancement of sixth-generation (6G) networks is accelerating the convergence of media intelligence and communication intelligence, driving media communication beyond conventional bit-level delivery toward intelligent, semantic-aware, and generative paradigms. Emerging media services require not only high data rates and low latency, but also semantic awareness, perceptual quality assurance, adaptive resource orchestration, trustworthy content processing, and personalized media generation. Meanwhile, media technologies are evolving from handcrafted signal processing and conventional coding toward artificial intelligence (AI)-driven representation learning, content understanding, and generative reconstruction. Motivated by these trends, this paper presents a systematic survey of media communication technologies for 6G vision communication by revisiting the evolution of communication and media technologies and clarifying the intrinsic relationship between media content processing and wireless transmission. We introduce a unified framework consisting of four key dimensions: AI-driven media technologies, media-aware wireless transmission, large model-enabled media communication, and intelligent network infrastructures. Specifically, AI-driven media technologies encompass media coding, content understanding, quality assessment, security and compliance detection, and AIGC-enabled media generation, while media-aware wireless transmission is examined from three complementary perspectives: semantic joint source-channel optimization, which jointly encodes task-relevant semantic information; source-aware transmission optimization, which leverages media characteristics for channel adaptation, prediction, and compensation; and channel-aware source optimization, which adapts media coding and reconstruction based on real-time channel conditions.

cs.IT↗

arXiv2026

Communication-Efficient Digital-Twin Coordination for Heterogeneous LLM Embodied Agents over Computing Power Networks

Embodied agent teams powered by heterogeneous large language models (LLMs) are being widely deployed in physical artificial intelligence such as smart factories, warehouses, and service robotics. To enable collaboration among such an agent team, efficient coordination mechanisms that operate reliably under limited network resources are required. However, existing heterogeneous LLM-agent coordination frameworks that rely on multi-round natural-language-based conversations introduce three coupled challenges. First, inter-agent dialogue incurs communication overhead that grows rapidly with team size. Second, the quality of coordination is constrained by the heterogeneous capabilities of the agent team's LLMs. Third, agents may suffer from action delays due to iterative negotiation. To address these challenges, we propose LDT-Coord, a networked coordination framework built upon a lightweight digital twin (DT). Specifically, each agent independently selects its intended action and reports both the action decision and a structured temporal constraint over shared resources to the DT server, thereby decoupling coordination performance from natural-language reasoning ability. Then, DT executes a training-free, rule-based orchestrator algorithm to resolve cross-agent conflicts and returns coordination instructions to prevent such conflicts. To further reduce communication overhead, we formulate agent reporting control as a constrained partially observable Markov decision process (C-POMDP) and solve it with the PPO-Lagrangian algorithm. Simulation results show that LDT-Coord achieves a task success rate comparable to conventional coordination methods while reducing communication overhead by more than 70x and maintaining robustness under LLM heterogeneity.

cs.AI↗

arXiv2026

The Past Is Prologue: A Plug-in Controller for Selective Updates in Sequentially Evolving LLM Memory

Sequentially evolving LLM memory enables agents to reuse past experience, but existing systems usually deploy each locally generated memory update without checking whether it improves future behavior. As a result, updates that help the current task may overwrite useful knowledge, introduce over-specific rules, or bias the final memory toward recent examples. We propose Janus, a plug-in memory controller that decides whether to accept a candidate memory update or retain the previous memory. To make this decision efficient, Janus uses a Memory Momentum Trigger to identify suspicious deviations in the memory-update trajectory, and compares old and new memories on a compact hybrid evaluation set of coverage, boundary, and fresh tasks instead of replaying the full history. Janus is method-agnostic and wraps existing updaters without changing their update rules. Across six datasets, two backbone LLMs, and two memory updaters, Janus improves average accuracy by +2.7 to +4.6 points over the corresponding base updaters.

cs.AI↗

arXiv2026

Leveraging Phase Polynomials for Quantum Circuit Optimization

Quantum circuits on resource-limited hardware require optimizing regions dominated by $\{\mathrm{CNOT}, R_z\}$, which account for a large fraction of operations and often dominate execution cost. This optimization can be challenging because phase-polynomial blocks are fragmented by basis-changing gates such as $H$, and optimizing phase parities alone may increase the cost of downstream basis transformations. Existing phase-polynomial approaches are limited to single-block or phase-only optimization, while subcircuit rewriting approaches are local and scale poorly beyond small rewrite windows. We introduce \emph{PhasePoly}, a compiler optimization pass that jointly optimizes phase-parity and output-parity networks and employs a cross-block intermediate representation to reuse parities across phase-polynomial block barriers. This approach is effective because its unified parity-matrix representation exposes long-range $\{\mathrm{CNOT}, R_z\}$ structure that local rewriting and single-block methods cannot capture. \emph{PhasePoly} reduces total gate count by up to 50.00\% (34.70\% on average) and CNOT count by up to 48.57\% (26.83\% on average), while scaling to large circuits and improving both fault-tolerant compilation and near-term hardware execution. \emph{PhasePoly} is available at https://github.com/ruadapt/PhasePoly.

cs.PL↗

arXiv2026

FinInvest-GTCN: Explainable Graph-Temporal-Causal Modeling for Risk-Aware Investment Decision Optimization

Venture capital (VC) investment decisions face distinct challenges, such as multi-source heterogeneous data, non-stationary time series, and the demand for explainable predictions in high-stakes, low-data settings. To overcome these issues, we introduce \textbf{FinInvest-GTCN}, a Graph-Temporal-Causal Network that redefines the task from content recommendation to quantitative risk-return assessment. This architecture combines a relational graph encoder to capture the investment ecosystem's topology, a multi-scale temporal fusion module to handle long-term dependencies and non-stationarity, and a causal decision head that generates risk-adjusted predictions with interpretable causal attributions. A core innovation is the Meta-Causal Adaptation (MCA) strategy, which facilitates robust fine-tuning for new, data-scarce sectors by aligning updates with causally-plausible structures derived from meta-pretraining. Comprehensive experiments on proprietary VC datasets show that FinInvest-GTCN delivers state-of-the-art results, markedly lowering the primary Risk-Adjusted Mean Squared Error (RA-MSE) to 2.51 from a baseline of 3.05 and boosting the cumulative return of a simulated portfolio by 18.7\%. Ablation studies underscore the essential role of each component, while additional analyses confirm the model's stability, interpretability, and enhanced adaptability. This work pioneers a data-driven, explainable framework for investment decision support.

cs.CL↗

arXiv2026

EVLA: An Electro-Aware Multimodal Assistant for Physically-Grounded Driving Reasoning and Control

Modern vision-language models (VLMs) for driving assistants typically treat vehicle dynamics as a black box, resulting in decisions that lack awareness of the vehicle's real-time electro-mechanical state. To bridge this gap, we introduce the Electro-Visual-Language Assistant (EVLA) -- a novel framework that combines multi-modal scene understanding with real-time perception of the electrified powertrain state (e.g., motor torque, battery SOC). Our approach features two key innovations: first, a Unified Co-State Encoder (UCSE) that fuses visual, textual, and vehicle-state inputs into a shared latent representation, augmented with an Energy-Efficiency Field to model spatial energy costs; and second, an Electro-aware Structured Reasoning Chain (ESRC), which replaces external chain-of-thought prompting with an internal, deterministic reasoning process grounded in physical constraints and optimization objectives. Trained end-to-end with a physics-guided joint loss, EVLA learns to generate context-aware and energy-optimal driving decisions. Extensive evaluations on a driving QA benchmark demonstrate that EVLA substantially outperforms strong fine-tuned VLM baselines, improving the final score by +0.0871 and accuracy by +5.6\%. Ablation studies validate the necessity of each component, and efficiency analyses show that EVLA achieves 36\% faster inference than multi-stage pipelines. This work underscores that integrating vehicle-state awareness and structured physical reasoning is crucial for developing next-generation, physically-grounded driving assistants.

cs.CL↗

arXiv2026

Priority-Aware Learning-Unlearning Correction for Dynamic Decentralized LoRA Fine-Tuning

As large language models (LLMs) are increasingly deployed at the network edge to provide pervasive generative AI services, decentralized federated learning (DFL) provides a vital mechanism for privacy-preserving, domain-specific fine-tuning through peer-to-peer exchanges of parameter-efficient updates. However, the dynamic nature of practical decentralized edge networks, where devices may dynamically join or leave the collaborative training process, requires the system to continuously adapt to new data while selectively removing prior contributions. This correction process remains a significant bottleneck, as individual device updates become deeply entangled within the global fine-tuned parameters. To address this challenge, we propose a priority-aware learning-unlearning correction framework based on orthogonal LoRA that can enhance the knowledge evaluation through topology adjustment. Specifically, we first design an orthogonal LoRA mechanism that yields post-training contribution coordinates, enabling history-free projection addition and deletion in response to membership changes. We then analyze the correction bottleneck and develop a priority-aware policy that selects among topology refinement, local correction, proximal damping, and synchronization scheduling according to the dominant residual term. A resource allocation algorithm is further developed to allocate limited communication across layer groups, prioritizing the primary bottlenecks within per-round wireless constraints. Experiments demonstrate that the proposed framework achieves robust post-event correction for both device join and leave events and validate that different residual regimes necessitate distinct correction actions.

cs.LG↗

arXiv2026

Channel-Wise Mixed-Precision Quantization for Large Language Models

Large Language Models (LLMs) have demonstrated remarkable success across a wide range of language tasks, but their deployment on edge devices remains challenging due to the substantial memory requirements imposed by their large parameter sizes. Weight-only quantization presents a promising solution to reduce the memory footprint of LLMs. However, existing approaches primarily focus on integer-bit quantization, limiting their adaptability to fractional-bit quantization tasks and preventing the full utilization of available storage space on devices. In this paper, we introduce Channel-Wise Mixed-Precision Quantization (CMPQ), a novel mixed-precision quantization method that allocates quantization precision in a channel-wise pattern based on activation distributions. By assigning different precision levels to different weight channels, CMPQ supports arbitrary average bit-widths in the low-bit regime (e.g., between 2 and 4 bits). CMPQ employs a non-uniform quantization strategy and incorporates two outlier extraction techniques that collaboratively preserve the critical information, thereby minimizing the quantization loss. Experiments on nine different LLMs demonstrate that CMPQ not only enhances performance in integer-bit quantization tasks but also achieves significant performance gains with a modest increase in memory usage by performing in a mixed-precision way. CMPQ represents an adaptive and effective approach to LLM quantization, offering substantial benefits across diverse device capabilities.

cs.CL↗

arXiv2026

Rethinking RL Evaluation: Can Benchmarks Truly Reveal Failures of RL Methods?

Current benchmarks are inadequate for evaluating progress in reinforcement learning (RL) for large language models (LLMs).Despite recent benchmark gains reported for RL, we find that training on these benchmarks' training sets achieves nearly the same performance as training directly on the test sets, suggesting that the benchmarks cannot reliably separate further progress.To study this phenomenon, we introduce a diagnostic suite and the Oracle Performance Gap (OPG) metric that quantifies the performance difference between training on the train split versus the test split of a benchmark. We further analyze this phenomenon with stress tests and find that, despite strong benchmark scores, existing RL methods struggle to generalize across distribution shifts, varying levels of difficulty, and counterfactual scenarios: shortcomings that current benchmarks fail to reveal.We conclude that current benchmarks are insufficient for evaluating generalization and propose three core principles for designing more faithful benchmarks: sufficient difficulty, balanced evaluation, and distributional robustness.

cs.LG↗

arXiv2026

The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs

Large Language Models (LLMs) aligned via outcome-based Reinforcement Learning (RL) frequently exhibit a critical failure mode: they achieve high performance on in-distribution benchmarks while demonstrating brittle reasoning capabilities on out-of-distribution (OOD) tasks. We term this phenomenon Reward-Induced Manifold Collapse. We establish a theoretical framework bridging Structural Causal Models (SCM) and the Information Bottleneck (IB) principle to explain this paradox. We define reasoning as a high-complexity causal process and shortcut learning as the exploitation of low-complexity spurious correlations. Under the implicit inductive bias of Stochastic Gradient Descent (SGD), models optimized for outcome rewards are biased toward shortcut solutions whenever the training distribution allows for a ``Markovian Screening'' of the true causal mechanism. We derive a new generalization bound based on Semantic Coverage Measure ($η$) rather than sample size, showing why data scaling on homogeneous distributions may fail to correct reasoning flaws. We also show that Process Reward Models (PRMs) function as Topological Filters, enforcing step-wise mutual information constraints that render the low-complexity shortcut manifold inadmissible. These results provide a mathematical grounding for the role of process supervision beyond simple credit assignment.

cs.LG↗

arXiv2026

Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory

Memory plays a central role in enabling large language models (LLMs) to operate over sequential tasks by accumulating and reusing experience over time. However, existing evaluations of LLM memory mostly rely on aggregate metrics such as final hold-out accuracy or cumulative online performance, which can obscure critical failure modes such as forgetting and negative transfer. In this paper, we introduce SeqMem-Eval, a diagnostic evaluation framework for sequentially evolving LLM memory. Drawing inspiration from continual learning, it targets a test-time setting in which memory is external, prompt-mediated, and updated without modifying model parameters. Rather than focusing only on final performance, SeqMem-Eval evaluates how memory states evolve, generalize, consolidate experience, and retain useful information during sequential inference. Specifically, it measures online utility, hold-out generalization, backward transfer, and forgetting, providing a finer-grained view of memory quality. Through extensive experiments across diverse tasks and memory methods, we show that higher final or cumulative accuracy does not necessarily imply better memory quality: many methods exhibit strong performance gains while suffering from substantial forgetting or negative transfer. Moreover, different memory designs exhibit distinct trade-offs between adaptability and stability that remain invisible under standard evaluation metrics.

cs.LG↗

arXiv2026

A Survey of Scaling in Large Language Model Reasoning

The rapid advancements in large Language models (LLMs) have significantly enhanced their reasoning capabilities, driven by various strategies such as multi-agent collaboration. However, unlike the well-established performance improvements achieved through scaling data and model size, the scaling of reasoning in LLMs is more complex and can even negatively impact reasoning performance, introducing new challenges in model alignment and robustness. In this survey, we provide a comprehensive examination of scaling in LLM reasoning, categorizing it into multiple dimensions and analyzing how and to what extent different scaling strategies contribute to improving reasoning capabilities. We begin by exploring scaling in input size, which enables LLMs to process and utilize a more extensive context for improved reasoning. Next, we analyze scaling in reasoning steps that improve multi-step inference and logical consistency. We then examine scaling in reasoning rounds, where iterative interactions refine reasoning outcomes. Furthermore, we discuss scaling in training-enabled reasoning, focusing on optimization through iterative model improvement. Finally, we outline future directions for further advancing LLM reasoning. By synthesizing these diverse perspectives, this survey aims to provide insights into how scaling strategies fundamentally enhance the reasoning capabilities of LLMs and further guide the development of next-generation AI systems.

cs.AI↗

arXiv2026

Verification of Machine Unlearning is Fragile

As privacy concerns escalate in the realm of machine learning, data owners now have the option to utilize machine unlearning to remove their data from machine learning models, following recent legislation. To enhance transparency in machine unlearning and avoid potential dishonesty by model providers, various verification strategies have been proposed. These strategies enable data owners to ascertain whether their target data has been effectively unlearned from the model. However, our understanding of the safety issues of machine unlearning verification remains nascent. In this paper, we explore the novel research question of whether model providers can circumvent verification strategies while retaining the information of data supposedly unlearned. Our investigation leads to a pessimistic answer: \textit{the verification of machine unlearning is fragile}. Specifically, we categorize the current verification strategies regarding potential dishonesty among model providers into two types. Subsequently, we introduce two novel adversarial unlearning processes capable of circumventing both types. We validate the efficacy of our methods through theoretical analysis and empirical experiments using real-world datasets. This study highlights the vulnerabilities and limitations in machine unlearning verification, paving the way for further research into the safety of machine unlearning.

cs.LG↗

arXiv2026

Testing holographic duality in hyperbolic lattices

The celebrated holographic duality posits a correspondence between a quantum gravity in a bulk spacetime and a quantum field theory (QFT) defined on its lower-dimensional boundary. This duality not only offers deep insights into the enigmatic nature of quantum gravity but also provides an efficient methodology for studying strongly correlated systems. However, despite its profound significance in modern physics, holographic duality remains a conjecture, and further experimental exploration is highly sought after. Here, we present the first experimental test of holographic duality between a three-dimensional bulk gravity and a two-dimensional boundary QFT using hyperbolic lattices. By experimentally measuring the classical scalar field propagator in hyperbolic circuits, we reproduce the equal-time two-point correlation function of the dual boundary conformal field theory (CFT), verifying its exponential dependence on the boundary separation and the conformal dimension-scalar mass relation. Furthermore, by leveraging the two-point correlation function, we reconstruct the entanglement entropy for a boundary CFT subsystem, confirming that it follows the Ryu-Takayanagi formula. These results constitute the first direct experimental evidence that quantum properties of the QFT can be holographically reproduced through its dual classical field in curved space. This heuristic experimental effort opens a new avenue for in-depth investigations on the holographic duality and extensive exploration of quantum-gravity-inspired phenomena in classical systems.

hep-lat↗