Searcharxiv⌕ Search

arXiv subjects

Wei Jiang

Publications and source records attributed to Wei Jiang.

At least 91 records · Page 5Linked to original sources
arXiv2026

Tracking vs. Deciding: The Dual-Capability Bottleneck in Searchless Chess Transformers

A human-like chess engine should mimic the style, errors, and consistency of a strong human player rather than maximize playing strength. We show that training from move sequences alone forces a model to learn two capabilities: state tracking, which reconstructs the board from move history, and decision quality, which selects good moves from that reconstructed state. These impose contradictory data requirements: low-rated games provide the diversity needed for tracking, while high-rated games provide the quality signal for decision learning. Removing low-rated data degrades performance. We formalize this tension as a dual-capability bottleneck, P <= min(T,Q), where overall performance is limited by the weaker capability. Guided by this view, we scale the model from 28M to 120M parameters to improve tracking, then introduce Elo-weighted training to improve decisions while preserving diversity. A 2 x 2 factorial ablation shows that scaling improves tracking, weighting improves decisions, and their combination is superadditive. Linear weighting works best, while overly aggressive weighting harms tracking despite lower validation loss. We also introduce a coverage-decay formula, t* = log(N/kcrit)/log b, as a reliability horizon for intra-game degeneration risk. Our final 120M-parameter model, without search, reached Lichess bullet 2570 over 253 rated games. On human move prediction it achieves 55.2% Top-1 accuracy, exceeding Maia-2 rapid and Maia-2 blitz. Unlike position-based methods, sequence input naturally encodes full game history, enabling history-dependent decisions that single-position models cannot exhibit.

cs.AI↗
arXiv2026

Mapping the Midweek Mountain: The New Geography of Hybrid Work

This paper provides a behavioral analysis of the post-pandemic transformation of work, using a dataset of approximately 41 billion mobile geolocation records from 73.5 million individuals in the five largest U.S. metropolitan areas from the pre- to post- pandemic periods. By tracking movements between corporate headquarters, residences, and other points of interest, we document a structural shift in work patterns. Office based workdays declined from 42% in 2019 to 20.7% in 2022, before settling at 29.1% in 2023, a new equilibrium significantly below pre-pandemic levels. A "midweek mountain" peak of office attendance on Tuesdays through Thursdays, emerged as a robust new phenomenon post-pandemic. The nature of remote work has also changed: both in and after the pandemic, employees working from home allocated significantly more time to non-work locations like parks and malls during the workday. These findings indicate that the pandemic catalyzed a lasting transformation not just in work arrangements but also in the integration of personal and professional life, with implications for corporate policy, urban economics, and the future of work.

q-fin.CP↗
arXiv2026

LogPTR: Variable-Aware Log Parsing with Pointer Network

Due to the sheer size of software logs, developers rely on automated log analysis. Log parsing, which parses semi-structured logs into a structured format, is a prerequisite of automated log analysis. However, existing log parsers are unsatisfactory when applied in practice because they 1) ignore categories of variables, and 2) need labor-intensive model tuning. To address these limitations, we propose LogPTR, a variable-aware log parser that can extract the static and dynamic parts in logs, and further identify categories of variables. The key of LogPTR is formulating log parsing as a text summarization problem and using a pointer mechanism to copy words from the log message and label tokens indicating categories of variables. The experimental results on widely-used benchmark datasets show that LogPTR outperforms state-of-the-art log parsers on both general log parsing that extracts log templates and variable-aware log parsing that further identifies categories of variables.

cs.SE↗
arXiv2026

CRED: Counterfactual Reasoning and Environment Design for Active Preference Learning

As a robot's operational environment and tasks to perform within it grow in complexity, the explicit specification and balancing of optimization objectives to achieve a preferred behavior profile moves increasingly farther out of reach. These systems benefit strongly by being able to align their behavior to reflect human preferences and respond to corrections, but manually encoding this feedback is infeasible. Active preference learning (APL) learns human reward functions by presenting trajectories for ranking. However, existing methods sample from fixed trajectory sets or replay buffers that limit query diversity and often fail to identify informative comparisons. We propose CRED, a novel trajectory generation method for APL that improves reward inference by jointly optimizing environment design and trajectory selection to efficiently query and extract preferences from users. CRED "imagines" new scenarios through environment design and leverages counterfactual reasoning -- by sampling possible rewards from its current belief and asking "What if this were the true preference?" -- to generate trajectory pairs that expose differences between competing reward functions. Comprehensive experiments and a user study show that CRED significantly outperforms state-of-the-art methods in reward accuracy and sample efficiency and receives higher user ratings.

cs.RO↗
arXiv2026

Distributed vs. Centralized Precoding in Cell-Free Systems: Impact of Realistic Per-AP Power Limits

In cell-free massive MIMO, centralized precoding is {theoretically known} to {remarkably} outperform its distributed counterparts, albeit {with} high implementation complexity. However, this letter highlights a practical limitation {often overlooked:} {widely used closed-form} centralized {precoders} are typically derived under a sum-power constraint, which often demands unrealistic power allocation that exceeds hardware capabilities. {When two simple heuristics (global power scaling and local normalization) are applied to enforce the per-AP instantaneous power constraint}, the centralized performance superiority disappears, making distributed precoding {a robust option}.

cs.IT↗
arXiv2026

Adaptive Memory Admission Control for LLM Agents

LLM-based agents increasingly rely on long-term memory to support multi-session reasoning and interaction, yet current systems provide little control over what information is retained. In practice, agents either accumulate large volumes of conversational content, including hallucinated or obsolete facts, or depend on opaque, fully LLM-driven memory policies that are costly and difficult to audit. As a result, memory admission remains a poorly specified and weakly controlled component in agent architectures. To address this gap, we propose Adaptive Memory Admission Control (A-MAC), a framework that treats memory admission as a structured decision problem. A-MAC decomposes memory value into five complementary and interpretable factors: future utility, factual confidence, semantic novelty, temporal recency, and content type prior. The framework combines lightweight rule-based feature extraction with a single LLM-assisted utility assessment, and learns domain-adaptive admission policies through cross-validated optimization. This design enables transparent and efficient control over long-term memory. Experiments on the LoCoMo benchmark show that A-MAC achieves a superior precision-recall tradeoff, improving F1 to 0.583 while reducing latency by 31% compared to state-of-the-art LLM-native memory systems. Ablation results identify content type prior as the most influential factor for reliable memory admission. These findings demonstrate that explicit and interpretable admission control is a critical design principle for scalable and reliable memory in LLM-based agents.

cs.AI↗
arXiv2026

Agentic Mixed-Source Multi-Modal Misinformation Detection with Adaptive Test-Time Scaling

Vision-language models (VLMs) have been proven effective for detecting multi-modal misinformation on social platforms, especially in zero-shot settings with unavailable or delayed annotations. However, a single VLM's capacity falls short in the more complex mixed-source multi-modal misinformation detection (M3D) task. Taking captioned images as an example, in M3D, false information can originate from untruthful texts, forged images, or mismatches between the two modalities. Although recent agentic systems can handle zero-shot M3D by connecting modality-specific VLM agents, their effectiveness is still bottlenecked by their architecture. In existing agentic M3D solutions, for any input sample, each agent performs only one forward reasoning pass, making decisions prone to model randomness and reasoning errors in challenging cases. Moreover, the lack of exploration over alternative reasoning paths prevents modern VLMs from fully utilizing their reasoning capacity. In this work, we present AgentM3D, a multi-agent framework for zero-shot M3D. To amplify the reasoning capability of VLMs, we introduce an adaptive test-time scaling paradigm in which each modality-specific VLM agent applies a Best-of-N mechanism, coupled with a critic agent for task-aligned scoring. The agents are organized in a cascading, modality-specific decision chain to reduce unnecessary computation and limit error propagation. To ensure scalability, a planning agent dynamically determines the maximum number of reasoning paths based on sample difficulty, and an adaptive stopping mechanism prevents excessive reasoning within each agent. Extensive experiments on two M3D benchmarks demonstrate that AgentM3D achieves state-of-the-art zero-shot detection performance compared with various VLM-based and agentic baselines.

cs.MM↗
arXiv2026

Securing the Floor and Raising the Ceiling: A Merging-based Paradigm for Multi-modal Search Agents

Recent advances in Vision-Language Models (VLMs) have motivated the development of multi-modal search agents that can actively invoke external search tools and integrate retrieved evidence through multi-step reasoning. While promising, existing approaches typically rely on large-scale supervised trajectories or expensive reinforcement learning (RL), leading to high training cost, instability, and a severe cold-start problem for standard VLMs. We propose a training-free paradigm to empower VLMs with autonomous search capabilities via cross-modal model merging. By fusing a text-based search agent with a base VLM, we show that multi-modal search capabilities can be effectively composed without any additional multi-modal training data. To mitigate parameter interference during cross-modal integration, we introduce Optimal Brain Merging (OBM), a saliency-aware merging algorithm that identifies task-critical parameters based on their impact on model loss using only a small set of calibration samples. Extensive experiments on search-intensive benchmarks (e.g., InfoSeek, MMSearch) reveal that: (1) Model merging secures a reasonable performance floor as a zero-shot agent, with OBM achieving superior search rates; (2) OBM significantly raises the performance ceiling as a warm-start strategy, achieving faster convergence and higher peak accuracy than standard VLM initialization.

cs.AI↗
arXiv2026

Huawei Cloud Model-as-a-Service on the CloudMatrix384 SuperPod

Scaled-out MoE LLMs and scaled-up SuperPods create new systems challenges for production Model-as-a-Service (MaaS), requiring disaggregation, low-latency communication, and decentralized serving. This report presents xDeepServe, the production serving system behind Huawei Cloud's MaaS offering on CloudMatrix384, a 48-server SuperPod with 384 Ascend 910C chips connected by a high-bandwidth UB fabric and global shared memory. It serves models including DeepSeek, Kimi, GLM, Qwen, and MiniMax, among others. xDeepServe is built around Transformerless, a disaggregated execution architecture that decomposes transformer inference into modular units -- attention, feedforward, and MoE -- and supports disaggregated Prefill-Decode and MoE-Attention deployments. To enable disaggregation, we develop XCCL, a memory-semantic communication layer providing microsecond-level point-to-point and scalable all-to-all primitives, and we extend FlowServe with decentralized DP groups and techniques to mitigate stragglers and synchronization variance. In a peak decoding configuration, xDeepServe reaches 2400 tokens/s per Ascend 910C chip at ~50ms time-per-output-token (TPOT).

cs.DC↗
arXiv2026

MLICv2: Enhanced Multi-Reference Entropy Modeling for Learned Image Compression

Recent advances in learned image compression (LIC) have achieved remarkable performance improvements over traditional codecs. Notably, the MLIC series-LICs equipped with multi-reference entropy models-have substantially surpassed conventional image codecs such as Versatile Video Coding (VVC) Intra. However, existing MLIC variants suffer from several limitations: performance degradation at high bitrates due to insufficient transform capacity, suboptimal entropy modeling that fails to capture global correlations in initial slices, and lack of adaptive channel importance modeling. In this paper, we propose MLICv2 and MLICv2+, enhanced successors that systematically address these limitations through improved transform design, dvanced entropy modeling, and exploration of the potential of instance-specific optimization. For transform enhancement, we introduce a lightweight token mixing block inspired by the MetaFormer architecture, which effectively mitigates high-bitrate performance degradation while maintaining computational efficiency. For entropy modeling improvements, we propose hyperprior-guided global correlation prediction to extract global context even in the initial slice of latent representation, complemented by a channel reweighting module that dynamically emphasizes informative channels. We further explore enhanced positional embedding and guided selective compression strategies for superior context modeling. Additionally, we apply the Stochastic Gumbel Annealing (SGA) to demonstrate the potential for further performance improvements through input-specific optimization. Extensive experiments demonstrate that MLICv2 and MLICv2+ achieve state-of-the-art results, reducing Bjøntegaard-Delta Rate by 16.54%, 21.61%, 16.05% and 20.46%, 24.35%, 19.14% on Kodak, Tecnick, and CLIC Pro Val datasets, respectively, compared to VTM-17.0 Intra.

eess.IV↗
arXiv2026

Development and Application of an eV Neutron Polarization for Parity Violation Studies at CSNS Back-n Beamline

The dynamic enhancement of symmetry-breaking effects in neutron-nucleus resonances provides a sensitive testing ground for Time-Reversal Invariance Violation (TRIV). Exploiting this mechanism, the Neutron Optics Parity and Time Reversal Experiment (NOPTREX) seeks to elucidate the origin of the universe's baryon asymmetry. Critical to this effort is the precise measurement of Parity Violation (PV) asymmetries, which is essential to calibrate the nuclear parameters required for future TRIV experiments. To facilitate these studies, we developed an eV polarized neutron at the Back-n white neutron beamline of the China Spallation Neutron Source (CSNS). Neutron polarization is generated by an in-situ Spin-Exchange Optical Pumping (SEOP) $^3$He filter. Spin manipulation is performed by an adiabatic spin flipper, while spin polarization is preserved over the flight path by a vacuum transport system equipped with a solenoidal guide field. Experiments successfully measured an asymmetry of approximately $7.8 \pm 2.4$ (stat.) $\pm 0.3$ (sys.) % at the 0.747 eV p-wave resonance of $^{139}$La. These results are in agreement with previous results on this resonance and validate the system's capability for PV measurements.

physics.ins-det↗
arXiv2026

OMGs: A multi-agent system supporting MDT decision-making across the ovarian tumour care continuum

Ovarian tumour management has increasingly relied on multidisciplinary tumour board (MDT) deliberation to address treatment complexity and disease heterogeneity. However, most patients worldwide lack access to timely expert consensus, particularly in resource-constrained centres where MDT resources are scarce or unavailable. Here we present OMGs (Ovarian tumour Multidisciplinary intelligent aGent System), a multi-agent AI framework where domain-specific agents deliberate collaboratively to integrate multidisciplinary evidence and generate MDT-style recommendations with transparent rationales. To systematically evaluate MDT recommendation quality, we developed SPEAR (Safety, Personalization, Evidence, Actionability, Robustness) and validated OMGs across diverse clinical scenarios spanning the care continuum. In multicentre re-evaluation, OMGs achieved performance comparable to expert MDT consensus ($4.45 \pm 0.30$ versus $4.53 \pm 0.23$), with higher Evidence scores (4.57 versus 3.92). In prospective multicentre evaluation (59 patients), OMGs demonstrated high concordance with routine MDT decisions. Critically, in paired human-AI studies, OMGs most substantially enhanced clinicians' recommendations in Evidence and Robustness, the dimensions most compromised when multidisciplinary expertise is unavailable. These findings suggest that multi-agent deliberative systems can achieve performance comparable to expert MDT consensus, with potential to expand access to specialized oncology expertise in resource-limited settings.

cs.CL↗
arXiv2026

QoE-Driven Multi-Task Offloading for Semantic-Aware Edge Computing Systems

Mobile edge computing (MEC) provides low-latency offloading solutions for computationally intensive tasks, effectively improving the computing efficiency and battery life of mobile devices. However, for data-intensive tasks or scenarios with limited uplink bandwidth, network congestion might occur due to massive simultaneous offloading nodes, increasing transmission latency and affecting task performance. In this paper, we propose a semantic-aware multi-modal task offloading framework to address the challenges posed by limited uplink bandwidth. By introducing a semantic extraction factor, we balance the relationship among transmission latency, computation energy consumption, and task performance. To measure the offloading performance of multi-modal tasks, we design a unified and fair quality of experience (QoE) metric that includes execution latency, energy consumption, and task performance. Lastly, we formulate the optimization problem as a Markov decision process (MDP) and exploit the multi-agent proximal policy optimization (MAPPO) reinforcement learning algorithm to jointly optimize the semantic extraction factor, communication resources, and computing resources to maximize overall QoE. Experimental results show that the proposed method achieves a reduction in execution latency and energy consumption of 18.1% and 12.9%, respectively compared with the semantic-unaware approach. Moreover, the proposed approach can be easily extended to models with different user preferences.

cs.NI↗
arXiv2026

MOVA: Towards Scalable and Synchronized Video-Audio Generation

Audio is indispensable for real-world video, yet generation models have largely overlooked audio components. Current approaches to producing audio-visual content often rely on cascaded pipelines, which increase cost, accumulate errors, and degrade overall quality. While systems such as Veo 3 and Sora 2 emphasize the value of simultaneous generation, joint multimodal modeling introduces unique challenges in architecture, data, and training. Moreover, the closed-source nature of existing systems limits progress in the field. In this work, we introduce MOVA (MOSS Video and Audio), an open-source model capable of generating high-quality, synchronized audio-visual content, including realistic lip-synced speech, environment-aware sound effects, and content-aligned music. MOVA employs a Mixture-of-Experts (MoE) architecture, with a total of 32B parameters, of which 18B are active during inference. It supports IT2VA (Image-Text to Video-Audio) generation task. By releasing the model weights and code, we aim to advance research and foster a vibrant community of creators. The released codebase features comprehensive support for efficient inference, LoRA fine-tuning, and prompt enhancement.

cs.CV↗
arXiv2026

Analysis of Converged 3D Gaussian Splatting Solutions: Density Effects and Prediction Limit

We investigate what structure emerges in 3D Gaussian Splatting (3DGS) solutions from standard multi-view optimization. We term these Rendering-Optimal References (RORs) and analyze their statistical properties, revealing stable patterns: mixture-structured scales and bimodal radiance across diverse scenes. To understand what determines these parameters, we apply learnability probes by training predictors to reconstruct RORs from point clouds without rendering supervision. Our analysis uncovers fundamental density-stratification. Dense regions exhibit geometry-correlated parameters amenable to render-free prediction, while sparse regions show systematic failure across architectures. We formalize this through variance decomposition, demonstrating that visibility heterogeneity creates covariance-dominated coupling between geometric and appearance parameters in sparse regions. This reveals the dual character of RORs: geometric primitives where point clouds suffice, and view synthesis primitives where multi-view constraints are essential. We provide density-aware strategies that improve training robustness and discuss architectural implications for systems that adaptively balance feed-forward prediction and rendering-based refinement.

cs.CV↗
arXiv2026

Efficient Post-Training Pruning of Large Language Models with Statistical Correction

Post-training pruning is an effective approach for reducing the size and inference cost of large language models (LLMs), but existing methods often face a trade-off between pruning quality and computational efficiency. Heuristic pruning methods are efficient but sensitive to activation outliers, while reconstruction-based approaches improve fidelity at the cost of heavy computation. In this work, we propose a lightweight post-training pruning framework based on first-order statistical properties of model weights and activations. During pruning, channel-wise statistics are used to calibrate magnitude-based importance scores, reducing bias from activation-dominated channels. After pruning, we apply an analytic energy compensation to correct distributional distortions caused by weight removal. Both steps operate without retraining, gradients, or second-order information. Experiments across multiple LLM families, sparsity patterns, and evaluation tasks show that the proposed approach improves pruning performance while maintaining computational cost comparable to heuristic methods. The results suggest that simple statistical corrections can be effective for post-training pruning of LLMs.

cs.CL↗
arXiv2026

A Tutorial on 3GPP Rel-19 Channel Modeling for 6G FR3 (7-24 GHz): From Standard Specification to Simulation Implementation

The upper-mid band (7-24 GHz), designated as Frequency Range 3 (FR3), has emerged as a definitive ``golden band" for 6G networks, strategically balancing the wide coverage of sub-6 GHz with the high capacity of mmWave. To compensate for the severe path loss inherent to this band, the deployment of Extremely Large Aperture Arrays (ELAA) is indispensable. However, the legacy 3GPP TR 38.901 channel model faces critical validity challenges when applied to 6G FR3, stemming from both the distinct propagation characteristics of this frequency band and the fundamental physical paradigm shift induced by ELAA. In response, 3GPP Release 19 (Rel-19) has validated the model through extensive new measurements and introduced significant enhancements. This tutorial provides a comprehensive guide to the Rel-19 channel model for 6G FR3, bridging the gap between standardization specifications and practical simulation implementation. First, we provide a high-level overview of the fundamental principles of the 3GPP channel modeling framework. Second, we detail the specific enhancements and modifications introduced in Rel-19, including the rationale behind the new Suburban Macro (SMa) scenario, the mathematical modeling of ELAA-driven features such as near-field and spatial non-stationarity, and the recalibration of large-scale parameters. Overall, this tutorial serves as an essential guide for researchers and engineers to master the latest 3GPP channel modeling methodology, laying a solid foundation for the accurate design and performance evaluation of future 6G FR3 networks.

eess.SP↗
arXiv2026

EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering

Agentic Test-Time Scaling (TTS) has delivered state-of-the-art (SOTA) performance on complex software engineering tasks such as code generation and bug fixing. However, its practical adoption remains limited due to significant computational overhead, primarily driven by two key challenges: (1) the high cost associated with deploying excessively large ensembles, and (2) the lack of a reliable mechanism for selecting the optimal candidate solution, ultimately constraining the performance gains that can be realized. To address these challenges, we propose Entropy-Guided Stepwise Scaling (EGSS), a novel TTS framework that dynamically balances efficiency and effectiveness through entropy-guided adaptive search and robust test-suite augmentation. Extensive experiments on SWE-Bench-Verified demonstrate that EGSS consistently boosts performance by 5-10% across all evaluated models. Specifically, it increases the resolved ratio of Kimi-K2-Intruct from 63.2% to 72.2%, and GLM-4.6 from 65.8% to 74.6%. Furthermore, when paired with GLM-4.6, EGSS achieves a new state-of-the-art among open-source large language models. In addition to these accuracy improvements, EGSS reduces inference-time token usage by over 28% compared to existing TTS methods, achieving simultaneous gains in both effectiveness and computational efficiency.

cs.SE↗