arXiv subjects

Zhiqiang Zhou

Publications and source records attributed to Zhiqiang Zhou.

At least 19 recordsLinked to original sources

arXiv2026

Bridging Severe Cross-Modal Misalignment: End-to-End Visible-Infrared Object Detection via Explicit Feature-Domain Affine Registration

Visible-infrared object detection relies on complementary RGB and thermal cues, but its performance is often degraded by cross-modal spatial misalignment. Most existing methods rely on implicit feature adaptation to handle weakly misaligned scenarios, while large-offset geometric discrepancies remain insufficiently addressed. In this paper, we propose a Joint Feature-domain Registration and Detection network (JFRDet), an end-to-end visible-infrared oriented object detector tailored for severely cross-modal geometric discrepancies. JFRDet introduces a Cross-Modal Affine Alignment (CMAA) module to estimate an image-level affine transformation for explicit multi-level feature alignment. Note that illumination changes directly affect the reliability of RGB cues, an Illumination-Guided Complementary Fusion (IGCF) module adaptively exploits modality reliability under varying illumination conditions for cross-modal fusion. Then, an Alignment Quality-Consistency Gating (AQCG) strategy stabilizes joint optimization by modulating detection supervision according to alignment reliability and gradient consistency. We further construct DroneVehicle Misaligned (DVMA), a benchmark for evaluating visible-infrared oriented object detection under severe cross-modal geometric misalignment. The proposed JFRDet achieves 69.7\% $\mathrm{mAP}_{50}$ on DVMA, which represents state-of-the-art (SOTA) performance. The code and dataset will be available on GitHub.

cs.CV↗

arXiv2026

FiLM-Coordinated Dual-Branch Transformer for Global-Local Dependency Modeling in Language Modeling

Standard Transformers use a single self-attention pathway to model both global dependencies and local patterns, creating tension between long-range structural reasoning and fine-grained local representation learning. We propose a FiLM-coordinated dual-branch Transformer for language modeling, where each layer explicitly contains a global branch and a local branch, and feature-wise linear modulation (FiLM) is used for dynamic cross-branch coordination instead of simple concatenation or static addition. The key idea is that the two branches represent different dependency views of the same input, making channel-wise calibration more suitable than heavy token-level interaction. We therefore design a bidirectional FiLM module in which each branch generates per-channel scaling and shifting parameters to condition the other. Experiments on multiple small-scale language modeling settings show that the proposed structure consistently outperforms same-width single-branch baselines and weakened dual-branch variants under a fixed lightweight configuration. On TinyShakespeare and a 1M-character subset of WikiText-2, the full dual-branch FiLM model achieves the best results among same-width structural baselines. Multi-seed results support the stability of the gains, while mechanistic analyses show that FiLM learns input-dependent, layer-dependent, and channel-selective modulation patterns rather than static scaling. Parameter-matched widened single-branch baselines also indicate that the current design still leaves room for improvement in parameter efficiency.

cs.CL↗

arXiv2026

Gen-VCoT: Generative Visual Chain-of-Thought Reasoning via Diffusion-Based RGB Intermediate Representations

Multimodal large language models (MLLMs) excel at visual reasoning but rely on text-based chain-of-thought (CoT), lacking interpretable visual intermediates. Existing methods use opaque tokens or external tools, missing key properties. We propose Gen-VCoT, a framework using expert vision models to generate RGB images as reasoning intermediates. It has three stages: visual grounding (SAM segmentation), geometric reasoning (Marigold depth maps), and semantic reasoning (Qwen2-VL integration). An adaptive router selects reasoning depth. Evaluations show Gen-VCoT improves spatial (25% better) and depth (50% better) questions, but may hurt simple factual queries. Text CoT outperforms visual intermediates on CLEVR (91.2% vs 62.5%), showing task-dependent optimal representations. Gen-VCoT establishes a new paradigm for interpretable multimodal reasoning.

cs.CV↗

arXiv2026

TriAdReview: Triangular Adversarial Review Architecture for Multi-Model Technical Document Generation

Large language models (LLMs) are increasingly used for technical document generation, yet single-model outputs often suffer from over-engineering, security blind spots, and incomplete coverage. We propose TriAdReview, a triangular adversarial review architecture that employs two independent reviewer models (engineering and boundary perspectives) and a triangular judging mechanism to iteratively improve a generator model's output. We evaluate TriAdReview across five benchmark tasks - architecture design, code generation, proposal review, security audit, and requirements analysis - using three configurations: single model (baseline), dual model (single review), and triple model (full system). Results across 75 experiments (n=5 per cell) show that the triple model configuration achieves a 10.1% overall improvement over the single model baseline (26.2 vs. 23.8 out of 50; p<0.05, paired t-test), with particularly strong gains on security audit (+27.6%), code generation (+20.8%), and architecture design (+15.6%). A second scorer (mimo-v2.5-pro) confirms the direction with a smaller effect (+2.7%), suggesting moderate inter-rater agreement. However, the system shows a -7.5% degradation on requirements analysis, revealing that adversarial review architectures have a structural bias toward simplification that is counterproductive for completeness-oriented tasks. We analyze this boundary condition through a task-type framework and demonstrate that reviewer prompt adaptation partially mitigates the issue. Our findings provide the first empirical characterization of when multi-model adversarial review helps versus harms, with implications for the design of collaborative AI systems.

cs.LG↗

arXiv2026

CLP: Collocation-Length Prediction for Zero-Loss Adaptive Multi-Token Inference

Large language model inference is bottlenecked by autoregressive decoding, where each token requires a full forward pass. Multi-token prediction (MTP) offers a promising acceleration path, but existing approaches suffer from a fundamental architectural flaw: the MTP head for the first token competes with the backbone's own language model (LM) head, leading to severe quality degradation when predictions are accepted. We identify this head-backbone competition as the root cause of repetitive and incoherent outputs in prior MTP-based acceleration methods. To address this, we propose Backbone-as-Architect, a design principle where the backbone LM head always generates the first token, and MTP heads are responsible only for subsequent tokens. Building on this principle, we introduce CLP (Collocation-Length Predictor), a lightweight span-level decision layer that predicts how many additional tokens can be safely accepted at each decoding step. CLP uses only a single linear layer (4.6K--7.7K parameters), replacing the over-engineered 1M-parameter gate networks used in prior work. Experiments on Qwen2.5 models (0.5B, 1.5B, 7B) show that CLP achieves 1.20x--1.29x speedup on 1.5B and 1.14x--1.20x on 7B, with zero quality degradation (repetition ratio < 0.02), while gate-based approaches fail to accelerate (1.07x) or produce severely degraded outputs (repetition ratio > 0.5%). We further demonstrate that shorter prediction horizons (k=2) recover 24% higher MTP head accuracy on large models, establishing a scaling-aware design principle. We identify MTP head prediction accuracy as the binding constraint on acceleration and establish a clear roadmap for future improvements.

cs.LG↗

arXiv2026

Feature Alignment Determines Fusion Strategy: A Comparative Study of Cross-Attention and Concatenation in Multimodal Learning

The choice between cross-attention and concatenation for multimodal fusion remains governed by practitioner intuition rather than principled understanding. In this paper, we demonstrate that feature alignment quality, not data scale alone, is the primary determinant of which fusion strategy excels. Through controlled experiments on Flickr8k using two feature extraction backbones (ResNet18 and CLIP ViT-B/32), we show that concatenation outperforms cross-attention by 4.1-5.1 percentage points across all tested scales (2048-16384 samples) when features are pre-aligned by a vision-language pretraining objective. We provide a theoretical explanation grounded in sample complexity analysis: concatenation requires O(d_v + d_t) samples to learn its fusion projection, while cross-attention requires O(d_v * d_t) samples to learn bilinear attention weights, over 256 times as many for 512-dimensional CLIP features. When features are already aligned, the approximation error gap between the two methods vanishes, and concatenation's sample efficiency dominates at all practical dataset sizes. An alignment degradation study confirms a monotonic trend: as feature alignment degrades, concatenation's advantage grows from 1.3% to 2.8%. These findings provide a principled decision framework for fusion method selection in multimodal systems, with direct implications for the design of Multimodal Large Language Models.

cs.CV↗

arXiv2025

Each Prompt Matters: Scaling Reinforcement Learning Without Wasting Rollouts on Hundred-Billion-Scale MoE

We present CompassMax-V3-Thinking, a hundred-billion-scale MoE reasoning model trained with a new RL framework built on one principle: each prompt must matter. Scaling RL to this size exposes critical inefficiencies-zero-variance prompts that waste rollouts, unstable importance sampling over long horizons, advantage inversion from standard reward models, and systemic bottlenecks in rollout processing. To overcome these challenges, we introduce several unified innovations: (1) Multi-Stage Zero-Variance Elimination, which filters out non-informative prompts and stabilizes group-based policy optimization (e.g. GRPO) by removing wasted rollouts; (2) ESPO, an entropy-adaptive optimization method that balances token-level and sequence-level importance sampling to maintain stable learning dynamics; (3) a Router Replay strategy that aligns training-time MoE router decisions with inference-time behavior to mitigate train-infer discrepancies, coupled with a reward model adjustment to prevent advantage inversion; (4) a high-throughput RL system with FP8-precision rollouts, overlapped reward computation, and length-aware scheduling to eliminate performance bottlenecks. Together, these contributions form a cohesive pipeline that makes RL on hundred-billion-scale MoE models stable and efficient. The resulting model delivers strong performance across both internal and public evaluations.

cs.AI↗

arXiv2025

Infrared and Visible Image Fusion with Language-Driven Loss in CLIP Embedding Space

Infrared-visible image fusion (IVIF) has attracted much attention owing to the highly-complementary properties of the two image modalities. Due to the lack of ground-truth fused images, the fusion output of current deep-learning based methods heavily depends on the loss functions defined mathematically. As it is hard to well mathematically define the fused image without ground truth, the performance of existing fusion methods is limited. In this paper, we propose to use natural language to express the objective of IVIF, which can avoid the explicit mathematical modeling of fusion output in current losses, and make full use of the advantage of language expression to improve the fusion performance. For this purpose, we present a comprehensive language-expressed fusion objective, and encode relevant texts into the multi-modal embedding space using CLIP. A language-driven fusion model is then constructed in the embedding space, by establishing the relationship among the embedded vectors representing the fusion objective and input image modalities. Finally, a language-driven loss is derived to make the actual IVIF aligned with the embedded language-driven fusion model via supervised training. Experiments show that our method can obtain much better fusion results than existing techniques. The code is available at https://github.com/wyhlaowang/LDFusion.

cs.CV↗

arXiv2025

Towards Reliable Evaluation of Large Language Models for Multilingual and Multimodal E-Commerce Applications

Large Language Models (LLMs) excel on general-purpose NLP benchmarks, yet their capabilities in specialized domains remain underexplored. In e-commerce, existing evaluations-such as EcomInstruct, ChineseEcomQA, eCeLLM, and Shopping MMLU-suffer from limited task diversity (e.g., lacking product guidance and after-sales issues), limited task modalities (e.g., absence of multimodal data), synthetic or curated data, and a narrow focus on English and Chinese, leaving practitioners without reliable tools to assess models on complex, real-world shopping scenarios. We introduce EcomEval, a comprehensive multilingual and multimodal benchmark for evaluating LLMs in e-commerce. EcomEval covers six categories and 37 tasks (including 8 multimodal tasks), sourced primarily from authentic customer queries and transaction logs, reflecting the noisy and heterogeneous nature of real business interactions. To ensure both quality and scalability of reference answers, we adopt a semi-automatic pipeline in which large models draft candidate responses subsequently reviewed and modified by over 50 expert annotators with strong e-commerce and multilingual expertise. We define difficulty levels for each question and task category by averaging evaluation scores across models with different sizes and capabilities, enabling challenge-oriented and fine-grained assessment. EcomEval also spans seven languages-including five low-resource Southeast Asian languages-offering a multilingual perspective absent from prior work.

cs.AI↗

arXiv2025

Mid-Training of Large Language Models: A Survey

Large language models (LLMs) are typically developed through large-scale pre-training followed by task-specific fine-tuning. Recent advances highlight the importance of an intermediate mid-training stage, where models undergo multiple annealing-style phases that refine data quality, adapt optimization schedules, and extend context length. This stage mitigates diminishing returns from noisy tokens, stabilizes convergence, and expands model capability in late training. Its effectiveness can be explained through gradient noise scale, the information bottleneck, and curriculum learning, which together promote generalization and abstraction. Despite widespread use in state-of-the-art systems, there has been no prior survey of mid-training as a unified paradigm. We introduce the first taxonomy of LLM mid-training spanning data distribution, learning-rate scheduling, and long-context extension. We distill practical insights, compile evaluation benchmarks, and report gains to enable structured comparisons across models. We also identify open challenges and propose avenues for future research and practice.

cs.CL↗

arXiv2025

Faster and Better: Reinforced Collaborative Distillation and Self-Learning for Infrared-Visible Image Fusion

Infrared and visible image fusion plays a critical role in enhancing scene perception by combining complementary information from different modalities. Despite recent advances, achieving high-quality image fusion with lightweight models remains a significant challenge. To bridge this gap, we propose a novel collaborative distillation and self-learning framework for image fusion driven by reinforcement learning. Unlike conventional distillation, this approach not only enables the student model to absorb image fusion knowledge from the teacher model, but more importantly, allows the student to perform self-learning on more challenging samples to enhance its capabilities. Particularly, in our framework, a reinforcement learning agent explores and identifies a more suitable training strategy for the student. The agent takes both the student's performance and the teacher-student gap as inputs, which leads to the generation of challenging samples to facilitate the student's self-learning. Simultaneously, it dynamically adjusts the teacher's guidance strength based on the student's state to optimize the knowledge transfer. Experimental results demonstrate that our method can significantly improve student performance and achieve better fusion results compared to existing techniques.

cs.CV↗

arXiv2025

CoCAViT: Compact Vision Transformer with Robust Global Coordination

In recent years, large-scale visual backbones have demonstrated remarkable capabilities in learning general-purpose features from images via extensive pre-training. Concurrently, many efficient architectures have emerged that have performance comparable to that of larger models on in-domain benchmarks. However, we observe that for smaller models, the performance drop on out-of-distribution (OOD) data is disproportionately larger, indicating a deficiency in the generalization performance of existing efficient models. To address this, we identify key architectural bottlenecks and inappropriate design choices that contribute to this issue, retaining robustness for smaller models. To restore the global field of pure window attention, we further introduce a Coordinator-patch Cross Attention (CoCA) mechanism, featuring dynamic, domain-aware global tokens that enhance local-global feature modeling and adaptively capture robust patterns across domains with minimal computational overhead. Integrating these advancements, we present CoCAViT, a novel visual backbone designed for robust real-time visual representation. Extensive experiments empirically validate our design. At a resolution of 224*224, CoCAViT-28M achieves 84.0% top-1 accuracy on ImageNet-1K, with significant gains on multiple OOD benchmarks, compared to competing models. It also attains 52.2 mAP on COCO object detection and 51.3 mIOU on ADE20K semantic segmentation, while maintaining low latency.

cs.CV↗

arXiv2025

Coulomb Crystallization of Highly Charged Ni^12+ Ions in a Linear Paul Trap

Optical clocks have garnered widespread attention due to their unparalleled precision in time-frequency standards, geodetic measurements, and fundamental physics research. Among emerging developments, highly charged ion (HCI)-based optical clocks have attracted significant scientific interest owing to their exceptional resilience against electromagnetic perturbations and enhanced sensitivity to variations in the fine-structure constant ($α$). While the recent successful demonstration of an Ar$^{13+}$ optical clock has validated the feasibility of HCI-based systems, Ni$^{12+}$ -- featuring an ultranarrow clock transition linewidth -- stands out as a superior candidate for achieving HCI optical clocks with $10^{-19}$ level uncertainty and stability. In this work, we report the Coulomb crystallization of nickel highly charged ions (Ni-HCIs). Through a precision deceleration and sympathetic cooling protocol in a room-temperature Paul trap, high-energy Ni-HCI bunches were sympathetically cooled from megakelvin to the 100-millikelvin range using laser-cooled Be$^{+}$ ions. This work represents a pivotal step toward the realization of an optical clock based on the Ni$^{12+}$ ion.

physics.atom-ph↗

arXiv2024

GraphSubDetector: Time Series Subsequence Anomaly Detection via Density-Aware Adaptive Graph Neural Network

Time series subsequence anomaly detection is an important task in a large variety of real-world applications ranging from health monitoring to AIOps, and is challenging due to the following reasons: 1) how to effectively learn complex dynamics and dependencies in time series; 2) diverse and complicated anomalous subsequences as well as the inherent variance and noise of normal patterns; 3) how to determine the proper subsequence length for effective detection, which is a required parameter for many existing algorithms. In this paper, we present a novel approach to subsequence anomaly detection, namely GraphSubDetector. First, it adaptively learns the appropriate subsequence length with a length selection mechanism that highlights the characteristics of both normal and anomalous patterns. Second, we propose a density-aware adaptive graph neural network (DAGNN), which can generate further robust representations against variance of normal data for anomaly detection by message passing between subsequences. The experimental results demonstrate the effectiveness of the proposed algorithm, which achieves superior performance on multiple time series anomaly benchmark datasets compared to state-of-the-art algorithms.

cs.LG↗

arXiv2024

Semantic Object-level Modeling for Robust Visual Camera Relocalization

Visual relocalization is crucial for autonomous visual localization and navigation of mobile robotics. Due to the improvement of CNN-based object detection algorithm, the robustness of visual relocalization is greatly enhanced especially in viewpoints where classical methods fail. However, ellipsoids (quadrics) generated by axis-aligned object detection may limit the accuracy of the object-level representation and degenerate the performance of visual relocalization system. In this paper, we propose a novel method of automatic object-level voxel modeling for accurate ellipsoidal representations of objects. As for visual relocalization, we design a better pose optimization strategy for camera pose recovery, to fully utilize the projection characteristics of 2D fitted ellipses and the 3D accurate ellipsoids. All of these modules are entirely intergrated into visual SLAM system. Experimental results show that our semantic object-level mapping and object-based visual relocalization methods significantly enhance the performance of visual relocalization in terms of robustness to new viewpoints.

cs.CV↗

arXiv2023

Precision Measurement of M1 Optical Clock Transition in Ni12+

Highly charged ions (HCIs) have drawn significant interest in quantum metrology and in search for new physics. Among these, Ni12+ is considered as one of the most promising candidates for the next generation of HCI optical clocks, due to its two E1-forbidden transitions M1 and E2, which occur in the visible spectral range. In this work, we used the Shanghai-Wuhan Electron Beam Ion Trap to perform a high-precision measurement of the M1 transition wavelength. Our approach involved an improved calibration scheme for the spectra, utilizing auxiliary Ar+ lines for calibration and correction. Our final measured result of the M1 transition wavelength demonstrates a five-fold improvement in accuracy compared to our previous findings, reaching the sub-picometer level accuracy. In combination with our rigorous atomic-structure calculations to capture the electron correlations and relativistic effects, the quantum electrodynamic (QED) corrections were extracted. Moreover, comparing with an estimate of the one-electron QED contributions by using the GRASP2018 package, we found that the present experimental accuracy is high enough for testing the higher-order QED corrections for such a complex system with four electrons in the p subshell.

physics.atom-ph↗

arXiv2023

AHPA: Adaptive Horizontal Pod Autoscaling Systems on Alibaba Cloud Container Service for Kubernetes

The existing resource allocation policy for application instances in Kubernetes cannot dynamically adjust according to the requirement of business, which would cause an enormous waste of resources during fluctuations. Moreover, the emergence of new cloud services puts higher resource management requirements. This paper discusses horizontal POD resources management in Alibaba Cloud Container Services with a newly deployed AI algorithm framework named AHPA -- the adaptive horizontal pod auto-scaling system. Based on a robust decomposition forecasting algorithm and performance training model, AHPA offers an optimal pod number adjustment plan that could reduce POD resources and maintain business stability. Since being deployed in April 2021, this system has expanded to multiple customer scenarios, including logistics, social networks, AI audio and video, e-commerce, etc. Compared with the previous algorithms, AHPA solves the elastic lag problem, increasing CPU usage by 10% and reducing resource cost by more than 20%. In addition, AHPA can automatically perform flexible planning according to the predicted business volume without manual intervention, significantly saving operation and maintenance costs.

cs.LG↗

arXiv2023

Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment

The goal of sequential event prediction is to estimate the next event based on a sequence of historical events, with applications to sequential recommendation, user behavior analysis and clinical treatment. In practice, the next-event prediction models are trained with sequential data collected at one time and need to generalize to newly arrived sequences in remote future, which requires models to handle temporal distribution shift from training to testing. In this paper, we first take a data-generating perspective to reveal a negative result that existing approaches with maximum likelihood estimation would fail for distribution shift due to the latent context confounder, i.e., the common cause for the historical events and the next event. Then we devise a new learning objective based on backdoor adjustment and further harness variational inference to make it tractable for sequence learning problems. On top of that, we propose a framework with hierarchical branching structures for learning context-specific representations. Comprehensive experiments on diverse tasks (e.g., sequential recommendation) demonstrate the effectiveness, applicability and scalability of our method with various off-the-shelf models as backbones.

cs.LG↗