arXiv subjects

Chang Gao

Publications and source records attributed to Chang Gao.

At least 19 recordsLinked to original sources

arXiv2026

RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents

Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development through code and the command line. Real digital work requires both, interleaved rather than stacked end to end. We study hybrid CUAs that autonomously decide when to explore an interface, implement software, and run and visually verify their artifacts. We introduce RecreationWorld, a five-platform framework built around recreation: given a running reference, an agent must discover its behavior and build a faithful implementation with no prescribed workflow. RecreationWorld provides reproducible environments on Ubuntu, macOS, Windows, Android, and Web, plus a unified harness with native GUI control and coding tools. The running reference serves as an oracle for hidden behavioral tests, providing execution-grounded rewards. We scale trajectory generation with high-quality open-source applications. Models trained on these trajectories improve across five out-of-distribution coding and hybrid computer-use benchmarks and more frequently verify their rendered outputs, providing evidence of transfer beyond recreation. For held-out evaluation, we introduce RecreationBench, comprising 250 diverse tasks across domains and platforms. Reference-grounded programmatic and visual assertions cover action-conditioned outcomes at multiple interaction depths; each is validated on the reference and by human reviewers before the suite is frozen for automatic scoring. GPT-6 Astra leads at 58.1% overall, but passes all programmatic tests on just 2.8% of tasks. Agents reproduce static interface structure more reliably than interactions and computed outputs, while generated applications remain smaller and more monolithic than their references. We release the benchmark, environments, and test suites.

cs.CL↗

arXiv2026

AVT-Fabric: Active Visuo-Tactile Perception via Adaptive Evidence Selection for Efficient Robotic Fabric Comparison

Robotic fabric comparison needs to actively combine visual appearance and tactile cues. Here, we present AVT-Fabric, an RGB-first framework that allocates tactile evidence according to the difficulty of each comparison. A dual-scale gate evaluates answer-token confidence and raw logit separation to determine whether another force-tagged GelSight observation is needed. Compact textual memory preserves the executed history, and majority voting consolidates the selected predictions. On 400 held-out comparisons, AVT-Fabric achieves 98.0% accuracy with a compact 7B Multimodal Large Language Model (MLLM), surpassing the 94.0% reported by the 90B MLLM-Fabric baseline by 4.0 percentage points while processing only 1.60 of five available stages on average. It improves on matched passive inference by 9.25 percentage points and reduces model-side latency by 61.8%, while also improving on RGB-only accuracy. Four additional MLLM backbones support the generalizability, accuracy, and efficiency of the framework. This framework is also deployed on a real robotic system, achieving 78.1% pairwise ranking accuracy and correct fabric selection in seven of eight application scenarios. AVT-Fabric demonstrates that adaptive evidence selection can improve both the accuracy and efficiency of robotic visuo-tactile reasoning.

cs.RO↗

arXiv2026

GrainSpeech: Less Context, More Detail for Compact Speech Synthesis

Compact acoustic models face a challenging quality-capacity trade-off. We investigate two factors in this regime: encoder context and Mel-spectrogram supervision. A receptive-field-scaling study shows that expanding self-attention beyond 15 phonemes provides no consistent gains in pitch, energy, or duration prediction. Guided by this finding, we introduce a fixed-receptive-field convolutional encoder that reduces the respective prediction errors by 36.0%, 17.3%, and 3.4%. We further show that directly transferring image-domain gradient-variance supervision restores fine-scale variation but degrades predicted quality, motivating a Mel-specific formulation with axis-specific gradients, overlapping local statistics, and log-domain variance matching. GrainSpeech contains only 264.8K parameters and achieves 17.9x real-time Mel generation on a microcontroller (MCU), while attaining UTMOS scores comparable to substantially larger models with less than 1.5% of their parameters. Source code and demos are available at https://github.com/lab-emi/GrainSpeech.

eess.AS↗

arXiv2026

Deep Uncertainty-aware Tracking for Maneuvering Targets

Traditional target tracking approaches typically presuppose a target motion model. Once the target maneuvers, the model may get mismatched and is incapable of depicting the complex motion characteristics of the target. Most data-driven methods are designed based on a regression-only framework, which increases the difficulty of network training. Moreover, these methods are typically designed under the assumption of a fixed measurement noise distribution. However, the measurement noise distribution of actual radar is influenced by fluctuations in the target's radar cross section. Such fluctuations may lead to a degradation in tracking performance. In this paper, we propose a representation method for radar measurements, referred to as the measurement uncertainty projection operator (MUPO). It projects the measurement onto a target state space to capture the measurement noise distribution. Additionally, we propose a framework that reformulates maneuvering target tracking as a hybrid task of classification and regression. To realize the functionality of this framework, we establish a MUPO-based target tracking network. The rationality of the proposed network structure is supported by the validation experiment. Numerical results demonstrate that the proposed method achieves superior estimation precision compared with existing data-driven methods during target maneuvers. Furthermore, the proposed algorithm retains its superior tracking performance when extended to 3D maneuvering target tracking and multi-target tracking scenarios.

eess.SP↗

arXiv2026

OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding

Large language model (LLM) agents are increasingly expected to assist users in completing tasks. However, existing benchmarks provide limited support for evaluating whether agents can carry out office-suite workflows at a reasonable cost. We introduce OmegaUse-OfficeVal, a benchmark for evaluating LLM agents on long-horizon office-suite tasks with task-level economic grounding. The benchmark comprises 100 tasks derived from office-suite requests proposed by practitioners and adapted through a privacy-preserving process. On average, these tasks require 2.32 hours of human labor to complete. An important feature of the benchmark is that each task is paired with two economic signals: human labor time and task price proxy. These signals enable direct comparisons between human costs and LLM inference costs, as well as value-weighted evaluation. To support stable evaluation, we develop code-based verifiers from fine-grained rubrics. We evaluate several frontier LLMs together with a human baseline. Although all evaluated LLMs are substantially cheaper and faster than human workers, they have not yet approached human-level deliverable quality. The code and dataset are fully open-sourced, and more information is available on our project website: https://omegause-officeval.github.io.

cs.AI↗

arXiv2026

OpenDPDv2: A Unified Learning and Optimization Framework for Neural Network Digital Predistortion

Neural network (NN)-based Digital Predistortion (DPD) improves linearization for wideband radio frequency (RF) power amplifiers (PAs) but often increases the complexity of the digital back-end. This paper presents OpenDPDv2, an open-source end-to-end framework that unifies PA modeling, NN-DPD learning, and deployment-oriented optimization. OpenDPDv2 introduces temporal residual (TRes)-Delta Gated Recurrent Unit (DeltaGRU), a delta-RNN DPD architecture with a lightweight temporal residual path for robust operation under aggressive temporal sparsity, and supports joint optimization with fixed-point quantization. On a 3.5 GHz GaN Doherty PA driven by a TM3.1a 200 MHz 256-QAM OFDM signal, the FP32 TRes-DeltaGRU model achieves -59.9 dBc Adjacent Channel Power Ratio (ACPR) and -42.1 dB Error Vector Magnitude (EVM). With 56% temporal sparsity and W12A12 quantization, the model uses 450 active parameters while maintaining -51.8 dBc ACPR and -35.2 dB EVM. Timing-accurate Gem5-based evaluation further indicates a 4.5x reduction in forward-pass energy for this deployment-oriented operating point. Code, datasets, and documentation are publicly available at https://github.com/lab-emi/OpenDPD.

eess.SP↗

arXiv2026

BitFair: A 12-nm Bit-Serial CNN Accelerator with Learnable Early Termination and Adaptive Bit Ordering for Ultra-Low-Power XR Vision

Extended Reality (XR) wearables require always-on perception within tight power envelopes of a few watts and motion-to-photon latency budgets below 20 ms, leaving only a few milliseconds for neural-network inference. Bit-serial computing is attractive for such energy-efficient neural network acceleration, but many existing architectures still process all bits even when ReLU sets the final output to zero. This paper presents BitFair, a software-hardware co-designed bit-serial CNN accelerator with learnable bit-level early termination and adaptive bit ordering, working under the ultra-low-power and strict latency requirements of XR applications. BitFair exploits dynamic bit-level sparsity by learning per-layer thresholds that trigger early termination when partial sums reliably predict that the final ReLU output will be zero. Furthermore, it searches for layer-wise bit orders that prioritize informative bits, maximizing early termination without sacrificing accuracy. A GlobalFoundries 12-nm FinFET implementation with a core area of 0.34 mm^2, 104 KB on-chip memory, and voltage scaling from 0.55 to 0.70 V achieves sub-millisecond latency, up to 117.0 BTOPS/W, and 0.07 pJ/SOP. On IBM DVS128 Gesture and N-MNIST, BitFair achieves 96.5% and 97.7% accuracy, respectively, while improving effective energy efficiency by 4.0-22.1x and accuracy by up to 9.2% over prior fabricated XR vision accelerators.

cs.AR↗

arXiv2026

Qwen-CUA: Native Computer Use for (almost) Everything

Native computer use offers a general interface for agents to operate almost any software available to people, but requires long-horizon state tracking, large-scale interactive experience, and learning from sparse yet verifiable outcomes. We introduce Qwen-CUA, a native computer-use agent with a 397B-A17B Qwen mixture-of-experts backbone. It observes only screenshots and acts through keyboard and mouse events, without DOM trees, accessibility metadata, or task-specific APIs. Its scaffold maintains up to 20 active screenshots and folds older visual history in fixed-size blocks to retain recent evidence while preserving reusable prompt prefixes. For training, we build a cloud rollout fleet with access to nearly 100,000 vCPUs and tens of thousands of concurrent environments, construct approximately 40,000 verifiable tasks, and collect personalized long-horizon workflows across everyday and professional software. We optimize complete trajectories with verifiable rewards and trajectory slicing, while iterative training runs refresh supervised data and recalibrate reinforcement-learning tasks. Across eight benchmarks, Qwen-CUA outperforms Qwen3.7 and remains competitive with leading proprietary systems, reaching 86.2 on OSWorld-Verified and 18.5/48.4 binary/partial completion on OSWorld 2.0. Scaling the same recipe to a model with over one trillion parameters yields Qwen-CUA-Max, improving these scores to 87.6 and 21.2/53.3. Qwen-CUA also reduces RedTeamCUA attack success from 36.6 to 16.4 relative to Qwen3.7. Efficiency analyses, a browser deployment, and Bash-augmented experiments further characterize practical behavior. These results establish native computer use as a broadly capable agent foundation and highlight scalable verifiable interaction and hybrid tool use as key directions.

cs.LG↗

arXiv2026

AutoIQ: An Ensemble Framework for Automatic Assessment of Geometric Distortion in Prostate Diffusion-Weighted Imaging

Geometric distortion in prostate diffusion-weighted imaging (DWI) can impair lesion localization and reduce the reliability of MRI-based clinical assessment. We propose AutoIQ, an ensemble machine learning framework for automatic quantification and classification of DWI geometric distortion severity. A total of 140 retrospective prostate biparametric MRI examinations were analyzed, including 33 scans with severe distortion requiring repeat acquisition and 107 scans with acceptable distortion based on expert radiologist assessment. AutoIQ combines two complementary distortion quantification strategies: a segmentation-based method measuring prostate boundary mismatch between T2-weighted imaging (T2WI) and DWI, and a registration-based method estimating deformation magnitude after DWI-to-T2WI alignment. The resulting distortion scores were used to train individual classifiers and a logistic-regression ensemble model. Both computational methods significantly differentiated severe from acceptable distortion cases (p < 0.001). On an independent test set, the ensemble model achieved an accuracy of 0.95, F1-score of 0.93, and AUC of 0.98, outperforming individual models. These results suggest that AutoIQ can provide automated, quantitative quality assessment for prostate DWI and may help identify scans that require repeat acquisition.

eess.IV↗

arXiv2026

Efficient LLM-based Advertising via Model Compression and Parallel Verification

Large language models (LLMs) have shown remarkable potential in advertising scenarios such as ad creative generation and targeted advertising. However, deploying LLMs in real-time advertising systems poses significant challenges due to their high inference latency and computational cost. In this paper, we propose an Efficient Generative Targeting framework that integrates adaptive group quantization, layer-adaptive hierarchical sparsification, and prefix-tree parallel verification to accelerate LLM inference while preserving generation quality. Extensive experiments on two real-world advertising scenarios demonstrate that our framework achieves significant speedup with acceptable quality degradation, making it operationally viable for practical deployments.

cs.CL↗

arXiv2026

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning

Vision-language models (VLMs) show strong multimodal capabilities but still struggle with fine-grained vision-language reasoning. We find that long chain-of-thought (CoT) reasoning exposes diverse failure modes, including perception, reasoning, knowledge, and hallucination errors, which can compound across intermediate steps. However, most existing vision-language data used for reinforcement learning with verifiable rewards (RLVR) does not involve complex reasoning chains that rely on visual evidence throughout, leaving these weaknesses largely unexposed. We therefore propose HopChain, a scalable framework for synthesizing multi-hop vision-language reasoning data for RLVR training of VLMs. Each synthesized multi-hop query forms a logically dependent chain of instance-grounded hops, where earlier hops establish the instances, sets, or conditions needed for later hops, while the final answer remains a specific, unambiguous number suitable for verifiable rewards. We train Qwen3.5-35B-A3B and Qwen3.5-397B-A17B under two RLVR settings: the original data alone, and the original data plus HopChain's multi-hop data, and compare them across 24 benchmarks spanning STEM and Puzzle, General VQA, Text Recognition and Document Understanding, and Video Understanding. Although this multi-hop data is not synthesized for any specific benchmark, it improves 20 of 24 benchmarks on both models, indicating broad and generalizable gains. Consistently, replacing full chained queries with half-multi-hop or single-hop variants reduces the average score across five representative benchmarks from 70.4 to 66.7 and 64.3, respectively. Notably, multi-hop gains peak in long-CoT vision-language reasoning, exceeding 50 points in the ultra-long-CoT regime. These experiments establish HopChain as an effective, scalable framework for synthesizing multi-hop data that improves generalizable vision-language reasoning.

cs.CV↗

arXiv2026

Revealing Behavioral Plasticity in Large Language Models: A Token-Conditional Perspective

In this work, we reveal that Large Language Models (LLMs) possess intrinsic behavioral plasticity-akin to chameleons adapting their coloration to environmental cues-that can be exposed through token-conditional generation and stabilized via reinforcement learning. Specifically, by conditioning generation on carefully selected token prefixes sampled from responses exhibiting desired behaviors, LLMs seamlessly adapt their behavioral modes at inference time (e.g., switching from step-by-step reasoning to direct answering) without retraining. Based on this insight, we propose Token-Conditioned Reinforcement Learning (ToCoRL), a principled framework that leverages RL to internalize this chameleon-like plasticity, transforming transient inference-time adaptations into stable and learnable behavioral patterns. ToCoRL guides exploration with token-conditional generation and keep enhancing exploitation, enabling emergence of appropriate behaviors. Extensive experiments show that ToCoRL enables precise behavioral control without capability degradation. Notably, we show that large reasoning models, while performing strongly on complex mathematics, can be effectively adapted to excel at factual question answering, which was a capability previously hindered by their step-by-step reasoning patterns.

cs.CL↗

arXiv2026

Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models

Generative Reward Models (GenRMs) and LLM-as-a-Judge exhibit deceptive alignment by producing correct judgments for incorrect reasons, as they are trained and evaluated to prioritize Outcome Accuracy, which undermines their ability to generalize during RLHF. We introduce Rationale Consistency, a fine-grained metric that quantifies the alignment between the model's reasoning process and human judgment. Our evaluation of frontier models reveals that rationale consistency effectively discriminates among state-of-the-art models and detects deceptive alignment, while outcome accuracy falls short in both respects. To mitigate this gap, we introduce a hybrid signal that combines rationale consistency with outcome accuracy for GenRM training. Our training method achieves state-of-the-art performance on RM-Bench (87.1%) and JudgeBench (82%), surpassing outcome-only baselines by an average of 5%. Using RM during RLHF, our method effectively improves performance as demonstrated on Arena Hard v2, notably yielding a 7% improvement in creative writing tasks. Further analysis confirms that our method escapes the deceptive alignment trap, effectively reversing the decline in rationale consistency observed in outcome-only training.

cs.CL↗

arXiv2026

Learning Neural Operators from Partial Observations via Latent Autoregressive Modeling

Real-world scientific applications frequently encounter incomplete observational data due to sensor limitations, geographic constraints, or measurement costs. Although neural operators significantly advanced PDE solving in terms of computational efficiency and accuracy, their underlying assumption of fully-observed spatial inputs severely restricts applicability in real-world applications. We introduce the first systematic framework for learning neural operators from partial observation. We identify and formalize two fundamental obstacles: (i) the supervision gap in unobserved regions that prevents effective learning of physical correlations, and (ii) the dynamic spatial mismatch between incomplete inputs and complete solution fields. Specifically, our proposed Latent Autoregressive Neural Operator(LANO) introduces two novel components designed explicitly to address the core difficulties of partial observations: (i) a mask-to-predict training strategy that creates artificial supervision by strategically masking observed regions, and (ii) a Physics-Aware Latent Propagator that reconstructs solutions through boundary-first autoregressive generation in latent space. Additionally, we develop POBench-PDE, a dedicated and comprehensive benchmark designed specifically for evaluating neural operators under partial observation conditions across three PDE-governed tasks. LANO achieves state-of-the-art performance with 18--69$\%$ relative L2 error reduction across all benchmarks under patch-wise missingness with less than 50$\%$ missing rate, including real-world climate prediction. Our approach effectively addresses practical scenarios involving up to 75$\%$ missing rate, to some extent bridging the existing gap between idealized research settings and the complexities of real-world scientific computing.

cs.LG↗

arXiv2025

RadMamba: Efficient Human Activity Recognition through Radar-based Micro-Doppler-Oriented Mamba State-Space Model

Radar-based Human Activity Recognition (HAR) is an attractive alternative to wearables and cameras because it preserves privacy, and is contactless and robust to occlusions. However, dominant Convolutional Neural Network (CNN)- and Recurrent Neural Network (RNN)-based solutions are computationally intensive at deployment, and recent lightweight Vision Transformer (ViT) and State Space Model (SSM) variants still exhibit substantial complexity. In this paper, we present RadMamba, a parameter-efficient, micro-Doppler-oriented Mamba SSM tailored to radar HAR under on-sensor compute, latency, and energy constraints typical of distributed radar systems. RadMamba combines (i) channel fusion with downsampling, (ii) Doppler-aligned segmentation that preserves the physical continuity of Doppler over time, and (iii) convolutional token projections that better capture Doppler-span variations, thereby retaining temporal-Doppler structure while reducing the number of Floating-point Operations per Inference (#FLOP/Inf.). Evaluated across three datasets with different radars and types of activities, RadMamba matches the prior best 99.8% accuracy of a recent SSM-based model on the Continuous Wave (CW) radar dataset, while requiring only 1/400 of its parameters. On a dataset of non-continuous activities with Frequency Modulated Continuous Wave (FMCW) radar, RadMamba remains competitive with leading 92.0% results using about 1/10 of the parameters, and on a continuous FMCW radar dataset it surpasses methods with far more parameters by at least 3%, using only 6.7k parameters. Code: https://github.com/lab-emi/AIRHAR.

cs.CV↗

arXiv2025

Multiframe Detection via Graph Neural Networks: A Link Prediction Approach

Multi-frame detection algorithms can effectively utilize the correlation between consecutive echoes to improve the detection performance of weak targets. Existing efficient multi-frame detection algorithms are typically based on three sequential steps: plot extraction via a relative low primary threshold, track search and track detection. However, these three-stage processing algorithms may result in a notable loss of detection performance and do not fully leverage the available echo information across frames. As to applying graph neural networks in multi-frame detection, the algorithms are primarily based on node classification tasks, which cannot directly output target tracks. In this paper, we reformulate the multi-frame detection problem as a link prediction task in graphs. First, we perform a rough association of multi-frame observations that exceed the low threshold to construct observation association graphs. Subsequently, a multi-feature link prediction network is designed based on graph neural networks, which integrates multi-dimensional information, including echo structure, Doppler information, and spatio-temporal coupling of plots. By leveraging the principle of link prediction, we unifies the processes of track search and track detection into one step to reduce performance loss and directly output target tracks. Experimental results indicate that, compared with traditional single-frame and multi-frame detection algorithms, the proposed algorithm improves the detection performance of weak targets while suppressing false alarms. Additionally, interpretable analysis shows that the designed network effectively integrates the utilized features, allowing for accurate associations between targets and false alarms.

eess.SP↗

arXiv2025

Optimizing Drivers' Discount Order Acceptance Strategies: A Policy-Improved Deep Deterministic Policy Gradient Framework

The rapid expansion of platform integration has emerged as an effective solution to mitigate market fragmentation by consolidating multiple ride-hailing platforms into a single application. To address heterogeneous passenger preferences, third-party integrators provide Discount Express service delivered by express drivers at lower trip fares. For the individual platform, encouraging broader participation of drivers in Discount Express services has the potential to expand the accessible demand pool and improve matching efficiency, but often at the cost of reduced profit margins. This study aims to dynamically manage drivers' acceptance of Discount Express from the perspective of an individual platform. The lack of historical data under the new business model necessitates online learning. However, early-stage exploration through trial and error can be costly in practice, highlighting the need for reliable early-stage performance in real-world deployment. To address these challenges, this study formulates the decision regarding the proportion of drivers accepting discount orders as a continuous control task. In response to the high stochasticity and the opaque matching mechanisms employed by third-party integrator, we propose an innovative policy-improved deep deterministic policy gradient (pi-DDPG) framework. The proposed framework incorporates a refiner module to boost policy performance during the early training phase. A customized simulator based on a real-world dataset is developed to validate the effectiveness of the proposed pi-DDPG. Numerical experiments demonstrate that pi-DDPG achieves superior learning efficiency and significantly reduces early-stage training losses, enhancing its applicability to practical ride-hailing scenarios.

cs.LG↗

arXiv2025

Soft Adaptive Policy Optimization

Reinforcement learning (RL) plays an increasingly important role in enhancing the reasoning capabilities of large language models (LLMs), yet stable and performant policy optimization remains challenging. Token-level importance ratios often exhibit high variance-a phenomenon exacerbated in Mixture-of-Experts models-leading to unstable updates. Existing group-based policy optimization methods, such as GSPO and GRPO, alleviate this problem via hard clipping, making it difficult to maintain both stability and effective learning. We propose Soft Adaptive Policy Optimization (SAPO), which replaces hard clipping with a smooth, temperature-controlled gate that adaptively attenuates off-policy updates while preserving useful learning signals. Compared with GSPO and GRPO, SAPO is both sequence-coherent and token-adaptive. Like GSPO, SAPO maintains sequence-level coherence, but its soft gating forms a continuous trust region that avoids the brittle hard clipping band used in GSPO. When a sequence contains a few highly off-policy tokens, GSPO suppresses all gradients for that sequence, whereas SAPO selectively down-weights only the offending tokens and preserves the learning signal from the near-on-policy ones, improving sample efficiency. Relative to GRPO, SAPO replaces hard token-level clipping with smooth, temperature-controlled scaling, enabling more informative and stable updates. Empirical results on mathematical reasoning benchmarks indicate that SAPO exhibits improved training stability and higher Pass@1 performance under comparable training budgets. Moreover, we employ SAPO to train the Qwen3-VL model series, demonstrating that SAPO yields consistent performance gains across diverse tasks and different model sizes. Overall, SAPO provides a more reliable, scalable, and effective optimization strategy for RL training of LLMs.

cs.LG↗