arXiv subjects

Chang Gao

Publications and source records attributed to Chang Gao.

At least 37 records · Page 2Linked to original sources

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↗

arXiv2025

Qwen3-VL Technical Report

We introduce Qwen3-VL, the most capable vision-language model in the Qwen series to date, achieving superior performance across a broad range of multimodal benchmarks. It natively supports interleaved contexts of up to 256K tokens, seamlessly integrating text, images, and video. The model family includes both dense (2B/4B/8B/32B) and mixture-of-experts (30B-A3B/235B-A22B) variants to accommodate diverse latency-quality trade-offs. Qwen3-VL delivers three core pillars: (i) markedly stronger pure-text understanding, surpassing comparable text-only backbones in several cases; (ii) robust long-context comprehension with a native 256K-token window for both text and interleaved multimodal inputs, enabling faithful retention, retrieval, and cross-referencing across long documents and videos; and (iii) advanced multimodal reasoning across single-image, multi-image, and video tasks, demonstrating leading performance on comprehensive evaluations such as MMMU and visual-math benchmarks (e.g., MathVista and MathVision). Architecturally, we introduce three key upgrades: (i) an enhanced interleaved-MRoPE for stronger spatial-temporal modeling across images and video; (ii) DeepStack integration, which effectively leverages multi-level ViT features to tighten vision-language alignment; and (iii) text-based time alignment for video, evolving from T-RoPE to explicit textual timestamp alignment for more precise temporal grounding. Under comparable token budgets and latency constraints, Qwen3-VL achieves superior performance in both dense and Mixture-of-Experts (MoE) architectures. We envision Qwen3-VL serving as a foundational engine for image-grounded reasoning, agentic decision-making, and multimodal code intelligence in real-world workflows.

cs.CV↗

arXiv2025

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful approach to enhancing the reasoning capabilities of Large Language Models (LLMs), while its mechanisms are not yet well understood. In this work, we undertake a pioneering exploration of RLVR through the novel perspective of token entropy patterns, comprehensively analyzing how different tokens influence reasoning performance. By examining token entropy patterns in Chain-of-Thought (CoT) reasoning, we observe that only a small fraction of tokens exhibit high entropy, and these tokens act as critical forks that steer the model toward diverse reasoning pathways. Furthermore, studying how entropy patterns evolve during RLVR training reveals that RLVR largely adheres to the base model's entropy patterns, primarily adjusting the entropy of high-entropy tokens. These findings highlight the significance of high-entropy tokens (i.e., forking tokens) to RLVR. We ultimately improve RLVR by restricting policy gradient updates to forking tokens and uncover a finding even beyond the 80/20 rule: utilizing only 20% of the tokens while maintaining performance comparable to full-gradient updates on the Qwen3-8B base model and significantly surpassing full-gradient updates on the Qwen3-32B (+11.04 on AIME'25 and +7.71 on AIME'24) and Qwen3-14B (+4.79 on AIME'25 and +5.21 on AIME'24) base models, highlighting a strong scaling trend. In contrast, training exclusively on the 80% lowest-entropy tokens leads to a marked decline in performance. These findings indicate that the efficacy of RLVR primarily arises from optimizing the high-entropy tokens that decide reasoning directions. Collectively, our results highlight the potential to understand RLVR through a token-entropy perspective and optimize RLVR by leveraging high-entropy minority tokens to further improve LLM reasoning.

cs.CL↗

arXiv2025

JaneEye: A 12-nm 2K-FPS 18.9-$μ$J/Frame Event-based Eye Tracking Accelerator

Eye tracking has become a key technology for gaze-based interactions in Extended Reality (XR). However, conventional frame-based eye-tracking systems often fall short of XR's stringent requirements for high accuracy, low latency, and energy efficiency. Event cameras present a compelling alternative, offering ultra-high temporal resolution and low power consumption. In this paper, we present JaneEye, an energy-efficient event-based eye-tracking hardware accelerator designed specifically for wearable devices, leveraging sparse, high-temporal-resolution event data. We introduce an ultra-lightweight neural network architecture featuring a novel ConvJANET layer, which simplifies the traditional ConvLSTM by retaining only the forget gate, thereby halving computational complexity without sacrificing temporal modeling capability. Our proposed model achieves high accuracy with a pixel error of 2.45 on the 3ET+ dataset, using only 17.6K parameters, with up to 1250 Hz event frame rate. To further enhance hardware efficiency, we employ custom linear approximations of activation functions (hardsigmoid and hardtanh) and fixed-point quantization. Through software-hardware co-design, our 12-nm ASIC implementation operates at 400 MHz, delivering an end-to-end latency of 0.5 ms (equivalent to 2000 Frames Per Second (FPS)) at an energy efficiency of 18.9 $μ$J/frame. JaneEye sets a new benchmark in low-power, high-performance eye-tracking solutions suitable for integration into next-generation XR wearables.

eess.SP↗

arXiv2025

Neural-HAR: A Dimension-Gated CNN Accelerator for Real-Time Radar Human Activity Recognition

Radar-based human activity recognition (HAR) is attractive for unobtrusive and privacy-preserving monitoring, yet many CNN/RNN solutions remain too heavy for edge deployment, and even lightweight ViT/SSM variants often exceed practical compute and memory budgets. We introduce Neural-HAR, a dimension-gated CNN accelerator tailored for real-time radar HAR on resource-constrained platforms. At its core is GateCNN, a parameter-efficient Doppler-temporal network that (i) embeds Doppler vectors to emphasize frequency evolution over time and (ii) applies dual-path gated convolutions that modulate Doppler-aware content features with temporal gates, complemented by a residual path for stable training. On the University of Glasgow UoG2020 continuous radar dataset, GateCNN attains 86.4% accuracy with only 2.7k parameters and 0.28M FLOPs per inference, comparable to CNN-BiGRU at a fraction of the complexity. Our FPGA prototype on Xilinx Zynq-7000 Z-7007S reaches 107.5 $μ$s latency and 15 mW dynamic power using LUT-based ROM and distributed RAM only (zero DSP/BRAM), demonstrating real-time, energy-efficient edge inference. Code and HLS conversion scripts are available at https://github.com/lab-emi/AIRHAR.

eess.SP↗

arXiv2025

Confidence as a Reward: Transforming LLMs into Reward Models

Reward models can significantly enhance the reasoning capabilities of large language models (LLMs), but they typically require extensive curated data and costly training. To mitigate these challenges, training-free approaches such as LLM-as-a-Judge leverage the intrinsic reasoning abilities of LLMs to evaluate responses, achieving promising results. Recent works have also indicated that model confidence can serve effectively as a reward metric, distinguishing between chain-of-thought (CoT) and non-CoT paths. However, the concept of using confidence as a reward has not been comprehensively studied. In this work, we systematically investigate Confidence-as-a-Reward (CRew), a simple yet powerful training-free method that utilizes token-level confidence in the model's final answers as a proxy for reward, especially suitable for close-ended tasks. Through extensive experiments on mathematical reasoning tasks, we demonstrate that CRew outperforms existing training-free reward approaches on the MATH500 and RewardMATH benchmarks, and even surpasses most trained reward models. We further identify a strong correlation between CRew scores and the actual reasoning performance of the model. Additionally, we find that CRew can effectively filter high-quality training data. Building upon these insights, we propose CRew-DPO, a training strategy that constructs preference data from confidence scores combined with correctness signals. Finetuning with CRew-DPO further enhances the model's judging capabilities and consistently outperforms existing self-training methods.

cs.AI↗

arXiv2025

Hugoniot equation of state and sound velocity of CaSiO3 glass under shock compression

Davemaoite, as the third most abundant mineral in the lower mantle, constitutes significant amounts in pyrolite and mid-ocean ridge basalts. Due to its unquenchable nature, measurements by static compression techniques on physical properties of davemaoite at lower mantle conditions are rare and technically challenging, and those are essential to constrain compositions and properties of mineralogical models in the lower mantle. Here, we present Hugoniot equation of state and sound velocity of CaSiO3 glass under shock compression. The CaSiO3 glass transforms into the crystalline phase above 34 GPa and completely transforms into davemaoite above 120 GPa. Thermal equation of state and Hugoniot temperature of davemaoite have been derived from the shock wave data. The CaSiO3 glass under shcok compression has very high shock temperature. Shock wave experiments for sound velocity of CaSiO3 glass indicate that no melting is observed at Hugoniot pressure up to 117.6 GPa. We propose that the melting temperature of davemaoite should be higher than those reported theoretically by now.

physics.geo-ph↗

arXiv2025

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

Unified multimodal Large Language Models (LLMs) that can both understand and generate visual content hold immense potential. However, existing open-source models often suffer from a performance trade-off between these capabilities. We present Manzano, a simple and scalable unified framework that substantially reduces this tension by coupling a hybrid image tokenizer with a well-curated training recipe. A single shared vision encoder feeds two lightweight adapters that produce continuous embeddings for image-to-text understanding and discrete tokens for text-to-image generation within a common semantic space. A unified autoregressive LLM predicts high-level semantics in the form of text and image tokens, with an auxiliary diffusion decoder subsequently translating the image tokens into pixels. The architecture, together with a unified training recipe over understanding and generation data, enables scalable joint learning of both capabilities. Manzano achieves state-of-the-art results among unified models, and is competitive with specialist models, particularly on text-rich evaluation. Our studies show minimal task conflicts and consistent gains from scaling model size, validating our design choice of a hybrid tokenizer.

cs.CV↗

arXiv2025

AS-ASR: A Lightweight Framework for Aphasia-Specific Automatic Speech Recognition

This paper proposes AS-ASR, a lightweight aphasia-specific speech recognition framework based on Whisper-tiny, tailored for low-resource deployment on edge devices. Our approach introduces a hybrid training strategy that systematically combines standard and aphasic speech at varying ratios, enabling robust generalization, and a GPT-4-based reference enhancement method that refines noisy aphasic transcripts, improving supervision quality. We conduct extensive experiments across multiple data mixing configurations and evaluation settings. Results show that our fine-tuned model significantly outperforms the zero-shot baseline, reducing WER on aphasic speech by over 30% while preserving performance on standard speech. The proposed framework offers a scalable, efficient solution for real-world disordered speech recognition.

eess.AS↗

arXiv2025

EvHand-FPV: Efficient Event-Based 3D Hand Tracking from First-Person View

Hand tracking holds great promise for intuitive interaction paradigms, but frame-based methods often struggle to meet the requirements of accuracy, low latency, and energy efficiency, especially in resource-constrained settings such as Extended Reality (XR) devices. Event cameras provide $μ$s-level temporal resolution at mW-level power by asynchronously sensing brightness changes. In this work, we present EvHand-FPV, a lightweight framework for egocentric First-Person-View 3D hand tracking from a single event camera. We construct an event-based FPV dataset that couples synthetic training data with 3D labels and real event data with 2D labels for evaluation to address the scarcity of egocentric benchmarks. EvHand-FPV also introduces a wrist-based region of interest (ROI) that localizes the hand region via geometric cues, combined with an end-to-end mapping strategy that embeds ROI offsets into the network to reduce computation without explicit reconstruction, and a multi-task learning strategy with an auxiliary geometric feature head that improves representations without test-time overhead. On our real FPV test set, EvHand-FPV improves 2D-AUCp from 0.77 to 0.85 while reducing parameters from 11.2M to 1.2M by 89% and FLOPs per inference from 1.648G to 0.185G by 89%. It also maintains a competitive 3D-AUCp of 0.84 on synthetic data. These results demonstrate accurate and efficient egocentric event-based hand tracking suitable for on-device XR applications. The dataset and code are available at https://github.com/zen5x5/EvHand-FPV.

cs.CV↗

arXiv2025

Group Sequence Policy Optimization

This paper introduces Group Sequence Policy Optimization (GSPO), our stable, efficient, and performant reinforcement learning algorithm for training large language models. Unlike previous algorithms that adopt token-level importance ratios, GSPO defines the importance ratio based on sequence likelihood and performs sequence-level clipping, rewarding, and optimization. We demonstrate that GSPO achieves superior training efficiency and performance compared to the GRPO algorithm, notably stabilizes Mixture-of-Experts (MoE) RL training, and has the potential for simplifying the design of RL infrastructure. These merits of GSPO have contributed to the remarkable improvements in the latest Qwen3 models.

cs.LG↗

arXiv2025

Maximum Redundancy Pruning: A Principle-Driven Layerwise Sparsity Allocation for LLMs

Large language models (LLMs) have demonstrated impressive capabilities, but their enormous size poses significant challenges for deployment in real-world applications. To address this issue, researchers have sought to apply network pruning techniques to LLMs. A critical challenge in pruning is allocation the sparsity for each layer. Recent sparsity allocation methods is often based on heuristics or search that can easily lead to suboptimal performance. In this paper, we conducted an extensive investigation into various LLMs and revealed three significant discoveries: (1) the layerwise pruning sensitivity (LPS) of LLMs is highly non-uniform, (2) the choice of pruning metric affects LPS, and (3) the performance of a sparse model is related to the uniformity of its layerwise redundancy level. Based on these observations, we propose that the layerwise sparsity of LLMs should adhere to three principles: \emph{non-uniformity}, \emph{pruning metric dependency}, and \emph{uniform layerwise redundancy level} in the pruned model. To this end, we proposed Maximum Redundancy Pruning (MRP), an iterative pruning algorithm that prunes in the most redundant layers (\emph{i.e.}, those with the highest non-outlier ratio) at each iteration. The achieved layerwise sparsity aligns with the outlined principles. We conducted extensive experiments on publicly available LLMs, including the LLaMA2 and OPT, across various benchmarks. Experimental results validate the effectiveness of MRP, demonstrating its superiority over previous methods.

cs.LG↗

arXiv2025

SparseDPD: A Sparse Neural Network-based Digital Predistortion FPGA Accelerator for RF Power Amplifier Linearization

Digital predistortion (DPD) is crucial for linearizing radio frequency (RF) power amplifiers (PAs), improving signal integrity and efficiency in wireless systems. Neural network (NN)-based DPD methods surpass traditional polynomial models but face computational challenges limiting their practical deployment. This paper introduces SparseDPD, an FPGA accelerator employing a spatially sparse phase-normalized time-delay neural network (PNTDNN), optimized through unstructured pruning to reduce computational load without accuracy loss. Implemented on a Xilinx Zynq-7Z010 FPGA, SparseDPD operates at 170 MHz, achieving exceptional linearization performance (ACPR: -59.4 dBc, EVM: -54.0 dBc, NMSE: -48.2 dB) with only 241 mW dynamic power, using 64 parameters with 74% sparsity. This work demonstrates FPGA-based acceleration, making NN-based DPD practical and efficient for real-time wireless communication applications. Code is publicly available at https://github.com/MannoVersluis/SparseDPD.

cs.AR↗

arXiv2025

TCN-DPD: Parameter-Efficient Temporal Convolutional Networks for Wideband Digital Predistortion

Digital predistortion (DPD) is essential for mitigating nonlinearity in RF power amplifiers, particularly for wideband applications. This paper presents TCN-DPD, a parameter-efficient architecture based on temporal convolutional networks, integrating noncausal dilated convolutions with optimized activation functions. Evaluated on the OpenDPD framework with the DPA_200MHz dataset, TCN-DPD achieves simulated ACPRs of -51.58/-49.26 dBc (L/R), EVM of -47.52 dB, and NMSE of -44.61 dB with 500 parameters and maintains superior linearization than prior models down to 200 parameters, making it promising for efficient wideband PA linearization.

eess.SP↗

arXiv2025

JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning

Instruction tuning is vital for enhancing the performance of large language models (LLMs), but existing text-to-text methods, referred to as TextTuning, struggle with issues such as generalization, robustness, and controllability due to their lack of explicit task structures. We introduce JsonTuning, a structure-to-structure approach that uses JSON structures to represent tasks. This method improves generalization by clarifying task elements and their relations, boosts robustness by minimizing ambiguity, and enhances controllability by allowing precise control over outputs. We conduct an extensive comparative analysis between JsonTuning and TextTuning using various language models and benchmarks. Our findings reveal that JsonTuning consistently surpasses TextTuning in terms of performance, robustness, and controllability across different scenarios. By overcoming the limitations of TextTuning, JsonTuning demonstrates significant potential for developing more effective and reliable LLMs capable of handling diverse scenarios.

cs.CL↗

arXiv2025

Beyond 2:4: exploring V:N:M sparsity for efficient transformer inference on GPUs

To date, 2:4 sparsity has stood as the only sparse pattern that can be accelerated using sparse tensor cores on GPUs. In practice, 2:4 sparsity often possesses low actual speedups ($\leq 1.3$) and requires fixed sparse ratios, meaning that other ratios, such as 4:8, 8:16, or those exceeding 50% sparsity, do not incur any speedups on GPUs. Recent studies suggest that V:N:M sparsity is promising in addressing these limitations of 2:4 sparsity. However, regarding accuracy, the effects of V:N:M sparsity on broader Transformer models, such as vision Transformers and large language models (LLMs), are largely unexamined. Moreover, Some specific issues related to V:N:M sparsity, such as how to select appropriate V and M values, remain unresolved. In this study, we thoroughly investigate the application of V:N:M sparsity in vision models and LLMs across multiple tasks, from pertaining to downstream tasks. We propose three key approaches to enhance the applicability and accuracy of V:N:M-sparse Transformers, including heuristic V and M selection, V:N:M-specific channel permutation, and three-staged LoRA training techniques. Experimental results show that, with our methods, the DeiT-small achieves lossless accuracy at 64:2:5 sparsity, while the DeiT-base maintains accuracy even at 64:2:8 sparsity. In addition, the fine-tuned LLama2-7B at 64:2:5 sparsity performs comparably or better than training-free 2:4 sparse alternatives on downstream tasks. More importantly, V:N:M-sparse Transformers offer a wider range of speedup-accuracy trade-offs compared to 2:4 sparsity. Overall, our exploration largely facilitates the V:N:M sparsity to act as a truly effective acceleration solution for Transformers in cost-sensitive inference scenarios.

cs.LG↗

arXiv2025

Qwen3 Technical Report

In this work, we present Qwen3, the latest version of the Qwen model family. Qwen3 comprises a series of large language models (LLMs) designed to advance performance, efficiency, and multilingual capabilities. The Qwen3 series includes models of both dense and Mixture-of-Expert (MoE) architectures, with parameter scales ranging from 0.6 to 235 billion. A key innovation in Qwen3 is the integration of thinking mode (for complex, multi-step reasoning) and non-thinking mode (for rapid, context-driven responses) into a unified framework. This eliminates the need to switch between different models--such as chat-optimized models (e.g., GPT-4o) and dedicated reasoning models (e.g., QwQ-32B)--and enables dynamic mode switching based on user queries or chat templates. Meanwhile, Qwen3 introduces a thinking budget mechanism, allowing users to allocate computational resources adaptively during inference, thereby balancing latency and performance based on task complexity. Moreover, by leveraging the knowledge from the flagship models, we significantly reduce the computational resources required to build smaller-scale models, while ensuring their highly competitive performance. Empirical evaluations demonstrate that Qwen3 achieves state-of-the-art results across diverse benchmarks, including tasks in code generation, mathematical reasoning, agent tasks, etc., competitive against larger MoE models and proprietary models. Compared to its predecessor Qwen2.5, Qwen3 expands multilingual support from 29 to 119 languages and dialects, enhancing global accessibility through improved cross-lingual understanding and generation capabilities. To facilitate reproducibility and community-driven research and development, all Qwen3 models are publicly accessible under Apache 2.0.

cs.CL↗