Showing 1–50 of 154 results for author: Liang, Q

Modular connectivity in neural networks emerges from Poisson noise-motivated regularisation, and promotes robustness and compositional generalisation

Authors: Daoyuan Qian, Qiyao Liang, Ila Fiete

Abstract: Circuits in the brain commonly exhibit modular architectures that factorise complex tasks, resulting in the ability to compositionally generalise and reduce catastrophic forgetting. In contrast, artificial neural networks (ANNs) appear to mix all processing, because modular solutions are difficult to find as they are vanishing subspaces in the space of possible solutions. Here, we draw inspiration… ▽ More Circuits in the brain commonly exhibit modular architectures that factorise complex tasks, resulting in the ability to compositionally generalise and reduce catastrophic forgetting. In contrast, artificial neural networks (ANNs) appear to mix all processing, because modular solutions are difficult to find as they are vanishing subspaces in the space of possible solutions. Here, we draw inspiration from fault-tolerant computation and the Poisson-like firing of real neurons to show that activity-dependent neural noise, combined with nonlinear neural responses, drives the emergence of solutions that reflect an accurate understanding of modular tasks, corresponding to acquisition of a correct world model. We find that noise-driven modularisation can be recapitulated by a deterministic regulariser that multiplicatively combines weights and activations, revealing rich phenomenology not captured in linear networks or by standard regularisation methods. Though the emergence of modular structure requires sufficiently many training samples (exponential in the number of modular task dimensions), we show that pre-modularised ANNs exhibit superior noise-robustness and the ability to generalise and extrapolate well beyond training data, compared to ANNs without such inductive biases. Together, our work demonstrates a regulariser and architectures that could encourage modularity emergence to yield functional benefits. △ Less

Submitted 5 December, 2025; originally announced December 2025.

Rethinking Surgical Smoke: A Smoke-Type-Aware Laparoscopic Video Desmoking Method and Dataset

Authors: Qifan Liang, Junlin Li, Zhen Han, Xihao Wang, Zhongyuan Wang, Bin Mei

Abstract: Electrocautery or lasers will inevitably generate surgical smoke, which hinders the visual guidance of laparoscopic videos for surgical procedures. The surgical smoke can be classified into different types based on its motion patterns, leading to distinctive spatio-temporal characteristics across smoky laparoscopic videos. However, existing desmoking methods fail to account for such smoke-type-spe… ▽ More Electrocautery or lasers will inevitably generate surgical smoke, which hinders the visual guidance of laparoscopic videos for surgical procedures. The surgical smoke can be classified into different types based on its motion patterns, leading to distinctive spatio-temporal characteristics across smoky laparoscopic videos. However, existing desmoking methods fail to account for such smoke-type-specific distinctions. Therefore, we propose the first Smoke-Type-Aware Laparoscopic Video Desmoking Network (STANet) by introducing two smoke types: Diffusion Smoke and Ambient Smoke. Specifically, a smoke mask segmentation sub-network is designed to jointly conduct smoke mask and smoke type predictions based on the attention-weighted mask aggregation, while a smokeless video reconstruction sub-network is proposed to perform specially desmoking on smoky features guided by two types of smoke mask. To address the entanglement challenges of two smoke types, we further embed a coarse-to-fine disentanglement module into the mask segmentation sub-network, which yields more accurate disentangled masks through the smoke-type-aware cross attention between non-entangled and entangled regions. In addition, we also construct the first large-scale synthetic video desmoking dataset with smoke type annotations. Extensive experiments demonstrate that our method not only outperforms state-of-the-art approaches in quality evaluations, but also exhibits superior generalization across multiple downstream surgical tasks. △ Less

Submitted 2 December, 2025; originally announced December 2025.

Comments: 12 pages, 15 figures. Accepted to AAAI-26 (Main Technical Track)

From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning Tasks

Authors: Changpeng Yang, Jinyang Wu, Yuchen Liu, Shuai Zhang, Yang Li, Qiliang Liang, Hongzhen Wang, Shuai Nie, Jiaming Xu, Runyu Shi, Ying Huang, Guoquan Zhang

Abstract: Reinforcement learning has emerged as a paradigm for post-training large language models, boosting their reasoning capabilities. Such approaches compute an advantage value for each sample, reflecting better or worse performance than expected, thereby yielding both positive and negative signals for training. However, the indiscriminate mixing of the two signals in existing methods, especially from… ▽ More Reinforcement learning has emerged as a paradigm for post-training large language models, boosting their reasoning capabilities. Such approaches compute an advantage value for each sample, reflecting better or worse performance than expected, thereby yielding both positive and negative signals for training. However, the indiscriminate mixing of the two signals in existing methods, especially from the early stages, may lead to ambiguous guidance and limited gains. To address this issue, we propose **CAPO** (**C**urriculum **A**dvantage **P**olicy **O**ptimization), an adaptive curriculum mechanism based on advantage signals. The proposed mechanism bootstraps imitation learning with positive-only advantage samples to establish robust foundations, and subsequently introduces negative signals to cultivate discriminative capabilities, thereby improving generalization across complex scenarios. Compatible with diverse optimization methods including GRPO, PPO, RLOO, and Reinforce++, our method consistently achieves stable and significant improvements in mathematical reasoning tasks, and further generalizes effectively to multimodal Graphical User Interface (GUI) reasoning scenarios, establishing itself as a versatile and robust optimization framework. △ Less

Submitted 15 December, 2025; v1 submitted 2 December, 2025; originally announced December 2025.

Comments: Accepted by AAAI 2026

Bootstrap Dynamic-Aware 3D Visual Representation for Scalable Robot Learning

Authors: Qiwei Liang, Boyang Cai, Minghao Lai, Sitong Zhuang, Tao Lin, Yan Qin, Yixuan Ye, Jiaming Liang, Renjing Xu

Abstract: Despite strong results on recognition and segmentation, current 3D visual pre-training methods often underperform on robotic manipulation. We attribute this gap to two factors: the lack of state-action-state dynamics modeling and the unnecessary redundancy of explicit geometric reconstruction. We introduce AFRO, a self-supervised framework that learns dynamics-aware 3D representations without acti… ▽ More Despite strong results on recognition and segmentation, current 3D visual pre-training methods often underperform on robotic manipulation. We attribute this gap to two factors: the lack of state-action-state dynamics modeling and the unnecessary redundancy of explicit geometric reconstruction. We introduce AFRO, a self-supervised framework that learns dynamics-aware 3D representations without action or reconstruction supervision. AFRO casts state prediction as a generative diffusion process and jointly models forward and inverse dynamics in a shared latent space to capture causal transition structure. To prevent feature leakage in action learning, we employ feature differencing and inverse-consistency supervision, improving the quality and stability of visual features. When combined with Diffusion Policy, AFRO substantially increases manipulation success rates across 16 simulated and 4 real-world tasks, outperforming existing pre-training approaches. The framework also scales favorably with data volume and task complexity. Qualitative visualizations indicate that AFRO learns semantically rich, discriminative features, offering an effective pre-training solution for 3D representation learning in robotics. Project page: https://kolakivy.github.io/AFRO/ △ Less

Submitted 3 December, 2025; v1 submitted 24 November, 2025; originally announced December 2025.

GramTrans: A Better Code Representation Approach in Code Generation

Authors: Zhao Zhang, Qingyuan Liang, Zeyu Sun, Yizhou Chen, Guoqing Wang, Yican Sun, Lu Zhang, Ge Li, Yingfei Xiong

Abstract: Code generation has shown great promise in assisting software development. A fundamental yet underexplored question is how the choice of code representation affects model performance. While existing studies employ various representations, such as treating code as plain text, grammar rule sequences, or syntax tree sequences, they lack a principled understanding of the relationship between parsing d… ▽ More Code generation has shown great promise in assisting software development. A fundamental yet underexplored question is how the choice of code representation affects model performance. While existing studies employ various representations, such as treating code as plain text, grammar rule sequences, or syntax tree sequences, they lack a principled understanding of the relationship between parsing difficulty and model effectiveness. This paper proposes a conjecture: the easier a representation is to parse, the better performance the model achieves. We formalize this idea using grammar classes, where representations in simpler classes (e.g., LL(1)) are easier to parse. Through a controlled experiment on a Python-based DSL, we show that parsing difficulty strongly correlates with model performance. Motivated by this finding, we present GramTrans, a general approach that automatically transforms a context-free language into a representation within the LL(1) class. GramTrans introduces a novel hierarchical conflict elimination algorithm, enabling a flexible trade-off between syntactic simplicity and token efficiency. We evaluate GramTrans on both Python and Java using three code generation models: StarCoder 1B, DeepSeek-Coder 1.3B, and Qwen2.5 1.5B. Across multiple benchmarks, GramTrans consistently delivers significant improvements over baseline representations. Furthermore, our analysis of existing representations reconfirms the strong alignment between parsing difficulty and model performance, providing additional support for the conjecture. △ Less

Submitted 3 October, 2025; originally announced October 2025.

Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning

Authors: Xin Qiu, Yulu Gan, Conor F. Hayes, Qiyao Liang, Elliot Meyerson, Babak Hodjat, Risto Miikkulainen

Abstract: Fine-tuning pre-trained large language models (LLMs) for down-stream tasks is a critical step in the AI deployment pipeline. Reinforcement learning (RL) is arguably the most prominent fine-tuning method, contributing to the birth of many state-of-the-art LLMs. In contrast, evolution strategies (ES), which once showed comparable performance to RL on models with a few million parameters, was neglect… ▽ More Fine-tuning pre-trained large language models (LLMs) for down-stream tasks is a critical step in the AI deployment pipeline. Reinforcement learning (RL) is arguably the most prominent fine-tuning method, contributing to the birth of many state-of-the-art LLMs. In contrast, evolution strategies (ES), which once showed comparable performance to RL on models with a few million parameters, was neglected due to the pessimistic perception of its scalability to larger models. In this work, we report the first successful attempt to scale up ES for fine-tuning the full parameters of LLMs, showing the surprising fact that ES can search efficiently over billions of parameters and outperform existing RL fine-tuning methods in multiple respects, including sample efficiency, tolerance to long-horizon rewards, robustness to different base LLMs, less tendency to reward hacking, and more stable performance across runs. It therefore serves as a basis to unlock a new direction in LLM fine-tuning beyond what current RL techniques provide. The source codes are provided at: https://github.com/VsonicV/es-fine-tuning-paper. △ Less

Submitted 29 September, 2025; originally announced September 2025.

Comments: 24 pages, including the appendix

Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generation

Authors: Hongtao Yang, Bineng Zhong, Qihua Liang, Zhiruo Zhu, Yaozong Zheng, Ning Li

Abstract: Recently, visual prompt tuning is introduced to RGB-Thermal (RGB-T) tracking as a parameter-efficient finetuning (PEFT) method. However, these PEFT-based RGB-T tracking methods typically rely solely on spatial domain information as prompts for feature extraction. As a result, they often fail to achieve optimal performance by overlooking the crucial role of frequency-domain information in prompt le… ▽ More Recently, visual prompt tuning is introduced to RGB-Thermal (RGB-T) tracking as a parameter-efficient finetuning (PEFT) method. However, these PEFT-based RGB-T tracking methods typically rely solely on spatial domain information as prompts for feature extraction. As a result, they often fail to achieve optimal performance by overlooking the crucial role of frequency-domain information in prompt learning. To address this issue, we propose an efficient Visual Fourier Prompt Tracking (named VFPTrack) method to learn modality-related prompts via Fast Fourier Transform (FFT). Our method consists of symmetric feature extraction encoder with shared parameters, visual fourier prompts, and Modality Fusion Prompt Generator that generates bidirectional interaction prompts through multi-modal feature fusion. Specifically, we first use a frozen feature extraction encoder to extract RGB and thermal infrared (TIR) modality features. Then, we combine the visual prompts in the spatial domain with the frequency domain prompts obtained from the FFT, which allows for the full extraction and understanding of modality features from different domain information. Finally, unlike previous fusion methods, the modality fusion prompt generation module we use combines features from different modalities to generate a fused modality prompt. This modality prompt is interacted with each individual modality to fully enable feature interaction across different modalities. Extensive experiments conducted on three popular RGB-T tracking benchmarks show that our method demonstrates outstanding performance. △ Less

Submitted 23 September, 2025; originally announced September 2025.

Comments: Accepted by TMM2025

SateLight: A Satellite Application Update Framework for Satellite Computing

Authors: Jinfeng Wen, Jianshu Zhao, Zixi Zhu, Xiaomin Zhang, Qi Liang, Ao Zhou, Shangguang Wang

Abstract: Satellite computing is an emerging paradigm that empowers satellites to perform onboard processing tasks (i.e., \textit{satellite applications}), thereby reducing reliance on ground-based systems and improving responsiveness. However, enabling application software updates in this context remains a fundamental challenge due to application heterogeneity, limited ground-to-satellite bandwidth, and ha… ▽ More Satellite computing is an emerging paradigm that empowers satellites to perform onboard processing tasks (i.e., \textit{satellite applications}), thereby reducing reliance on ground-based systems and improving responsiveness. However, enabling application software updates in this context remains a fundamental challenge due to application heterogeneity, limited ground-to-satellite bandwidth, and harsh space conditions. Existing software update approaches, designed primarily for terrestrial systems, fail to address these constraints, as they assume abundant computational capacity and stable connectivity. To address this gap, we propose SateLight, a practical and effective satellite application update framework tailored for satellite computing. SateLight leverages containerization to encapsulate heterogeneous applications, enabling efficient deployment and maintenance. SateLight further integrates three capabilities: (1) a content-aware differential strategy that minimizes communication data volume, (2) a fine-grained onboard update design that reconstructs target applications, and (3) a layer-based fault-tolerant recovery mechanism to ensure reliability under failure-prone space conditions. Experimental results on a satellite simulation environment with 10 representative satellite applications demonstrate that SateLight reduces transmission latency by up to 91.18% (average 56.54%) compared to the best currently available baseline. It also consistently ensures 100% update correctness across all evaluated applications. Furthermore, a case study on a real-world in-orbit satellite demonstrates the practicality of our approach. △ Less

Submitted 16 September, 2025; originally announced September 2025.

Comments: This paper has been accepted for publication in ASE 2025!

Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning

Authors: Haiyang Yu, Yuchuan Wu, Fan Shi, Lei Liao, Jinghui Lu, Xiaodong Ge, Han Wang, Minghan Zhuo, Xuecheng Wu, Xiang Fei, Hao Feng, Guozhi Tang, An-Lan Wang, Hanshen Zhu, Yangfan He, Quanhuan Liang, Liyuan Meng, Chao Feng, Can Huang, Jingqun Tang, Bin Li

Abstract: Chinese ancient documents, invaluable carriers of millennia of Chinese history and culture, hold rich knowledge across diverse fields but face challenges in digitization and understanding, i.e., traditional methods only scan images, while current Vision-Language Models (VLMs) struggle with their visual and linguistic complexity. Existing document benchmarks focus on English printed texts or simpli… ▽ More Chinese ancient documents, invaluable carriers of millennia of Chinese history and culture, hold rich knowledge across diverse fields but face challenges in digitization and understanding, i.e., traditional methods only scan images, while current Vision-Language Models (VLMs) struggle with their visual and linguistic complexity. Existing document benchmarks focus on English printed texts or simplified Chinese, leaving a gap for evaluating VLMs on ancient Chinese documents. To address this, we present AncientDoc, the first benchmark for Chinese ancient documents, designed to assess VLMs from OCR to knowledge reasoning. AncientDoc includes five tasks (page-level OCR, vernacular translation, reasoning-based QA, knowledge-based QA, linguistic variant QA) and covers 14 document types, over 100 books, and about 3,000 pages. Based on AncientDoc, we evaluate mainstream VLMs using multiple metrics, supplemented by a human-aligned large language model for scoring. △ Less

Submitted 10 September, 2025; originally announced September 2025.

Dynamic Structural Recovery Parameters Enhance Prediction of Visual Outcomes After Macular Hole Surgery

Authors: Yinzheng Zhao, Zhihao Zhao, Rundong Jiang, Louisa Sackewitz, Quanmin Liang, Mathias Maier, Daniel Zapp, Peter Charbel Issa, Mohammad Ali Nasseri

Abstract: Purpose: To introduce novel dynamic structural parameters and evaluate their integration within a multimodal deep learning (DL) framework for predicting postoperative visual recovery in idiopathic full-thickness macular hole (iFTMH) patients. Methods: We utilized a publicly available longitudinal OCT dataset at five stages (preoperative, 2 weeks, 3 months, 6 months, and 12 months). A stage specifi… ▽ More Purpose: To introduce novel dynamic structural parameters and evaluate their integration within a multimodal deep learning (DL) framework for predicting postoperative visual recovery in idiopathic full-thickness macular hole (iFTMH) patients. Methods: We utilized a publicly available longitudinal OCT dataset at five stages (preoperative, 2 weeks, 3 months, 6 months, and 12 months). A stage specific segmentation model delineated related structures, and an automated pipeline extracted quantitative, composite, qualitative, and dynamic features. Binary logistic regression models, constructed with and without dynamic parameters, assessed their incremental predictive value for best-corrected visual acuity (BCVA). A multimodal DL model combining clinical variables, OCT-derived features, and raw OCT images was developed and benchmarked against regression models. Results: The segmentation model achieved high accuracy across all timepoints (mean Dice > 0.89). Univariate and multivariate analyses identified base diameter, ellipsoid zone integrity, and macular hole area as significant BCVA predictors (P < 0.05). Incorporating dynamic recovery rates consistently improved logistic regression AUC, especially at the 3-month follow-up. The multimodal DL model outperformed logistic regression, yielding higher AUCs and overall accuracy at each stage. The difference is as high as 0.12, demonstrating the complementary value of raw image volume and dynamic parameters. Conclusions: Integrating dynamic parameters into the multimodal DL model significantly enhances the accuracy of predictions. This fully automated process therefore represents a promising clinical decision support tool for personalized postoperative management in macular hole surgery. △ Less

Submitted 11 September, 2025; originally announced September 2025.

Comments: TVST

ACM Class: I.4.6

UOPSL: Unpaired OCT Predilection Sites Learning for Fundus Image Diagnosis Augmentation

Authors: Zhihao Zhao, Yinzheng Zhao, Junjie Yang, Xiangtong Yao, Quanmin Liang, Daniel Zapp, Kai Huang, Nassir Navab, M. Ali Nasseri

Abstract: Significant advancements in AI-driven multimodal medical image diagnosis have led to substantial improvements in ophthalmic disease identification in recent years. However, acquiring paired multimodal ophthalmic images remains prohibitively expensive. While fundus photography is simple and cost-effective, the limited availability of OCT data and inherent modality imbalance hinder further progress.… ▽ More Significant advancements in AI-driven multimodal medical image diagnosis have led to substantial improvements in ophthalmic disease identification in recent years. However, acquiring paired multimodal ophthalmic images remains prohibitively expensive. While fundus photography is simple and cost-effective, the limited availability of OCT data and inherent modality imbalance hinder further progress. Conventional approaches that rely solely on fundus or textual features often fail to capture fine-grained spatial information, as each imaging modality provides distinct cues about lesion predilection sites. In this study, we propose a novel unpaired multimodal framework \UOPSL that utilizes extensive OCT-derived spatial priors to dynamically identify predilection sites, enhancing fundus image-based disease recognition. Our approach bridges unpaired fundus and OCTs via extended disease text descriptions. Initially, we employ contrastive learning on a large corpus of unpaired OCT and fundus images while simultaneously learning the predilection sites matrix in the OCT latent space. Through extensive optimization, this matrix captures lesion localization patterns within the OCT feature space. During the fine-tuning or inference phase of the downstream classification task based solely on fundus images, where paired OCT data is unavailable, we eliminate OCT input and utilize the predilection sites matrix to assist in fundus image classification learning. Extensive experiments conducted on 9 diverse datasets across 28 critical categories demonstrate that our framework outperforms existing benchmarks. △ Less

Submitted 10 September, 2025; originally announced September 2025.

Comments: BIBM

ACM Class: I.4.10

CLAPS: A CLIP-Unified Auto-Prompt Segmentation for Multi-Modal Retinal Imaging

Authors: Zhihao Zhao, Yinzheng Zhao, Junjie Yang, Xiangtong Yao, Quanmin Liang, Shahrooz Faghihroohi, Kai Huang, Nassir Navab, M. Ali Nasseri

Abstract: Recent advancements in foundation models, such as the Segment Anything Model (SAM), have significantly impacted medical image segmentation, especially in retinal imaging, where precise segmentation is vital for diagnosis. Despite this progress, current methods face critical challenges: 1) modality ambiguity in textual disease descriptions, 2) a continued reliance on manual prompting for SAM-based… ▽ More Recent advancements in foundation models, such as the Segment Anything Model (SAM), have significantly impacted medical image segmentation, especially in retinal imaging, where precise segmentation is vital for diagnosis. Despite this progress, current methods face critical challenges: 1) modality ambiguity in textual disease descriptions, 2) a continued reliance on manual prompting for SAM-based workflows, and 3) a lack of a unified framework, with most methods being modality- and task-specific. To overcome these hurdles, we propose CLIP-unified Auto-Prompt Segmentation (\CLAPS), a novel method for unified segmentation across diverse tasks and modalities in retinal imaging. Our approach begins by pre-training a CLIP-based image encoder on a large, multi-modal retinal dataset to handle data scarcity and distribution imbalance. We then leverage GroundingDINO to automatically generate spatial bounding box prompts by detecting local lesions. To unify tasks and resolve ambiguity, we use text prompts enhanced with a unique "modality signature" for each imaging modality. Ultimately, these automated textual and spatial prompts guide SAM to execute precise segmentation, creating a fully automated and unified pipeline. Extensive experiments on 12 diverse datasets across 11 critical segmentation categories show that CLAPS achieves performance on par with specialized expert models while surpassing existing benchmarks across most metrics, demonstrating its broad generalizability as a foundation model. △ Less

Submitted 10 September, 2025; originally announced September 2025.

Comments: BIBM

ACM Class: I.4.6

CISAF: A Framework for Estimating the Security Posture of Academic and Research Cyberinfrastructure

Authors: Qishen Liang, Jelena Mirkovic, Brian Kocoloski

Abstract: Academic and research cyberinfrastructures (AR-CIs) present unique security challenges due to their collaborative nature, heterogeneous components, and the lack of practical security assessment frameworks tailored to their needs. We propose Cyber Infrastructure Security Analysis Framework (CISAF) -- a simple, systematic, mission-centric approach to analyze the security posture of a CI and prioriti… ▽ More Academic and research cyberinfrastructures (AR-CIs) present unique security challenges due to their collaborative nature, heterogeneous components, and the lack of practical security assessment frameworks tailored to their needs. We propose Cyber Infrastructure Security Analysis Framework (CISAF) -- a simple, systematic, mission-centric approach to analyze the security posture of a CI and prioritize mitigation actions. CISAF guides administrators through a top-down process: (1) defining unacceptable losses, (2) identifying associated system hazards and critical assets, (3) analyzing possible attack paths that target these critical assets, and (4) analyzing security mechanisms that lie on these attack paths. By combining information about the CI architecture, mission, attack vectors, and security mechanisms, CISAF provides a clear overview of potential security risks and offers valuable information to prioritize mitigation actions. △ Less

Submitted 7 November, 2025; v1 submitted 29 August, 2025; originally announced September 2025.

Comments: 8 pages, 2 figures. This version is a derivative of the previous tech report, with more formal expressions

MuSpike: A Benchmark and Evaluation Framework for Symbolic Music Generation with Spiking Neural Networks

Authors: Qian Liang, Menghaoran Tang, Yi Zeng

Abstract: Symbolic music generation has seen rapid progress with artificial neural networks, yet remains underexplored in the biologically plausible domain of spiking neural networks (SNNs), where both standardized benchmarks and comprehensive evaluation methods are lacking. To address this gap, we introduce MuSpike, a unified benchmark and evaluation framework that systematically assesses five representati… ▽ More Symbolic music generation has seen rapid progress with artificial neural networks, yet remains underexplored in the biologically plausible domain of spiking neural networks (SNNs), where both standardized benchmarks and comprehensive evaluation methods are lacking. To address this gap, we introduce MuSpike, a unified benchmark and evaluation framework that systematically assesses five representative SNN architectures (SNN-CNN, SNN-RNN, SNN-LSTM, SNN-GAN and SNN-Transformer) across five typical datasets, covering tonal, structural, emotional, and stylistic variations. MuSpike emphasizes comprehensive evaluation, combining established objective metrics with a large-scale listening study. We propose new subjective metrics, targeting musical impression, autobiographical association, and personal preference, that capture perceptual dimensions often overlooked in prior work. Results reveal that (1) different SNN models exhibit distinct strengths across evaluation dimensions; (2) participants with different musical backgrounds exhibit diverse perceptual patterns, with experts showing greater tolerance toward AI-composed music; and (3) a noticeable misalignment exists between objective and subjective evaluations, highlighting the limitations of purely statistical metrics and underscoring the value of human perceptual judgment in assessing musical quality. MuSpike provides the first systematic benchmark and systemic evaluation framework for SNN models in symbolic music generation, establishing a solid foundation for future research into biologically plausible and cognitively grounded music generation. △ Less

Submitted 8 August, 2025; originally announced August 2025.

M3HG: Multimodal, Multi-scale, and Multi-type Node Heterogeneous Graph for Emotion Cause Triplet Extraction in Conversations

Authors: Qiao Liang, Ying Shen, Tiantian Chen, Lin Zhang

Abstract: Emotion Cause Triplet Extraction in Multimodal Conversations (MECTEC) has recently gained significant attention in social media analysis, aiming to extract emotion utterances, cause utterances, and emotion categories simultaneously. However, the scarcity of related datasets, with only one published dataset featuring highly uniform dialogue scenarios, hinders model development in this field. To add… ▽ More Emotion Cause Triplet Extraction in Multimodal Conversations (MECTEC) has recently gained significant attention in social media analysis, aiming to extract emotion utterances, cause utterances, and emotion categories simultaneously. However, the scarcity of related datasets, with only one published dataset featuring highly uniform dialogue scenarios, hinders model development in this field. To address this, we introduce MECAD, the first multimodal, multi-scenario MECTEC dataset, comprising 989 conversations from 56 TV series spanning a wide range of dialogue contexts. In addition, existing MECTEC methods fail to explicitly model emotional and causal contexts and neglect the fusion of semantic information at different levels, leading to performance degradation. In this paper, we propose M3HG, a novel model that explicitly captures emotional and causal contexts and effectively fuses contextual information at both inter- and intra-utterance levels via a multimodal heterogeneous graph. Extensive experiments demonstrate the effectiveness of M3HG compared with existing state-of-the-art methods. The codes and dataset are available at https://github.com/redifinition/M3HG. △ Less

Submitted 26 August, 2025; originally announced August 2025.

Comments: 16 pages, 8 figures. Accepted to Findings of ACL 2025

Journal ref: Findings of ACL 2025 (2025) 11416-11431

SPG: Style-Prompting Guidance for Style-Specific Content Creation

Authors: Qian Liang, Zichong Chen, Yang Zhou, Hui Huang

Abstract: Although recent text-to-image (T2I) diffusion models excel at aligning generated images with textual prompts, controlling the visual style of the output remains a challenging task. In this work, we propose Style-Prompting Guidance (SPG), a novel sampling strategy for style-specific image generation. SPG constructs a style noise vector and leverages its directional deviation from unconditional nois… ▽ More Although recent text-to-image (T2I) diffusion models excel at aligning generated images with textual prompts, controlling the visual style of the output remains a challenging task. In this work, we propose Style-Prompting Guidance (SPG), a novel sampling strategy for style-specific image generation. SPG constructs a style noise vector and leverages its directional deviation from unconditional noise to guide the diffusion process toward the target style distribution. By integrating SPG with Classifier-Free Guidance (CFG), our method achieves both semantic fidelity and style consistency. SPG is simple, robust, and compatible with controllable frameworks like ControlNet and IPAdapter, making it practical and widely applicable. Extensive experiments demonstrate the effectiveness and generality of our approach compared to state-of-the-art methods. Code is available at https://github.com/Rumbling281441/SPG. △ Less

Submitted 15 August, 2025; originally announced August 2025.

Comments: Accepted to the Journal track of Pacific Graphics 2025

TRACY: Benchmarking Execution Efficiency of LLM-Based Code Translation

Authors: Zhihao Gong, Zeyu Sun, Dong Huang, Qingyuan Liang, Jie M. Zhang, Dan Hao

Abstract: Automatic code translation is a fundamental task in modern software development. While the advent of Large Language Models (LLMs) has significantly improved the correctness of code translation, the critical dimension of execution efficiency remains overlooked. To address this gap, we introduce TRACY, the first comprehensive benchmark designed to evaluate the execution efficiency of LLM-translated… ▽ More Automatic code translation is a fundamental task in modern software development. While the advent of Large Language Models (LLMs) has significantly improved the correctness of code translation, the critical dimension of execution efficiency remains overlooked. To address this gap, we introduce TRACY, the first comprehensive benchmark designed to evaluate the execution efficiency of LLM-translated code. TRACY is constructed through an LLM-driven two-stage pipeline: an initial stage generates a suite of stress tests to amplify performance differences, followed by an efficiency-oriented task pruning stage that isolates the efficiency-distinguishing tasks. The resulting benchmark comprises 1,011 code translation tasks across C++, Java, and Python, each accompanied by an average of 22.1 verified reference translations and 10 computationally demanding tests. Our extensive evaluation of 26 representative LLMs reveals that even top-tier LLMs struggle to consistently produce efficient code translations. For instance, Claude-4-think, the leading model for correctness, ranks eighth overall when time efficiency is taken into account, surpassed by several smaller open-source models. We further pinpoint that algorithmic flaws and improper resource handling are the most detrimental, causing a median time slowdown of 5.6$\times$ and memory increase of 12.0$\times$, respectively. Our work underscores the necessity of jointly optimizing for correctness and efficiency in future LLM-based code translation. △ Less

Submitted 15 August, 2025; originally announced August 2025.

MM-R1: Unleashing the Power of Unified Multimodal Large Language Models for Personalized Image Generation

Authors: Qian Liang, Yujia Wu, Kuncheng Li, Jiwei Wei, Shiyuan He, Jinyu Guo, Ning Xie

Abstract: Multimodal Large Language Models (MLLMs) with unified architectures excel across a wide range of vision-language tasks, yet aligning them with personalized image generation remains a significant challenge. Existing methods for MLLMs are frequently subject-specific, demanding a data-intensive fine-tuning process for every new subject, which limits their scalability. In this paper, we introduce MM-R… ▽ More Multimodal Large Language Models (MLLMs) with unified architectures excel across a wide range of vision-language tasks, yet aligning them with personalized image generation remains a significant challenge. Existing methods for MLLMs are frequently subject-specific, demanding a data-intensive fine-tuning process for every new subject, which limits their scalability. In this paper, we introduce MM-R1, a framework that integrates a cross-modal Chain-of-Thought (X-CoT) reasoning strategy to unlock the inherent potential of unified MLLMs for personalized image generation. Specifically, we structure personalization as an integrated visual reasoning and generation process: (1) grounding subject concepts by interpreting and understanding user-provided images and contextual cues, and (2) generating personalized images conditioned on both the extracted subject representations and user prompts. To further enhance the reasoning capability, we adopt Grouped Reward Proximal Policy Optimization (GRPO) to explicitly align the generation. Experiments demonstrate that MM-R1 unleashes the personalization capability of unified MLLMs to generate images with high subject fidelity and strong text alignment in a zero-shot manner. △ Less

Submitted 26 August, 2025; v1 submitted 15 August, 2025; originally announced August 2025.

Whole-Body Coordination for Dynamic Object Grasping with Legged Manipulators

Authors: Qiwei Liang, Boyang Cai, Rongyi He, Hui Li, Tao Teng, Haihan Duan, Changxin Huang, Runhao Zeng

Abstract: Quadrupedal robots with manipulators offer strong mobility and adaptability for grasping in unstructured, dynamic environments through coordinated whole-body control. However, existing research has predominantly focused on static-object grasping, neglecting the challenges posed by dynamic targets and thus limiting applicability in dynamic scenarios such as logistics sorting and human-robot collabo… ▽ More Quadrupedal robots with manipulators offer strong mobility and adaptability for grasping in unstructured, dynamic environments through coordinated whole-body control. However, existing research has predominantly focused on static-object grasping, neglecting the challenges posed by dynamic targets and thus limiting applicability in dynamic scenarios such as logistics sorting and human-robot collaboration. To address this, we introduce DQ-Bench, a new benchmark that systematically evaluates dynamic grasping across varying object motions, velocities, heights, object types, and terrain complexities, along with comprehensive evaluation metrics. Building upon this benchmark, we propose DQ-Net, a compact teacher-student framework designed to infer grasp configurations from limited perceptual cues. During training, the teacher network leverages privileged information to holistically model both the static geometric properties and dynamic motion characteristics of the target, and integrates a grasp fusion module to deliver robust guidance for motion planning. Concurrently, we design a lightweight student network that performs dual-viewpoint temporal modeling using only the target mask, depth map, and proprioceptive state, enabling closed-loop action outputs without reliance on privileged data. Extensive experiments on DQ-Bench demonstrate that DQ-Net achieves robust dynamic objects grasping across multiple task settings, substantially outperforming baseline methods in both success rate and responsiveness. △ Less

Submitted 10 August, 2025; originally announced August 2025.

Decoupled Spatio-Temporal Consistency Learning for Self-Supervised Tracking

Authors: Yaozong Zheng, Bineng Zhong, Qihua Liang, Ning Li, Shuxiang Song

Abstract: The success of visual tracking has been largely driven by datasets with manual box annotations. However, these box annotations require tremendous human effort, limiting the scale and diversity of existing tracking datasets. In this work, we present a novel Self-Supervised Tracking framework named \textbf{\tracker}, designed to eliminate the need of box annotations. Specifically, a decoupled spatio… ▽ More The success of visual tracking has been largely driven by datasets with manual box annotations. However, these box annotations require tremendous human effort, limiting the scale and diversity of existing tracking datasets. In this work, we present a novel Self-Supervised Tracking framework named \textbf{\tracker}, designed to eliminate the need of box annotations. Specifically, a decoupled spatio-temporal consistency training framework is proposed to learn rich target information across timestamps through global spatial localization and local temporal association. This allows for the simulation of appearance and motion variations of instances in real-world scenarios. Furthermore, an instance contrastive loss is designed to learn instance-level correspondences from a multi-view perspective, offering robust instance supervision without additional labels. This new design paradigm enables {\tracker} to effectively learn generic tracking representations in a self-supervised manner, while reducing reliance on extensive box annotations. Extensive experiments on nine benchmark datasets demonstrate that {\tracker} surpasses \textit{SOTA} self-supervised tracking methods, achieving an improvement of more than 25.3\%, 20.4\%, and 14.8\% in AUC (AO) score on the GOT10K, LaSOT, TrackingNet datasets, respectively. Code: https://github.com/GXNU-ZhongLab/SSTrack. △ Less

Submitted 29 July, 2025; originally announced July 2025.

Comments: Accepted by AAAI2025

Towards Universal Modal Tracking with Online Dense Temporal Token Learning

Authors: Yaozong Zheng, Bineng Zhong, Qihua Liang, Shengping Zhang, Guorong Li, Xianxian Li, Rongrong Ji

Abstract: We propose a universal video-level modality-awareness tracking model with online dense temporal token learning (called {\modaltracker}). It is designed to support various tracking tasks, including RGB, RGB+Thermal, RGB+Depth, and RGB+Event, utilizing the same model architecture and parameters. Specifically, our model is designed with three core goals: \textbf{Video-level Sampling}. We expand the m… ▽ More We propose a universal video-level modality-awareness tracking model with online dense temporal token learning (called {\modaltracker}). It is designed to support various tracking tasks, including RGB, RGB+Thermal, RGB+Depth, and RGB+Event, utilizing the same model architecture and parameters. Specifically, our model is designed with three core goals: \textbf{Video-level Sampling}. We expand the model's inputs to a video sequence level, aiming to see a richer video context from an near-global perspective. \textbf{Video-level Association}. Furthermore, we introduce two simple yet effective online dense temporal token association mechanisms to propagate the appearance and motion trajectory information of target via a video stream manner. \textbf{Modality Scalable}. We propose two novel gated perceivers that adaptively learn cross-modal representations via a gated attention mechanism, and subsequently compress them into the same set of model parameters via a one-shot training manner for multi-task inference. This new solution brings the following benefits: (i) The purified token sequences can serve as temporal prompts for the inference in the next video frames, whereby previous information is leveraged to guide future inference. (ii) Unlike multi-modal trackers that require independent training, our one-shot training scheme not only alleviates the training burden, but also improves model representation. Extensive experiments on visible and multi-modal benchmarks show that our {\modaltracker} achieves a new \textit{SOTA} performance. The code will be available at https://github.com/GXNU-ZhongLab/ODTrack. △ Less

Submitted 27 July, 2025; originally announced July 2025.

Comments: arXiv admin note: text overlap with arXiv:2401.01686

Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding

Authors: StepFun, :, Bin Wang, Bojun Wang, Changyi Wan, Guanzhe Huang, Hanpeng Hu, Haonan Jia, Hao Nie, Mingliang Li, Nuo Chen, Siyu Chen, Song Yuan, Wuxun Xie, Xiaoniu Song, Xing Chen, Xingping Yang, Xuelin Zhang, Yanbo Yu, Yaoyu Wang, Yibo Zhu, Yimin Jiang, Yu Zhou, Yuanwei Lu, Houyi Li , et al. (175 additional authors not shown)

Abstract: Large language models (LLMs) face low hardware efficiency during decoding, especially for long-context reasoning tasks. This paper introduces Step-3, a 321B-parameter VLM with hardware-aware model-system co-design optimized for minimizing decoding costs. Step-3 innovates in two key dimensions: (1) A novel Multi-Matrix Factorization Attention (MFA) mechanism that significantly reduces both KV cache… ▽ More Large language models (LLMs) face low hardware efficiency during decoding, especially for long-context reasoning tasks. This paper introduces Step-3, a 321B-parameter VLM with hardware-aware model-system co-design optimized for minimizing decoding costs. Step-3 innovates in two key dimensions: (1) A novel Multi-Matrix Factorization Attention (MFA) mechanism that significantly reduces both KV cache size and computation while maintaining high attention expressiveness, and (2) Attention-FFN Disaggregation (AFD), a distributed inference system that decouples attention and Feed-Forward Network (FFN) layers into specialized subsystems. This co-design achieves unprecedented cost efficiency: Step-3 significantly reduces theoretical decoding costs compared with models like DeepSeek-V3 and Qwen3 MoE 235B, with the gains widening at longer context. Step-3 achieves low cost while activating 38B parameters per token (more than DeepSeek-V3 and Qwen3 MoE 235B), demonstrating that hardware-aligned attention arithmetic intensity, MoE sparsity, and AFD are critical to cost-effectiveness. We perform a head-to-head comparison with DeepSeek-V3 in its favorable scenarios. Our implementation on Hopper GPUs achieves a decoding throughput of up to 4,039 tokens per second per GPU under 50ms TPOT SLA (4K context, FP8, no MTP). It is higher than DeepSeek-V3's 2,324 in the same setup and sets a new Pareto frontier for LLM decoding. △ Less

Submitted 25 July, 2025; originally announced July 2025.

RAD: Retrieval High-quality Demonstrations to Enhance Decision-making

Authors: Lu Guo, Yixiang Shan, Zhengbang Zhu, Qifan Liang, Lichang Song, Ting Long, Weinan Zhang, Yi Chang

Abstract: Offline reinforcement learning (RL) enables agents to learn policies from fixed datasets, avoiding costly or unsafe environment interactions. However, its effectiveness is often limited by dataset sparsity and the lack of transition overlap between suboptimal and expert trajectories, which makes long-horizon planning particularly challenging. Prior solutions based on synthetic data augmentation or… ▽ More Offline reinforcement learning (RL) enables agents to learn policies from fixed datasets, avoiding costly or unsafe environment interactions. However, its effectiveness is often limited by dataset sparsity and the lack of transition overlap between suboptimal and expert trajectories, which makes long-horizon planning particularly challenging. Prior solutions based on synthetic data augmentation or trajectory stitching often fail to generalize to novel states and rely on heuristic stitching points. To address these challenges, we propose Retrieval High-quAlity Demonstrations (RAD) for decision-making, which combines non-parametric retrieval with diffusion-based generative modeling. RAD dynamically retrieves high-return states from the offline dataset as target states based on state similarity and return estimation, and plans toward them using a condition-guided diffusion model. Such retrieval-guided generation enables flexible trajectory stitching and improves generalization when encountered with underrepresented or out-of-distribution states. Extensive experiments confirm that RAD achieves competitive or superior performance compared to baselines across diverse benchmarks, validating its effectiveness. △ Less

Submitted 21 July, 2025; originally announced July 2025.

FCRF: Flexible Constructivism Reflection for Long-Horizon Robotic Task Planning with Large Language Models

Authors: Yufan Song, Jiatao Zhang, Zeng Gu, Qingmiao Liang, Tuocheng Hu, Wei Song, Shiqiang Zhu

Abstract: Autonomous error correction is critical for domestic robots to achieve reliable execution of complex long-horizon tasks. Prior work has explored self-reflection in Large Language Models (LLMs) for task planning error correction; however, existing methods are constrained by inflexible self-reflection mechanisms that limit their effectiveness. Motivated by these limitations and inspired by human cog… ▽ More Autonomous error correction is critical for domestic robots to achieve reliable execution of complex long-horizon tasks. Prior work has explored self-reflection in Large Language Models (LLMs) for task planning error correction; however, existing methods are constrained by inflexible self-reflection mechanisms that limit their effectiveness. Motivated by these limitations and inspired by human cognitive adaptation, we propose the Flexible Constructivism Reflection Framework (FCRF), a novel Mentor-Actor architecture that enables LLMs to perform flexible self-reflection based on task difficulty, while constructively integrating historical valuable experience with failure lessons. We evaluated FCRF on diverse domestic tasks through simulation in AlfWorld and physical deployment in the real-world environment. Experimental results demonstrate that FCRF significantly improves overall performance and self-reflection flexibility in complex long-horizon robotic tasks. △ Less

Submitted 16 September, 2025; v1 submitted 20 July, 2025; originally announced July 2025.

Comments: 8 pages, 6 figures, IROS 2025

MEL: Multi-level Ensemble Learning for Resource-Constrained Environments

Authors: Krishna Praneet Gudipaty, Walid A. Hanafy, Kaan Ozkara, Qianlin Liang, Jesse Milzman, Prashant Shenoy, Suhas Diggavi

Abstract: AI inference at the edge is becoming increasingly common for low-latency services. However, edge environments are power- and resource-constrained, and susceptible to failures. Conventional failure resilience approaches, such as cloud failover or compressed backups, often compromise latency or accuracy, limiting their effectiveness for critical edge inference services. In this paper, we propose Mul… ▽ More AI inference at the edge is becoming increasingly common for low-latency services. However, edge environments are power- and resource-constrained, and susceptible to failures. Conventional failure resilience approaches, such as cloud failover or compressed backups, often compromise latency or accuracy, limiting their effectiveness for critical edge inference services. In this paper, we propose Multi-Level Ensemble Learning (MEL), a new framework for resilient edge inference that simultaneously trains multiple lightweight backup models capable of operating collaboratively, refining each other when multiple servers are available, and independently under failures while maintaining good accuracy. Specifically, we formulate our approach as a multi-objective optimization problem with a loss formulation that inherently encourages diversity among individual models to promote mutually refining representations, while ensuring each model maintains good standalone performance. Empirical evaluations across vision, language, and audio datasets show that MEL provides performance comparable to original architectures while also providing fault tolerance and deployment flexibility across edge platforms. Our results show that our ensemble model, sized at 40\% of the original model, achieves similar performance, while preserving 95.6\% of ensemble accuracy in the case of failures when trained using MEL. △ Less

Submitted 24 June, 2025; originally announced June 2025.

RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation

Authors: Tianxing Chen, Zanxin Chen, Baijun Chen, Zijian Cai, Yibin Liu, Zixuan Li, Qiwei Liang, Xianliang Lin, Yiheng Ge, Zhenyu Gu, Weiliang Deng, Yubin Guo, Tian Nian, Xuanbing Xie, Qiangyu Chen, Kailun Su, Tianling Xu, Guodong Liu, Mengkang Hu, Huan-ang Gao, Kaixuan Wang, Zhixuan Liang, Yusen Qin, Xiaokang Yang, Ping Luo , et al. (1 additional authors not shown)

Abstract: Simulation-based data synthesis has emerged as a powerful paradigm for advancing real-world robotic manipulation. Yet existing datasets remain insufficient for robust bimanual manipulation due to (1) the lack of scalable task generation methods and (2) oversimplified simulation environments. We present RoboTwin 2.0, a scalable framework for automated, large-scale generation of diverse and realisti… ▽ More Simulation-based data synthesis has emerged as a powerful paradigm for advancing real-world robotic manipulation. Yet existing datasets remain insufficient for robust bimanual manipulation due to (1) the lack of scalable task generation methods and (2) oversimplified simulation environments. We present RoboTwin 2.0, a scalable framework for automated, large-scale generation of diverse and realistic data, together with unified evaluation protocols for dual-arm manipulation. At its core is RoboTwin-OD, an object library of 731 instances across 147 categories with semantic and manipulation-relevant annotations. Building on this, we design an expert data synthesis pipeline that leverages multimodal language models (MLLMs) and simulation-in-the-loop refinement to automatically generate task-level execution code. To improve sim-to-real transfer, RoboTwin 2.0 applies structured domain randomization along five axes: clutter, lighting, background, tabletop height, and language, enhancing data diversity and policy robustness. The framework is instantiated across 50 dual-arm tasks and five robot embodiments. Empirically, it yields a 10.9% gain in code generation success rate. For downstream policy learning, a VLA model trained with synthetic data plus only 10 real demonstrations achieves a 367% relative improvement over the 10-demo baseline, while zero-shot models trained solely on synthetic data obtain a 228% gain. These results highlight the effectiveness of RoboTwin 2.0 in strengthening sim-to-real transfer and robustness to environmental variations. We release the data generator, benchmark, dataset, and code to support scalable research in robust bimanual manipulation. Project Page: https://robotwin-platform.github.io/, Code: https://github.com/robotwin-Platform/robotwin/. △ Less

Submitted 27 August, 2025; v1 submitted 22 June, 2025; originally announced June 2025.

Comments: Project Page: https://robotwin-platform.github.io/, Code: https://github.com/robotwin-Platform/robotwin, Doc: https://robotwin-platform.github.io/doc/

FSHNet: Fully Sparse Hybrid Network for 3D Object Detection

Authors: Shuai Liu, Mingyue Cui, Boyang Li, Quanmin Liang, Tinghe Hong, Kai Huang, Yunxiao Shan, Kai Huang

Abstract: Fully sparse 3D detectors have recently gained significant attention due to their efficiency in long-range detection. However, sparse 3D detectors extract features only from non-empty voxels, which impairs long-range interactions and causes the center feature missing. The former weakens the feature extraction capability, while the latter hinders network optimization. To address these challenges, w… ▽ More Fully sparse 3D detectors have recently gained significant attention due to their efficiency in long-range detection. However, sparse 3D detectors extract features only from non-empty voxels, which impairs long-range interactions and causes the center feature missing. The former weakens the feature extraction capability, while the latter hinders network optimization. To address these challenges, we introduce the Fully Sparse Hybrid Network (FSHNet). FSHNet incorporates a proposed SlotFormer block to enhance the long-range feature extraction capability of existing sparse encoders. The SlotFormer divides sparse voxels using a slot partition approach, which, compared to traditional window partition, provides a larger receptive field. Additionally, we propose a dynamic sparse label assignment strategy to deeply optimize the network by providing more high-quality positive samples. To further enhance performance, we introduce a sparse upsampling module to refine downsampled voxels, preserving fine-grained details crucial for detecting small objects. Extensive experiments on the Waymo, nuScenes, and Argoverse2 benchmarks demonstrate the effectiveness of FSHNet. The code is available at https://github.com/Say2L/FSHNet. △ Less

Submitted 4 June, 2025; originally announced June 2025.

Comments: Accepted by CVPR2025

Rethinking the effects of data contamination in Code Intelligence

Authors: Zhen Yang, Hongyi Lin, Yifan He, Jie Xu, Zeyu Sun, Shuo Liu, Pengpeng Wang, Zhongxing Yu, Qingyuan Liang

Abstract: In recent years, code intelligence has gained increasing importance in the field of automated software engineering. Meanwhile, the widespread adoption of Pretrained Language Models (PLMs) and Large Language Models (LLMs) has raised concerns regarding data contamination and its potential impact on model performance evaluation. This paper presents a systematic empirical study to investigate the fine… ▽ More In recent years, code intelligence has gained increasing importance in the field of automated software engineering. Meanwhile, the widespread adoption of Pretrained Language Models (PLMs) and Large Language Models (LLMs) has raised concerns regarding data contamination and its potential impact on model performance evaluation. This paper presents a systematic empirical study to investigate the fine-grained data contamination on code intelligence tasks. Our study involves diverse representative PLMs, namely RoBERTa and GPT-2, and LLMs, namely LLaMA and StarCoder, covering three major tasks: code translation, code generation, and code summarization. We categorize contamination scenarios into four types according to the code intelligence practice, namely input-only, output-only, unpaired, and paired contamination settings, and construct corresponding experimental and control groups for exploration. Experimental results show that, under the pre-training, fine-tuning, and inference paradigm adopted by PLMs, even deliberately injecting paired contamination does not lead to significant performance overestimation. But direct inference or small-scale fine-tuning uncovers the contamination effects. In contrast, LLMs with pre-training and inference paradigm are significantly affected by the paired contamination. Apart from the above, other contamination scenarios have no impact on both PLMs and LLMs. Our findings challenge the conventional belief that contamination inevitably leads to performance overestimation, providing new insights into the evaluation and deployment of code intelligence models. △ Less

Submitted 8 June, 2025; v1 submitted 3 June, 2025; originally announced June 2025.

PathGene: Benchmarking Driver Gene Mutations and Exon Prediction Using Multicenter Lung Cancer Histopathology Image Dataset

Authors: Liangrui Pan, Qingchun Liang, Shen Zhao, Songqing Fan, Shaoliang Peng

Abstract: Accurately predicting gene mutations, mutation subtypes and their exons in lung cancer is critical for personalized treatment planning and prognostic assessment. Faced with regional disparities in medical resources and the high cost of genomic assays, using artificial intelligence to infer these mutations and exon variants from routine histopathology images could greatly facilitate precision thera… ▽ More Accurately predicting gene mutations, mutation subtypes and their exons in lung cancer is critical for personalized treatment planning and prognostic assessment. Faced with regional disparities in medical resources and the high cost of genomic assays, using artificial intelligence to infer these mutations and exon variants from routine histopathology images could greatly facilitate precision therapy. Although some prior studies have shown that deep learning can accelerate the prediction of key gene mutations from lung cancer pathology slides, their performance remains suboptimal and has so far been limited mainly to early screening tasks. To address these limitations, we have assembled PathGene, which comprises histopathology images paired with next-generation sequencing reports from 1,576 patients at the Second Xiangya Hospital, Central South University, and 448 TCGA-LUAD patients. This multi-center dataset links whole-slide images to driver gene mutation status, mutation subtypes, exon, and tumor mutational burden (TMB) status, with the goal of leveraging pathology images to predict mutations, subtypes, exon locations, and TMB for early genetic screening and to advance precision oncology. Unlike existing datasets, we provide molecular-level information related to histopathology images in PathGene to facilitate the development of biomarker prediction models. We benchmarked 11 multiple-instance learning methods on PathGene for mutation, subtype, exon, and TMB prediction tasks. These experimental methods provide valuable alternatives for early genetic screening of lung cancer patients and assisting clinicians to quickly develop personalized precision targeted treatment plans for patients. Code and data are available at https://github.com/panliangrui/NIPS2025/. △ Less

Submitted 26 November, 2025; v1 submitted 30 May, 2025; originally announced June 2025.

Comments: Withdrawn due to issues related to data permissions/ethics

GaussianFusion: Gaussian-Based Multi-Sensor Fusion for End-to-End Autonomous Driving

Authors: Shuai Liu, Quanmin Liang, Zefeng Li, Boyang Li, Kai Huang

Abstract: Multi-sensor fusion is crucial for improving the performance and robustness of end-to-end autonomous driving systems. Existing methods predominantly adopt either attention-based flatten fusion or bird's eye view fusion through geometric transformations. However, these approaches often suffer from limited interpretability or dense computational overhead. In this paper, we introduce GaussianFusion,… ▽ More Multi-sensor fusion is crucial for improving the performance and robustness of end-to-end autonomous driving systems. Existing methods predominantly adopt either attention-based flatten fusion or bird's eye view fusion through geometric transformations. However, these approaches often suffer from limited interpretability or dense computational overhead. In this paper, we introduce GaussianFusion, a Gaussian-based multi-sensor fusion framework for end-to-end autonomous driving. Our method employs intuitive and compact Gaussian representations as intermediate carriers to aggregate information from diverse sensors. Specifically, we initialize a set of 2D Gaussians uniformly across the driving scene, where each Gaussian is parameterized by physical attributes and equipped with explicit and implicit features. These Gaussians are progressively refined by integrating multi-modal features. The explicit features capture rich semantic and spatial information about the traffic scene, while the implicit features provide complementary cues beneficial for trajectory planning. To fully exploit rich spatial and semantic information in Gaussians, we design a cascade planning head that iteratively refines trajectory predictions through interactions with Gaussians. Extensive experiments on the NAVSIM and Bench2Drive benchmarks demonstrate the effectiveness and robustness of the proposed GaussianFusion framework. The source code will be released at https://github.com/Say2L/GaussianFusion. △ Less

Submitted 27 October, 2025; v1 submitted 26 May, 2025; originally announced June 2025.

Comments: Accepted at NeurIPS2025 (Spotlight)

On the Same Page: Dimensions of Perceived Shared Understanding in Human-AI Interaction

Authors: Qingyu Liang, Jaime Banks

Abstract: Shared understanding plays a key role in the effective communication in and performance of human-human interactions. With the increasingly common integration of AI into human contexts, the future of personal and workplace interactions will likely see human-AI interaction (HAII) in which the perception of shared understanding is important. Existing literature has addressed the processes and effects… ▽ More Shared understanding plays a key role in the effective communication in and performance of human-human interactions. With the increasingly common integration of AI into human contexts, the future of personal and workplace interactions will likely see human-AI interaction (HAII) in which the perception of shared understanding is important. Existing literature has addressed the processes and effects of PSU in human-human interactions, but the construal remains underexplored in HAII. To better understand PSU in HAII, we conducted an online survey to collect user reflections on interactions with a large language model when it sunderstanding of a situation was thought to be similar to or different from the participant's. Through inductive thematic analysis, we identified eight dimensions comprising PSU in human-AI interactions: Fluency, aligned operation, fluidity, outcome satisfaction, contextual awareness, lack of humanlike abilities, computational limits, and suspicion. △ Less

Submitted 26 May, 2025; originally announced May 2025.

EvidenceBench: A Benchmark for Extracting Evidence from Biomedical Papers

Authors: Jianyou Wang, Weili Cao, Kaicheng Wang, Xiaoyue Wang, Ashish Dalvi, Gino Prasad, Qishan Liang, Hsuan-lin Her, Ming Wang, Qin Yang, Gene W. Yeo, David E. Neal, Maxim Khan, Christopher D. Rosin, Ramamohan Paturi, Leon Bergen

Abstract: We study the task of automatically finding evidence relevant to hypotheses in biomedical papers. Finding relevant evidence is an important step when researchers investigate scientific hypotheses. We introduce EvidenceBench to measure models performance on this task, which is created by a novel pipeline that consists of hypothesis generation and sentence-by-sentence annotation of biomedical papers… ▽ More We study the task of automatically finding evidence relevant to hypotheses in biomedical papers. Finding relevant evidence is an important step when researchers investigate scientific hypotheses. We introduce EvidenceBench to measure models performance on this task, which is created by a novel pipeline that consists of hypothesis generation and sentence-by-sentence annotation of biomedical papers for relevant evidence, completely guided by and faithfully following existing human experts judgment. We demonstrate the pipeline's validity and accuracy with multiple sets of human-expert annotations. We evaluated a diverse set of language models and retrieval systems on the benchmark and found that model performances still fall significantly short of the expert level on this task. To show the scalability of our proposed pipeline, we create a larger EvidenceBench-100k with 107,461 fully annotated papers with hypotheses to facilitate model training and development. Both datasets are available at https://github.com/EvidenceBench/EvidenceBench △ Less

Submitted 7 August, 2025; v1 submitted 25 April, 2025; originally announced April 2025.

Comments: Published at Conference on Language Modeling (COLM) 2025

FASR-Net: Unsupervised Shadow Removal Leveraging Inherent Frequency Priors

Authors: Tao Lin, Qingwang Wang, Qiwei Liang, Minghua Tang, Yuxuan Sun

Abstract: Shadow removal is challenging due to the complex interaction of geometry, lighting, and environmental factors. Existing unsupervised methods often overlook shadow-specific priors, leading to incomplete shadow recovery. To address this issue, we propose a novel unsupervised Frequency Aware Shadow Removal Network (FASR-Net), which leverages the inherent frequency characteristics of shadow regions. S… ▽ More Shadow removal is challenging due to the complex interaction of geometry, lighting, and environmental factors. Existing unsupervised methods often overlook shadow-specific priors, leading to incomplete shadow recovery. To address this issue, we propose a novel unsupervised Frequency Aware Shadow Removal Network (FASR-Net), which leverages the inherent frequency characteristics of shadow regions. Specifically, the proposed Wavelet Attention Downsampling Module (WADM) integrates wavelet-based image decomposition and deformable attention, effectively breaking down the image into frequency components to enhance shadow details within specific frequency bands. We also introduce several new loss functions for precise shadow-free image reproduction: a frequency loss to capture image component details, a brightness-chromaticity loss that references the chromaticity of shadow-free regions, and an alignment loss to ensure smooth transitions between shadowed and shadow-free regions. Experimental results on the AISTD and SRD datasets demonstrate that our method achieves superior shadow removal performance. △ Less

Submitted 8 April, 2025; originally announced April 2025.

Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models

Authors: Qiao Liang, Yanjiang Liu, Weixiang Zhou, Ben He, Yaojie Lu, Hongyu Lin, Jia Zheng, Xianpei Han, Le Sun, Yingfei Sun

Abstract: Does the prior knowledge of the vision encoder constrain the capability boundary of Multi-modal Large Language Models (MLLMs)? While most existing research treats MLLMs as unified systems optimized through end-to-end training, the impact of vision encoder's prior knowledge is seldom investigated. In this work, we introduce a novel metric, $Rank_e$, to quantify the effect of prior knowledge of the… ▽ More Does the prior knowledge of the vision encoder constrain the capability boundary of Multi-modal Large Language Models (MLLMs)? While most existing research treats MLLMs as unified systems optimized through end-to-end training, the impact of vision encoder's prior knowledge is seldom investigated. In this work, we introduce a novel metric, $Rank_e$, to quantify the effect of prior knowledge of the vision encoder on MLLM performance. Our analysis reveals a positive correlation between prior knowledge and MLLM performance. Moreover, we find that domain-specific fine-tuning using solely end-to-end visual question answering (VQA) data is insufficient, particularly for entities with low inherent visual prior knowledge. To address this issue, we propose VisPRE (Vision Prior Remediation), a two-stage training framework that explicitly incorporates prior knowledge at the vision encoder level. Experimental results demonstrate that augmenting vision encoder's prior knowledge substantially boosts the visual understanding capabilities of MLLMs, offering a novel and effective strategy for improving performance, especially in scenarios involving uncommon visual entities. △ Less

Submitted 30 May, 2025; v1 submitted 23 March, 2025; originally announced March 2025.

SMILE: a Scale-aware Multiple Instance Learning Method for Multicenter STAS Lung Cancer Histopathology Diagnosis

Authors: Liangrui Pan, Xiaoyu Li, Yutao Dou, Qiya Song, Jiadi Luo, Qingchun Liang, Shaoliang Peng

Abstract: Spread through air spaces (STAS) represents a newly identified aggressive pattern in lung cancer, which is known to be associated with adverse prognostic factors and complex pathological features. Pathologists currently rely on time consuming manual assessments, which are highly subjective and prone to variation. This highlights the urgent need for automated and precise diag nostic solutions. 2,97… ▽ More Spread through air spaces (STAS) represents a newly identified aggressive pattern in lung cancer, which is known to be associated with adverse prognostic factors and complex pathological features. Pathologists currently rely on time consuming manual assessments, which are highly subjective and prone to variation. This highlights the urgent need for automated and precise diag nostic solutions. 2,970 lung cancer tissue slides are comprised from multiple centers, re-diagnosed them, and constructed and publicly released three lung cancer STAS datasets: STAS CSU (hospital), STAS TCGA, and STAS CPTAC. All STAS datasets provide corresponding pathological feature diagnoses and related clinical data. To address the bias, sparse and heterogeneous nature of STAS, we propose an scale-aware multiple instance learning(SMILE) method for STAS diagnosis of lung cancer. By introducing a scale-adaptive attention mechanism, the SMILE can adaptively adjust high attention instances, reducing over-reliance on local regions and promoting consistent detection of STAS lesions. Extensive experiments show that SMILE achieved competitive diagnostic results on STAS CSU, diagnosing 251 and 319 STAS samples in CPTAC andTCGA,respectively, surpassing clinical average AUC. The 11 open baseline results are the first to be established for STAS research, laying the foundation for the future expansion, interpretability, and clinical integration of computational pathology technologies. The datasets and code are available at https://anonymous.4open.science/r/IJCAI25-1DA1. △ Less

Submitted 17 March, 2025; originally announced March 2025.

Prompt Alchemy: Automatic Prompt Refinement for Enhancing Code Generation

Authors: Sixiang Ye, Zeyu Sun, Guoqing Wang, Liwei Guo, Qingyuan Liang, Zheng Li, Yong Liu

Abstract: Code generation has emerged as a key task to automate software development by converting high-level descriptions into executable code. Large language models (LLMs) excel at this but depend heavily on input prompt quality.Manual prompt engineering can be time-consuming and inconsistent, limiting LLM effectiveness. This paper introduces Prochemy, an innovative method for automatically refining promp… ▽ More Code generation has emerged as a key task to automate software development by converting high-level descriptions into executable code. Large language models (LLMs) excel at this but depend heavily on input prompt quality.Manual prompt engineering can be time-consuming and inconsistent, limiting LLM effectiveness. This paper introduces Prochemy, an innovative method for automatically refining prompts to boost code generation. Prochemy overcomes manual prompt limitations by automating optimization, ensuring consistency during inference, and supporting multi-agent systems.It iteratively refines prompts based on model performance, using an optimized final prompt for improved consistency across tasks. We tested Prochemy on natural language-based code generation and translation tasks using three LLM series. Results indicate Prochemy enhances existing methods, improving performance by 5.0% for GPT-3.5-Turbo and 1.9% for GPT-4o over zero-shot baselines on HumanEval. In state-of-the-art LDB, Prochemy + LDB surpasses standalone methods by 1.2-1.8%. For code translation, Prochemy boosts GPT-4o's Java-to-Python (AVATAR) performance from 74.5 to 84.1 (+12.9%) and Python-to-Java from 66.8 to 78.2 (+17.1%). Moreover, Prochemy maintains strong performance when integrated with the o1-mini model, validating its efficacy in code tasks. Designed as plug-and-play, Prochemy optimizes prompts with minimal human input, bridging the gap between simple prompts and complex frameworks. △ Less

Submitted 14 March, 2025; originally announced March 2025.

Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking

Authors: Chaocan Xue, Bineng Zhong, Qihua Liang, Yaozong Zheng, Ning Li, Yuanliang Xue, Shuxiang Song

Abstract: Vision transformers (ViTs) have emerged as a popular backbone for visual tracking. However, complete ViT architectures are too cumbersome to deploy for unmanned aerial vehicle (UAV) tracking which extremely emphasizes efficiency. In this study, we discover that many layers within lightweight ViT-based trackers tend to learn relatively redundant and repetitive target representations. Based on this… ▽ More Vision transformers (ViTs) have emerged as a popular backbone for visual tracking. However, complete ViT architectures are too cumbersome to deploy for unmanned aerial vehicle (UAV) tracking which extremely emphasizes efficiency. In this study, we discover that many layers within lightweight ViT-based trackers tend to learn relatively redundant and repetitive target representations. Based on this observation, we propose a similarity-guided layer adaptation approach to optimize the structure of ViTs. Our approach dynamically disables a large number of representation-similar layers and selectively retains only a single optimal layer among them, aiming to achieve a better accuracy-speed trade-off. By incorporating this approach into existing ViTs, we tailor previously complete ViT architectures into an efficient similarity-guided layer-adaptive framework, namely SGLATrack, for real-time UAV tracking. Extensive experiments on six tracking benchmarks verify the effectiveness of the proposed approach, and show that our SGLATrack achieves a state-of-the-art real-time speed while maintaining competitive tracking precision. Codes and models are available at https://github.com/GXNU-ZhongLab/SGLATrack. △ Less

Submitted 9 March, 2025; originally announced March 2025.

Dynamic Updates for Language Adaptation in Visual-Language Tracking

Authors: Xiaohai Li, Bineng Zhong, Qihua Liang, Zhiyi Mo, Jian Nong, Shuxiang Song

Abstract: The consistency between the semantic information provided by the multi-modal reference and the tracked object is crucial for visual-language (VL) tracking. However, existing VL tracking frameworks rely on static multi-modal references to locate dynamic objects, which can lead to semantic discrepancies and reduce the robustness of the tracker. To address this issue, we propose a novel vision-langua… ▽ More The consistency between the semantic information provided by the multi-modal reference and the tracked object is crucial for visual-language (VL) tracking. However, existing VL tracking frameworks rely on static multi-modal references to locate dynamic objects, which can lead to semantic discrepancies and reduce the robustness of the tracker. To address this issue, we propose a novel vision-language tracking framework, named DUTrack, which captures the latest state of the target by dynamically updating multi-modal references to maintain consistency. Specifically, we introduce a Dynamic Language Update Module, which leverages a large language model to generate dynamic language descriptions for the object based on visual features and object category information. Then, we design a Dynamic Template Capture Module, which captures the regions in the image that highly match the dynamic language descriptions. Furthermore, to ensure the efficiency of description generation, we design an update strategy that assesses changes in target displacement, scale, and other factors to decide on updates. Finally, the dynamic template and language descriptions that record the latest state of the target are used to update the multi-modal references, providing more accurate reference information for subsequent inference and enhancing the robustness of the tracker. DUTrack achieves new state-of-the-art performance on four mainstream vision-language and two vision-only tracking benchmarks, including LaSOT, LaSOT$_{\rm{ext}}$, TNL2K, OTB99-Lang, GOT-10K, and UAV123. Code and models are available at https://github.com/GXNU-ZhongLab/DUTrack. △ Less

Submitted 9 March, 2025; originally announced March 2025.

Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?

Authors: Qingyuan Liang, Zhao Zhang, Zeyu Sun, Zheng Lin, Qi Luo, Yueyi Xiao, Yizhou Chen, Yuqun Zhang, Haotian Zhang, Lu Zhang, Bin Chen, Yingfei Xiong

Abstract: Grammar serves as a cornerstone in programming languages and software engineering, providing frameworks to define the syntactic space and program structure. Existing research demonstrates the effectiveness of grammar-based code representations in small-scale models, showing their ability to reduce syntax errors and enhance performance. However, as language models scale to the billion level or beyo… ▽ More Grammar serves as a cornerstone in programming languages and software engineering, providing frameworks to define the syntactic space and program structure. Existing research demonstrates the effectiveness of grammar-based code representations in small-scale models, showing their ability to reduce syntax errors and enhance performance. However, as language models scale to the billion level or beyond, syntax-level errors become rare, making it unclear whether grammar information still provides performance benefits. To explore this, we develop a series of billion-scale GrammarCoder models, incorporating grammar rules in the code generation process. Experiments on HumanEval (+) and MBPP (+) demonstrate a notable improvement in code generation accuracy. Further analysis shows that grammar-based representations enhance LLMs' ability to discern subtle code differences, reducing semantic errors caused by minor variations. These findings suggest that grammar-based code representations remain valuable even in billion-scale models, not only by maintaining syntax correctness but also by improving semantic differentiation. △ Less

Submitted 10 December, 2025; v1 submitted 7 March, 2025; originally announced March 2025.

A Multifacet Hierarchical Sentiment-Topic Model with Application to Multi-Brand Online Review Analysis

Authors: Qiao Liang, Xinwei Deng

Abstract: Multi-brand analysis based on review comments and ratings is a commonly used strategy to compare different brands in marketing. It can help consumers make more informed decisions and help marketers understand their brand's position in the market. In this work, we propose a multifacet hierarchical sentiment-topic model (MH-STM) to detect brand-associated sentiment polarities towards multiple compar… ▽ More Multi-brand analysis based on review comments and ratings is a commonly used strategy to compare different brands in marketing. It can help consumers make more informed decisions and help marketers understand their brand's position in the market. In this work, we propose a multifacet hierarchical sentiment-topic model (MH-STM) to detect brand-associated sentiment polarities towards multiple comparative aspects from online customer reviews. The proposed method is built on a unified generative framework that explains review words with a hierarchical brand-associated topic model and the overall polarity score with a regression model on the empirical topic distribution. Moreover, a novel hierarchical Polya urn (HPU) scheme is proposed to enhance the topic-word association among topic hierarchy, such that the general topics shared by all brands are separated effectively from the unique topics specific to individual brands. The performance of the proposed method is evaluated on both synthetic data and two real-world review corpora. Experimental studies demonstrate that the proposed method can be effective in detecting reasonable topic hierarchy and deriving accurate brand-associated rankings on multi-aspects. △ Less

Submitted 26 February, 2025; originally announced February 2025.

Comments: 21 pages, 6 figures, 4 tables

Corotational Hinge-based Thin Plates/Shells

Authors: Qixin Liang

Abstract: We present six thin plate/shell models, derived from three distinct types of curvature operators formulated within the corotational frame, for simulating both rest-flat and rest-curved triangular meshes. Each curvature operator derives a curvature expression corresponding to both a plate model and a shell model. The corotational edge-based hinge model uses an edge-based stencil to compute directio… ▽ More We present six thin plate/shell models, derived from three distinct types of curvature operators formulated within the corotational frame, for simulating both rest-flat and rest-curved triangular meshes. Each curvature operator derives a curvature expression corresponding to both a plate model and a shell model. The corotational edge-based hinge model uses an edge-based stencil to compute directional curvature, while the corotational FVM hinge model utilizes a triangle-centered stencil, applying the finite volume method (FVM) to superposition directional curvatures across edges, yielding a generalized curvature. The corotational smoothed hinge model also employs a triangle-centered stencil but transforms directional curvatures into a generalized curvature based on a quadratic surface fit. All models assume small strain and small curvature, leading to constant bending energy Hessians, which benefit implicit integrators. Through quantitative benchmarks and qualitative elastodynamic simulations with large time steps, we demonstrate the accuracy, efficiency, and stability of these models. Our contributions enhance the thin plate/shell library for use in both computer graphics and engineering applications. △ Less

Submitted 4 June, 2025; v1 submitted 15 February, 2025; originally announced February 2025.

Comments: Accepted at Eurographics 2025

Journal ref: Comput. Graph. Forum 44(2), e70022 (Proc. Eurographics 2025)

Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model

Authors: Guoqing Ma, Haoyang Huang, Kun Yan, Liangyu Chen, Nan Duan, Shengming Yin, Changyi Wan, Ranchen Ming, Xiaoniu Song, Xing Chen, Yu Zhou, Deshan Sun, Deyu Zhou, Jian Zhou, Kaijun Tan, Kang An, Mei Chen, Wei Ji, Qiling Wu, Wen Sun, Xin Han, Yanan Wei, Zheng Ge, Aojie Li, Bin Wang , et al. (90 additional authors not shown)

Abstract: We present Step-Video-T2V, a state-of-the-art text-to-video pre-trained model with 30B parameters and the ability to generate videos up to 204 frames in length. A deep compression Variational Autoencoder, Video-VAE, is designed for video generation tasks, achieving 16x16 spatial and 8x temporal compression ratios, while maintaining exceptional video reconstruction quality. User prompts are encoded… ▽ More We present Step-Video-T2V, a state-of-the-art text-to-video pre-trained model with 30B parameters and the ability to generate videos up to 204 frames in length. A deep compression Variational Autoencoder, Video-VAE, is designed for video generation tasks, achieving 16x16 spatial and 8x temporal compression ratios, while maintaining exceptional video reconstruction quality. User prompts are encoded using two bilingual text encoders to handle both English and Chinese. A DiT with 3D full attention is trained using Flow Matching and is employed to denoise input noise into latent frames. A video-based DPO approach, Video-DPO, is applied to reduce artifacts and improve the visual quality of the generated videos. We also detail our training strategies and share key observations and insights. Step-Video-T2V's performance is evaluated on a novel video generation benchmark, Step-Video-T2V-Eval, demonstrating its state-of-the-art text-to-video quality when compared with both open-source and commercial engines. Additionally, we discuss the limitations of current diffusion-based model paradigm and outline future directions for video foundation models. We make both Step-Video-T2V and Step-Video-T2V-Eval available at https://github.com/stepfun-ai/Step-Video-T2V. The online version can be accessed from https://yuewen.cn/videos as well. Our goal is to accelerate the innovation of video foundation models and empower video content creators. △ Less

Submitted 24 February, 2025; v1 submitted 14 February, 2025; originally announced February 2025.

Comments: 36 pages, 14 figures

Adaptive Perception for Unified Visual Multi-modal Object Tracking

Authors: Xiantao Hu, Bineng Zhong, Qihua Liang, Zhiyi Mo, Liangtao Shi, Ying Tai, Jian Yang

Abstract: Recently, many multi-modal trackers prioritize RGB as the dominant modality, treating other modalities as auxiliary, and fine-tuning separately various multi-modal tasks. This imbalance in modality dependence limits the ability of methods to dynamically utilize complementary information from each modality in complex scenarios, making it challenging to fully perceive the advantages of multi-modal.… ▽ More Recently, many multi-modal trackers prioritize RGB as the dominant modality, treating other modalities as auxiliary, and fine-tuning separately various multi-modal tasks. This imbalance in modality dependence limits the ability of methods to dynamically utilize complementary information from each modality in complex scenarios, making it challenging to fully perceive the advantages of multi-modal. As a result, a unified parameter model often underperforms in various multi-modal tracking tasks. To address this issue, we propose APTrack, a novel unified tracker designed for multi-modal adaptive perception. Unlike previous methods, APTrack explores a unified representation through an equal modeling strategy. This strategy allows the model to dynamically adapt to various modalities and tasks without requiring additional fine-tuning between different tasks. Moreover, our tracker integrates an adaptive modality interaction (AMI) module that efficiently bridges cross-modality interactions by generating learnable tokens. Experiments conducted on five diverse multi-modal datasets (RGBT234, LasHeR, VisEvent, DepthTrack, and VOT-RGBD2022) demonstrate that APTrack not only surpasses existing state-of-the-art unified multi-modal trackers but also outperforms trackers designed for specific multi-modal tasks. △ Less

Submitted 10 February, 2025; originally announced February 2025.

Compositional Generalization via Forced Rendering of Disentangled Latents

Authors: Qiyao Liang, Daoyuan Qian, Liu Ziyin, Ila Fiete

Abstract: Composition-the ability to generate myriad variations from finite means-is believed to underlie powerful generalization. However, compositional generalization remains a key challenge for deep learning. A widely held assumption is that learning disentangled (factorized) representations naturally supports this kind of extrapolation. Yet, empirical results are mixed, with many generative models faili… ▽ More Composition-the ability to generate myriad variations from finite means-is believed to underlie powerful generalization. However, compositional generalization remains a key challenge for deep learning. A widely held assumption is that learning disentangled (factorized) representations naturally supports this kind of extrapolation. Yet, empirical results are mixed, with many generative models failing to recognize and compose factors to generate out-of-distribution (OOD) samples. In this work, we investigate a controlled 2D Gaussian "bump" generation task with fully disentangled (x,y) inputs, demonstrating that standard generative architectures still fail in OOD regions when training with partial data, by re-entangling latent representations in subsequent layers. By examining the model's learned kernels and manifold geometry, we show that this failure reflects a "memorization" strategy for generation via data superposition rather than via composition of the true factorized features. We show that when models are forced-through architectural modifications with regularization or curated training data-to render the disentangled latents into the full-dimensional representational (pixel) space, they can be highly data-efficient and effective at composing in OOD regions. These findings underscore that disentangled latents in an abstract representation are insufficient and show that if models can represent disentangled factors directly in the output representational space, it can achieve robust compositional generalization. △ Less

Submitted 24 May, 2025; v1 submitted 30 January, 2025; originally announced January 2025.

Comments: 9 pages, 4 figures, plus appendix

Directional Diffusion-Style Code Editing Pre-training

Authors: Qingyuan Liang, Zeyu Sun, Qihao Zhu, Junhao Hu, Yifan Zhao, Yizhou Chen, Mingxuan Zhu, Guoqing Wang, Lu Zhang

Abstract: Code pre-trained models have shown promising effectiveness in various software engineering tasks. Among these tasks, many tasks are related to software evolution and/or code editing. However, existing code pre-trained models often overlook the real-world code editing data and the evolutionary nature of the editing process. In this paper, to simulate the step-by-step code editing process of human d… ▽ More Code pre-trained models have shown promising effectiveness in various software engineering tasks. Among these tasks, many tasks are related to software evolution and/or code editing. However, existing code pre-trained models often overlook the real-world code editing data and the evolutionary nature of the editing process. In this paper, to simulate the step-by-step code editing process of human developers, we propose DivoT5, a pre-trained model based on directional diffusion at the data level. In DivoT5, we adopt two categories of pre-training tasks. The first category is mask and denoising tasks augmented with a diffusion direction representing code evolution. That is, we first apply a noising process to the code snippets before evolution, and then ask the pre-training process to restore the snippets with noise into the code snippets after evolution. The second category is tasks aiming to reinforce the evolutionary direction. That is, we first generate various intermediate versions for each pair of snippets before and after evolution, and then ask the pre-training process to transform the intermediate versions into the snippet after evolution for each pair. We evaluate DivoT5 for two code-editing scenarios and one non-editing scenario using five downstream tasks. Given each downstream task, we fine-tune the pre-trained DivoT5 to evaluate its effectiveness. Our experimental results show that DivoT5 achieves state-of-the-art (SOTA) performance on most tasks in comparison to models of the same scale (220M), large scale (770M) models in fine-tuning, and billion-scale (6.7B, 8B, ChatGPT) models in few-shot settings. For one code-editing task (i.e., automated code review), DivoT5 pre-trained on top of CodeT5-small (60M) can even outperform CodeT5-base (220M) and other pre-trained models with 220M parameters except for DivoT5 pre-trained on top of CodeT5-base (220M). △ Less

Submitted 10 December, 2025; v1 submitted 21 January, 2025; originally announced January 2025.

Navigating Robot Swarm Through a Virtual Tube with Flow-Adaptive Distribution Control

Authors: Yongwei Zhang, Shuli Lv, Kairong Liu, Quanyi Liang, Quan Quan, Zhikun She

Abstract: With the rapid development of robot swarm technology and its diverse applications, navigating robot swarms through complex environments has emerged as a critical research direction. To ensure safe navigation and avoid potential collisions with obstacles, the concept of virtual tubes has been introduced to define safe and navigable regions. However, current control methods in virtual tubes face the… ▽ More With the rapid development of robot swarm technology and its diverse applications, navigating robot swarms through complex environments has emerged as a critical research direction. To ensure safe navigation and avoid potential collisions with obstacles, the concept of virtual tubes has been introduced to define safe and navigable regions. However, current control methods in virtual tubes face the congestion issues, particularly in narrow ones with low throughput. To address these challenges, we first propose a novel control method that combines a modified artificial potential field (APF) for swarm navigation and density feedback control for distribution regulation. Then we generate a global velocity field that not only ensures collision-free navigation but also achieves locally input-to-state stability (LISS) for density tracking. Finally, numerical simulations and realistic applications validate the effectiveness and advantages of the proposed method in navigating robot swarms through narrow virtual tubes. △ Less

Submitted 13 August, 2025; v1 submitted 21 January, 2025; originally announced January 2025.

Comments: 8 pages(brief paper), 12 figures

Automatically Learning a Precise Measurement for Fault Diagnosis Capability of Test Cases

Authors: Yifan Zhao, Zeyu Sun, Guoqing Wang, Qingyuan Liang, Yakun Zhang, Yiling Lou, Dan Hao, Lu Zhang

Abstract: Prevalent Fault Localization (FL) techniques rely on tests to localize buggy program elements. Tests could be treated as fuel to further boost FL by providing more debugging information. Therefore, it is highly valuable to measure the Fault Diagnosis Capability (FDC) of a test for diagnosing faults, so as to select or generate tests to better help FL. To this end, researchers have proposed many FD… ▽ More Prevalent Fault Localization (FL) techniques rely on tests to localize buggy program elements. Tests could be treated as fuel to further boost FL by providing more debugging information. Therefore, it is highly valuable to measure the Fault Diagnosis Capability (FDC) of a test for diagnosing faults, so as to select or generate tests to better help FL. To this end, researchers have proposed many FDC metrics, which serve as the selection criterion in FL-oriented test selection or the fitness function in FL-oriented test generation. Existing FDC metrics can be classified into result-agnostic and result-aware metrics depending on whether they take test results (i.e., passing or failing) as input. Although result-aware metrics perform better in test selection, they have restricted applications due to the input of test results, e.g., they cannot be applied to guide test generation. Moreover, all the existing FDC metrics are designed based on some predefined heuristics and have achieved limited FL performance due to their inaccuracy. To address these issues, in this paper, we reconsider result-agnostic metrics, and propose a novel result-agnostic metric RLFDC which predicts FDC values of tests through reinforcement learning. In particular, we treat FL results as reward signals, and train an FDC prediction model with the direct FL feedback to automatically learn a more accurate measurement rather than design one based on predefined heuristics. Finally, we evaluate the proposed RLFDC on Defects4J by applying the studied metrics to test selection and generation. According to the experimental results, the proposed RLFDC outperforms all the result-agnostic metrics in both test selection and generation. △ Less

Submitted 4 January, 2025; originally announced January 2025.

Comments: This paper has been accepted by TOSEM

Less is More: Token Context-aware Learning for Object Tracking

Authors: Chenlong Xu, Bineng Zhong, Qihua Liang, Yaozong Zheng, Guorong Li, Shuxiang Song

Abstract: Recently, several studies have shown that utilizing contextual information to perceive target states is crucial for object tracking. They typically capture context by incorporating multiple video frames. However, these naive frame-context methods fail to consider the importance of each patch within a reference frame, making them susceptible to noise and redundant tokens, which deteriorates trackin… ▽ More Recently, several studies have shown that utilizing contextual information to perceive target states is crucial for object tracking. They typically capture context by incorporating multiple video frames. However, these naive frame-context methods fail to consider the importance of each patch within a reference frame, making them susceptible to noise and redundant tokens, which deteriorates tracking performance. To address this challenge, we propose a new token context-aware tracking pipeline named LMTrack, designed to automatically learn high-quality reference tokens for efficient visual tracking. Embracing the principle of Less is More, the core idea of LMTrack is to analyze the importance distribution of all reference tokens, where important tokens are collected, continually attended to, and updated. Specifically, a novel Token Context Memory module is designed to dynamically collect high-quality spatio-temporal information of a target in an autoregressive manner, eliminating redundant background tokens from the reference frames. Furthermore, an effective Unidirectional Token Attention mechanism is designed to establish dependencies between reference tokens and search frame, enabling robust cross-frame association and target localization. Extensive experiments demonstrate the superiority of our tracker, achieving state-of-the-art results on tracking benchmarks such as GOT-10K, TrackingNet, and LaSOT. △ Less

Submitted 1 January, 2025; originally announced January 2025.

Comments: Accepted by AAAI 2025

Quantifying the Dynamics of Harm Caused by Retracted Research

Authors: Yunyou Huang, Jiahui Zhao, Dandan Cui, Zhengxin Yang, Bingjie Xia, Qi Liang, Wenjing Liu, Li Ma, Suqin Tang, Tianyong Hao, Zhifei Zhang, Wanling Gao, Jianfeng Zhan

Abstract: Despite enormous efforts devoted to understand the characteristics and impacts of retracted papers, little is known about the mechanisms underlying the dynamics of their harm and the dynamics of its propagation. Here, we propose a citation-based framework to quantify the harm caused by retracted papers, aiming to uncover why their harm persists and spreads so widely. We uncover an ''attention esca… ▽ More Despite enormous efforts devoted to understand the characteristics and impacts of retracted papers, little is known about the mechanisms underlying the dynamics of their harm and the dynamics of its propagation. Here, we propose a citation-based framework to quantify the harm caused by retracted papers, aiming to uncover why their harm persists and spreads so widely. We uncover an ''attention escape'' mechanism, wherein retracted papers postpone significant harm, more prominently affect indirectly citing papers, and inflict greater harm on citations in journals with an impact factor less than 10. This mechanism allows retracted papers to inflict harm outside the attention of authors and publishers, thereby evading their intervention. This study deepens understanding of the harm caused by retracted papers, emphasizes the need to activate and enhance the attention of authors and publishers, and offers new insights and a foundation for strategies to mitigate their harm and prevent its spread. △ Less

Submitted 18 February, 2025; v1 submitted 31 December, 2024; originally announced January 2025.

Condor: A Code Discriminator Integrating General Semantics with Code Details

Authors: Qingyuan Liang, Zhao Zhang, Chen Liu, Zeyu Sun, Wenjie Zhang, Yizhou Chen, Zixiao Zhao, Qi Luo, Wentao Wang, Yanjie Jiang, Yingfei Xiong, Lu Zhang

Abstract: LLMs demonstrate significant potential across various software engineering tasks. However, they still face challenges in generating correct code on the first attempt when addressing complex requirements. Introducing a discriminator to select reliable outputs from multiple generated results is an effective way to enhance their reliability and stability. Currently, these discriminators fall into two… ▽ More LLMs demonstrate significant potential across various software engineering tasks. However, they still face challenges in generating correct code on the first attempt when addressing complex requirements. Introducing a discriminator to select reliable outputs from multiple generated results is an effective way to enhance their reliability and stability. Currently, these discriminators fall into two categories: execution-based discriminators and non-execution-based discriminators. Execution-based discriminators face flexibility challenges due to difficulties in obtaining test cases and security concerns, while non-execution-based discriminators, although more flexible, struggle to capture subtle differences in code details. To maintain flexibility while improving the model's ability to capture fine-grained code details, this paper proposes Condor. We first design contrastive learning to optimize the code representations of the base model, enabling it to reflect differences in code details. Then, we leverage intermediate data from the code modification process to further enrich the discriminator's training data, enhancing its ability to discern code details. Experimental results indicate that on the subtle code difference dataset (i.e., CodeNanoFix), Condor significantly outperforms other discriminators in discriminative performance: Condor (1.3B) improves the discriminative F1 score of DeepSeek-Coder (1.3B) from 67% to 73%. In discriminating LLM-generated outputs, Condor (1.3B) and Condor (110M) raise the Pass@1 score of Meta-Llama-3.1-Instruct (70B) on the CodeNanoFix dataset from 52.64% to 62.63% and 59.64%, respectively. Moreover, Condor demonstrates strong generalization capabilities on the APPS, MBPP, and LiveCodeBench datasets. For example, Condor (1.3B) improves the Pass@1 of Meta-Llama-3.1-Instruct (70B) on the APPS dataset by 147.05%. △ Less

Submitted 10 December, 2025; v1 submitted 23 December, 2024; originally announced December 2024.