Showing 1–50 of 166 results for author: You, H

Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs

Authors: Kai Wang, Haoyang You, Yang Zhang, Zhongjie Wang

Abstract: A core challenge for faithful LLM role-playing is sustaining consistent characterization throughout long, open-ended dialogues, as models frequently fail to recall and accurately apply their designated persona knowledge without explicit cues. To tackle this, we propose the Memory-Driven Role-Playing paradigm. Inspired by Stanislavski's "emotional memory" acting theory, this paradigm frames persona… ▽ More A core challenge for faithful LLM role-playing is sustaining consistent characterization throughout long, open-ended dialogues, as models frequently fail to recall and accurately apply their designated persona knowledge without explicit cues. To tackle this, we propose the Memory-Driven Role-Playing paradigm. Inspired by Stanislavski's "emotional memory" acting theory, this paradigm frames persona knowledge as the LLM's internal memory store, requiring retrieval and application based solely on dialogue context, thereby providing a rigorous test of depth and autonomous use of knowledge. Centered on this paradigm, we contribute: (1) MREval, a fine-grained evaluation framework assessing four memory-driven abilities - Anchoring, Recalling, Bounding, and Enacting; (2) MRPrompt, a prompting architecture that guides structured memory retrieval and response generation; and (3) MRBench, a bilingual (Chinese/English) benchmark for fine-grained diagnosis. The novel paradigm provides a comprehensive diagnostic for four-staged role-playing abilities across 12 LLMs. Crucially, experiments show that MRPrompt allows small models (e.g., Qwen3-8B) to match the performance of much larger closed-source LLMs (e.g., Qwen3-Max and GLM-4.7), and confirms that upstream memory gains directly enhance downstream response quality, validating the staged theoretical foundation. △ Less

Submitted 14 March, 2026; originally announced March 2026.

Comments: 34 pages

TEGA: A Tactile-Enhanced Grasping Assistant for Assistive Robotics via Sensor Fusion and Closed-Loop Haptic Feedback

Authors: Hengxu You, Tianyu Zhou, Fang Xu, Kaleb Smith, Eric Jing Du

Abstract: Recent advances in teleoperation have enabled sophisticated manipulation of dexterous robotic hands, with most systems concentrating on guiding finger positions to achieve desired grasp configurations. However, while accurate finger positioning is essential, it often overlooks the equally critical task of grasp force modulation, vital for handling objects of diverse hardness, texture, and shape. T… ▽ More Recent advances in teleoperation have enabled sophisticated manipulation of dexterous robotic hands, with most systems concentrating on guiding finger positions to achieve desired grasp configurations. However, while accurate finger positioning is essential, it often overlooks the equally critical task of grasp force modulation, vital for handling objects of diverse hardness, texture, and shape. This limitation poses a significant challenge for users, especially individuals with upper limb disabilities who lack natural tactile feedback and rely on indirect cues to infer appropriate force levels. To address this gap, We present the tactile enhanced grasping assistant (TEGA), a closed loop assistive teleoperation framework that fuses EMG based intent2force inference with visuotactile sensing mapped into real time vibrotactile feedback via a wearable haptic vest, enabling intuitive, proportional force adjustment during manipulation. A wearable haptic vest delivers real time tactile feedback, allowing users to dynamically refine grasp force during manipulation. User studies confirm that the system substantially improves grasp stability and task success, underscoring its potential for assistive robotic applications. △ Less

Submitted 4 March, 2026; originally announced March 2026.

Comments: Accepted to include in ICRA 2026

Principled Learning-to-Communicate with Quasi-Classical Information Structures

Authors: Xiangyu Liu, Haoyi You, Kaiqing Zhang

Abstract: Learning-to-communicate (LTC) in partially observable environments has received increasing attention in deep multi-agent reinforcement learning, where the control and communication strategies are jointly learned. Meanwhile, the impact of communication on decision-making has been extensively studied in control theory. In this paper, we seek to formalize and better understand LTC by bridging these t… ▽ More Learning-to-communicate (LTC) in partially observable environments has received increasing attention in deep multi-agent reinforcement learning, where the control and communication strategies are jointly learned. Meanwhile, the impact of communication on decision-making has been extensively studied in control theory. In this paper, we seek to formalize and better understand LTC by bridging these two lines of work, through the lens of information structures (ISs). To this end, we formalize LTC in decentralized partially observable Markov decision processes (Dec-POMDPs) under the common-information-based framework from decentralized stochastic control, and classify LTC problems based on the ISs before (additional) information sharing. We first show that non-classical LTCs are computationally intractable in general, and thus focus on quasi-classical (QC) LTCs. We then propose a series of conditions for QC LTCs, under which LTCs preserve the QC IS after information sharing, whereas violating which can cause computational hardness in general. Further, we develop provable planning and learning algorithms for QC LTCs, and establish quasi-polynomial time and sample complexities for several QC LTC examples that satisfy the above conditions. Along the way, we also establish results on the relationship between (strictly) QC IS and the condition of having strategy-independent common-information-based beliefs (SI-CIBs), as well as on solving Dec-POMDPs without computationally intractable oracles but beyond those with SI-CIBs, which may be of independent interest. △ Less

Submitted 3 March, 2026; originally announced March 2026.

Comments: Preliminary version appeared at IEEE CDC 2025

Multivariate Spatio-Temporal Neural Hawkes Processes

Authors: Christopher Chukwuemeka, Hojun You, Mikyoung Jun

Abstract: We propose a Multivariate Spatio-Temporal Neural Hawkes Process for modeling complex multivariate event data with spatio-temporal dynamics. The proposed model extends continuous-time neural Hawkes processes by integrating spatial information into latent state evolution through learned temporal and spatial decay dynamics, enabling flexible modeling of excitation and inhibition without predefined tr… ▽ More We propose a Multivariate Spatio-Temporal Neural Hawkes Process for modeling complex multivariate event data with spatio-temporal dynamics. The proposed model extends continuous-time neural Hawkes processes by integrating spatial information into latent state evolution through learned temporal and spatial decay dynamics, enabling flexible modeling of excitation and inhibition without predefined triggering kernels. By analyzing fitted intensity functions of deep learning-based temporal Hawkes process models, we identify a modeling gap in how fitted intensity behavior is captured beyond likelihood-based performance, which motivates the proposed spatio-temporal approach. Simulation studies show that the proposed method successfully recovers sensible temporal and spatial intensity structure in multivariate spatio-temporal point patterns, while existing temporal neural Hawkes process approach fails to do so. An application to terrorism data from Pakistan further demonstrates the proposed model's ability to capture complex spatio-temporal interaction across multiple event types. △ Less

Submitted 1 March, 2026; v1 submitted 26 February, 2026; originally announced February 2026.

Comments: 16 pages, 20 figures (including supplementary material)

MSC Class: 60G55 (Primary); 62M30; 68T07 (Secondary) ACM Class: I.2.6; G.3

Generalized Radius and Integrated Codebook Transforms for Differentiable Vector Quantization

Authors: Haochen You, Heng Zhang, Hongyang He, Yuqi Li, Baojing Liu

Abstract: Vector quantization (VQ) underpins modern generative and representation models by turning continuous latents into discrete tokens. Yet hard nearest-neighbor assignments are non-differentiable and are typically optimized with heuristic straight-through estimators, which couple the update step size to the quantization gap and train each code in isolation, leading to unstable gradients and severe cod… ▽ More Vector quantization (VQ) underpins modern generative and representation models by turning continuous latents into discrete tokens. Yet hard nearest-neighbor assignments are non-differentiable and are typically optimized with heuristic straight-through estimators, which couple the update step size to the quantization gap and train each code in isolation, leading to unstable gradients and severe codebook under-utilization at scale. In this paper, we introduce GRIT-VQ (Generalized Radius and Integrated Transform-Vector Quantization), a unified surrogate framework that keeps hard assignments in the forward pass while making VQ fully differentiable. GRIT-VQ replaces the straight-through estimator with a radius-based update that moves latents along the quantization direction with a controllable, geometry-aware step, and applies a data-agnostic integrated transform to the codebook so that all codes are updated through shared parameters instead of independently. Our theoretical analysis clarifies the fundamental optimization dynamics introduced by GRIT-VQ, establishing conditions for stable gradient flow, coordinated codebook evolution, and reliable avoidance of collapse across a broad family of quantizers. Across image reconstruction, image generation, and recommendation tokenization benchmarks, GRIT-VQ consistently improves reconstruction error, generative quality, and recommendation accuracy while substantially increasing codebook utilization compared to existing VQ variants. △ Less

Submitted 1 February, 2026; originally announced February 2026.

Comments: This paper has been accepted as a conference paper at CPAL 2026

A Comprehensive Study of Deep Learning Model Fixing Approaches

Authors: Hanmo You, Zan Wang, Zishuo Dong, Luanqi Mo, Jianjun Zhao, Junjie Chen

Abstract: Deep Learning (DL) has been widely adopted in diverse industrial domains, including autonomous driving, intelligent healthcare, and aided programming. Like traditional software, DL systems are also prone to faults, whose malfunctioning may expose users to significant risks. Consequently, numerous approaches have been proposed to address these issues. In this paper, we conduct a large-scale empiric… ▽ More Deep Learning (DL) has been widely adopted in diverse industrial domains, including autonomous driving, intelligent healthcare, and aided programming. Like traditional software, DL systems are also prone to faults, whose malfunctioning may expose users to significant risks. Consequently, numerous approaches have been proposed to address these issues. In this paper, we conduct a large-scale empirical study on 16 state-of-the-art DL model fixing approaches, spanning model-level, layer-level, and neuron-level categories, to comprehensively evaluate their performance. We assess not only their fixing effectiveness (their primary purpose) but also their impact on other critical properties, such as robustness, fairness, and backward compatibility. To ensure comprehensive and fair evaluation, we employ a diverse set of datasets, model architectures, and application domains within a uniform experimental setup for experimentation. We summarize several key findings with implications for both industry and academia. For example, model-level approaches demonstrate superior fixing effectiveness compared to others. No single approach can achieve the best fixing performance while improving accuracy and maintaining all other properties. Thus, academia should prioritize research on mitigating these side effects. These insights highlight promising directions for future exploration in this field. △ Less

Submitted 26 December, 2025; originally announced December 2025.

Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training

Authors: Hong-Jie You, Jie-Jing Shao, Xiao-Wen Yang, Lin-Han Jia, Lan-Zhe Guo, Yu-Feng Li

Abstract: Existing methods for expressive music performance rendering rely on supervised learning over small labeled datasets, which limits scaling of both data volume and model size, despite the availability of vast unlabeled music, as in vision and language. To address this gap, we introduce Pianist Transformer, with four key contributions: 1) a unified Musical Instrument Digital Interface (MIDI) data rep… ▽ More Existing methods for expressive music performance rendering rely on supervised learning over small labeled datasets, which limits scaling of both data volume and model size, despite the availability of vast unlabeled music, as in vision and language. To address this gap, we introduce Pianist Transformer, with four key contributions: 1) a unified Musical Instrument Digital Interface (MIDI) data representation for learning the shared principles of musical structure and expression without explicit annotation; 2) an efficient asymmetric architecture, enabling longer contexts and faster inference without sacrificing rendering quality; 3) a self-supervised pre-training pipeline with 10B tokens and 135M-parameter model, unlocking data and model scaling advantages for expressive performance rendering; 4) a state-of-the-art performance model, which achieves strong objective metrics and human-level subjective ratings. Overall, Pianist Transformer establishes a scalable path toward human-like performance synthesis in the music domain. △ Less

Submitted 2 December, 2025; originally announced December 2025.

Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning

Authors: Qi Wang, Mian Wu, Yuyang Zhang, Mingqi Yuan, Wenyao Zhang, Haoxiang You, Yunbo Wang, Xin Jin, Xiaokang Yang, Wenjun Zeng

Abstract: Reinforcement Learning (RL) has achieved remarkable success in various domains, yet it often relies on carefully designed programmatic reward functions to guide agent behavior. Designing such reward functions can be challenging and may not generalize well across different tasks. To address this limitation, we leverage the rich world knowledge contained in pretrained video diffusion models to provi… ▽ More Reinforcement Learning (RL) has achieved remarkable success in various domains, yet it often relies on carefully designed programmatic reward functions to guide agent behavior. Designing such reward functions can be challenging and may not generalize well across different tasks. To address this limitation, we leverage the rich world knowledge contained in pretrained video diffusion models to provide goal-driven reward signals for RL agents without ad-hoc design of reward. Our key idea is to exploit off-the-shelf video diffusion models pretrained on large-scale video datasets as informative reward functions in terms of video-level and frame-level goals. For video-level rewards, we first finetune a pretrained video diffusion model on domain-specific datasets and then employ its video encoder to evaluate the alignment between the latent representations of agent's trajectories and the generated goal videos. To enable more fine-grained goal-achievement, we derive a frame-level goal by identifying the most relevant frame from the generated video using CLIP, which serves as the goal state. We then employ a learned forward-backward representation that represents the probability of visiting the goal state from a given state-action pair as frame-level reward, promoting more coherent and goal-driven trajectories. Experiments on Meta-World and Distracting Control Suite demonstrate the effectiveness of our approach. △ Less

Submitted 3 April, 2026; v1 submitted 30 November, 2025; originally announced December 2025.

Comments: Accepted by CVPR 2026. Project page: https://qiwang067.github.io/genreward

Pharos-ESG: A Framework for Multimodal Parsing, Contextual Narration, and Hierarchical Labeling of ESG Report

Authors: Yan Chen, Yu Zou, Jialei Zeng, Haoran You, Xiaorui Zhou, Aixi Zhong

Abstract: Environmental, Social, and Governance (ESG) principles are reshaping the foundations of global financial governance, transforming capital allocation architectures, regulatory frameworks, and systemic risk coordination mechanisms. However, as the core medium for assessing corporate ESG performance, the ESG reports present significant challenges for large-scale understanding, due to chaotic reading… ▽ More Environmental, Social, and Governance (ESG) principles are reshaping the foundations of global financial governance, transforming capital allocation architectures, regulatory frameworks, and systemic risk coordination mechanisms. However, as the core medium for assessing corporate ESG performance, the ESG reports present significant challenges for large-scale understanding, due to chaotic reading order from slide-like irregular layouts and implicit hierarchies arising from lengthy, weakly structured content. To address these challenges, we propose Pharos-ESG, a unified framework that transforms ESG reports into structured representations through multimodal parsing, contextual narration, and hierarchical labeling. It integrates a reading-order modeling module based on layout flow, hierarchy-aware segmentation guided by table-of-contents anchors, and a multi-modal aggregation pipeline that contextually transforms visual elements into coherent natural language. The framework further enriches its outputs with ESG, GRI, and sentiment labels, yielding annotations aligned with the analytical demands of financial research. Extensive experiments on annotated benchmarks demonstrate that Pharos-ESG consistently outperforms both dedicated document parsing systems and general-purpose multimodal models. In addition, we release Aurora-ESG, the first large-scale public dataset of ESG reports, spanning Mainland China, Hong Kong, and U.S. markets, featuring unified structured representations of multi-modal content, enriched with fine-grained layout and semantic annotations to better support ESG integration in financial governance and decision-making. △ Less

Submitted 29 March, 2026; v1 submitted 20 November, 2025; originally announced November 2025.

ACM Class: I.2.7

UniSER: A Foundation Model for Unified Soft Effects Removal

Authors: Jingdong Zhang, Lingzhi Zhang, Qing Liu, Mang Tik Chiu, Connelly Barnes, Yizhou Wang, Haoran You, Xiaoyang Liu, Yuqian Zhou, Zhe Lin, Eli Shechtman, Sohrab Amirghodsi, Xin Li, Wenping Wang, Xiaohang Zhan

Abstract: Digital images are often degraded by soft effects such as lens flare, haze, shadows, and reflections, which reduce aesthetics even though the underlying pixels remain partially visible. The prevailing works address these degradations in isolation, developing highly specialized, specialist models that lack scalability and fail to exploit the shared underlying essences of these restoration problems.… ▽ More Digital images are often degraded by soft effects such as lens flare, haze, shadows, and reflections, which reduce aesthetics even though the underlying pixels remain partially visible. The prevailing works address these degradations in isolation, developing highly specialized, specialist models that lack scalability and fail to exploit the shared underlying essences of these restoration problems. Meanwhile, although recent large-scale generalist models (e.g., GPT-4o, Flux Kontext, Nano Banana) offer powerful text-driven editing capabilities, they heavily rely on detailed prompts and often fail to achieve robust removal on such fine-grained tasks while preserving the scene's identity. Leveraging the common essence of soft effects, i.e., semi-transparent occlusions, we introduce a foundational versatile model UniSER, capable of addressing diverse degradations caused by soft effects within a single framework. Our methodology centers on curating a massive 3.8M-pair dataset to ensure robustness and generalization, which includes novel, physically-plausible data to fill critical gaps in public benchmarks, and a tailored training pipeline that fine-tunes a Diffusion Transformer to learn robust restoration priors from this diverse data, integrating fine-grained mask and strength controls. This synergistic approach allows UniSER to significantly outperform both specialist and generalist models, achieving robust, high-fidelity restoration in the wild. △ Less

Submitted 27 March, 2026; v1 submitted 18 November, 2025; originally announced November 2025.

G2rammar: Bilingual Grammar Modeling for Enhanced Text-attributed Graph Learning

Authors: Heng Zheng, Haochen You, Zijun Liu, Zijian Zhang, Lubin Gan, Hao Zhang, Wenjun Huang, Jin Huang

Abstract: Text-attributed graphs require models to effectively integrate both structural topology and semantic content. Recent approaches apply large language models to graphs by linearizing structures into token sequences through random walks. These methods create concise graph vocabularies to replace verbose natural language descriptions. However, they overlook a critical component that makes language exp… ▽ More Text-attributed graphs require models to effectively integrate both structural topology and semantic content. Recent approaches apply large language models to graphs by linearizing structures into token sequences through random walks. These methods create concise graph vocabularies to replace verbose natural language descriptions. However, they overlook a critical component that makes language expressive: grammar. In natural language, grammar assigns syntactic roles to words and defines their functions within sentences. Similarly, nodes in graphs play distinct structural roles as hubs, bridges, or peripheral members. Current graph language methods provide tokens without grammatical annotations to indicate these structural or semantic roles. This absence limits language models' ability to reason about graph topology effectively. We propose \textbf{G2rammar}, a bilingual grammar framework that explicitly encodes both structural and semantic grammar for text-attributed graphs. Structural grammar characterizes topological roles through centrality and neighborhood patterns. Semantic grammar captures content relationships through textual informativity. The framework implements two-stage learning with structural grammar pre-training followed by semantic grammar fine-tuning. Extensive experiments on real-world datasets demonstrate that G2rammar consistently outperforms competitive baselines by providing language models with the grammatical context needed to understand graph structures. △ Less

Submitted 22 December, 2025; v1 submitted 2 November, 2025; originally announced November 2025.

Comments: This submission has been withdrawn by the authors due to a fundamental error in the methodology that affects the validity of the main results

GraphGeo: Multi-Agent Debate Framework for Visual Geo-localization with Heterogeneous Graph Neural Networks

Authors: Heng Zheng, Yuling Shi, Xiaodong Gu, Haochen You, Zijian Zhang, Lubin Gan, Hao Zhang, Wenjun Huang, Jin Huang

Abstract: Visual geo-localization requires extensive geographic knowledge and sophisticated reasoning to determine image locations without GPS metadata. Traditional retrieval methods are constrained by database coverage and quality. Recent Large Vision-Language Models (LVLMs) enable direct location reasoning from image content, yet individual models struggle with diverse geographic regions and complex scene… ▽ More Visual geo-localization requires extensive geographic knowledge and sophisticated reasoning to determine image locations without GPS metadata. Traditional retrieval methods are constrained by database coverage and quality. Recent Large Vision-Language Models (LVLMs) enable direct location reasoning from image content, yet individual models struggle with diverse geographic regions and complex scenes. Existing multi-agent systems improve performance through model collaboration but treat all agent interactions uniformly. They lack mechanisms to handle conflicting predictions effectively. We propose \textbf{GraphGeo}, a multi-agent debate framework using heterogeneous graph neural networks for visual geo-localization. Our approach models diverse debate relationships through typed edges, distinguishing supportive collaboration, competitive argumentation, and knowledge transfer. We introduce a dual-level debate mechanism combining node-level refinement and edge-level argumentation modeling. A cross-level topology refinement strategy enables co-evolution between graph structure and agent representations. Experiments on multiple benchmarks demonstrate GraphGeo significantly outperforms state-of-the-art methods. Our framework transforms cognitive conflicts between agents into enhanced geo-localization accuracy through structured debate. △ Less

Submitted 22 December, 2025; v1 submitted 2 November, 2025; originally announced November 2025.

Comments: This submission has been withdrawn by the authors due to a fundamental error in the methodology that affects the validity of the main results

Empowering LLMs with Structural Role Inference for Zero-Shot Graph Learning

Authors: Heng Zhang, Jing Liu, Jiajun Wu, Haochen You, Lubin Gan, Yuling Shi, Xiaodong Gu, Zijian Zhang, Shuai Chen, Wenjun Huang, Jin Huang

Abstract: Large Language Models have emerged as a promising approach for graph learning due to their powerful reasoning capabilities. However, existing methods exhibit systematic performance degradation on structurally important nodes such as bridges and hubs. We identify the root cause of these limitations. Current approaches encode graph topology into static features but lack reasoning scaffolds to transf… ▽ More Large Language Models have emerged as a promising approach for graph learning due to their powerful reasoning capabilities. However, existing methods exhibit systematic performance degradation on structurally important nodes such as bridges and hubs. We identify the root cause of these limitations. Current approaches encode graph topology into static features but lack reasoning scaffolds to transform topological patterns into role-based interpretations. This limitation becomes critical in zero-shot scenarios where no training data establishes structure-semantics mappings. To address this gap, we propose DuoGLM, a training-free dual-perspective framework for structure-aware graph reasoning. The local perspective constructs relation-aware templates capturing semantic interactions between nodes and neighbors. The global perspective performs topology-to-role inference to generate functional descriptions of structural positions. These complementary perspectives provide explicit reasoning mechanisms enabling LLMs to distinguish topologically similar but semantically different nodes. Extensive experiments across eight benchmark datasets demonstrate substantial improvements. DuoGLM achieves 14.3\% accuracy gain in zero-shot node classification and 7.6\% AUC improvement in cross-domain transfer compared to existing methods. The results validate the effectiveness of explicit role reasoning for graph understanding with LLMs. △ Less

Submitted 22 December, 2025; v1 submitted 2 November, 2025; originally announced November 2025.

Comments: This submission has been withdrawn by the authors due to a fundamental error in the methodology that affects the validity of the main results

Sample-Based Hybrid Mode Control: Asymptotically Optimal Switching of Algorithmic and Non-Differentiable Control Modes

Authors: Yilang Liu, Haoxiang You, Ian Abraham

Abstract: This paper investigates a sample-based solution to the hybrid mode control problem across non-differentiable and algorithmic hybrid modes. Our approach reasons about a set of hybrid control modes as an integer-based optimization problem where we select what mode to apply, when to switch to another mode, and the duration for which we are in a given control mode. A sample-based variation is derived… ▽ More This paper investigates a sample-based solution to the hybrid mode control problem across non-differentiable and algorithmic hybrid modes. Our approach reasons about a set of hybrid control modes as an integer-based optimization problem where we select what mode to apply, when to switch to another mode, and the duration for which we are in a given control mode. A sample-based variation is derived to efficiently search the integer domain for optimal solutions. We find our formulation yields strong performance guarantees that can be applied to a number of robotics-related tasks. In addition, our approach is able to synthesize complex algorithms and policies to compound behaviors and achieve challenging tasks. Last, we demonstrate the effectiveness of our approach in real-world robotic examples that require reactive switching between long-term planning and high-frequency control. △ Less

Submitted 5 March, 2026; v1 submitted 21 October, 2025; originally announced October 2025.

MPI-over-CXL: Enhancing Communication Efficiency in Distributed HPC Systems

Authors: Miryeong Kwon, Donghyun Gouk, Hyein Woo, Junhee Kim, Jinwoo Baek, Kyungkuk Nam, Sangyoon Ji, Jiseon Kim, Hanyeoreum Bae, Junhyeok Jang, Hyunwoo You, Junseok Moon, Myoungsoo Jung

Abstract: MPI implementations commonly rely on explicit memory-copy operations, incurring overhead from redundant data movement and buffer management. This overhead notably impacts HPC workloads involving intensive inter-processor communication. In response, we introduce MPI-over-CXL, a novel MPI communication paradigm leveraging CXL, which provides cache-coherent shared memory across multiple hosts. MPI-ov… ▽ More MPI implementations commonly rely on explicit memory-copy operations, incurring overhead from redundant data movement and buffer management. This overhead notably impacts HPC workloads involving intensive inter-processor communication. In response, we introduce MPI-over-CXL, a novel MPI communication paradigm leveraging CXL, which provides cache-coherent shared memory across multiple hosts. MPI-over-CXL replaces traditional data-copy methods with direct shared memory access, significantly reducing communication latency and memory bandwidth usage. By mapping shared memory regions directly into the virtual address spaces of MPI processes, our design enables efficient pointer-based communication, eliminating redundant copying operations. To validate this approach, we implement a comprehensive hardware and software environment, including a custom CXL 3.2 controller, FPGA-based multi-host emulation, and dedicated software stack. Our evaluations using representative benchmarks demonstrate substantial performance improvements over conventional MPI systems, underscoring MPI-over-CXL's potential to enhance efficiency and scalability in large-scale HPC environments. △ Less

Submitted 16 October, 2025; originally announced October 2025.

H4G: Unlocking Faithful Inference for Zero-Shot Graph Learning in Hyperbolic Space

Authors: Heng Zhang, Tianyi Zhang, Zijun Liu, Yuling Shi, Yaomin Shen, Haochen You, Haichuan Hu, Lubin Gan, Jin Huang

Abstract: Text-attributed graphs are widely used across domains, offering rich opportunities for zero-shot learning via graph-text alignment. However, existing methods struggle with tasks requiring fine-grained pattern recognition, particularly on heterophilic graphs. Through empirical and theoretical analysis, we identify an \textbf{over-abstraction problem}: current approaches operate at excessively large… ▽ More Text-attributed graphs are widely used across domains, offering rich opportunities for zero-shot learning via graph-text alignment. However, existing methods struggle with tasks requiring fine-grained pattern recognition, particularly on heterophilic graphs. Through empirical and theoretical analysis, we identify an \textbf{over-abstraction problem}: current approaches operate at excessively large hyperbolic radii, compressing multi-scale structural information into uniform high-level abstractions. This abstraction-induced information loss obscures critical local patterns essential for accurate predictions. By analyzing embeddings in hyperbolic space, we demonstrate that optimal graph learning requires \textbf{faithful preservation} of fine-grained structural details, better retained by representations positioned closer to the origin. To address this, we propose \textbf{H4G}, a framework that systematically reduces embedding radii using learnable block-diagonal scaling matrices and Möbius matrix multiplication. This approach restores access to fine-grained patterns while maintaining global receptive ability with minimal computational overhead. Experiments show H4G achieves state-of-the-art zero-shot performance with \textbf{12.8\%} improvement on heterophilic graphs and \textbf{8.4\%} on homophilic graphs, confirming that radius reduction enables faithful multi-scale representation for advancing zero-shot graph learning. △ Less

Submitted 13 October, 2025; originally announced October 2025.

GraphShaper: Geometry-aware Alignment for Improving Transfer Learning in Text-Attributed Graphs

Authors: Heng Zhang, Tianyi Zhang, Yuling Shi, Xiaodong Gu, Yaomin Shen, Haochen You, Zijian Zhang, Yilei Yuan, Jin Huang

Abstract: Graph foundation models represent a transformative paradigm for learning transferable representations across diverse graph domains. Recent methods leverage large language models to unify graph and text modalities into a shared representation space using contrastive learning. However, systematic evaluations reveal significant performance degradation at structural boundaries where distinct topologic… ▽ More Graph foundation models represent a transformative paradigm for learning transferable representations across diverse graph domains. Recent methods leverage large language models to unify graph and text modalities into a shared representation space using contrastive learning. However, systematic evaluations reveal significant performance degradation at structural boundaries where distinct topological patterns converge, with accuracy losses exceeding 20 percentage points. This issue arises from a key limitation: current methods assume all graph structures can be encoded within a single Euclidean space. In reality, tree structures require hyperbolic geometry to preserve hierarchical branching, while cyclic patterns depend on spherical geometry for closure properties. At structural boundaries, nodes experience conflicting geometric constraints that uniform encoding spaces cannot resolve. This raises a crucial challenge: \textbf{Can alignment frameworks be designed to respect the intrinsic geometric diversity of graph structures?} We introduce \textbf{GraphShaper}, a geometry-aware framework that enhances graph encoding through multi-geometric specialization. Our approach employs expert networks tailored to different geometric spaces, dynamically computing fusion weights to adaptively integrate geometric properties based on local structural characteristics. This adaptive fusion preserves structural integrity before alignment with text embeddings. Extensive experiments demonstrate that GraphShaper achieves 9.47\% accuracy improvements on citation networks and 7.63\% on social networks in zero-shot settings. △ Less

Submitted 22 December, 2025; v1 submitted 13 October, 2025; originally announced October 2025.

Comments: This submission has been withdrawn by the authors due to a fundamental error in the methodology that affects the validity of the main results

HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communication

Authors: Heng Zhang, Yuling Shi, Xiaodong Gu, Zijian Zhang, Haochen You, Lubin Gan, Yilei Yuan, Jin Huang

Abstract: Recent advances in large language model-powered multi-agent systems have demonstrated remarkable collective intelligence through effective communication. However, existing approaches face two primary challenges: (i) \textit{Ineffective group collaboration modeling}, as they rely on pairwise edge representations in graph structures, limiting their ability to capture relationships among multiple age… ▽ More Recent advances in large language model-powered multi-agent systems have demonstrated remarkable collective intelligence through effective communication. However, existing approaches face two primary challenges: (i) \textit{Ineffective group collaboration modeling}, as they rely on pairwise edge representations in graph structures, limiting their ability to capture relationships among multiple agents; and (ii) \textit{Limited task-adaptiveness in communication topology design}, leading to excessive communication cost for simple tasks and insufficient coordination for complex scenarios. These issues restrict the scalability and practical deployment of adaptive collaboration frameworks. To address these challenges, we propose \textbf{HyperAgent}, a hypergraph-based framework that optimizes communication topologies and effectively captures group collaboration patterns using direct hyperedge representations. Unlike edge-based approaches, HyperAgent uses hyperedges to link multiple agents within the same subtask and employs hypergraph convolutional layers to achieve one-step information aggregation in collaboration groups. Additionally, it incorporates a variational autoencoder framework with sparsity regularization to dynamically adjust hypergraph topologies based on task complexity. Experiments highlight the superiority of HyperAgent in both performance and efficiency. For instance, on GSM8K, HyperAgent achieves 95.07\% accuracy while reducing token consumption by 25.33\%, demonstrating the potential of hypergraph-based optimization for multi-agent communication. △ Less

Submitted 25 February, 2026; v1 submitted 12 October, 2025; originally announced October 2025.

Comments: This submission has been withdrawn by the authors due to a fundamental error in the methodology that affects the validity of the main results

D3MAS: Decompose, Deduce, and Distribute for Enhanced Knowledge Sharing in Multi-Agent Systems

Authors: Heng Zhang, Yuling Shi, Xiaodong Gu, Haochen You, Zijian Zhang, Lubin Gan, Yilei Yuan, Jin Huang

Abstract: Multi-agent systems powered by large language models exhibit strong capabilities in collaborative problem-solving. However, these systems suffer from substantial knowledge redundancy. Agents duplicate efforts in retrieval and reasoning processes. This inefficiency stems from a deeper issue: current architectures lack mechanisms to ensure agents share minimal sufficient information at each operatio… ▽ More Multi-agent systems powered by large language models exhibit strong capabilities in collaborative problem-solving. However, these systems suffer from substantial knowledge redundancy. Agents duplicate efforts in retrieval and reasoning processes. This inefficiency stems from a deeper issue: current architectures lack mechanisms to ensure agents share minimal sufficient information at each operational stage. Empirical analysis reveals an average knowledge duplication rate of 47.3\% across agent communications. We propose D3MAS (Decompose, Deduce, and Distribute), a hierarchical coordination framework addressing redundancy through structural design rather than explicit optimization. The framework organizes collaboration across three coordinated layers. Task decomposition filters irrelevant sub-problems early. Collaborative reasoning captures complementary inference paths across agents. Distributed memory provides access to non-redundant knowledge. These layers coordinate through structured message passing in a unified heterogeneous graph. This cross-layer alignment ensures information remains aligned with actual task needs. Experiments on four challenging datasets show that D3MAS consistently improves reasoning accuracy by 8.7\% to 15.6\% and reduces knowledge redundancy by 46\% on average. △ Less

Submitted 25 February, 2026; v1 submitted 12 October, 2025; originally announced October 2025.

Comments: This submission has been withdrawn by the authors due to a fundamental error in the methodology that affects the validity of the main results

GraphTracer: Graph-Guided Failure Tracing in LLM Agents for Robust Multi-Turn Deep Search

Authors: Heng Zhang, Yuling Shi, Xiaodong Gu, Haochen You, Zijian Zhang, Lubin Gan, Yilei Yuan, Jin Huang

Abstract: Multi-agent systems powered by Large Language Models excel at complex tasks through coordinated collaboration, yet they face high failure rates in multi-turn deep search scenarios. Existing temporal attribution methods struggle to accurately diagnose root causes, particularly when errors propagate across multiple agents. Attempts to automate failure attribution by analyzing action sequences remain… ▽ More Multi-agent systems powered by Large Language Models excel at complex tasks through coordinated collaboration, yet they face high failure rates in multi-turn deep search scenarios. Existing temporal attribution methods struggle to accurately diagnose root causes, particularly when errors propagate across multiple agents. Attempts to automate failure attribution by analyzing action sequences remain ineffective due to their inability to account for information dependencies that span agents. This paper identifies two core challenges: \textit{(i) distinguishing symptoms from root causes in multi-agent error propagation}, and \textit{(ii) tracing information dependencies beyond temporal order}. To address these issues, we introduce \textbf{GraphTracer}, a framework that redefines failure attribution through information flow analysis. GraphTracer constructs Information Dependency Graphs (IDGs) to explicitly capture how agents reference and build on prior outputs. It localizes root causes by tracing through these dependency structures instead of relying on temporal sequences. GraphTracer also uses graph-aware synthetic data generation to target critical nodes, creating realistic failure scenarios. Evaluations on the Who\&When benchmark and integration into production systems demonstrate that GraphTracer-8B achieves up to 18.18\% higher attribution accuracy compared to state-of-the-art models and enables 4.8\% to 14.2\% performance improvements in deployed multi-agent frameworks, establishing a robust solution for multi-agent system debugging. △ Less

Submitted 22 December, 2025; v1 submitted 12 October, 2025; originally announced October 2025.

Comments: This submission has been withdrawn by the authors due to a fundamental error in the methodology that affects the validity of the main results

ReSSFormer: A Recursive Sparse Structured Transformer for Scalable and Long-Context Reasoning

Authors: Haochen You, Baojing Liu

Abstract: While Transformer architectures have demonstrated impressive scalability across domains, they continue to face challenges in long-context reasoning, computational efficiency, and structural generalization - largely due to rigid layer stacking, dense attention, and reliance on positional encodings. We present ReSSFormer, a Recursive Sparse Structured Transformer that integrates three complementary… ▽ More While Transformer architectures have demonstrated impressive scalability across domains, they continue to face challenges in long-context reasoning, computational efficiency, and structural generalization - largely due to rigid layer stacking, dense attention, and reliance on positional encodings. We present ReSSFormer, a Recursive Sparse Structured Transformer that integrates three complementary innovations: Recurrent Reasoning & Memory Unit (R2MU) for iterative reasoning with bounded depth, Adaptive Sparse Attention Module (ASAM) for efficient and focused context selection, and Self-Organizing Encoder Structure (SOES) for position-free structure induction. ReSSFormer replaces conventional depth stacking with recurrent inference, substitutes full attention with token- and expert-level sparsity, and models latent token topology directly from content. Across language modeling, multi-hop QA, and structure-sensitive tasks, ReSSFormer consistently outperforms strong baselines under comparable FLOPs and parameter budgets, highlighting its scalability, efficiency, and structural flexibility. △ Less

Submitted 1 October, 2025; originally announced October 2025.

Comments: Accepted as a short paper at ACM Multimedia Asia 2025

Gradient Shaping Beyond Clipping: A Functional Perspective on Update Magnitude Control

Authors: Haochen You, Baojing Liu

Abstract: Gradient clipping is widely used to stabilize deep network training, but its formulation as a hard, fixed threshold limits flexibility and ignores gradient distribution dynamics. We propose SPAMP (Statistical Per-layer Adaptive Modulation and Projection), a unified framework that generalizes clipping into smooth, per-layer gradient shaping. SPAMP tracks local gradient statistics, dynamically estim… ▽ More Gradient clipping is widely used to stabilize deep network training, but its formulation as a hard, fixed threshold limits flexibility and ignores gradient distribution dynamics. We propose SPAMP (Statistical Per-layer Adaptive Modulation and Projection), a unified framework that generalizes clipping into smooth, per-layer gradient shaping. SPAMP tracks local gradient statistics, dynamically estimates thresholds, and applies power-based transformations to modulate update magnitudes in a differentiable manner. This perspective recasts clipping and warmup as dual mechanisms for controlling the effective update scale $η_t \|g_t\|$, offering a principled alternative to rigid heuristics. Extensive experiments across image and language tasks demonstrate that SPAMP improves stability, convergence, and robustness over existing methods. △ Less

Submitted 1 October, 2025; originally announced October 2025.

Comments: Accepted as a conference paper at ACM Multimedia Asia 2025

A Multi-Level Framework for Multi-Objective Hypergraph Partitioning: Combining Minimum Spanning Tree and Proximal Gradient

Authors: Yingying Li, Mingxuan Xie, Hailong You, Yongqiang Yao, Hongwei Liu

Abstract: This paper proposes an efficient hypergraph partitioning framework based on a novel multi-objective non-convex constrained relaxation model. A modified accelerated proximal gradient algorithm is employed to generate diverse $k$-dimensional vertex features to avoid local optima and enhance partition quality. Two MST-based strategies are designed for different data scales: for small-scale data, the… ▽ More This paper proposes an efficient hypergraph partitioning framework based on a novel multi-objective non-convex constrained relaxation model. A modified accelerated proximal gradient algorithm is employed to generate diverse $k$-dimensional vertex features to avoid local optima and enhance partition quality. Two MST-based strategies are designed for different data scales: for small-scale data, the Prim algorithm constructs a minimum spanning tree followed by pruning and clustering; for large-scale data, a subset of representative nodes is selected to build a smaller MST, while the remaining nodes are assigned accordingly to reduce complexity. To further improve partitioning results, refinement strategies including greedy migration, swapping, and recursive MST-based clustering are introduced for partitions. Experimental results on public benchmark sets demonstrate that the proposed algorithm achieves reductions in cut size of approximately 2\%--5\% on average compared to KaHyPar in 2, 3, and 4-way partitioning, with improvements of up to 35\% on specific instances. Particularly on weighted vertex sets, our algorithm outperforms state-of-the-art partitioners including KaHyPar, hMetis, Mt-KaHyPar, and K-SpecPart, highlighting its superior partitioning quality and competitiveness. Furthermore, the proposed refinement strategy improves hMetis partitions by up to 16\%. A comprehensive evaluation based on virtual instance methodology and parameter sensitivity analysis validates the algorithm's competitiveness and characterizes its performance trade-offs. △ Less

Submitted 26 September, 2025; originally announced September 2025.

TRiCo: Triadic Game-Theoretic Co-Training for Robust Semi-Supervised Learning

Authors: Hongyang He, Xinyuan Song, Yangfan He, Zeyu Zhang, Yanshu Li, Haochen You, Lifan Sun, Wenqiao Zhang

Abstract: We introduce TRiCo, a novel triadic game-theoretic co-training framework that rethinks the structure of semi-supervised learning by incorporating a teacher, two students, and an adversarial generator into a unified training paradigm. Unlike existing co-training or teacher-student approaches, TRiCo formulates SSL as a structured interaction among three roles: (i) two student classifiers trained on… ▽ More We introduce TRiCo, a novel triadic game-theoretic co-training framework that rethinks the structure of semi-supervised learning by incorporating a teacher, two students, and an adversarial generator into a unified training paradigm. Unlike existing co-training or teacher-student approaches, TRiCo formulates SSL as a structured interaction among three roles: (i) two student classifiers trained on frozen, complementary representations, (ii) a meta-learned teacher that adaptively regulates pseudo-label selection and loss balancing via validation-based feedback, and (iii) a non-parametric generator that perturbs embeddings to uncover decision boundary weaknesses. Pseudo-labels are selected based on mutual information rather than confidence, providing a more robust measure of epistemic uncertainty. This triadic interaction is formalized as a Stackelberg game, where the teacher leads strategy optimization and students follow under adversarial perturbations. By addressing key limitations in existing SSL frameworks, such as static view interactions, unreliable pseudo-labels, and lack of hard sample modeling, TRiCo provides a principled and generalizable solution. Extensive experiments on CIFAR-10, SVHN, STL-10, and ImageNet demonstrate that TRiCo consistently achieves state-of-the-art performance in low-label regimes, while remaining architecture-agnostic and compatible with frozen vision backbones.Code:https://github.com/HoHongYeung/NeurIPS25-TRiCo. △ Less

Submitted 30 November, 2025; v1 submitted 25 September, 2025; originally announced September 2025.

Comments: Accepted by NeurIPS 2025

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

Authors: Yanghao Li, Rui Qian, Bowen Pan, Haotian Zhang, Haoshuo Huang, Bowen Zhang, Jialing Tong, Haoxuan You, Xianzhi Du, Zhe Gan, Hyunjik Kim, Chao Jia, Zhenbang Wang, Yinfei Yang, Mingfei Gao, Zi-Yi Dou, Wenze Hu, Chang Gao, Dongxu Li, Philipp Dufter, Zirui Wang, Guoli Yin, Zhengdong Zhang, Chen Chen, Yang Zhao , et al. (2 additional authors not shown)

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

Submitted 19 September, 2025; originally announced September 2025.

AsyMoE: Leveraging Modal Asymmetry for Enhanced Expert Specialization in Large Vision-Language Models

Authors: Heng Zhang, Haichuan Hu, Yaomin Shen, Weihao Yu, Yilei Yuan, Haochen You, Guo Cheng, Zijian Zhang, Lubin Gan, Huihui Wei, Hao Zhang, Jin Huang

Abstract: Large Vision-Language Models (LVLMs) have demonstrated impressive performance on multimodal tasks through scaled architectures and extensive training. However, existing Mixture of Experts (MoE) approaches face challenges due to the asymmetry between visual and linguistic processing. Visual information is spatially complete, while language requires maintaining sequential context. As a result, MoE m… ▽ More Large Vision-Language Models (LVLMs) have demonstrated impressive performance on multimodal tasks through scaled architectures and extensive training. However, existing Mixture of Experts (MoE) approaches face challenges due to the asymmetry between visual and linguistic processing. Visual information is spatially complete, while language requires maintaining sequential context. As a result, MoE models struggle to balance modality-specific features and cross-modal interactions. Through systematic analysis, we observe that language experts in deeper layers progressively lose contextual grounding and rely more on parametric knowledge rather than utilizing the provided visual and linguistic information. To address this, we propose AsyMoE, a novel architecture that models this asymmetry using three specialized expert groups. We design intra-modality experts for modality-specific processing, hyperbolic inter-modality experts for hierarchical cross-modal interactions, and evidence-priority language experts to suppress parametric biases and maintain contextual grounding. Extensive experiments demonstrate that AsyMoE achieves 26.58% and 15.45% accuracy improvements over vanilla MoE and modality-specific MoE respectively, with 25.45% fewer activated parameters than dense models. △ Less

Submitted 22 December, 2025; v1 submitted 16 September, 2025; originally announced September 2025.

Comments: This submission has been withdrawn by the authors due to a fundamental error in the methodology that affects the validity of the main results

FinSentLLM: Multi-LLM and Structured Semantic Signals for Enhanced Financial Sentiment Forecasting

Authors: Zijian Zhang, Rong Fu, Yangfan He, Xinze Shen, Yanlong Wang, Xiaojing Du, Haochen You, Jiazhao Shi, Simon Fong

Abstract: Financial sentiment analysis (FSA) has attracted significant attention, and recent studies increasingly explore large language models (LLMs) for this field. Yet most work evaluates only classification metrics, leaving unclear whether sentiment signals align with market behavior. We propose FinSentLLM, a lightweight multi-LLM framework that integrates an expert panel of sentiment forecasting LLMs,… ▽ More Financial sentiment analysis (FSA) has attracted significant attention, and recent studies increasingly explore large language models (LLMs) for this field. Yet most work evaluates only classification metrics, leaving unclear whether sentiment signals align with market behavior. We propose FinSentLLM, a lightweight multi-LLM framework that integrates an expert panel of sentiment forecasting LLMs, and structured semantic financial signals via a compact meta-classifier. This design captures expert complementarity, semantic reasoning signal, and agreement/divergence patterns without costly retraining, yielding consistent 3-6% gains over strong baselines in accuracy and F1-score on the Financial PhraseBank dataset. In addition, we also provide econometric evidence that financial sentiment and stock markets exhibit statistically significant long-run comovement, applying Dynamic Conditional Correlation GARCH (DCC-GARCH) and the Johansen cointegration test to daily sentiment scores computed from the FNSPID dataset and major stock indices. Together, these results demonstrate that FinSentLLM delivers superior forecasting accuracy for financial sentiment and further establish that sentiment signals are robustly linked to long-run equity market dynamics. △ Less

Submitted 15 September, 2025; originally announced September 2025.

FinZero: Launching Multi-modal Financial Time Series Forecast with Large Reasoning Model

Authors: Yanlong Wang, Jian Xu, Fei Ma, Hongkang Zhang, Hang Yu, Tiantian Gao, Yu Wang, Haochen You, Shao-Lun Huang, Danny Dongning Sun, Xiao-Ping Zhang

Abstract: Financial time series forecasting is both highly significant and challenging. Previous approaches typically standardized time series data before feeding it into forecasting models, but this encoding process inherently leads to a loss of important information. Moreover, past time series models generally require fixed numbers of variables or lookback window lengths, which further limits the scalabil… ▽ More Financial time series forecasting is both highly significant and challenging. Previous approaches typically standardized time series data before feeding it into forecasting models, but this encoding process inherently leads to a loss of important information. Moreover, past time series models generally require fixed numbers of variables or lookback window lengths, which further limits the scalability of time series forecasting. Besides, the interpretability and the uncertainty in forecasting remain areas requiring further research, as these factors directly impact the reliability and practical value of predictions. To address these issues, we first construct a diverse financial image-text dataset (FVLDB) and develop the Uncertainty-adjusted Group Relative Policy Optimization (UARPO) method to enable the model not only output predictions but also analyze the uncertainty of those predictions. We then proposed FinZero, a multimodal pre-trained model finetuned by UARPO to perform reasoning, prediction, and analytical understanding on the FVLDB financial time series. Extensive experiments validate that FinZero exhibits strong adaptability and scalability. After fine-tuning with UARPO, FinZero achieves an approximate 13.48\% improvement in prediction accuracy over GPT-4o in the high-confidence group, demonstrating the effectiveness of reinforcement learning fine-tuning in multimodal large model, including in financial time series forecasting tasks. △ Less

Submitted 10 September, 2025; originally announced September 2025.

GTA-Crime: A Synthetic Dataset and Generation Framework for Fatal Violence Detection with Adversarial Snippet-Level Domain Adaptation

Authors: Seongho Kim, Sejong Ryu, Hyoukjun You, Je Hyeong Hong

Abstract: Recent advancements in video anomaly detection (VAD) have enabled identification of various criminal activities in surveillance videos, but detecting fatal incidents such as shootings and stabbings remains difficult due to their rarity and ethical issues in data collection. Recognizing this limitation, we introduce GTA-Crime, a fatal video anomaly dataset and generation framework using Grand Theft… ▽ More Recent advancements in video anomaly detection (VAD) have enabled identification of various criminal activities in surveillance videos, but detecting fatal incidents such as shootings and stabbings remains difficult due to their rarity and ethical issues in data collection. Recognizing this limitation, we introduce GTA-Crime, a fatal video anomaly dataset and generation framework using Grand Theft Auto 5 (GTA5). Our dataset contains fatal situations such as shootings and stabbings, captured from CCTV multiview perspectives under diverse conditions including action types, weather, time of day, and viewpoints. To address the rarity of such scenarios, we also release a framework for generating these types of videos. Additionally, we propose a snippet-level domain adaptation strategy using Wasserstein adversarial training to bridge the gap between synthetic GTA-Crime features and real-world features like UCF-Crime. Experimental results validate our GTA-Crime dataset and demonstrate that incorporating GTA-Crime with our domain adaptation strategy consistently enhances real world fatal violence detection accuracy. Our dataset and the data generation framework are publicly available at https://github.com/ta-ho/GTA-Crime. △ Less

Submitted 9 September, 2025; originally announced September 2025.

MCIGLE: Multimodal Exemplar-Free Class-Incremental Graph Learning

Authors: Haochen You, Baojing Liu

Abstract: Exemplar-free class-incremental learning enables models to learn new classes over time without storing data from old ones. As multimodal graph-structured data becomes increasingly prevalent, existing methods struggle with challenges like catastrophic forgetting, distribution bias, memory limits, and weak generalization. We propose MCIGLE, a novel framework that addresses these issues by extracting… ▽ More Exemplar-free class-incremental learning enables models to learn new classes over time without storing data from old ones. As multimodal graph-structured data becomes increasingly prevalent, existing methods struggle with challenges like catastrophic forgetting, distribution bias, memory limits, and weak generalization. We propose MCIGLE, a novel framework that addresses these issues by extracting and aligning multimodal graph features and applying Concatenated Recursive Least Squares for effective knowledge retention. Through multi-channel processing, MCIGLE balances accuracy and memory preservation. Experiments on public datasets validate its effectiveness and generalizability. △ Less

Submitted 7 September, 2025; originally announced September 2025.

Comments: Accepted as a conference paper at KSEM 2025

Metric Embedding Initialization-Based Differentially Private and Explainable Graph Clustering

Authors: Haochen You, Baojing Liu

Abstract: Graph clustering under the framework of differential privacy, which aims to process graph-structured data while protecting individual privacy, has been receiving increasing attention. Despite significant achievements in current research, challenges such as high noise, low efficiency and poor interpretability continue to severely constrain the development of this field. In this paper, we construct… ▽ More Graph clustering under the framework of differential privacy, which aims to process graph-structured data while protecting individual privacy, has been receiving increasing attention. Despite significant achievements in current research, challenges such as high noise, low efficiency and poor interpretability continue to severely constrain the development of this field. In this paper, we construct a differentially private and interpretable graph clustering approach based on metric embedding initialization. Specifically, we construct an SDP optimization, extract the key set and provide a well-initialized clustering configuration using an HST-based initialization method. Subsequently, we apply an established k-median clustering strategy to derive the cluster results and offer comparative explanations for the query set through differences from the cluster centers. Extensive experiments on public datasets demonstrate that our proposed framework outperforms existing methods in various clustering metrics while strictly ensuring privacy. △ Less

Submitted 7 September, 2025; originally announced September 2025.

Comments: Accepted as a conference paper at KSEM 2025

Modular MeanFlow: Towards Stable and Scalable One-Step Generative Modeling

Authors: Haochen You, Baojing Liu, Hongyang He

Abstract: One-step generative modeling seeks to generate high-quality data samples in a single function evaluation, significantly improving efficiency over traditional diffusion or flow-based models. In this work, we introduce Modular MeanFlow (MMF), a flexible and theoretically grounded approach for learning time-averaged velocity fields. Our method derives a family of loss functions based on a differentia… ▽ More One-step generative modeling seeks to generate high-quality data samples in a single function evaluation, significantly improving efficiency over traditional diffusion or flow-based models. In this work, we introduce Modular MeanFlow (MMF), a flexible and theoretically grounded approach for learning time-averaged velocity fields. Our method derives a family of loss functions based on a differential identity linking instantaneous and average velocities, and incorporates a gradient modulation mechanism that enables stable training without sacrificing expressiveness. We further propose a curriculum-style warmup schedule to smoothly transition from coarse supervision to fully differentiable training. The MMF formulation unifies and generalizes existing consistency-based and flow-matching methods, while avoiding expensive higher-order derivatives. Empirical results across image synthesis and trajectory modeling tasks demonstrate that MMF achieves competitive sample quality, robust convergence, and strong generalization, particularly under low-data or out-of-distribution settings. △ Less

Submitted 24 August, 2025; originally announced August 2025.

Comments: Accepted as a conference paper at PRCV 2025

A biological vision inspired framework for machine perception of abutting grating illusory contours

Authors: Xiao Zhang, Kai-Fu Yang, Xian-Shi Zhang, Hong-Zhi You, Hong-Mei Yan, Yong-Jie Li

Abstract: Higher levels of machine intelligence demand alignment with human perception and cognition. Deep neural networks (DNN) dominated machine intelligence have demonstrated exceptional performance across various real-world tasks. Nevertheless, recent evidence suggests that DNNs fail to perceive illusory contours like the abutting grating, a discrepancy that misaligns with human perception patterns. Dep… ▽ More Higher levels of machine intelligence demand alignment with human perception and cognition. Deep neural networks (DNN) dominated machine intelligence have demonstrated exceptional performance across various real-world tasks. Nevertheless, recent evidence suggests that DNNs fail to perceive illusory contours like the abutting grating, a discrepancy that misaligns with human perception patterns. Departing from previous works, we propose a novel deep network called illusory contour perception network (ICPNet) inspired by the circuits of the visual cortex. In ICPNet, a multi-scale feature projection (MFP) module is designed to extract multi-scale representations. To boost the interaction between feedforward and feedback features, a feature interaction attention module (FIAM) is introduced. Moreover, drawing inspiration from the shape bias observed in human perception, an edge detection task conducted via the edge fusion module (EFM) injects shape constraints that guide the network to concentrate on the foreground. We assess our method on the existing AG-MNIST test set and the AG-Fashion-MNIST test sets constructed by this work. Comprehensive experimental results reveal that ICPNet is significantly more sensitive to abutting grating illusory contours than state-of-the-art models, with notable improvements in top-1 accuracy across various subsets. This work is expected to make a step towards human-level intelligence for DNN-based models. △ Less

Submitted 24 August, 2025; originally announced August 2025.

MOVER: Multimodal Optimal Transport with Volume-based Embedding Regularization

Authors: Haochen You, Baojing Liu

Abstract: Recent advances in multimodal learning have largely relied on pairwise contrastive objectives to align different modalities, such as text, video, and audio, in a shared embedding space. While effective in bi-modal setups, these approaches struggle to generalize across multiple modalities and often lack semantic structure in high-dimensional spaces. In this paper, we propose MOVER, a novel framewor… ▽ More Recent advances in multimodal learning have largely relied on pairwise contrastive objectives to align different modalities, such as text, video, and audio, in a shared embedding space. While effective in bi-modal setups, these approaches struggle to generalize across multiple modalities and often lack semantic structure in high-dimensional spaces. In this paper, we propose MOVER, a novel framework that combines optimal transport-based soft alignment with volume-based geometric regularization to build semantically aligned and structured multimodal representations. By integrating a transport-guided matching mechanism with a geometric volume minimization objective (GAVE), MOVER encourages consistent alignment across all modalities in a modality-agnostic manner. Experiments on text-video-audio retrieval tasks demonstrate that MOVER significantly outperforms prior state-of-the-art methods in both zero-shot and finetuned settings. Additional analysis shows improved generalization to unseen modality combinations and stronger structural consistency in the learned embedding space. △ Less

Submitted 16 August, 2025; originally announced August 2025.

Comments: Accepted as a conference paper at CIKM 2025

A Survey of Token Compression for Efficient Multimodal Large Language Models

Authors: Kele Shao, Keda Tao, Kejia Zhang, Sicheng Feng, Mu Cai, Yuzhang Shang, Haoxuan You, Can Qin, Yang Sui, Huan Wang

Abstract: Multimodal large language models (MLLMs) have made remarkable strides, largely driven by their ability to process increasingly long and complex contexts, such as high-resolution images, extended video sequences, and lengthy audio input. While this ability significantly enhances MLLM capabilities, it introduces substantial computational challenges, primarily due to the quadratic complexity of self-… ▽ More Multimodal large language models (MLLMs) have made remarkable strides, largely driven by their ability to process increasingly long and complex contexts, such as high-resolution images, extended video sequences, and lengthy audio input. While this ability significantly enhances MLLM capabilities, it introduces substantial computational challenges, primarily due to the quadratic complexity of self-attention mechanisms with numerous input tokens. To mitigate these bottlenecks, token compression has emerged as an auspicious and critical approach, efficiently reducing the number of tokens during both training and inference. In this paper, we present the first systematic survey and synthesis of the burgeoning field of multimodal long context token compression. Recognizing that effective compression strategies are deeply tied to the unique characteristics and redundancies of each modality, we categorize existing approaches by their primary data focus, enabling researchers to quickly access and learn methods tailored to their specific area of interest: (1) image-centric compression, which addresses spatial redundancy in visual data; (2) video-centric compression, which tackles spatio-temporal redundancy in dynamic sequences; and (3) audio-centric compression, which handles temporal and spectral redundancy in acoustic signals. Beyond this modality-driven categorization, we further dissect methods based on their underlying mechanisms, including transformation-based, similarity-based, attention-based, and query-based approaches. By providing a comprehensive and structured overview, this survey aims to consolidate current progress, identify key challenges, and inspire future research directions in this rapidly evolving domain. △ Less

Submitted 1 February, 2026; v1 submitted 27 July, 2025; originally announced July 2025.

Comments: For ongoing updates and to track the latest advances in this promising area, we maintain a public repository: https://github.com/cokeshao/Awesome-Multimodal-Token-Compression

LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models

Authors: Dachuan Shi, Yonggan Fu, Xiangchi Yuan, Zhongzhi Yu, Haoran You, Sixu Li, Xin Dong, Jan Kautz, Pavlo Molchanov, Yingyan, Lin

Abstract: Recent advancements in Large Language Models (LLMs) have spurred interest in numerous applications requiring robust long-range capabilities, essential for processing extensive input contexts and continuously generating extended outputs. As sequence lengths increase, the number of Key-Value (KV) pairs in LLMs escalates, creating a significant efficiency bottleneck. In this paper, we propose a new K… ▽ More Recent advancements in Large Language Models (LLMs) have spurred interest in numerous applications requiring robust long-range capabilities, essential for processing extensive input contexts and continuously generating extended outputs. As sequence lengths increase, the number of Key-Value (KV) pairs in LLMs escalates, creating a significant efficiency bottleneck. In this paper, we propose a new KV cache optimization paradigm called LaCache, a training-free method for efficient and accurate generative inference of LLMs. LaCache enables LLMs to simultaneously address both of the critical challenges in long-range modeling: robust long-range capabilities and continuous generation without running out-of-memory (OOM). Specifically, LaCache integrates two key innovations: (1) a ladder-shaped KV cache pattern that stores KV pairs not only sequentially (left-to-right within each layer) but also across layers (from shallow to deep), providing an extended span for capturing long-range dependencies under a fixed storage budget, thereby boosting long-range capabilities; and (2) an iterative compaction mechanism that progressively compresses older caches, freeing up space for new tokens within a fixed cache size. This token distance-based dynamic compression enables more effective continuous generation under constrained cache budgets. Experiments across various tasks, benchmarks, and LLM models consistently validate LaCache's effectiveness in enhancing LLMs' long-range capabilities. Our code is available at https://github.com/GATECH-EIC/LaCache. △ Less

Submitted 14 July, 2025; originally announced July 2025.

Comments: ICML 2025. Code: https://github.com/GATECH-EIC/LaCache

Apple Intelligence Foundation Language Models: Tech Report 2025

Authors: Ethan Li, Anders Boesen Lindbo Larsen, Chen Zhang, Xiyou Zhou, Jun Qin, Dian Ang Yap, Narendran Raghavan, Xuankai Chang, Margit Bowler, Eray Yildiz, John Peebles, Hannah Gillis Coleman, Matteo Ronchi, Peter Gray, Keen You, Anthony Spalvieri-Kruse, Ruoming Pang, Reed Li, Yuli Yang, Emad Soroush, Zhiyun Lu, Crystal Xiao, Rong Situ, Jordan Huffaker, David Griffiths , et al. (373 additional authors not shown)

Abstract: We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and services: i a 3B-parameter on-device model optimized for Apple silicon through architectural innovations such as KV-cache sharing and 2-bit quantization-aware training; and ii a scalable server model built on a novel Parallel-Track Mixture-of-Experts PT-MoE transform… ▽ More We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and services: i a 3B-parameter on-device model optimized for Apple silicon through architectural innovations such as KV-cache sharing and 2-bit quantization-aware training; and ii a scalable server model built on a novel Parallel-Track Mixture-of-Experts PT-MoE transformer that combines track parallelism, mixture-of-experts sparse computation, and interleaved global-local attention to deliver high quality with competitive cost on Apple's Private Cloud Compute platform. Both models are trained on large-scale multilingual and multimodal datasets sourced via responsible web crawling, licensed corpora, and high-quality synthetic data, then further refined with supervised fine-tuning and reinforcement learning on a new asynchronous platform. The resulting models support several additional languages while understanding images and executing tool calls. In public benchmarks and human evaluations, both the server model and the on-device model match or surpass comparably sized open baselines. A new Swift-centric Foundation Models framework exposes guided generation, constrained tool calling, and LoRA adapter fine-tuning, allowing developers to integrate these capabilities with a few lines of code. The latest advancements in Apple Intelligence models are grounded in our Responsible AI approach with safeguards like content filtering and locale-specific evaluation, as well as our commitment to protecting our users' privacy with innovations like Private Cloud Compute. △ Less

Submitted 27 August, 2025; v1 submitted 17 July, 2025; originally announced July 2025.

COREVQA: A Crowd Observation and Reasoning Entailment Visual Question Answering Benchmark

Authors: Ishant Chintapatla, Kazuma Choji, Naaisha Agarwal, Andrew Lin, Hannah You, Charles Duong, Kevin Zhu, Sean O'Brien, Vasu Sharma

Abstract: Recently, many benchmarks and datasets have been developed to evaluate Vision-Language Models (VLMs) using visual question answering (VQA) pairs, and models have shown significant accuracy improvements. However, these benchmarks rarely test the model's ability to accurately complete visual entailment, for instance, accepting or refuting a hypothesis based on the image. To address this, we propose… ▽ More Recently, many benchmarks and datasets have been developed to evaluate Vision-Language Models (VLMs) using visual question answering (VQA) pairs, and models have shown significant accuracy improvements. However, these benchmarks rarely test the model's ability to accurately complete visual entailment, for instance, accepting or refuting a hypothesis based on the image. To address this, we propose COREVQA (Crowd Observations and Reasoning Entailment), a benchmark of 5608 image and synthetically generated true/false statement pairs, with images derived from the CrowdHuman dataset, to provoke visual entailment reasoning on challenging crowded images. Our results show that even the top-performing VLMs achieve accuracy below 80%, with other models performing substantially worse (39.98%-69.95%). This significant performance gap reveals key limitations in VLMs' ability to reason over certain types of image-question pairs in crowded scenes. △ Less

Submitted 17 July, 2025; originally announced July 2025.

A Survey of Reinforcement Learning for Software Engineering

Authors: Dong Wang, Hanmo You, Lingwei Zhu, Kaiwei Lin, Zheng Chen, Chen Yang, Junji Yu, Zan Wang, Junjie Chen

Abstract: Reinforcement Learning (RL) has emerged as a powerful paradigm for sequential decision-making and has attracted growing interest across various domains, particularly following the advent of Deep Reinforcement Learning (DRL) in 2015. Simultaneously, the rapid advancement of Large Language Models (LLMs) has further fueled interest in integrating RL with LLMs to enable more adaptive and intelligent s… ▽ More Reinforcement Learning (RL) has emerged as a powerful paradigm for sequential decision-making and has attracted growing interest across various domains, particularly following the advent of Deep Reinforcement Learning (DRL) in 2015. Simultaneously, the rapid advancement of Large Language Models (LLMs) has further fueled interest in integrating RL with LLMs to enable more adaptive and intelligent systems. In the field of software engineering (SE), the increasing complexity of systems and the rising demand for automation have motivated researchers to apply RL to a broad range of tasks, from software design and development to quality assurance and maintenance. Despite growing research in RL-for-SE, there remains a lack of a comprehensive and systematic survey of this evolving field. To address this gap, we reviewed 115 peer-reviewed studies published across 22 premier SE venues since the introduction of DRL. We conducted a comprehensive analysis of publication trends, categorized SE topics and RL algorithms, and examined key factors such as dataset usage, model design and optimization, and evaluation practices. Furthermore, we identified open challenges and proposed future research directions to guide and inspire ongoing work in this evolving area. To summarize, this survey offers the first systematic mapping of RL applications in software engineering, aiming to support both researchers and practitioners in navigating the current landscape and advancing the field. Our artifacts are publicly available: https://github.com/KaiWei-Lin-lanina/RL4SE. △ Less

Submitted 14 July, 2025; originally announced July 2025.

Event-based evaluation of abstractive news summarization

Authors: Huiling You, Samia Touileb, Erik Velldal, Lilja Øvrelid

Abstract: An abstractive summary of a news article contains its most important information in a condensed version. The evaluation of automatically generated summaries by generative language models relies heavily on human-authored summaries as gold references, by calculating overlapping units or similarity scores. News articles report events, and ideally so should the summaries. In this work, we propose to e… ▽ More An abstractive summary of a news article contains its most important information in a condensed version. The evaluation of automatically generated summaries by generative language models relies heavily on human-authored summaries as gold references, by calculating overlapping units or similarity scores. News articles report events, and ideally so should the summaries. In this work, we propose to evaluate the quality of abstractive summaries by calculating overlapping events between generated summaries, reference summaries, and the original news articles. We experiment on a richly annotated Norwegian dataset comprising both events annotations and summaries authored by expert human annotators. Our approach provides more insight into the event information contained in the summaries. △ Less

Submitted 1 July, 2025; originally announced July 2025.

Comments: to appear at GEM2 workshop@ACL 2025

From Block to Byte: Transforming PCIe SSDs with CXL Memory Protocol and Instruction Annotation

Authors: Miryeong Kwon, Donghyun Gouk, Junhyeok Jang, Jinwoo Baek, Hyunwoo You, Sangyoon Ji, Hongjoo Jung, Junseok Moon, Seungkwan Kang, Seungjun Lee, Myoungsoo Jung

Abstract: This paper explores how Compute Express Link (CXL) can transform PCIe-based block storage into a scalable, byte-addressable working memory. We address the challenges of adapting block storage to CXL's memory-centric model by emphasizing cacheability as a key enabler and advocating for Type 3 endpoint devices, referred to as CXL-SSDs. To validate our approach, we prototype a CXL-SSD on a custom FPG… ▽ More This paper explores how Compute Express Link (CXL) can transform PCIe-based block storage into a scalable, byte-addressable working memory. We address the challenges of adapting block storage to CXL's memory-centric model by emphasizing cacheability as a key enabler and advocating for Type 3 endpoint devices, referred to as CXL-SSDs. To validate our approach, we prototype a CXL-SSD on a custom FPGA platform and propose annotation mechanisms, Determinism and Bufferability, to enhance performance while preserving data persistency. Our simulation-based evaluation demonstrates that CXL-SSD achieves 10.9x better performance than PCIe-based memory expanders and further reduces latency by 5.4x with annotation enhancements. In workloads with high locality, CXL-SSD approaches DRAM-like performance due to efficient on-chip caching. This work highlights the feasibility of integrating block storage into CXL's ecosystem and provides a foundation for future memory-storage convergence. △ Less

Submitted 18 June, 2025; originally announced June 2025.

Towards Seamless Borders: A Method for Mitigating Inconsistencies in Image Inpainting and Outpainting

Authors: Xingzhong Hou, Jie Wu, Boxiao Liu, Yi Zhang, Guanglu Song, Yunpeng Liu, Yu Liu, Haihang You

Abstract: Image inpainting is the task of reconstructing missing or damaged parts of an image in a way that seamlessly blends with the surrounding content. With the advent of advanced generative models, especially diffusion models and generative adversarial networks, inpainting has achieved remarkable improvements in visual quality and coherence. However, achieving seamless continuity remains a significant… ▽ More Image inpainting is the task of reconstructing missing or damaged parts of an image in a way that seamlessly blends with the surrounding content. With the advent of advanced generative models, especially diffusion models and generative adversarial networks, inpainting has achieved remarkable improvements in visual quality and coherence. However, achieving seamless continuity remains a significant challenge. In this work, we propose two novel methods to address discrepancy issues in diffusion-based inpainting models. First, we introduce a modified Variational Autoencoder that corrects color imbalances, ensuring that the final inpainted results are free of color mismatches. Second, we propose a two-step training strategy that improves the blending of generated and existing image content during the diffusion process. Through extensive experiments, we demonstrate that our methods effectively reduce discontinuity and produce high-quality inpainting results that are coherent and visually appealing. △ Less

Submitted 14 June, 2025; originally announced June 2025.

HoliTom: Holistic Token Merging for Fast Video Large Language Models

Authors: Kele Shao, Keda Tao, Can Qin, Haoxuan You, Yang Sui, Huan Wang

Abstract: Video large language models (video LLMs) excel at video comprehension but face significant computational inefficiency due to redundant video tokens. Existing token pruning methods offer solutions. However, approaches operating within the LLM (inner-LLM pruning), such as FastV, incur intrinsic computational overhead in shallow layers. In contrast, methods performing token pruning before the LLM (ou… ▽ More Video large language models (video LLMs) excel at video comprehension but face significant computational inefficiency due to redundant video tokens. Existing token pruning methods offer solutions. However, approaches operating within the LLM (inner-LLM pruning), such as FastV, incur intrinsic computational overhead in shallow layers. In contrast, methods performing token pruning before the LLM (outer-LLM pruning) primarily address spatial redundancy within individual frames or limited temporal windows, neglecting the crucial global temporal dynamics and correlations across longer video sequences. This leads to sub-optimal spatio-temporal reduction and does not leverage video compressibility fully. Crucially, the synergistic potential and mutual influence of combining these strategies remain unexplored. To further reduce redundancy, we introduce HoliTom, a novel training-free holistic token merging framework. HoliTom employs outer-LLM pruning through global redundancy-aware temporal segmentation, followed by spatial-temporal merging to reduce visual tokens by over 90%, significantly alleviating the LLM's computational burden. Complementing this, we introduce a robust inner-LLM token similarity-based merging approach, designed for superior performance and compatibility with outer-LLM pruning. Evaluations demonstrate our method's promising efficiency-performance trade-off on LLaVA-OneVision-7B, reducing computational costs to 6.9% of FLOPs while maintaining 99.1% of the original performance. Furthermore, we achieve a 2.28x reduction in Time-To-First-Token (TTFT) and a 1.32x acceleration in decoding throughput, highlighting the practical benefits of our integrated pruning approach for efficient video LLMs inference. △ Less

Submitted 10 October, 2025; v1 submitted 27 May, 2025; originally announced May 2025.

Comments: code link: https://github.com/cokeshao/HoliTom

Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval

Authors: Rong-Cheng Tu, Wenhao Sun, Hanzhe You, Yingjie Wang, Jiaxing Huang, Li Shen, Dacheng Tao

Abstract: Zero-Shot Composed Image Retrieval (ZS-CIR) aims to retrieve target images given a compositional query, consisting of a reference image and a modifying text-without relying on annotated training data. Existing approaches often generate a synthetic target text using large language models (LLMs) to serve as an intermediate anchor between the compositional query and the target image. Models are then… ▽ More Zero-Shot Composed Image Retrieval (ZS-CIR) aims to retrieve target images given a compositional query, consisting of a reference image and a modifying text-without relying on annotated training data. Existing approaches often generate a synthetic target text using large language models (LLMs) to serve as an intermediate anchor between the compositional query and the target image. Models are then trained to align the compositional query with the generated text, and separately align images with their corresponding texts using contrastive learning. However, this reliance on intermediate text introduces error propagation, as inaccuracies in query-to-text and text-to-image mappings accumulate, ultimately degrading retrieval performance. To address these problems, we propose a novel framework by employing a Multimodal Reasoning Agent (MRA) for ZS-CIR. MRA eliminates the dependence on textual intermediaries by directly constructing triplets, <reference image, modification text, target image>, using only unlabeled image data. By training on these synthetic triplets, our model learns to capture the relationships between compositional queries and candidate images directly. Extensive experiments on three standard CIR benchmarks demonstrate the effectiveness of our approach. On the FashionIQ dataset, our method improves Average R@10 by at least 7.5\% over existing baselines; on CIRR, it boosts R@1 by 9.6\%; and on CIRCO, it increases mAP@5 by 9.5\%. △ Less

Submitted 26 May, 2025; originally announced May 2025.

Accelerating Visual-Policy Learning through Parallel Differentiable Simulation

Authors: Haoxiang You, Yilang Liu, Ian Abraham

Abstract: In this work, we propose a computationally efficient algorithm for visual policy learning that leverages differentiable simulation and first-order analytical policy gradients. Our approach decouple the rendering process from the computation graph, enabling seamless integration with existing differentiable simulation ecosystems without the need for specialized differentiable rendering software. Thi… ▽ More In this work, we propose a computationally efficient algorithm for visual policy learning that leverages differentiable simulation and first-order analytical policy gradients. Our approach decouple the rendering process from the computation graph, enabling seamless integration with existing differentiable simulation ecosystems without the need for specialized differentiable rendering software. This decoupling not only reduces computational and memory overhead but also effectively attenuates the policy gradient norm, leading to more stable and smoother optimization. We evaluate our method on standard visual control benchmarks using modern GPU-accelerated simulation. Experiments show that our approach significantly reduces wall-clock training time and consistently outperforms all baseline methods in terms of final returns. Notably, on complex tasks such as humanoid locomotion, our method achieves a $4\times$ improvement in final return, and successfully learns a humanoid running policy within 4 hours on a single GPU. △ Less

Submitted 10 November, 2025; v1 submitted 15 May, 2025; originally announced May 2025.

Generative AI for Autonomous Driving: Frontiers and Opportunities

Authors: Yuping Wang, Shuo Xing, Cui Can, Renjie Li, Hongyuan Hua, Kexin Tian, Zhaobin Mo, Xiangbo Gao, Keshu Wu, Sulong Zhou, Hengxu You, Juntong Peng, Junge Zhang, Zehao Wang, Rui Song, Mingxuan Yan, Walter Zimmer, Xingcheng Zhou, Peiran Li, Zhaohan Lu, Chia-Ju Chen, Yue Huang, Ryan A. Rossi, Lichao Sun, Hongkai Yu , et al. (22 additional authors not shown)

Abstract: Generative Artificial Intelligence (GenAI) constitutes a transformative technological wave that reconfigures industries through its unparalleled capabilities for content creation, reasoning, planning, and multimodal understanding. This revolutionary force offers the most promising path yet toward solving one of engineering's grandest challenges: achieving reliable, fully autonomous driving, partic… ▽ More Generative Artificial Intelligence (GenAI) constitutes a transformative technological wave that reconfigures industries through its unparalleled capabilities for content creation, reasoning, planning, and multimodal understanding. This revolutionary force offers the most promising path yet toward solving one of engineering's grandest challenges: achieving reliable, fully autonomous driving, particularly the pursuit of Level 5 autonomy. This survey delivers a comprehensive and critical synthesis of the emerging role of GenAI across the autonomous driving stack. We begin by distilling the principles and trade-offs of modern generative modeling, encompassing VAEs, GANs, Diffusion Models, and Large Language Models (LLMs). We then map their frontier applications in image, LiDAR, trajectory, occupancy, video generation as well as LLM-guided reasoning and decision making. We categorize practical applications, such as synthetic data workflows, end-to-end driving strategies, high-fidelity digital twin systems, smart transportation networks, and cross-domain transfer to embodied AI. We identify key obstacles and possibilities such as comprehensive generalization across rare cases, evaluation and safety checks, budget-limited implementation, regulatory compliance, ethical concerns, and environmental effects, while proposing research plans across theoretical assurances, trust metrics, transport integration, and socio-technical influence. By unifying these threads, the survey provides a forward-looking reference for researchers, engineers, and policymakers navigating the convergence of generative AI and advanced autonomous mobility. An actively maintained repository of cited works is available at https://github.com/taco-group/GenAI4AD. △ Less

Submitted 13 May, 2025; originally announced May 2025.

Early-Bird Diffusion: Investigating and Leveraging Timestep-Aware Early-Bird Tickets in Diffusion Models for Efficient Training

Authors: Lexington Whalen, Zhenbang Du, Haoran You, Chaojian Li, Sixu Li, Yingyan, Lin

Abstract: Training diffusion models (DMs) requires substantial computational resources due to multiple forward and backward passes across numerous timesteps, motivating research into efficient training techniques. In this paper, we propose EB-Diff-Train, a new efficient DM training approach that is orthogonal to other methods of accelerating DM training, by investigating and leveraging Early-Bird (EB) ticke… ▽ More Training diffusion models (DMs) requires substantial computational resources due to multiple forward and backward passes across numerous timesteps, motivating research into efficient training techniques. In this paper, we propose EB-Diff-Train, a new efficient DM training approach that is orthogonal to other methods of accelerating DM training, by investigating and leveraging Early-Bird (EB) tickets -- sparse subnetworks that manifest early in the training process and maintain high generation quality. We first investigate the existence of traditional EB tickets in DMs, enabling competitive generation quality without fully training a dense model. Then, we delve into the concept of diffusion-dedicated EB tickets, drawing on insights from varying importance of different timestep regions. These tickets adapt their sparsity levels according to the importance of corresponding timestep regions, allowing for aggressive sparsity during non-critical regions while conserving computational resources for crucial timestep regions. Building on this, we develop an efficient DM training technique that derives timestep-aware EB tickets, trains them in parallel, and combines them during inference for image generation. Extensive experiments validate the existence of both traditional and timestep-aware EB tickets, as well as the effectiveness of our proposed EB-Diff-Train method. This approach can significantly reduce training time both spatially and temporally -- achieving 2.9$\times$ to 5.8$\times$ speedups over training unpruned dense models, and up to 10.3$\times$ faster training compared to standard train-prune-finetune pipelines -- without compromising generative quality. Our code is available at https://github.com/GATECH-EIC/Early-Bird-Diffusion. △ Less

Submitted 13 April, 2025; originally announced April 2025.

Comments: 10 pages, 5 figures. Accepted to the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025

Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models

Authors: Keda Tao, Haoxuan You, Yang Sui, Can Qin, Huan Wang

Abstract: Video large language models (VideoLLMs) have demonstrated the capability to process longer video inputs and enable complex reasoning and analysis. However, due to the thousands of visual tokens from the video frames, the key-value (KV) cache can significantly increase memory requirements, becoming a bottleneck for inference speed and memory usage. KV cache quantization is a widely used approach to… ▽ More Video large language models (VideoLLMs) have demonstrated the capability to process longer video inputs and enable complex reasoning and analysis. However, due to the thousands of visual tokens from the video frames, the key-value (KV) cache can significantly increase memory requirements, becoming a bottleneck for inference speed and memory usage. KV cache quantization is a widely used approach to address this problem. In this paper, we find that 2-bit KV quantization of VideoLLMs can hardly hurt the model performance, while the limit of KV cache quantization in even lower bits has not been investigated. To bridge this gap, we introduce VidKV, a plug-and-play KV cache quantization method to compress the KV cache to lower than 2 bits. Specifically, (1) for key, we propose a mixed-precision quantization strategy in the channel dimension, where we perform 2-bit quantization for anomalous channels and 1-bit quantization combined with FFT for normal channels; (2) for value, we implement 1.58-bit quantization while selectively filtering semantically salient visual tokens for targeted preservation, for a better trade-off between precision and model performance. Importantly, our findings suggest that the value cache of VideoLLMs should be quantized in a per-channel fashion instead of the per-token fashion proposed by prior KV cache quantization works for LLMs. Empirically, extensive results with LLaVA-OV-7B and Qwen2.5-VL-7B on six benchmarks show that VidKV effectively compresses the KV cache to 1.5-bit and 1.58-bit precision with almost no performance drop compared to the FP16 counterparts. △ Less

Submitted 28 September, 2025; v1 submitted 20 March, 2025; originally announced March 2025.

Comments: 12 pages

Is Bellman Equation Enough for Learning Control?

Authors: Haoxiang You, Lekan Molu, Ian Abraham

Abstract: The Bellman equation and its continuous-time counterpart, the Hamilton-Jacobi-Bellman (HJB) equation, serve as necessary conditions for optimality in reinforcement learning and optimal control. While the value function is known to be the unique solution to the Bellman equation in tabular settings, we demonstrate that this uniqueness fails to hold in continuous state spaces. Specifically, for linea… ▽ More The Bellman equation and its continuous-time counterpart, the Hamilton-Jacobi-Bellman (HJB) equation, serve as necessary conditions for optimality in reinforcement learning and optimal control. While the value function is known to be the unique solution to the Bellman equation in tabular settings, we demonstrate that this uniqueness fails to hold in continuous state spaces. Specifically, for linear dynamical systems, we prove the Bellman equation admits at least $\binom{2n}{n}$ solutions, where $n$ is the state dimension. Crucially, only one of these solutions yields both an optimal policy and a stable closed-loop system. We then demonstrate a common failure mode in value-based methods: convergence to unstable solutions due to the exponential imbalance between admissible and inadmissible solutions. Finally, we introduce a positive-definite neural architecture that guarantees convergence to the stable solution by construction to address this issue. △ Less

Submitted 5 March, 2025; v1 submitted 3 March, 2025; originally announced March 2025.

Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research

Authors: Xiang Liu, Penglei Sun, Shuyan Chen, Longhan Zhang, Peijie Dong, Huajie You, Yongqi Zhang, Chang Yan, Xiaowen Chu, Tong-yi Zhang

Abstract: The rapid advancement of perovskite solar cells (PSCs) has led to an exponential growth in research publications, creating an urgent need for efficient knowledge management and reasoning systems in this domain. We present a comprehensive knowledge-enhanced system for PSCs that integrates three key components. First, we develop Perovskite-KG, a domain-specific knowledge graph constructed from 1,517… ▽ More The rapid advancement of perovskite solar cells (PSCs) has led to an exponential growth in research publications, creating an urgent need for efficient knowledge management and reasoning systems in this domain. We present a comprehensive knowledge-enhanced system for PSCs that integrates three key components. First, we develop Perovskite-KG, a domain-specific knowledge graph constructed from 1,517 research papers, containing 23,789 entities and 22,272 relationships. Second, we create two complementary datasets: Perovskite-Chat, comprising 55,101 high-quality question-answer pairs generated through a novel multi-agent framework, and Perovskite-Reasoning, containing 2,217 carefully curated materials science problems. Third, we introduce two specialized large language models: Perovskite-Chat-LLM for domain-specific knowledge assistance and Perovskite-Reasoning-LLM for scientific reasoning tasks. Experimental results demonstrate that our system significantly outperforms existing models in both domain-specific knowledge retrieval and scientific reasoning tasks, providing researchers with effective tools for literature review, experimental design, and complex problem-solving in PSC research. △ Less

Submitted 9 October, 2025; v1 submitted 18 February, 2025; originally announced February 2025.

Comments: EMNLP 2025 Findings; NeurIPS 2025 AI for Science Workshop