Showing 1–50 of 83 results for author: Gu, F

ChainSpace: A Chained-Reasoning Paradigm for Spatial Intelligence

Authors: Xiaohan Zhang, Feng Gu, Xudong Rao, Xuhao Pan, Tao Wei, Zhou Pan, Kun Zhan

Abstract: Spatial intelligence requires foundation models to maintain coherent spatial state across interactions with the physical world. However, existing data-centric approaches typically treat spatial reasoning as independent question-answer instances, enabling shortcut-based answering and providing limited supervision for persistent spatial understanding. To address this, we introduce ChainSpace, a chai… ▽ More Spatial intelligence requires foundation models to maintain coherent spatial state across interactions with the physical world. However, existing data-centric approaches typically treat spatial reasoning as independent question-answer instances, enabling shortcut-based answering and providing limited supervision for persistent spatial understanding. To address this, we introduce ChainSpace, a chained-reasoning paradigm that structures spatial reasoning as a state-preserving multi-round process. In this paradigm, spatial questions are organized into logically constrained and jointly consistent chains, where later questions depend on spatial constraints established in earlier rounds. Following this principle, we instantiate ChainSpace-Bench, a manually annotated real-world multi-round benchmark with a Chain-Aware Metric, and ChainSpace-Pipeline, a simulator-based chain-structured supervision generation framework for spatial intelligence training. Experiments show that ChainSpace-Bench exposes chain-level failures that are not captured by isolated question accuracy. Additionally, with a relatively small amount of simulator-generated chained data, models trained by ChainSpace-Pipeline achieve the best performance among open-source models on ChainSpace-Bench and transfer competitively to multiple external spatial intelligence benchmarks. These results establish ChainSpace as an effective paradigm for more faithful evaluation and more data-efficient learning of spatial intelligence. △ Less

Submitted 16 August, 2026; originally announced August 2026.

CertBind from Multimodal Connectivity to Certifiable Retrieval Decisions

Authors: Shuheng Cao, Zhenhao Zhang, Ruiqi Chen, Renjie Cao, Weijia Zhang, Siyu Zhang, Jiaxin Liu, Xiangyu Zeng, Haotian Geng, Fan Gu

Abstract: Lightweight connectors make frozen multimodal encoders composable at the representation level. Deployment exposes a second problem at the level of task decisions. A connected route can expand cross-modal reach while changing an established native retrieval capability. We introduce CertBind, a multiscale theory of certifiable composition for frozen multimodal connector graphs. At the node scale, na… ▽ More Lightweight connectors make frozen multimodal encoders composable at the representation level. Deployment exposes a second problem at the level of task decisions. A connected route can expand cross-modal reach while changing an established native retrieval capability. We introduce CertBind, a multiscale theory of certifiable composition for frozen multimodal connector graphs. At the node scale, native anchors establish the exact task identification boundary under the stated chart model. At the edge scale, contract-aware conformal ranks provide graph-wide family-wise error control. At the path scale, an overlap-aware budget and clean calibration yield a finite-sample recovery radius under declared conditions. At the query scale, this radius yields a covered top-k candidate set that becomes a point certificate when its size equals k. CertBind therefore retains supported routes as Direct, sends only flagged routes to recovery, returns Certified for decisive recovery, and returns Abstain for unresolved queries. The evaluated C-MCR shared route reduced native CLIP R@1 from 0.524 to 0.290. The production fallback recovered 0.963 +- 0.002 of clean retrieval, while the passing branch recorded a no-harm value of 1.000. CertBind extends multimodal composability from connected representations to certifiable task decisions. △ Less

Submitted 6 August, 2026; originally announced August 2026.

RegisterBridgeMM: A Register-Centric Framework for RGB-Infrared Object Detection

Authors: Zian Wang, Hangchuan Liang, Yuehua Chen, Changchun Li, Chaoyi Guo, Mingzhe Liu, Fangming Gu

Abstract: RGB-infrared (RGB-IR) object detection benefits from complementary visible and thermal cues, but effective fusion remains challenging under illumination changes, weather variation, and cluttered scenes. Existing RGB-IR fusion methods often trade expressive patch-level interaction for lighter but more constrained adaptation mechanisms. We empirically observe that pretrained register tokens contain… ▽ More RGB-infrared (RGB-IR) object detection benefits from complementary visible and thermal cues, but effective fusion remains challenging under illumination changes, weather variation, and cluttered scenes. Existing RGB-IR fusion methods often trade expressive patch-level interaction for lighter but more constrained adaptation mechanisms. We empirically observe that pretrained register tokens contain both modality-shared and modality-specific information on paired RGB-IR inputs, suggesting that they can serve as a compact substrate for cross-modal communication. Building on this observation, we propose RegisterBridgeMM, a register-mediated fusion framework organized as a three-stage register lifecycle. Aggregate preserves per-modality register summarization inherited from pretraining; Bridge performs bidirectional register-to-patch reading with consensus-residual regulation; and Project translates the resulting register summary into spatially adaptive calibration of patch features. This register pathway avoids dense patch-to-patch cross-modal interaction while preserving the pretrained patch representation. With both backbone streams frozen, RegisterBridgeMM achieves the highest mAP50-95 among the evaluated methods on all four benchmarks: LLVIP, M3FD, DroneVehicle, and FLIR-Aligned. △ Less

Submitted 5 August, 2026; originally announced August 2026.

SG-Layout: Structured Scene Graph-Guided Layout Generation with LLMs

Authors: Junsheng Wang, Chao Chen, Mengying Xie, Mingyan Li, Fuqiang Gu

Abstract: Understanding and generating spatially coherent layouts from natural language remains a fundamental yet challenging task for large language models (LLMs). Existing LLMs often struggle to capture explicit geometric relationships and structural dependencies between objects. To address this issue, we propose SG-Layout, a graph-guided layout generation framework that explicitly incorporates structured… ▽ More Understanding and generating spatially coherent layouts from natural language remains a fundamental yet challenging task for large language models (LLMs). Existing LLMs often struggle to capture explicit geometric relationships and structural dependencies between objects. To address this issue, we propose SG-Layout, a graph-guided layout generation framework that explicitly incorporates structured spatial knowledge into LLMs. SG-Layout follows a two-stage training paradigm: (1) a graph-language feature alignment stage, where a relational graph encoder and a projector are trained to map scene-graph embeddings into the LLM's linguistic space; and (2) an instruction tuning stage, where LoRA-based adapters enable efficient fine-tuning for instruction-driven layout generation while keeping the backbone frozen. We evaluate SG-Layout on image layout generation, indoor scene synthesis and robotic object rearrangement tasks. Experimental results show that SG-Layout improves spatial reasoning accuracy and geometric consistency over the compact open-source backbone, with particularly clear advantages in relation-dense and compositionally complex scenes. These results highlight the effectiveness of graph-structured feature alignment for enhancing controllable layout generation. △ Less

Submitted 2 August, 2026; originally announced August 2026.

Comments: 16 pages, 5 figures. Accepted at WAICA 2026

EvidenceLens: A Claim-Evidence Matrix for Auditing Financial Question Answering

Authors: Fengchen Gu, Xiaotian Ren, Zhengyong Jiang, Zhilu Zhang, Ángel F. García-Fernández, Angelos Stefanidis, Mian Zhou, Huakang Li, Jionglong Su

Abstract: Large language models are increasingly used to answer questions over annual reports, earnings decks, and analyst notes, yet their outputs remain difficult to verify in high-stakes financial workflows. A fluent answer can blend directly grounded statements, weak synthesis, and unsupported claims across narrative text, tables, and charts. We present EvidenceLens, a visual analytics prototype that tr… ▽ More Large language models are increasingly used to answer questions over annual reports, earnings decks, and analyst notes, yet their outputs remain difficult to verify in high-stakes financial workflows. A fluent answer can blend directly grounded statements, weak synthesis, and unsupported claims across narrative text, tables, and charts. We present EvidenceLens, a visual analytics prototype that treats financial question answering as a claim-evidence alignment problem. The system decomposes an answer into atomic claims, summarizes support composition and confidence, support gaps, and coordinates claim-level inspection with source passages, table cells, and chart regions. Its core visual representation is a multimodal claim-evidence matrix that makes coverage, contradiction, and modality imbalance immediately visible. To support reproducibility, we also specify a JSON-based artifact schema, a lightweight multimodal alignment pipeline, and a deterministic review-priority ranking that maps backend signals into an auditable visual structure. Through representative report-auditing scenarios, we show how EvidenceLens helps analysts distinguish grounded claims from overconfident synthesis that conventional chat interfaces flatten. △ Less

Submitted 19 June, 2026; originally announced June 2026.

Text Dictates, Music Decorates: Energy-based Attention for Editable Dance Motion Generation

Authors: Seong Jong Yoo, Siyuan Peng, Felix Gu, Stratis Aloimonos, Cornelia Fermüller

Abstract: Choreographic motion generation poses unique challenges for AI, demanding precise semantic control over complex, temporally structured, and expressive full-body dynamics. While existing models can synthesize motion from music, they remain largely black boxes. Conversely, attempting to condition generation on both text and music frequently leads to modality collapse, where dense acoustic rhythms ov… ▽ More Choreographic motion generation poses unique challenges for AI, demanding precise semantic control over complex, temporally structured, and expressive full-body dynamics. While existing models can synthesize motion from music, they remain largely black boxes. Conversely, attempting to condition generation on both text and music frequently leads to modality collapse, where dense acoustic rhythms overwhelm sparse semantic text prompts, destroying user controllability. To resolve this spatial-temporal conflict, we propose STREAM (Structural-Temporal Rhythmic Energy-based Attention for Motion), a modality-decoupled diffusion transformer. STREAM strictly separates conditioning pathways: global text semantics dictate the kinematic structure via Adaptive Layer Normalization (AdaLN), while a novel Bimodal Energy-Based Attention Module (BEAM) routes these features to the musical beat without overwriting the semantics. We further introduce Motorica++, a newly curated dataset enriched with domain-specific dance vocabulary and frame-level semantic annotations from existing Motorica dataset. Additionally, to rigorously quantify zero-shot editability, we propose the Exchange Evaluation Protocol and Editable Dance Score (EDS). Through extensive experiments, STREAM achieves state-of-the-art alignment between motion and music while perfectly preserving choreographic semantics, positioning AI not merely as a reactive synthesizer, but as a controllable, collaborative partner for artistic direction. The source code and datasets are available at https://github.com/SeongJong-Yoo/STREAM. △ Less

Submitted 2 July, 2026; v1 submitted 21 June, 2026; originally announced June 2026.

Comments: Accepted to ECCV 2026

One-to-Two Acting: A Novel Framework for Single-arm Agent Action Expansion to Dual Arms

Authors: Youbin Yao, Nieqin Cao, Mingyan Li, Yan Ding, Fuqiang Gu, Chao Chen

Abstract: Dual-arm manipulation can improve throughput via parallel execution, but collecting bimanual demonstrations for training is costly and difficult. We present ExS2D, a hierarchical action expansion framework that enables dual-arm manipulation from single-arm supervision. ExS2D first generates structured subtasks from textual instructions while explicitly capturing temporal precedence. It then ground… ▽ More Dual-arm manipulation can improve throughput via parallel execution, but collecting bimanual demonstrations for training is costly and difficult. We present ExS2D, a hierarchical action expansion framework that enables dual-arm manipulation from single-arm supervision. ExS2D first generates structured subtasks from textual instructions while explicitly capturing temporal precedence. It then grounds each subtask into executable actions through subtask-guided action mapping in observation. Finally, precedence-aware action allocation and synchronized planning are performed by a multimodal large language model driven coordinator to select collision-free dual-arm executions. Simulation experiments demonstrate that ExS2D reduces the average execution steps by 54.4% while maintaining a comparable success rate to a single-arm baseline. Real-robot experiments on four tasks further demonstrate the reliability of ExS2D for dual-arm execution under few-shot single-arm samples, while using zero bimanual demonstrations. △ Less

Submitted 18 June, 2026; originally announced June 2026.

Comments: 6 pages, 5 figures, 3 tables

CoAction: Cross-task Correlation-aware Pareto Set Learning

Authors: Xinyue Chen, Yingxuan Liang, Yiqin Huang, Chikai Shang, Hai-Lin Liu, Fangqing Gu

Abstract: Pareto set learning (PSL) is an emerging paradigm in multi-objective optimization that trains neural networks to map preference vectors to Pareto optimal solutions. However, existing PSL methods primarily focus on solving a single multi-objective optimization problem at a time. This limitation not only increases computational costs in multi-objective multitask optimization scenarios by requiring a… ▽ More Pareto set learning (PSL) is an emerging paradigm in multi-objective optimization that trains neural networks to map preference vectors to Pareto optimal solutions. However, existing PSL methods primarily focus on solving a single multi-objective optimization problem at a time. This limitation not only increases computational costs in multi-objective multitask optimization scenarios by requiring a separate model for each task, but also fails to exploit the inter-task correlations across tasks. To address this, we propose a Cross-tAsk correlation-aware Pareto Set Learning (CoAction) framework, which leverages task-aware transformer to handle multiple tasks simultaneously. Specifically, by assigning task-specific embedding vectors to individual tasks, the model effectively distinguishes between tasks while facilitating knowledge sharing among them. We utilize a Transformer encoder as the backbone architecture to leverage its self-attention mechanism for capturing complex task dependencies. The proposed approach is evaluated on comprehensive multitask test suites covering both benchmark problems and real-world applications, demonstrating effectiveness and competitive performance in Hypervolume, Range, and Sparsity. △ Less

Submitted 2 June, 2026; v1 submitted 3 May, 2026; originally announced May 2026.

Comments: Accepted by ICIC 2026 (Oral)

SOLARIS: Speculative Offloading of Latent-bAsed Representation for Inference Scaling

Authors: Zikun Liu, Liang Luo, Qianru Li, Zhengyu Zhang, Wei Ling, Jingyi Shen, Zeliang Chen, Yaning Huang, Jingxian Huang, Abdallah Aboelela, Chonglin Sun, Feifan Gu, Fenggang Wu, Hang Qu, Huayu Li, Jill Pan, Kaidi Pei, Laming Chen, Longhao Jin, Qin Huang, Tongyi Tang, Varna Puvvada, Wenlin Chen, Xiaohan Wei, Xu Cao , et al. (9 additional authors not shown)

Abstract: Recent advances in recommendation scaling laws have led to foundation models of unprecedented complexity. While these models offer superior performance, their computational demands make real-time serving impractical, often forcing practitioners to rely on knowledge distillation-compromising serving quality for efficiency. To address this challenge, we present SOLARIS (Speculative Offloading of Lat… ▽ More Recent advances in recommendation scaling laws have led to foundation models of unprecedented complexity. While these models offer superior performance, their computational demands make real-time serving impractical, often forcing practitioners to rely on knowledge distillation-compromising serving quality for efficiency. To address this challenge, we present SOLARIS (Speculative Offloading of Latent-bAsed Representation for Inference Scaling), a novel framework inspired by speculative decoding. SOLARIS proactively precomputes user-item interaction embeddings by predicting which user-item pairs are likely to appear in future requests, and asynchronously generating their foundation model representations ahead of time. This approach decouples the costly foundation model inference from the latency-critical serving path, enabling real-time knowledge transfer from models previously considered too expensive for online use. Deployed across Meta's advertising system serving billions of daily requests, SOLARIS achieves 0.67% revenue-driving top-line metrics gain, demonstrating its effectiveness at scale. △ Less

Submitted 3 June, 2026; v1 submitted 13 April, 2026; originally announced April 2026.

Comments: Accepted to SIGIR 2026 Industry Track

From Indiscriminate to Targeted: Functionally Critical Signal-Driven Assertion Generation using LLMs for Efficient RTL Verification

Authors: Yonghao Wang, Hongqin Lyu, Boling Chen, Jiaxin Zhou, MinYang Bao, Wenchao Ding, Feng Gu, Zhiteng Chao, Jianan Mu, Kan Shi, Tiancheng Wang, Huawei Li

Abstract: Functional verification has become the most time-consuming phase in IC development, and Assertion-Based Verification (ABV) is key to reducing debugging time. However, existing LLM-based assertion generation methods typically pursue indiscriminate verification, aiming for maximal coverage without considering signal criticality, whereas industrial practice demands maximizing coverage with minimal ve… ▽ More Functional verification has become the most time-consuming phase in IC development, and Assertion-Based Verification (ABV) is key to reducing debugging time. However, existing LLM-based assertion generation methods typically pursue indiscriminate verification, aiming for maximal coverage without considering signal criticality, whereas industrial practice demands maximizing coverage with minimal verification cost. Consequently, identifying signals that have the greatest impact on design functionality and error propagation-enabling a shift from indiscriminate to targeted verification-remains a key challenge. To address this, we propose AgileAssert, a key signal-driven assertion generation framework that constructs RTL semantic graphs and identifies the top-K critical signals via a hybrid scoring and selection mechanism, followed by structure-aware RTL slicing to provide the LLM with precise targets and contextual information, thereby guiding LLMs to generate tightly constrained targeted assertions for efficient verification. Evaluated on block- and CPU-level designs, with an average 66.68% reduction in assertions, our approach outperforms three existing SOTA methods, and significantly improving coverage metrics while reducing input token consumption by 64%. In mutation testing, when our approach surpasses existing methods in error detection rate, the average number of assertions used decreases by 72.74%. △ Less

Submitted 11 August, 2026; v1 submitted 10 April, 2026; originally announced April 2026.

Comments: 11 pages, 9 figures

A novel three-step approach to forecast firm-specific technology convergence opportunity via multi-dimensional feature fusion

Authors: Fu Gu, Ao Chen, Yingwen Wu

Abstract: As a crucial innovation paradigm, technology convergence (TC) is gaining ever-increasing attention. Yet, existing studies primarily focus on predicting TC at the industry level, with little attention paid to TC forecast for firm-specific technology opportunity discovery (TOD). Moreover, although technological documents like patents contain a rich body of bibliometric, network structure, and textua… ▽ More As a crucial innovation paradigm, technology convergence (TC) is gaining ever-increasing attention. Yet, existing studies primarily focus on predicting TC at the industry level, with little attention paid to TC forecast for firm-specific technology opportunity discovery (TOD). Moreover, although technological documents like patents contain a rich body of bibliometric, network structure, and textual features, such features are underexploited in the extant TC predictions; most of the relevant studies only used one or two dimensions of these features, and all the three dimensional features have rarely been fused. Here we propose a novel approach that fuses multi-dimensional features from patents to predict TC for firm-specific TOD. Our method comprises three steps, which are elaborated as follows. First, bibliometric, network structure, and textual features are extracted from patent documents, and then fused at the International Patent Classification (IPC)-pair level using attention mechanisms. Second, IPC-level TC opportunities are identified using a two-stage ensemble learning model that incorporates various imbalance-handling strategies. Third, to acquire feasible firm-specific TC opportunities, the performance metrics of topic-level TC opportunities, which are refined from IPC-level opportunities, are evaluated via retrieval-augmented generation (RAG) with a large language model (LLM). We prove the effectiveness of our proposed approach by predicting TC opportunities for a leading Chinese auto part manufacturer, Zhejiang Sanhua Intelligent Controls co., ltd, in the domains of thermal management for energy storage and robotics. In sum, this work advances the theory and applicability of forecasting firm-specific TC opportunity through fusing multi-dimensional features and leveraging LLM-as-a-judge for technology opportunity evaluation. △ Less

Submitted 1 April, 2026; originally announced April 2026.

Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design

Authors: Bin Zhu, Qianghuai Jia, Tian Lan, Junyang Ren, Feng Gu, Feihu Jiang, Longyue Wang, Zhao Xu, Weihua Luo

Abstract: Deep research agents autonomously conduct open-ended investigations, integrating complex information retrieval with multi-step reasoning across diverse sources to solve real-world problems. To sustain this capability on long-horizon tasks, reliable verification is critical during both training and inference. A major bottleneck in existing paradigms stems from the lack of explicit verification mech… ▽ More Deep research agents autonomously conduct open-ended investigations, integrating complex information retrieval with multi-step reasoning across diverse sources to solve real-world problems. To sustain this capability on long-horizon tasks, reliable verification is critical during both training and inference. A major bottleneck in existing paradigms stems from the lack of explicit verification mechanisms in QA data synthesis, trajectory construction, and test-time scaling. Errors introduced at each stage propagate downstream and degrade the overall agent performance. To address this, we present Marco DeepResearch, a deep research agent optimized with a verification-centric framework design at three levels: \textbf{(1)~QA Data Synthesis:} We introduce verification mechanisms to graph-based and agent-based QA synthesis to control question difficulty while ensuring answers are unique and correct; \textbf{(2)~Trajectory Construction:} We design a verification-driven trajectory synthesis method that injects explicit verification patterns into training trajectories; and \textbf{(3)~Test-time scaling:} We use Marco DeepResearch itself as a verifier at inference time and effectively improve performance on challenging questions. Extensive experimental results demonstrate that our proposed Marco DeepResearch agent significantly outperforms 8B-scale deep research agents on most challenging benchmarks, such as BrowseComp and BrowseComp-ZH. Crucially, under a maximum budget of 600 tool calls, Marco DeepResearch even surpasses or approaches several 30B-scale agents, like Tongyi DeepResearch-30B. △ Less

Submitted 30 March, 2026; originally announced March 2026.

Learning Unbiased Cluster Descriptors for Interpretable Imbalanced Concept Drift Detection

Authors: Yiqun Zhang, Zhanpei Huang, Mingjie Zhao, Chuyao Zhang, Yang Lu, Yuzhu Ji, Fangqing Gu, An Zeng

Abstract: Unlabeled streaming data are usually collected to describe dynamic systems, where concept drift detection is a vital prerequisite to understanding the evolution of systems. However, the drifting concepts are usually imbalanced in most real cases, which brings great challenges to drift detection. That is, the dominant statistics of large clusters can easily mask the drifting of small cluster distri… ▽ More Unlabeled streaming data are usually collected to describe dynamic systems, where concept drift detection is a vital prerequisite to understanding the evolution of systems. However, the drifting concepts are usually imbalanced in most real cases, which brings great challenges to drift detection. That is, the dominant statistics of large clusters can easily mask the drifting of small cluster distributions (also called small concepts), which is known as the `masking effect'. Considering that most existing approaches only detect the overall existence of drift under the assumption of balanced concepts, two critical problems arise: 1) where the small concept is, and 2) how to detect its drift. To address the challenging concept drift detection for imbalanced data, we propose Imbalanced Cluster Descriptor-based Drift Detection (ICD3) approach that is unbiased to the imbalanced concepts. This approach first detects imbalanced concepts by employing a newly designed multi-distribution-granular search, which ensures that the distribution of both small and large concepts is effectively captured. Subsequently, it trains a One-Cluster Classifier (OCC) for each identified concept to carefully monitor their potential drifts in the upcoming data chunks. Since the detection is independently performed for each concept, the dominance of large clusters is thus circumvented. ICD3 demonstrates highly interpretability by specifically locating the drifted concepts, and is robust to the changing of the imbalance ratio of concepts. Comprehensive experiments with multi-aspect ablation studies conducted on various benchmark datasets demonstrate the superiority of ICD3 against the state-of-the-art counterparts. △ Less

Submitted 6 March, 2026; originally announced March 2026.

Comments: 14 pages, 7 figures

Journal ref: EEE Transactions on Emerging Topics in Computational Intelligence ( Volume: 10, Issue: 1, February 2026)

When Denoising Becomes Unsigning: Theoretical and Empirical Analysis of Watermark Fragility Under Diffusion-Based Image Editing

Authors: Fai Gu, Qiyu Tang, Te Wen, Emily Davis, Finn Carter

Abstract: Robust invisible watermarking systems aim to embed imperceptible payloads that remain decodable after common post-processing such as JPEG compression, cropping, and additive noise. In parallel, diffusion-based image editing has rapidly matured into a default transformation layer for modern content pipelines, enabling instruction-based editing, object insertion and composition, and interactive geom… ▽ More Robust invisible watermarking systems aim to embed imperceptible payloads that remain decodable after common post-processing such as JPEG compression, cropping, and additive noise. In parallel, diffusion-based image editing has rapidly matured into a default transformation layer for modern content pipelines, enabling instruction-based editing, object insertion and composition, and interactive geometric manipulation. This paper studies a subtle but increasingly consequential interaction between these trends: diffusion-based editing procedures may unintentionally compromise, and in extreme cases practically bypass, robust watermarking mechanisms that were explicitly engineered to survive conventional distortions. We develop a unified view of diffusion editors that (i) inject substantial Gaussian noise in a latent space and (ii) project back to the natural image manifold via learned denoising dynamics. Under this view, watermark payloads behave as low-energy, high-frequency signals that are systematically attenuated by the forward diffusion step and then treated as nuisance variation by the reverse generative process. We formalize this degradation using information-theoretic tools, proving that for broad classes of pixel-level watermark encoders/decoders the mutual information between the watermark payload and the edited output decays toward zero as the editing strength increases, yielding decoding error close to random guessing. We complement the theory with a realistic hypothetical experimental protocol and tables spanning representative watermarking methods and representative diffusion editors. Finally, we discuss ethical implications, responsible disclosure norms, and concrete design guidelines for watermarking schemes that remain meaningful in the era of generative transformations. △ Less

Submitted 4 March, 2026; originally announced March 2026.

Comments: Preprint

TAG: Thinking with Action Unit Grounding for Facial Expression Recognition

Authors: Haobo Lin, Tianyi Bai, Jiajun Zhang, Xuanhao Chang, Sheng Lu, Fangming Gu, Zengjie Hu, Wentao Zhang

Abstract: Facial Expression Recognition (FER) is a fine-grained visual understanding task where reliable predictions require reasoning over localized and meaningful facial cues. Recent vision--language models (VLMs) enable natural language explanations for FER, but their reasoning is often ungrounded, producing fluent yet unverifiable rationales that are weakly tied to visual evidence and prone to hallucina… ▽ More Facial Expression Recognition (FER) is a fine-grained visual understanding task where reliable predictions require reasoning over localized and meaningful facial cues. Recent vision--language models (VLMs) enable natural language explanations for FER, but their reasoning is often ungrounded, producing fluent yet unverifiable rationales that are weakly tied to visual evidence and prone to hallucination, leading to poor robustness across different datasets. We propose TAG (Thinking with Action Unit Grounding), a vision--language framework that explicitly constrains multimodal reasoning to be supported by facial Action Units (AUs). TAG requires intermediate reasoning steps to be grounded in AU-related facial regions, yielding predictions accompanied by verifiable visual evidence. The model is trained via supervised fine-tuning on AU-grounded reasoning traces followed by reinforcement learning with an AU-aware reward that aligns predicted regions with external AU detectors. Evaluated on RAF-DB, FERPlus, and AffectNet, TAG consistently outperforms strong open-source and closed-source VLM baselines while simultaneously improving visual faithfulness. Ablation and preference studies further show that AU-grounded rewards stabilize reasoning and mitigate hallucination, demonstrating the importance of structured grounded intermediate representations for trustworthy multimodal reasoning in FER. The code will be available at https://github.com/would1920/FER_TAG . △ Less

Submitted 21 February, 2026; originally announced February 2026.

Comments: 33 pages, 8 figures

TABI: Tight and Balanced Interactive Atlas Packing

Authors: Floria Gu, Nicholas Vining, Alla Sheffer

Abstract: Atlas packing is a key step in many computer graphics applications. Packing algorithms seek to arrange a set of charts within a fixed-size atlas with as little downscaling as possible. Many packing applications such as content creation tools, dynamic atlas generation for video games, and texture space shading require on-the-fly interactive atlas packing. Unfortunately, while many methods have been… ▽ More Atlas packing is a key step in many computer graphics applications. Packing algorithms seek to arrange a set of charts within a fixed-size atlas with as little downscaling as possible. Many packing applications such as content creation tools, dynamic atlas generation for video games, and texture space shading require on-the-fly interactive atlas packing. Unfortunately, while many methods have been developed for generating tight high-quality packings, they are designed for offline settings and have running times two or more orders of magnitude greater than what is required for interactive performance. While real-time GPU packing methods exist, they significantly downscale packed charts compared to offline methods. We introduce a GPU packing method that targets interactive speeds, provides packing quality approaching that of offline methods, and supports flexible user control over the tradeoff between performance and quality. We observe that current real-time packing methods leave large gaps between charts and often produce asymmetric, or poorly balanced, packings. These artifacts dramatically degrade packing quality. Our Tight And Balanced method eliminates these artifacts while retaining Interactive performance. TABI generates tight packings by compacting empty space between irregularly shaped charts both horizontally and vertically, using two approximations of chart shape that support efficient parallel processing. We balance packing outputs by automatically adjusting atlas row widths and orientations to accommodate varying chart heights. We show that our method significantly reduces chart downscaling compared to existing interactive methods while remaining orders of magnitude faster than offline alternatives. △ Less

Submitted 7 February, 2026; originally announced February 2026.

DDT: A Dual-Masking Dual-Expert Transformer for Energy Time-Series Forecasting

Authors: Mingnan Zhu, Qixuan Zhang, Yixuan Cheng, Fangzhou Gu, Shiming Lin

Abstract: Accurate energy time-series forecasting is crucial for ensuring grid stability and promoting the integration of renewable energy, yet it faces significant challenges from complex temporal dependencies and the heterogeneity of multi-source data. To address these issues, we propose DDT, a novel and robust deep learning framework for high-precision time-series forecasting. At its core, DDT introduces… ▽ More Accurate energy time-series forecasting is crucial for ensuring grid stability and promoting the integration of renewable energy, yet it faces significant challenges from complex temporal dependencies and the heterogeneity of multi-source data. To address these issues, we propose DDT, a novel and robust deep learning framework for high-precision time-series forecasting. At its core, DDT introduces two key innovations. First, we design a dual-masking mechanism that synergistically combines a strict causal mask with a data-driven dynamic mask. This novel design ensures theoretical causal consistency while adaptively focusing on the most salient historical information, overcoming the rigidity of traditional masking techniques. Second, our architecture features a dual-expert system that decouples the modeling of temporal dynamics and cross-variable correlations into parallel, specialized pathways, which are then intelligently integrated through a dynamic gated fusion module. We conducted extensive experiments on 7 challenging energy benchmark datasets, including ETTh, Electricity, and Solar. The results demonstrate that DDT consistently outperforms strong state-of-the-art baselines across all prediction horizons, establishing a new benchmark for the task. △ Less

Submitted 12 January, 2026; originally announced January 2026.

Detecting Autism Spectrum Disorder with Deep Eye Movement Features

Authors: Zhanpei Huang, Taochen chen, Fangqing Gu, Yiqun Zhang

Abstract: Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by deficits in social communication and behavioral patterns. Eye movement data offers a non-invasive diagnostic tool for ASD detection, as it is inherently discrete and exhibits short-term temporal dependencies, reflecting localized gaze focus between fixation points. These characteristics enable the data to provide deep… ▽ More Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by deficits in social communication and behavioral patterns. Eye movement data offers a non-invasive diagnostic tool for ASD detection, as it is inherently discrete and exhibits short-term temporal dependencies, reflecting localized gaze focus between fixation points. These characteristics enable the data to provide deeper insights into subtle behavioral markers, distinguishing ASD-related patterns from typical development. Eye movement signals mainly contain short-term and localized dependencies. However, despite the widespread application of stacked attention layers in Transformer-based models for capturing long-range dependencies, our experimental results indicate that this approach yields only limited benefits when applied to eye movement data. This may be because discrete fixation points and short-term dependencies in gaze focus reduce the utility of global attention mechanisms, making them less efficient than architectures focusing on local temporal patterns. To efficiently capture subtle and complex eye movement patterns, distinguishing ASD from typically developing (TD) individuals, a discrete short-term sequential (DSTS) modeling framework is designed with Class-aware Representation and Imbalance-aware Mechanisms. Through extensive experiments on several eye movement datasets, DSTS outperforms both traditional machine learning techniques and more sophisticated deep learning models. △ Less

Submitted 9 January, 2026; originally announced January 2026.

Comments: Accepted to CIS 2025

Heteroscedastic Bayesian Optimization-Based Dynamic PID Tuning for Accurate and Robust UAV Trajectory Tracking

Authors: Fuqiang Gu, Jiangshan Ai, Xu Lu, Xianlei Long, Yan Li, Tao Jiang, Chao Chen, Huidong Liu

Abstract: Unmanned Aerial Vehicles (UAVs) play an important role in various applications, where precise trajectory tracking is crucial. However, conventional control algorithms for trajectory tracking often exhibit limited performance due to the underactuated, nonlinear, and highly coupled dynamics of quadrotor systems. To address these challenges, we propose HBO-PID, a novel control algorithm that integrat… ▽ More Unmanned Aerial Vehicles (UAVs) play an important role in various applications, where precise trajectory tracking is crucial. However, conventional control algorithms for trajectory tracking often exhibit limited performance due to the underactuated, nonlinear, and highly coupled dynamics of quadrotor systems. To address these challenges, we propose HBO-PID, a novel control algorithm that integrates the Heteroscedastic Bayesian Optimization (HBO) framework with the classical PID controller to achieve accurate and robust trajectory tracking. By explicitly modeling input-dependent noise variance, the proposed method can better adapt to dynamic and complex environments, and therefore improve the accuracy and robustness of trajectory tracking. To accelerate the convergence of optimization, we adopt a two-stage optimization strategy that allow us to more efficiently find the optimal controller parameters. Through experiments in both simulation and real-world scenarios, we demonstrate that the proposed method significantly outperforms state-of-the-art (SOTA) methods. Compared to SOTA methods, it improves the position accuracy by 24.7% to 42.9%, and the angular accuracy by 40.9% to 78.4%. △ Less

Submitted 30 December, 2025; originally announced December 2025.

Comments: Accepted by IROS 2025 (2025 IEEE/RSJ International Conference on Intelligent Robots and Systems)

Journal ref: 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

MambaSeg: Harnessing Mamba for Accurate and Efficient Image-Event Semantic Segmentation

Authors: Fuqiang Gu, Yuanke Li, Xianlei Long, Kangping Ji, Chao Chen, Qingyi Gu, Zhenliang Ni

Abstract: Semantic segmentation is a fundamental task in computer vision with wide-ranging applications, including autonomous driving and robotics. While RGB-based methods have achieved strong performance with CNNs and Transformers, their effectiveness degrades under fast motion, low-light, or high dynamic range conditions due to limitations of frame cameras. Event cameras offer complementary advantages suc… ▽ More Semantic segmentation is a fundamental task in computer vision with wide-ranging applications, including autonomous driving and robotics. While RGB-based methods have achieved strong performance with CNNs and Transformers, their effectiveness degrades under fast motion, low-light, or high dynamic range conditions due to limitations of frame cameras. Event cameras offer complementary advantages such as high temporal resolution and low latency, yet lack color and texture, making them insufficient on their own. To address this, recent research has explored multimodal fusion of RGB and event data; however, many existing approaches are computationally expensive and focus primarily on spatial fusion, neglecting the temporal dynamics inherent in event streams. In this work, we propose MambaSeg, a novel dual-branch semantic segmentation framework that employs parallel Mamba encoders to efficiently model RGB images and event streams. To reduce cross-modal ambiguity, we introduce the Dual-Dimensional Interaction Module (DDIM), comprising a Cross-Spatial Interaction Module (CSIM) and a Cross-Temporal Interaction Module (CTIM), which jointly perform fine-grained fusion along both spatial and temporal dimensions. This design improves cross-modal alignment, reduces ambiguity, and leverages the complementary properties of each modality. Extensive experiments on the DDD17 and DSEC datasets demonstrate that MambaSeg achieves state-of-the-art segmentation performance while significantly reducing computational cost, showcasing its promise for efficient, scalable, and robust multimodal perception. △ Less

Submitted 30 December, 2025; originally announced December 2025.

Comments: Accepted by AAAI 2026

MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning

Authors: Jiawei Chen, Xintian Shen, Lihao Zheng, Zhenwei Shao, Handong Cui, Chaoqun Du, Li Gong, Feng Gu, Xuefeng Hao, Wei He, Jiabang He, Yi Hu, Bin Huang, Shanshan Li, Qizhen Li, Jing Luo, Zide Liu, Xiaobo Liu, Ning Mao, Lifu Mu, Xuhao Pan, Zhiheng Qu, Chang Ren, Xudong Rao, Haoyi Sun , et al. (21 additional authors not shown)

Abstract: Traditional workflow-based agents exhibit limited intelligence when addressing real-world problems requiring tool invocation. Tool-integrated reasoning (TIR) agents capable of autonomous reasoning and tool invocation are rapidly emerging as a powerful approach for complex decision-making tasks involving multi-step interactions with external environments. In this work, we introduce MindWatcher, a T… ▽ More Traditional workflow-based agents exhibit limited intelligence when addressing real-world problems requiring tool invocation. Tool-integrated reasoning (TIR) agents capable of autonomous reasoning and tool invocation are rapidly emerging as a powerful approach for complex decision-making tasks involving multi-step interactions with external environments. In this work, we introduce MindWatcher, a TIR agent integrating interleaved thinking and multimodal chain-of-thought (CoT) reasoning. MindWatcher can autonomously decide whether and how to invoke diverse tools and coordinate their use, without relying on human prompts or workflows. The interleaved thinking paradigm enables the model to switch between thinking and tool calling at any intermediate stage, while its multimodal CoT capability allows manipulation of images during reasoning to yield more precise search results. We implement automated data auditing and evaluation pipelines, complemented by manually curated high-quality datasets for training, and we construct a benchmark, called MindWatcher-Evaluate Bench (MWE-Bench), to evaluate its performance. MindWatcher is equipped with a comprehensive suite of auxiliary reasoning tools, enabling it to address broad-domain multimodal problems. A large-scale, high-quality local image retrieval database, covering eight categories including cars, animals, and plants, endows model with robust object recognition despite its small size. Finally, we design a more efficient training infrastructure for MindWatcher, enhancing training speed and hardware utilization. Experiments not only demonstrate that MindWatcher matches or exceeds the performance of larger or more recent models through superior tool invocation, but also uncover critical insights for agent training, such as the genetic inheritance phenomenon in agentic RL. △ Less

Submitted 7 January, 2026; v1 submitted 29 December, 2025; originally announced December 2025.

Comments: Technique Report

Contiguous Storage of Grid Data for Heterogeneous Computing

Authors: Fan Gu, Xiangyu Hu

Abstract: Structured Cartesian grids are a fundamental component in numerical simulations. Although these grids facilitate straightforward discretization schemes, their naïve use in sparse domains leads to excessive memory overhead and inefficient computation. Existing frameworks address are primarily optimized for CPU execution and exhibit performance bottlenecks on GPU architectures due to limited paralle… ▽ More Structured Cartesian grids are a fundamental component in numerical simulations. Although these grids facilitate straightforward discretization schemes, their naïve use in sparse domains leads to excessive memory overhead and inefficient computation. Existing frameworks address are primarily optimized for CPU execution and exhibit performance bottlenecks on GPU architectures due to limited parallelism and high memory access latency. This work presents a redesigned storage architecture optimized for GPU compatibility and efficient execution across heterogeneous platforms. By abstracting low-level GPU-specific details and adopting a unified programming model based on SYCL, the proposed data structure enables seamless integration across host and device environments. This architecture simplifies GPU programming for end-users while improving scalability and portability in sparse-grid and gird-particle coupling numerical simulations. △ Less

Submitted 12 December, 2025; originally announced December 2025.

Comments: 26 pages, 6 figures and 1 table

Meta Lattice: Model Space Redesign for Cost-Effective Industry-Scale Ads Recommendations

Authors: Liang Luo, Yuxin Chen, Zhengyu Zhang, Mengyue Hang, Andrew Gu, Buyun Zhang, Boyang Liu, Chen Chen, Chengze Fan, Dong Liang, Fan Yang, Feifan Gu, Huayu Li, Jade Nie, Jiayi Xu, Jiyan Yang, Jongsoo Park, Laming Chen, Longhao Jin, Qianru Li, Qin Huang, Shali Jiang, Shiwen Shen, Shuaiwen Wang, Sihan Zeng , et al. (17 additional authors not shown)

Abstract: The rapidly evolving landscape of products, surfaces, policies, and regulations poses significant challenges for deploying state-of-the-art recommendation models at industry scale, primarily due to data fragmentation across domains and escalating infrastructure costs that hinder sustained quality improvements. To address this challenge, we propose Lattice, a recommendation framework centered aro… ▽ More The rapidly evolving landscape of products, surfaces, policies, and regulations poses significant challenges for deploying state-of-the-art recommendation models at industry scale, primarily due to data fragmentation across domains and escalating infrastructure costs that hinder sustained quality improvements. To address this challenge, we propose Lattice, a recommendation framework centered around model space redesign that extends Multi-Domain, Multi-Objective (MDMO) learning beyond models and learning objectives. Lattice addresses these challenges through a comprehensive model space redesign that combines cross-domain knowledge sharing, data consolidation, model unification, distillation, and system optimizations to achieve significant improvements in both quality and cost-efficiency. Our deployment of Lattice at Meta has resulted in 10% revenue-driving top-line metrics gain, 11.5% user satisfaction improvement, 6% boost in conversion rate, with 20% capacity saving. △ Less

Submitted 14 December, 2025; v1 submitted 9 December, 2025; originally announced December 2025.

Comments: Accepted to KDD 2026

MindGPT-4ov: An Enhanced MLLM via a Multi-Stage Post-Training Paradigm

Authors: Wei Chen, Chaoqun Du, Feng Gu, Wei He, Qizhen Li, Zide Liu, Xuhao Pan, Chang Ren, Xudong Rao, Chenfeng Wang, Tao Wei, Chengjun Yu, Pengfei Yu, Yufei Zheng, Chunpeng Zhou, Pan Zhou, Xuhan Zhu

Abstract: We present MindGPT-4ov, a multimodal large language model (MLLM) that introduces a general post-training paradigm spanning data production, model training, and efficient deployment. It achieves state-of-the-art performance across multiple benchmarks at low cost, effectively enhancing the foundational capabilities of MLLMs and the generalization ability. Focusing on data construction, supervised fi… ▽ More We present MindGPT-4ov, a multimodal large language model (MLLM) that introduces a general post-training paradigm spanning data production, model training, and efficient deployment. It achieves state-of-the-art performance across multiple benchmarks at low cost, effectively enhancing the foundational capabilities of MLLMs and the generalization ability. Focusing on data construction, supervised fine-tuning strategies, and multimodal reinforcement learning methods, this work proposes three key innovations: (1) An information density-based data generation scheme, integrated with a dual-dimensional tree-structured label system, enabling automated generation of high-quality cross-domain data. (2) A collaborative curriculum supervised fine-tuning approach that balances the injection of domain-specific knowledge with the preservation of general capabilities. (3) A hybrid reinforcement learning paradigm that enhances reasoning ability while simultaneously addressing multi-objective optimization such as diversity exploration, maintenance of multimodal perception, and response conciseness. Moreover, we implement a series of infrastructure optimizations, such as 5D parallel training, operator optimization, and inference quantization to enhance training and inference efficiency while reducing the cost of domain adaptation. Experimental results demonstrate that the MindGPT-4ov model outperforms state-of-the-art models on benchmarks such as MMBench, MMStar, MathVision, and MathVista. In addition, MindGPT-4ov also demonstrates superior user experience in vertical domain tasks, enabling a seamless transition from academic research to industrial deployment. MindGPT-4ov provides a general post-training paradigm applicable to a wide range of MLLMs. The model weights, datasets, and code for the Qwen3-VL-based variants will be recently open-sourced to support the community's development of MLLMs. △ Less

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

Comments: 33 pages, 14 figures

RAISE: A self-driving laboratory for interfacial property formulation discovery

Authors: Mohammad Nazeri, Sheldon Mei, Jeffrey Watchorn, Alex Zhang, Erin Ng, Tao Wen, Abhijoy Mandal, Kevin Golovin, Alan Aspuru-Guzik, Frank Gu

Abstract: Surface wettability is a critical design parameter for biomedical devices, coatings, and textiles. Contact angle measurements quantify liquid-surface interactions, which depend strongly on liquid formulation. Herein, we present the Robotic Autonomous Imaging Surface Evaluator (RAISE), a closed-loop, self-driving laboratory that is capable of linking liquid formulation optimization with surface wet… ▽ More Surface wettability is a critical design parameter for biomedical devices, coatings, and textiles. Contact angle measurements quantify liquid-surface interactions, which depend strongly on liquid formulation. Herein, we present the Robotic Autonomous Imaging Surface Evaluator (RAISE), a closed-loop, self-driving laboratory that is capable of linking liquid formulation optimization with surface wettability assessment. RAISE comprises a full experimental orchestrator with the ability of mixing liquid ingredients to create varying formulation cocktails, transferring droplets of prepared formulations to a high-throughput stage, and using a pick-and-place camera tool for automated droplet image capture. The system also includes an automated image processing pipeline to measure contact angles. This closed loop experiment orchestrator is integrated with a Bayesian Optimization (BO) client, which enables iterative exploration of new formulations based on previous contact angle measurements to meet user-defined objectives. The system operates in a high-throughput manner and can achieve a measurement rate of approximately 1 contact angle measurement per minute. Here we demonstrate RAISE can be used to explore surfactant wettability and how surfactant combinations create tunable formulations that compensate for purity-related variations. Furthermore, multi-objective BO demonstrates how precise and optimal formulations can be reached based on application-specific goals. The optimization is guided by a desirability score, which prioritizes formulations that are within target contact angle ranges, minimize surfactant usage and reduce cost. This work demonstrates the capabilities of RAISE to autonomously link liquid formulations to contact angle measurements in a closed-loop system, using multi-objective BO to efficiently identify optimal formulations aligned with researcher-defined criteria. △ Less

Submitted 7 October, 2025; originally announced October 2025.

Comments: Mohammad Nazeri, Sheldon Mei, and Jeffrey Watchorn contributed equally to this work. *Corresponding author: Frank Gu (f.gu@utoronto.ca)

The Matthew Effect of AI Programming Assistants: A Hidden Bias in Software Evolution

Authors: Fei Gu, Zi Liang, Jiahao MA, Hongzong LI

Abstract: AI-assisted programming is rapidly reshaping software development, with large language models (LLMs) enabling new paradigms such as vibe coding and agentic coding. While prior works have focused on prompt design and code generation quality, the broader impact of LLM-driven development on the iterative dynamics of software engineering remains underexplored. In this paper, we conduct large-scale exp… ▽ More AI-assisted programming is rapidly reshaping software development, with large language models (LLMs) enabling new paradigms such as vibe coding and agentic coding. While prior works have focused on prompt design and code generation quality, the broader impact of LLM-driven development on the iterative dynamics of software engineering remains underexplored. In this paper, we conduct large-scale experiments on thousands of algorithmic programming tasks and hundreds of framework selection tasks to systematically investigate how AI-assisted programming interacts with the software ecosystem. Our analysis quantifies a substantial performance asymmetry: mainstream languages and frameworks achieve significantly higher success rates than niche ones. This disparity suggests a feedback loop consistent with the Matthew Effect, where data-rich ecosystems gain superior AI support. While not the sole driver of adoption, current models introduce a non-negligible productivity friction for niche technologies, representing a hidden bias in software evolution. △ Less

Submitted 9 February, 2026; v1 submitted 27 September, 2025; originally announced September 2025.

Supporting Car-Following Behavior through V2V-Based Beyond-Visual-Range Information Display

Authors: Feiqi Gu, Zhixiong Wang, Zhenyu Wang, Dengbo He

Abstract: Rear-end collisions constituted a large portion of crashes on the road, despite efforts to mitigate rear-end collisions, such as forward collision warnings. The chance of rear-end collisions is closely related to drivers' car-following (CF) behaviors in the traffic flow. Given that drivers may rely on more than the information of the direct lead vehicle (DLV) when making CF decisions, expanding dr… ▽ More Rear-end collisions constituted a large portion of crashes on the road, despite efforts to mitigate rear-end collisions, such as forward collision warnings. The chance of rear-end collisions is closely related to drivers' car-following (CF) behaviors in the traffic flow. Given that drivers may rely on more than the information of the direct lead vehicle (DLV) when making CF decisions, expanding drivers' perceptual range by providing beyond-visual-range (BVR) information based on vehicle-to-vehicle (V2V) communication may enhance CF safety. Thus, four different human-machine interfaces (HMIs) providing various types of BVR information in CF events were designed, including Brake-HMI showing only brake action of indirect lead vehicles (ILV), Dis-HMI and THW-HMI showing the relative distance and time headway between the ILV and DLV, respectively, and Video-HMI showing the live-stream video of ILV from the perspective of DLV. A driving simulator experiment with 40 participants was conducted to evaluate the impact of BVR-based HMI on driving safety in CF events. We found that, in general, BVR information could improve CF safety without overloading drivers and compromising their visual attention allocation strategies, particularly among novice drivers, by enabling quicker brake responses and increasing time headway and time-to-collision in brake events. The Brake-HMI yielded the safest performance in chain brake events, whereas Video-HMI increased attentional demands without observable benefits. This research provides insights into enabling drivers' BVR perception based on V2V communication to enhance driving safety in CF scenarios. △ Less

Submitted 23 June, 2025; originally announced June 2025.

ERASER: Efficient RTL FAult Simulation Framework with Trimmed Execution Redundancy

Authors: Jiaping Tang, Jianan Mu, Silin Liu, Zizhen Liu, Feng Gu, Xinyu Zhang, Leyan Wang, Shenwen Liang, Jing Ye, Huawei Li, Xiaowei Li

Abstract: As intelligent computing devices increasingly integrate into human life, ensuring the functional safety of the corresponding electronic chips becomes more critical. A key metric for functional safety is achieving a sufficient fault coverage. To meet this requirement, extensive time-consuming fault simulation of the RTL code is necessary during the chip design phase.The main overhead in RTL fault s… ▽ More As intelligent computing devices increasingly integrate into human life, ensuring the functional safety of the corresponding electronic chips becomes more critical. A key metric for functional safety is achieving a sufficient fault coverage. To meet this requirement, extensive time-consuming fault simulation of the RTL code is necessary during the chip design phase.The main overhead in RTL fault simulation comes from simulating behavioral nodes (always blocks). Due to the limited fault propagation capacity, fault simulation results often match the good simulation results for many behavioral nodes. A key strategy for accelerating RTL fault simulation is the identification and elimination of redundant simulations. Existing methods detect redundant executions by examining whether the fault inputs to each RTL node are consistent with the good inputs. However, we observe that this input comparison mechanism overlooks a significant amount of implicit redundant execution: although the fault inputs differ from the good inputs, the node's execution results remain unchanged. Our experiments reveal that this overlooked redundant execution constitutes nearly half of the total execution overhead of behavioral nodes, becoming a significant bottleneck in current RTL fault simulation. The underlying reason for this overlooked redundancy is that, in these cases, the true execution paths within the behavioral nodes are not affected by the changes in input values. In this work, we propose a behavior-level redundancy detection algorithm that focuses on the true execution paths. Building on the elimination of redundant executions, we further developed an efficient RTL fault simulation framework, Eraser.Experimental results show that compared to commercial tools, under the same fault coverage, our framework achieves a 3.9 $\times$ improvement in simulation performance on average. △ Less

Submitted 23 April, 2025; originally announced April 2025.

Comments: 7 pages

Filtering with Time-frequency Analysis: An Adaptive and Lightweight Model for Sequential Recommender Systems Based on Discrete Wavelet Transform

Authors: Sheng Lu, Mingxi Ge, Jiuyi Zhang, Wanli Zhu, Guanjin Li, Fangming Gu

Abstract: Sequential Recommender Systems (SRS) aim to model sequential behaviors of users to capture their interests which usually evolve over time. Transformer-based SRS have achieved distinguished successes recently. However, studies reveal self-attention mechanism in Transformer-based models is essentially a low-pass filter and ignores high frequency information potentially including meaningful user inte… ▽ More Sequential Recommender Systems (SRS) aim to model sequential behaviors of users to capture their interests which usually evolve over time. Transformer-based SRS have achieved distinguished successes recently. However, studies reveal self-attention mechanism in Transformer-based models is essentially a low-pass filter and ignores high frequency information potentially including meaningful user interest patterns. This motivates us to seek better filtering technologies for SRS, and finally we find Discrete Wavelet Transform (DWT), a famous time-frequency analysis technique from digital signal processing field, can effectively process both low-frequency and high-frequency information. We design an adaptive time-frequency filter with DWT technique, which decomposes user interests into multiple signals with different frequency and time, and can automatically learn weights of these signals. Furthermore, we develop DWTRec, a model for sequential recommendation all based on the adaptive time-frequency filter. Thanks to fast DWT technique, DWTRec has a lower time complexity and space complexity theoretically, and is Proficient in modeling long sequences. Experiments show that our model outperforms state-of-the-art baseline models in datasets with different domains, sparsity levels and average sequence lengths. Especially, our model shows great performance increase in contrast with previous models when the sequence grows longer, which demonstrates another advantage of our model. △ Less

Submitted 4 May, 2025; v1 submitted 30 March, 2025; originally announced March 2025.

Comments: 17pages, accepted by ICIC 2025 oral

PRO-VPT: Distribution-Adaptive Visual Prompt Tuning via Prompt Relocation

Authors: Chikai Shang, Mengke Li, Yiqun Zhang, Zhen Chen, Jinlin Wu, Fangqing Gu, Yang Lu, Yiu-ming Cheung

Abstract: Visual prompt tuning (VPT), i.e., fine-tuning some lightweight prompt tokens, provides an efficient and effective approach for adapting pre-trained models to various downstream tasks. However, most prior art indiscriminately uses a fixed prompt distribution across different tasks, neglecting the importance of each block varying depending on the task. In this paper, we introduce adaptive distributi… ▽ More Visual prompt tuning (VPT), i.e., fine-tuning some lightweight prompt tokens, provides an efficient and effective approach for adapting pre-trained models to various downstream tasks. However, most prior art indiscriminately uses a fixed prompt distribution across different tasks, neglecting the importance of each block varying depending on the task. In this paper, we introduce adaptive distribution optimization (ADO) by tackling two key questions: (1) How to appropriately and formally define ADO, and (2) How to design an adaptive distribution strategy guided by this definition? Through empirical analysis, we first confirm that properly adjusting the distribution significantly improves VPT performance, and further uncover a key insight that a nested relationship exists between ADO and VPT. Based on these findings, we propose a new VPT framework, termed PRO-VPT (iterative Prompt RelOcation-based VPT), which adaptively adjusts the distribution built upon a nested optimization formulation. Specifically, we develop a prompt relocation strategy derived from this formulation, comprising two steps: pruning idle prompts from prompt-saturated blocks, followed by allocating these prompts to the most prompt-needed blocks. By iteratively performing prompt relocation and VPT, our proposal can adaptively learn the optimal prompt distribution in a nested optimization-based manner, thereby unlocking the full potential of VPT. Extensive experiments demonstrate that our proposal significantly outperforms advanced VPT methods, e.g., PRO-VPT surpasses VPT by 1.6 pp and 2.0 pp average accuracy, leading prompt-based methods to state-of-the-art performance on VTAB-1k and FGVC benchmarks. The code is available at https://github.com/ckshang/PRO-VPT. △ Less

Submitted 6 October, 2025; v1 submitted 10 March, 2025; originally announced March 2025.

Comments: Accepted by ICCV 2025

Large Language Models Are Effective Human Annotation Assistants, But Not Good Independent Annotators

Authors: Feng Gu, Zongxia Li, Carlos Rafael Colon, Benjamin Evans, Ishani Mondal, Jordan Lee Boyd-Graber

Abstract: Event annotation is important for identifying market changes, monitoring breaking news, and understanding sociological trends. Although expert annotators set the gold standards, human coding is expensive and inefficient. Unlike information extraction experiments that focus on single contexts, we evaluate a holistic workflow that removes irrelevant documents, merges documents about the same event,… ▽ More Event annotation is important for identifying market changes, monitoring breaking news, and understanding sociological trends. Although expert annotators set the gold standards, human coding is expensive and inefficient. Unlike information extraction experiments that focus on single contexts, we evaluate a holistic workflow that removes irrelevant documents, merges documents about the same event, and annotates the events. Although LLM-based automated annotations are better than traditional TF-IDF-based methods or Event Set Curation, they are still not reliable annotators compared to human experts. However, adding LLMs to assist experts for Event Set Curation can reduce the time and mental effort required for Variable Annotation. When using LLMs to extract event variables to assist expert annotators, they agree more with the extracted variables than fully automated LLMs for annotation. △ Less

Submitted 27 April, 2026; v1 submitted 9 March, 2025; originally announced March 2025.

Comments: 9 pages, 4 figures

Journal ref: ACL 2026 Findings

MTS: A Deep Reinforcement Learning Portfolio Management Framework with Time-Awareness and Short-Selling

Authors: Fengchen Gu, Zhengyong Jiang, Ángel F. García-Fernández, Angelos Stefanidis, Jionglong Su, Huakang Li

Abstract: Portfolio management remains a crucial challenge in finance, with traditional methods often falling short in complex and volatile market environments. While deep reinforcement approaches have shown promise, they still face limitations in dynamic risk management, exploitation of temporal markets, and incorporation of complex trading strategies such as short-selling. These limitations can lead to su… ▽ More Portfolio management remains a crucial challenge in finance, with traditional methods often falling short in complex and volatile market environments. While deep reinforcement approaches have shown promise, they still face limitations in dynamic risk management, exploitation of temporal markets, and incorporation of complex trading strategies such as short-selling. These limitations can lead to suboptimal portfolio performance, increased vulnerability to market volatility, and missed opportunities in capturing potential returns from diverse market conditions. This paper introduces a Deep Reinforcement Learning Portfolio Management Framework with Time-Awareness and Short-Selling (MTS), offering a robust and adaptive strategy for sustainable investment performance. This framework utilizes a novel encoder-attention mechanism to address the limitations by incorporating temporal market characteristics, a parallel strategy for automated short-selling based on market trends, and risk management through innovative Incremental Conditional Value at Risk, enhancing adaptability and performance. Experimental validation on five diverse datasets from 2019 to 2023 demonstrates MTS's superiority over traditional algorithms and advanced machine learning techniques. MTS consistently achieves higher cumulative returns, Sharpe, Omega, and Sortino ratios, underscoring its effectiveness in balancing risk and return while adapting to market dynamics. MTS demonstrates an average relative increase of 30.67% in cumulative returns and 29.33% in Sharpe ratio compared to the next best-performing strategies across various datasets. △ Less

Submitted 6 March, 2025; originally announced March 2025.

Journal ref: Intelligent Data Analysis, 2025

Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring Models

Authors: Dilxat Muhtar, Enzhuo Zhang, Zhenshi Li, Feng Gu, Yanglangxing He, Pengfeng Xiao, Xueliang Zhang

Abstract: Vision-Language Models (VLMs) have demonstrated great potential in interpreting remote sensing (RS) images through language-guided semantic. However, the effectiveness of these VLMs critically depends on high-quality image-text training data that captures rich semantic relationships between visual content and language descriptions. Unlike natural images, RS lacks large-scale interleaved image-text… ▽ More Vision-Language Models (VLMs) have demonstrated great potential in interpreting remote sensing (RS) images through language-guided semantic. However, the effectiveness of these VLMs critically depends on high-quality image-text training data that captures rich semantic relationships between visual content and language descriptions. Unlike natural images, RS lacks large-scale interleaved image-text pairs from web data, making data collection challenging. While current approaches rely primarily on rule-based methods or flagship VLMs for data synthesis, a systematic framework for automated quality assessment of such synthetically generated RS vision-language data is notably absent. To fill this gap, we propose a novel score model trained on large-scale RS vision-language preference data for automated quality assessment. Our empirical results demonstrate that fine-tuning CLIP or advanced VLMs (e.g., Qwen2-VL) with the top 30% of data ranked by our score model achieves superior accuracy compared to both full-data fine-tuning and CLIP-score-based ranking approaches. Furthermore, we demonstrate applications of our scoring model for reinforcement learning (RL) training and best-of-N (BoN) test-time scaling, enabling significant improvements in VLM performance for RS tasks. Our code, model, and dataset are publicly available △ Less

Submitted 19 September, 2025; v1 submitted 2 March, 2025; originally announced March 2025.

Comments: 39 pages, 13 figures. Accept for NeruIPS2025

FastAtlas: Real-Time Compact Atlases for Texture Space Shading

Authors: Nicholas Vining, Alexander Majercik, Floria Gu, Towaki Takikawa, Ty Trusty, Paul Lalonde, Morgan McGuire, Alla Sheffer

Abstract: Texture-space shading (TSS) methods decouple shading and rasterization, allowing shading to be performed at a different framerate and spatial resolution than rasterization. TSS has many potential applications, including streaming shading across networks, and reducing rendering cost via shading reuse across consecutive frames and/or shading at reduced resolutions relative to display resolution. Rea… ▽ More Texture-space shading (TSS) methods decouple shading and rasterization, allowing shading to be performed at a different framerate and spatial resolution than rasterization. TSS has many potential applications, including streaming shading across networks, and reducing rendering cost via shading reuse across consecutive frames and/or shading at reduced resolutions relative to display resolution. Real-time TSS shading requires texture atlases small enough to be easily stored in GPU memory. Using static atlases leads to significant space wastage, motivating real-time per-frame atlassing strategies that pack only the content visible in each frame. We propose FastAtlas, a novel atlasing method that runs entirely on the GPU and is fast enough to be performed at interactive rates per-frame. Our method combines new per-frame chart computation and parametrization strategies and an efficient general chart packing algorithm. Our chartification strategy removes visible seams in output renders, and our parameterization ensures a constant texel-to-pixel ratio, avoiding undesirable undersampling artifacts. Our packing method is more general, and produces more tightly packed atlases, than previous work. Jointly, these innovations enable us to produce shading outputs of significantly higher visual quality than those produced using alternative atlasing strategies. We validate FastAtlas by shading and rendering challenging scenes using different atlasing settings, reflecting the needs of different TSS applications (temporal reuse, streaming, reduced or elevated shading rates). We extensively compare FastAtlas to prior alternatives and demonstrate that it achieves better shading quality and reduces texture stretch compared to prior approaches using the same settings. △ Less

Submitted 20 February, 2025; originally announced February 2025.

Comments: 30 pages, 26 figures

ACM Class: I.3.7

External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation

Authors: Mingfu Liang, Xi Liu, Rong Jin, Boyang Liu, Qiuling Suo, Qinghai Zhou, Song Zhou, Laming Chen, Hua Zheng, Zhiyuan Li, Shali Jiang, Jiyan Yang, Xiaozhen Xia, Fan Yang, Yasmine Badr, Ellie Wen, Shuyu Xu, Hansey Chen, Zhengyu Zhang, Jade Nie, Chunzhi Yang, Zhichen Zeng, Weilin Zhang, Xingliang Huang, Qianru Li , et al. (82 additional authors not shown)

Abstract: Ads recommendation is a prominent service of online advertising systems and has been actively studied. Recent studies indicate that scaling-up and advanced design of the recommendation model can bring significant performance improvement. However, with a larger model scale, such prior studies have a significantly increasing gap from industry as they often neglect two fundamental challenges in indus… ▽ More Ads recommendation is a prominent service of online advertising systems and has been actively studied. Recent studies indicate that scaling-up and advanced design of the recommendation model can bring significant performance improvement. However, with a larger model scale, such prior studies have a significantly increasing gap from industry as they often neglect two fundamental challenges in industrial-scale applications. First, training and inference budgets are restricted for the model to be served, exceeding which may incur latency and impair user experience. Second, large-volume data arrive in a streaming mode with data distributions dynamically shifting, as new users/ads join and existing users/ads leave the system. We propose the External Large Foundation Model (ExFM) framework to address the overlooked challenges. Specifically, we develop external distillation and a data augmentation system (DAS) to control the computational cost of training/inference while maintaining high performance. We design the teacher in a way like a foundation model (FM) that can serve multiple students as vertical models (VMs) to amortize its building cost. We propose Auxiliary Head and Student Adapter to mitigate the data distribution gap between FM and VMs caused by the streaming data issue. Comprehensive experiments on internal industrial-scale applications and public datasets demonstrate significant performance gain by ExFM. △ Less

Submitted 13 July, 2025; v1 submitted 20 February, 2025; originally announced February 2025.

Comments: Accepted by the ACM Web Conference (WWW) 2025 Industrial Track as Oral Presentation

Should I Trust You? Detecting Deception in Negotiations using Counterfactual RL

Authors: Wichayaporn Wongkamjan, Yanze Wang, Feng Gu, Denis Peskoff, Jonathan K. Kummerfeld, Jonathan May, Jordan Lee Boyd-Graber

Abstract: An increasingly common socio-technical problem is people being taken in by offers that sound ``too good to be true'', where persuasion and trust shape decision-making. This paper investigates how \abr{ai} can help detect these deceptive scenarios. We analyze how humans strategically deceive each other in \textit{Diplomacy}, a board game that requires both natural language communication and strateg… ▽ More An increasingly common socio-technical problem is people being taken in by offers that sound ``too good to be true'', where persuasion and trust shape decision-making. This paper investigates how \abr{ai} can help detect these deceptive scenarios. We analyze how humans strategically deceive each other in \textit{Diplomacy}, a board game that requires both natural language communication and strategic reasoning. This requires extracting logical forms of proposed agreements in player communications and computing the relative rewards of the proposal using agents' value functions. Combined with text-based features, this can improve our deception detection. Our method detects human deception with a high precision when compared to a Large Language Model approach that flags many true messages as deceptive. Future human-\abr{ai} interaction tools can build on our methods for deception detection by triggering \textit{friction} to give users a chance of interrogating suspicious proposals. △ Less

Submitted 5 June, 2025; v1 submitted 17 February, 2025; originally announced February 2025.

Comments: ACL Findings 2025

MIGT: Memory Instance Gated Transformer Framework for Financial Portfolio Management

Authors: Fengchen Gu, Angelos Stefanidis, Ángel García-Fernández, Jionglong Su, Huakang Li

Abstract: Deep reinforcement learning (DRL) has been applied in financial portfolio management to improve returns in changing market conditions. However, unlike most fields where DRL is widely used, the stock market is more volatile and dynamic as it is affected by several factors such as global events and investor sentiment. Therefore, it remains a challenge to construct a DRL-based portfolio management fr… ▽ More Deep reinforcement learning (DRL) has been applied in financial portfolio management to improve returns in changing market conditions. However, unlike most fields where DRL is widely used, the stock market is more volatile and dynamic as it is affected by several factors such as global events and investor sentiment. Therefore, it remains a challenge to construct a DRL-based portfolio management framework with strong return capability, stable training, and generalization ability. This study introduces a new framework utilizing the Memory Instance Gated Transformer (MIGT) for effective portfolio management. By incorporating a novel Gated Instance Attention module, which combines a transformer variant, instance normalization, and a Lite Gate Unit, our approach aims to maximize investment returns while ensuring the learning process's stability and reducing outlier impacts. Tested on the Dow Jones Industrial Average 30, our framework's performance is evaluated against fifteen other strategies using key financial metrics like the cumulative return and risk-return ratios (Sharpe, Sortino, and Omega ratios). The results highlight MIGT's advantage, showcasing at least a 9.75% improvement in cumulative returns and a minimum 2.36% increase in risk-return ratios over competing strategies, marking a significant advancement in DRL for portfolio management. △ Less

Submitted 11 February, 2025; originally announced February 2025.

Journal ref: 2025 IEEE International Conference on Big Data (BigData), pp. 4566-4575

SLTNet: Efficient Event-based Semantic Segmentation with Spike-driven Lightweight Transformer-based Networks

Authors: Xianlei Long, Xiaxin Zhu, Fangming Guo, Wanyi Zhang, Qingyi Gu, Chao Chen, Fuqiang Gu

Abstract: Event-based semantic segmentation has great potential in autonomous driving and robotics due to the advantages of event cameras, such as high dynamic range, low latency, and low power cost. Unfortunately, current artificial neural network (ANN)-based segmentation methods suffer from high computational demands, the requirements for image frames, and massive energy consumption, limiting their effici… ▽ More Event-based semantic segmentation has great potential in autonomous driving and robotics due to the advantages of event cameras, such as high dynamic range, low latency, and low power cost. Unfortunately, current artificial neural network (ANN)-based segmentation methods suffer from high computational demands, the requirements for image frames, and massive energy consumption, limiting their efficiency and application on resource-constrained edge/mobile platforms. To address these problems, we introduce SLTNet, a spike-driven lightweight transformer-based network designed for event-based semantic segmentation. Specifically, SLTNet is built on efficient spike-driven convolution blocks (SCBs) to extract rich semantic features while reducing the model's parameters. Then, to enhance the long-range contextural feature interaction, we propose novel spike-driven transformer blocks (STBs) with binary mask operations. Based on these basic blocks, SLTNet employs a high-efficiency single-branch architecture while maintaining the low energy consumption of the Spiking Neural Network (SNN). Finally, extensive experiments on DDD17 and DSEC-Semantic datasets demonstrate that SLTNet outperforms state-of-the-art (SOTA) SNN-based methods by at most 9.06% and 9.39% mIoU, respectively, with extremely 4.58x lower energy consumption and 114 FPS inference speed. Our code is open-sourced and available at https://github.com/longxianlei/SLTNet-v1.0. △ Less

Submitted 13 August, 2025; v1 submitted 17 December, 2024; originally announced December 2024.

Comments: Accepted by IROS 2025 (2025 IEEE/RSJ International Conference on Intelligent Robots and Systems)

Journal ref: 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

LHRS-Bot-Nova: Improved Multimodal Large Language Model for Remote Sensing Vision-Language Interpretation

Authors: Zhenshi Li, Dilxat Muhtar, Feng Gu, Xueliang Zhang, Pengfeng Xiao, Guangjun He, Xiaoxiang Zhu

Abstract: Automatically and rapidly understanding Earth's surface is fundamental to our grasp of the living environment and informed decision-making. This underscores the need for a unified system with comprehensive capabilities in analyzing Earth's surface to address a wide range of human needs. The emergence of multimodal large language models (MLLMs) has great potential in boosting the efficiency and con… ▽ More Automatically and rapidly understanding Earth's surface is fundamental to our grasp of the living environment and informed decision-making. This underscores the need for a unified system with comprehensive capabilities in analyzing Earth's surface to address a wide range of human needs. The emergence of multimodal large language models (MLLMs) has great potential in boosting the efficiency and convenience of intelligent Earth observation. These models can engage in human-like conversations, serve as unified platforms for understanding images, follow diverse instructions, and provide insightful feedbacks. In this study, we introduce LHRS-Bot-Nova, an MLLM specialized in understanding remote sensing (RS) images, designed to expertly perform a wide range of RS understanding tasks aligned with human instructions. LHRS-Bot-Nova features an enhanced vision encoder and a novel bridge layer, enabling efficient visual compression and better language-vision alignment. To further enhance RS-oriented vision-language alignment, we propose a large-scale RS image-caption dataset, generated through feature-guided image recaptioning. Additionally, we introduce an instruction dataset specifically designed to improve spatial recognition abilities. Extensive experiments demonstrate superior performance of LHRS-Bot-Nova across various RS image understanding tasks. We also evaluate different MLLM performances in complex RS perception and instruction following using a complicated multi-choice question evaluation benchmark, providing a reliable guide for future model selection and improvement. Data, code, and models will be available at https://github.com/NJU-LHRS/LHRS-Bot. △ Less

Submitted 14 November, 2024; originally announced November 2024.

Personalized Help for Optimizing Low-Skilled Users' Strategy

Authors: Feng Gu, Wichayaporn Wongkamjan, Jonathan K. Kummerfeld, Denis Peskoff, Jonathan May, Jordan Boyd-Graber

Abstract: AIs can beat humans in game environments; however, how helpful those agents are to human remains understudied. We augment CICERO, a natural language agent that demonstrates superhuman performance in Diplomacy, to generate both move and message advice based on player intentions. A dozen Diplomacy games with novice and experienced players, with varying advice settings, show that some of the generate… ▽ More AIs can beat humans in game environments; however, how helpful those agents are to human remains understudied. We augment CICERO, a natural language agent that demonstrates superhuman performance in Diplomacy, to generate both move and message advice based on player intentions. A dozen Diplomacy games with novice and experienced players, with varying advice settings, show that some of the generated advice is beneficial. It helps novices compete with experienced players and in some instances even surpass them. The mere presence of advice can be advantageous, even if players do not follow it. △ Less

Submitted 23 February, 2026; v1 submitted 13 November, 2024; originally announced November 2024.

Comments: 9 pages, 3 figures

Reverse Question Answering: Can an LLM Write a Question so Hard (or Bad) that it Can't Answer?

Authors: Nishant Balepur, Feng Gu, Abhilasha Ravichander, Shi Feng, Jordan Boyd-Graber, Rachel Rudinger

Abstract: Question answering (QA), giving correct answers to questions, is a popular task, but we test reverse question answering (RQA): for an input answer, give a question with that answer. Past work tests QA and RQA separately, but we test them jointly, comparing their difficulty, aiding benchmark design, and checking reasoning consistency. We run 16 LLMs on QA and RQA with trivia questions/answers, reve… ▽ More Question answering (QA), giving correct answers to questions, is a popular task, but we test reverse question answering (RQA): for an input answer, give a question with that answer. Past work tests QA and RQA separately, but we test them jointly, comparing their difficulty, aiding benchmark design, and checking reasoning consistency. We run 16 LLMs on QA and RQA with trivia questions/answers, revealing: 1) Versus QA, LLMs are much less accurate in RQA for numerical answers, but slightly more accurate in RQA for textual answers; 2) LLMs often answer their own invalid questions from RQA accurately in QA, so RQA errors are not from knowledge gaps alone; 3) RQA errors correlate with question difficulty and inversely correlate with answer frequencies in the Dolma corpus; and 4) LLMs struggle to provide valid multi-hop questions. By finding question and answer types that lead to RQA errors, we suggest improvements for LLM reasoning. △ Less

Submitted 11 February, 2025; v1 submitted 20 October, 2024; originally announced October 2024.

Comments: NAACL 2025

More Victories, Less Cooperation: Assessing Cicero's Diplomacy Play

Authors: Wichayaporn Wongkamjan, Feng Gu, Yanze Wang, Ulf Hermjakob, Jonathan May, Brandon M. Stewart, Jonathan K. Kummerfeld, Denis Peskoff, Jordan Lee Boyd-Graber

Abstract: The boardgame Diplomacy is a challenging setting for communicative and cooperative artificial intelligence. The most prominent communicative Diplomacy AI, Cicero, has excellent strategic abilities, exceeding human players. However, the best Diplomacy players master communication, not just tactics, which is why the game has received attention as an AI challenge. This work seeks to understand the de… ▽ More The boardgame Diplomacy is a challenging setting for communicative and cooperative artificial intelligence. The most prominent communicative Diplomacy AI, Cicero, has excellent strategic abilities, exceeding human players. However, the best Diplomacy players master communication, not just tactics, which is why the game has received attention as an AI challenge. This work seeks to understand the degree to which Cicero succeeds at communication. First, we annotate in-game communication with abstract meaning representation to separate in-game tactics from general language. Second, we run two dozen games with humans and Cicero, totaling over 200 human-player hours of competition. While AI can consistently outplay human players, AI-Human communication is still limited because of AI's difficulty with deception and persuasion. This shows that Cicero relies on strategy and has not yet reached the full promise of communicative and cooperative AI. △ Less

Submitted 7 June, 2024; originally announced June 2024.

A Neighbor-Searching Discrepancy-based Drift Detection Scheme for Learning Evolving Data

Authors: Feng Gu, Jie Lu, Zhen Fang, Kun Wang, Guangquan Zhang

Abstract: Uncertain changes in data streams present challenges for machine learning models to dynamically adapt and uphold performance in real-time. Particularly, classification boundary change, also known as real concept drift, is the major cause of classification performance deterioration. However, accurately detecting real concept drift remains challenging because the theoretical foundations of existing… ▽ More Uncertain changes in data streams present challenges for machine learning models to dynamically adapt and uphold performance in real-time. Particularly, classification boundary change, also known as real concept drift, is the major cause of classification performance deterioration. However, accurately detecting real concept drift remains challenging because the theoretical foundations of existing drift detection methods - two-sample distribution tests and monitoring classification error rate, both suffer from inherent limitations such as the inability to distinguish virtual drift (changes not affecting the classification boundary, will introduce unnecessary model maintenance), limited statistical power, or high computational cost. Furthermore, no existing detection method can provide information on the trend of the drift, which could be invaluable for model maintenance. This work presents a novel real concept drift detection method based on Neighbor-Searching Discrepancy, a new statistic that measures the classification boundary difference between two samples. The proposed method is able to detect real concept drift with high accuracy while ignoring virtual drift. It can also indicate the direction of the classification boundary change by identifying the invasion or retreat of a certain class, which is also an indicator of separability change between classes. A comprehensive evaluation of 11 experiments is conducted, including empirical verification of the proposed theory using artificial datasets, and experimental comparisons with commonly used drift handling methods on real-world datasets. The results show that the proposed theory is robust against a range of distributions and dimensions, and the drift detection method outperforms state-of-the-art alternative methods. △ Less

Submitted 23 May, 2024; originally announced May 2024.

A Novel Wide-Area Multiobject Detection System with High-Probability Region Searching

Authors: Xianlei Long, Hui Zhao, Chao Chen, Fuqiang Gu, Qingyi Gu

Abstract: In recent years, wide-area visual surveillance systems have been widely applied in various industrial and transportation scenarios. These systems, however, face significant challenges when implementing multi-object detection due to conflicts arising from the need for high-resolution imaging, efficient object searching, and accurate localization. To address these challenges, this paper presents a h… ▽ More In recent years, wide-area visual surveillance systems have been widely applied in various industrial and transportation scenarios. These systems, however, face significant challenges when implementing multi-object detection due to conflicts arising from the need for high-resolution imaging, efficient object searching, and accurate localization. To address these challenges, this paper presents a hybrid system that incorporates a wide-angle camera, a high-speed search camera, and a galvano-mirror. In this system, the wide-angle camera offers panoramic images as prior information, which helps the search camera capture detailed images of the targeted objects. This integrated approach enhances the overall efficiency and effectiveness of wide-area visual detection systems. Specifically, in this study, we introduce a wide-angle camera-based method to generate a panoramic probability map (PPM) for estimating high-probability regions of target object presence. Then, we propose a probability searching module that uses the PPM-generated prior information to dynamically adjust the sampling range and refine target coordinates based on uncertainty variance computed by the object detector. Finally, the integration of PPM and the probability searching module yields an efficient hybrid vision system capable of achieving 120 fps multi-object search and detection. Extensive experiments are conducted to verify the system's effectiveness and robustness. △ Less

Submitted 7 May, 2024; originally announced May 2024.

Comments: Accepted by ICRA 2024

Journal ref: 2024 IEEE International Conference on Robotics and Automation (ICRA)

Collaborative Pareto Set Learning in Multiple Multi-Objective Optimization Problems

Authors: Chikai Shang, Rongguang Ye, Jiaqi Jiang, Fangqing Gu

Abstract: Pareto Set Learning (PSL) is an emerging research area in multi-objective optimization, focusing on training neural networks to learn the mapping from preference vectors to Pareto optimal solutions. However, existing PSL methods are limited to addressing a single Multi-objective Optimization Problem (MOP) at a time. When faced with multiple MOPs, this limitation results in significant inefficienci… ▽ More Pareto Set Learning (PSL) is an emerging research area in multi-objective optimization, focusing on training neural networks to learn the mapping from preference vectors to Pareto optimal solutions. However, existing PSL methods are limited to addressing a single Multi-objective Optimization Problem (MOP) at a time. When faced with multiple MOPs, this limitation results in significant inefficiencies and hinders the ability to exploit potential synergies across varying MOPs. In this paper, we propose a Collaborative Pareto Set Learning (CoPSL) framework, which learns the Pareto sets of multiple MOPs simultaneously in a collaborative manner. CoPSL particularly employs an architecture consisting of shared and MOP-specific layers. The shared layers are designed to capture commonalities among MOPs collaboratively, while the MOP-specific layers tailor these general insights to generate solution sets for individual MOPs. This collaborative approach enables CoPSL to efficiently learn the Pareto sets of multiple MOPs in a single execution while leveraging the potential relationships among various MOPs. To further understand these relationships, we experimentally demonstrate that shareable representations exist among MOPs. Leveraging these shared representations effectively improves the capability to approximate Pareto sets. Extensive experiments underscore the superior efficiency and robustness of CoPSL in approximating Pareto sets compared to state-of-the-art approaches on a variety of synthetic and real-world MOPs. Code is available at https://github.com/ckshang/CoPSL. △ Less

Submitted 5 April, 2025; v1 submitted 1 April, 2024; originally announced April 2024.

Comments: Accepted by IJCNN 2024 (Oral)

MoMa-Pos: An Efficient Object-Kinematic-Aware Base Placement Optimization Framework for Mobile Manipulation

Authors: Beichen Shao, Nieqing Cao, Yan Ding, Xingchen Wang, Fuqiang Gu, Chao Chen

Abstract: In this work, we present MoMa-Pos, a framework that optimizes base placement for mobile manipulators, focusing on navigation-manipulation tasks in environments with both rigid and articulated objects. Base placement is particularly critical in such environments, where improper positioning can severely hinder task execution if the object's kinematics are not adequately accounted for. MoMa-Pos selec… ▽ More In this work, we present MoMa-Pos, a framework that optimizes base placement for mobile manipulators, focusing on navigation-manipulation tasks in environments with both rigid and articulated objects. Base placement is particularly critical in such environments, where improper positioning can severely hinder task execution if the object's kinematics are not adequately accounted for. MoMa-Pos selectively reconstructs the environment by prioritizing task-relevant key objects, enhancing computational efficiency and ensuring that only essential kinematic details are processed. The framework leverages a graph-based neural network to predict object importance, allowing for focused modeling while minimizing unnecessary computations. Additionally, MoMa-Pos integrates inverse reachability maps with environmental kinematic properties to identify feasible base positions tailored to the specific robot model. Extensive evaluations demonstrate that MoMa-Pos outperforms existing methods in both real and simulated environments, offering improved efficiency, precision, and adaptability across diverse settings and robot models. Supplementary material can be found at https://yding25.com/MoMa-Pos △ Less

Submitted 28 October, 2024; v1 submitted 28 March, 2024; originally announced March 2024.

Comments: Submitted to ICRA 2025

Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations

Authors: Jiaqi Zhai, Lucy Liao, Xing Liu, Yueming Wang, Rui Li, Xuan Cao, Leon Gao, Zhaojie Gong, Fangda Gu, Michael He, Yinghai Lu, Yu Shi

Abstract: Large-scale recommendation systems are characterized by their reliance on high cardinality, heterogeneous features and the need to handle tens of billions of user actions on a daily basis. Despite being trained on huge volume of data with thousands of features, most Deep Learning Recommendation Models (DLRMs) in industry fail to scale with compute. Inspired by success achieved by Transformers in… ▽ More Large-scale recommendation systems are characterized by their reliance on high cardinality, heterogeneous features and the need to handle tens of billions of user actions on a daily basis. Despite being trained on huge volume of data with thousands of features, most Deep Learning Recommendation Models (DLRMs) in industry fail to scale with compute. Inspired by success achieved by Transformers in language and vision domains, we revisit fundamental design choices in recommendation systems. We reformulate recommendation problems as sequential transduction tasks within a generative modeling framework ("Generative Recommenders"), and propose a new architecture, HSTU, designed for high cardinality, non-stationary streaming recommendation data. HSTU outperforms baselines over synthetic and public datasets by up to 65.8% in NDCG, and is 5.3x to 15.2x faster than FlashAttention2-based Transformers on 8192 length sequences. HSTU-based Generative Recommenders, with 1.5 trillion parameters, improve metrics in online A/B tests by 12.4% and have been deployed on multiple surfaces of a large internet platform with billions of users. More importantly, the model quality of Generative Recommenders empirically scales as a power-law of training compute across three orders of magnitude, up to GPT-3/LLaMa-2 scale, which reduces carbon footprint needed for future model developments, and further paves the way for the first foundational models in recommendations. △ Less

Submitted 5 May, 2024; v1 submitted 26 February, 2024; originally announced February 2024.

Comments: 26 pages, 13 figures. ICML'24. Code available at https://github.com/facebookresearch/generative-recommenders

LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model

Authors: Dilxat Muhtar, Zhenshi Li, Feng Gu, Xueliang Zhang, Pengfeng Xiao

Abstract: The revolutionary capabilities of large language models (LLMs) have paved the way for multimodal large language models (MLLMs) and fostered diverse applications across various specialized domains. In the remote sensing (RS) field, however, the diverse geographical landscapes and varied objects in RS imagery are not adequately considered in recent MLLM endeavors. To bridge this gap, we construct a… ▽ More The revolutionary capabilities of large language models (LLMs) have paved the way for multimodal large language models (MLLMs) and fostered diverse applications across various specialized domains. In the remote sensing (RS) field, however, the diverse geographical landscapes and varied objects in RS imagery are not adequately considered in recent MLLM endeavors. To bridge this gap, we construct a large-scale RS image-text dataset, LHRS-Align, and an informative RS-specific instruction dataset, LHRS-Instruct, leveraging the extensive volunteered geographic information (VGI) and globally available RS images. Building on this foundation, we introduce LHRS-Bot, an MLLM tailored for RS image understanding through a novel multi-level vision-language alignment strategy and a curriculum learning method. Additionally, we introduce LHRS-Bench, a benchmark for thoroughly evaluating MLLMs' abilities in RS image understanding. Comprehensive experiments demonstrate that LHRS-Bot exhibits a profound understanding of RS images and the ability to perform nuanced reasoning within the RS domain. △ Less

Submitted 15 July, 2024; v1 submitted 4 February, 2024; originally announced February 2024.

Comments: 36 pages, 10 figures. Github https://github.com/NJU-LHRS/LHRS-Bot

Robust Control of An Aerial Manipulator Based on A Variable Inertia Parameters Model

Authors: Guangyu Zhang, Yuqing He, Bo Dai, Feng Gu, Jianda Han, Guangjun Liu

Abstract: Aerial manipulator, which is composed of an UAV (Unmanned Aerial Vehicle) and a multi-link manipulator and can perform aerial manipulation, has shown great potential of applications. However, dynamic coupling between the UAV and the manipulator makes it difficult to control the aerial manipulator with high performance. In this paper, system modeling and control problem of the aerial manipulator ar… ▽ More Aerial manipulator, which is composed of an UAV (Unmanned Aerial Vehicle) and a multi-link manipulator and can perform aerial manipulation, has shown great potential of applications. However, dynamic coupling between the UAV and the manipulator makes it difficult to control the aerial manipulator with high performance. In this paper, system modeling and control problem of the aerial manipulator are studied. Firstly, an UAV dynamic model is proposed with consideration of the dynamic coupling from an attached manipulator, which is treated as disturbance for the UAV. In the dynamic model, the disturbance is affected by the variable inertia parameters of the aerial manipulator system. Then, based on the proposed dynamic model, a disturbance compensation robust $H_{\infty}$ controller is designed to stabilize flight of the UAV while the manipulator is in operation. Finally, experiments are conducted and the experimental results demonstrate the feasibility and validity of the proposed control scheme. △ Less

Submitted 8 January, 2024; originally announced January 2024.

Journal ref: IEEE Trans. Ind. Electron. 67(2020)9515-9525

A Survey on Robotic Manipulation of Deformable Objects: Recent Advances, Open Challenges and New Frontiers

Authors: Feida Gu, Yanmin Zhou, Zhipeng Wang, Shuo Jiang, Bin He

Abstract: Deformable object manipulation (DOM) for robots has a wide range of applications in various fields such as industrial, service and health care sectors. However, compared to manipulation of rigid objects, DOM poses significant challenges for robotic perception, modeling and manipulation, due to the infinite dimensionality of the state space of deformable objects (DOs) and the complexity of their dy… ▽ More Deformable object manipulation (DOM) for robots has a wide range of applications in various fields such as industrial, service and health care sectors. However, compared to manipulation of rigid objects, DOM poses significant challenges for robotic perception, modeling and manipulation, due to the infinite dimensionality of the state space of deformable objects (DOs) and the complexity of their dynamics. The development of computer graphics and machine learning has enabled novel techniques for DOM. These techniques, based on data-driven paradigms, can address some of the challenges that analytical approaches of DOM face. However, some existing reviews do not include all aspects of DOM, and some previous reviews do not summarize data-driven approaches adequately. In this article, we survey more than 150 relevant studies (data-driven approaches mainly) and summarize recent advances, open challenges, and new frontiers for aspects of perception, modeling and manipulation for DOs. Particularly, we summarize initial progress made by Large Language Models (LLMs) in robotic manipulation, and indicates some valuable directions for further research. We believe that integrating data-driven approaches and analytical approaches can provide viable solutions to open challenges of DOM. △ Less

Submitted 16 December, 2023; originally announced December 2023.

Comments: 15 pages