论文检索

Aoran Xiao, Shihao Cheng, Yonghao Xu, Yexian Ren, Hongruixuan Chen, Naoto Yokoya

Recent advances in multimodal large language models (MLLMs) have accelerated progress in domain-oriented AI, yet their development in geoscience and remote sensing (RS) remains constrained by distinctive challenges: wide-ranging disciplinary knowledge, heterogeneous sensor modalities, and a fragmented spectrum of tasks. To bridge these gaps, we introduce GeoMMBench, a comprehensive multimodal question-answering benchmark covering diverse RS disciplines, sensors, and tasks, enabling broader and more rigorous evaluation than prior benchmarks. Using GeoMMBench, we assess 36 open-source and proprietary large language models (LLMs), uncovering systematic deficiencies in domain knowledge, perceptual grounding, and reasoning--capabilities essential for expert-level geospatial interpretation. Beyond evaluation, we propose GeoMMAgent, a multi-agent framework that strategically integrates retrieval, perception, and reasoning through domain-specific RS models and tools. Extensive experimental results demonstrate that GeoMMAgent significantly outperforms standalone LLMs, underscoring the importance of tool-augmented agents for dynamically tackling complex geoscience and RS challenges.

Yule Xie, Jiaxin Ding, Cheng Deng, Shiqing Gao, Junran Zhang, Sibo Zhang, Zeyuan Wang, Ke Wu, Xin Ding, Luoyi Fu 等

Reinforcement learning (RL) has recently shown remarkable ability to enhance reasoning in large language models (LLMs), yet its potential in scientific domains beyond mathematics remains largely unexplored. Geoscience questions couple broad factual knowledge with multi-step inference and often rely on visual evidence such as maps, cross-sections, and diagrams, making them a challenging but verifiable testbed for RL-based reasoning. To enable this study, we introduce GeoMC-10K, a dataset of 10,000 geoscience multiple-choice questions spanning physical to human geography and high-school to professional levels; over 30% of the questions are image dependent. To support text-only RL on these multimodal questions, we design GeoM2T, a multi-agent framework that converts multimodal questions into descriptive text while preserving answerability and difficulty. Fine-tuning LLaMA-3.1-8B and Qwen-3-8B with Group Relative Policy Optimization (GRPO), incorporating a factual reward mechanism, yields GR1, which achieves absolute accuracy improvements of 5.9% and 13.3%, respectively, and it generalizes to out-of-distribution geoscience benchmarks. Together, GeoMC-10K, GeoM2T, and GR1 establish a scalable benchmark and baseline for RL-enhanced geoscience reasoning.

Bingxian Wu, Yu Zhang, Zonghao Guo, Tang Liu, Chen Qian, Yuxiang Lu, Xingbo Du, Yanghao Li, Yidan Zhang, Chi Chen 等

Geoscience research requires complex analysis and domain expertise, with remote sensing (RS) observations as a key foundation. However, existing RS agents built on general-purpose LLMs remain largely domain-agnostic, resulting in brittle and error-prone workflows. Moreover, these failures are seldom consolidated into a reusable experience for subsequent analyses. To address this issue, we introduce RSMeM, a knowledge-enhanced memory evolution mechanism that bootstraps RS agents with pre-distilled domain knowledge and iteratively integrates online experience for robust multi-step tool execution. RSMeM is composed of two components: (i) Hierarchical Knowledge Grounding, which performs taxonomy-aware retrieval over a hierarchical domain corpus to guide planning and tool selection; and (ii) Failure-Aware Experience Refinement, which distills failure-annotated tool-use traces into reusable constraints for next-round tool execution. By iteratively employing these two processes, RS agents can evolve to absorb task-level domain knowledge and effectively translate it into instance-level execution experience. Extensive experiments on EarthBench demonstrate that RSMeM consistently improves tool-use performance and end-to-end accuracy across a diverse set of LLM backbones. Notably, RSMeM achieves a 6% accuracy improvement on DeepSeek-V3.2 with less than 1% additional experience tokens, demonstrating the knowledge density of our distilled experience. All codes and models will be released to support reproducible research.

Jingru Li, Wei Ren, Tianqing Zhu

Large Vision-Language Models (LVLMs) rely on attention-based retrieval of safety instructions to maintain alignment during generation. Existing attacks typically optimize image perturbations to maximize harmful output likelihood, but suffer from slow convergence due to gradient conflict between adversarial objectives and the model’s safety-retrieval mechanism. We propose Attention-Guided Visual Jailbreaking, which circumvents rather than overpowers safety alignment by directly manipulating attention patterns. Our method introduces two simple auxiliary objectives: (1) suppressing attention to system-prompt tokens and (2) anchoring generation on adversarial image features. This simple yet effective push-pull formulation reduces gradient conflict by 45% and achieves 94.4% attack success rate on Qwen-VL (vs. 68.8% baseline) with 40% fewer iterations. At tighter perturbation budgets (\epsilon=8/255), we maintain 59.0% ASR compared to 45.7% for standard methods. Mechanistic analysis reveals a failure mode we term safety blindness: successful attacks suppress system-prompt attention by 80%, causing models to generate harmful content not by overriding safety rules, but by failing to retrieve them.

Applications · Computer Vision

Jun Lin, Jiayu Ding, Xiangtian Si, Xitong Cao, Lixin Hong, Zhang Chen, Chenxi Lv, Wenqian Wang

Existing 3D Visual Question Answering (3D-VQA) methods rely on generative paradigms, producing ambiguous descriptions that hinder deterministic decision-making. We introduce 3D Scene Assertion Verification, a task requiring models to verify natural language assertions in 3D scenes with strict binary judgments. To enable rigorous evaluation, we present 3DSAV, the first large-scale diagnostic benchmark comprising 22.5k samples tailored for this objective. We observe that current 3D-VQA models struggle in this setting due to a lack of specialized reasoning mechanisms. To address this, we propose DualLPSS. This framework uses a dual-stage routing mechanism to enable type-aware cross-modal fusion and scene-guided assertion focusing. Extensive experiments show that DualLPSS achieves state-of-the-art performance on 3DSAV, distinguishing itself by correctly handling complex logical assertions where baselines fail. The code and dataset will be made publicly available.

Zitong Li, Jinzhuo Wu, Fukang Zhao, Xinyue Wang, Jun Chen-CUG, Zhuo Cheng, Dapeng Luo

Recent Open-vocabulary Object Detection (OVD) approaches adapt CLIP through region-level distillation to improve semantic alignment for novel categories. However, the distilled regional features are often used for both classification and localization, enhancing semantic consistency at the expense of spatial fidelity. To resolve this, we propose Object-level Semantic and Spatial Distillation (OSSD), a two-stage framework that explicitly decouples semantic and spatial feature learning. OSSD first distills object-level semantics from CLIP’s global [CLS] embeddings to enhance region discrimination, and then injects fine-grained spatial and structural priors via spatial distillation from a detector trained only on COCO base categories. Furthermore, we propose a Location Quality Estimation Head (LQEH) that predicts class-agnostic localization quality, complementing objectness confidence to improve the novel-object perception. Extensive experiments show that our method achieves 49.2 AP50 on the OV-COCO benchmark. exceeding the best previous result by 3.6\%, On the OV-LVIS benchmark, our method reaches 40.5 mAP on novel categories, outperforming previous state-of-the-art methods.

Optimization · Zero-order and Black-box Optimization

Yukun Du, Haiyue Yu, Jiang Jiang, Shuaiwen Tang, Xiaotong Xie, Haobo Liu, Chongshuang Hu, Shengkun Chang

Existing Meta-Black-Box Optimization (MetaBBO) methods focus on how to search when controlling optimizers, but largely overlook where to search. We propose MetaSG-SAEA, a bi-level MetaBBO framework for expensive constrained multi-objective optimization problems (ECMOPs), in which a meta-policy provides search guidance to the low-level Surrogate-Assisted Evolutionary Algorithm (SAEA). To achieve this, we introduce Max–Min Constraint-Calibrated Inequality (MM-CCI), a compact, problem-agnostic region abstraction that maps heterogeneous constraint evaluations to an ordered scalar level; we further provide a theoretical analysis of its fundamental properties. Building on this region abstraction, we adopt diffusion-based population initialization to translate the meta-policy’s region-level guidance into solution-level priors for the SAEA. To make MetaSG-SAEA scalable, we construct an attention-based state representation across varying problem dimensions, population sizes, and numbers of objectives and constraints. Experimental results demonstrate that MetaSG-SAEA outperforms state-of-the-art baselines across diverse benchmarks and exhibits the ability to generalize across problem distributions.

Deep Learning · Large Language Models

Shuofei Qiao, Yunxiang Wei, Xuehai Wang, Bin Wu, Boyang XUE, Ningyu Zhang, Hossein A. Rahmani, Wang Yanshan, Qiang Zhang, Keyan Ding 等

The rapid evolution of Large Language Models has catalyzed a surge in scientific idea production, yet this leap has not been accompanied by a matching advance in idea evaluation. The fundamental nature of scientific evaluation needs knowledgeable grounding, collective deliberation, and multi-criteria decision-making. However, existing idea evaluation methods often suffer from narrow knowledge horizons, flattened evaluation dimensions, and the inherent bias in LLM-as-a-Judge. To address these, we regard idea evaluation as a knowledge-grounded, multi-perspective reasoning problem and introduce **InnoEval**, a deep innovation evaluation framework designed to emulate human-level idea assessment. We apply a heterogeneous deep knowledge search engine that retrieves and grounds dynamic evidence from diverse online sources. We further achieve review consensus with an innovation review board containing reviewers with distinct academic backgrounds, enabling a multi-dimensional decoupled evaluation across multiple metrics. We construct comprehensive datasets derived from authoritative peer-reviewed submissions to benchmark InnoEval. Experiments demonstrate that InnoEval can consistently outperform baselines in point-wise, pair-wise, and group-wise evaluation tasks, exhibiting judgment patterns and consensus highly aligned with human experts.

Optimization · Zero-order and Black-box Optimization

Yanchi Li, Jiao Liu, Wenyin Gong, Qiong Gu, Yue Zhao, Yew Soon ONG

Evolutionary multi-tasking accelerates black-box optimization via knowledge transfer but falters in scenarios involving many low-similarity tasks. We identify this scalability barrier as the *Multi-Task Curse*, driven by evaluation budget dispersion and negative transfer. To overcome this, we propose MES-RET (*M*any-task *E*volution *S*trategy with *R*eward-weighted *E*valuation and *T*ransfer), which combats budget dispersion via a reward-weighted evaluation scheme that guarantees superior expected improvement, while simultaneously mitigating negative transfer through a robust reward-weighted aggregation of mean and covariance statistics, ensuring a safe fallback to independent evolution. Furthermore, to handle neural dimensional mismatches in many-task policy search, we introduce a semantic parameter alignment strategy that bridges heterogeneous state-action spaces. Extensive experiments on synthetic benchmarks, real-world engineering problems, and reinforcement learning tasks demonstrate that MES-RET consistently outperforms state-of-the-art methods, notably enabling skill transfer across morphologically distinct policies.

Applications · Computer Vision

Xiaoxuan He, Siming Fu, Zeyue Xue, Weijie Wang, Ruizhe He, Yuming Li, Dacheng Yin, Shuai Dong, Haoyang Huang, Hongfa Wang 等

Group Relative Policy Optimization has emerged as essential for aligning video diffusion models with human preferences, but faces a critical computational bottleneck: training a 14B parametered model typically demands hundreds of GPU days per experiment. Existing efficiency methods reduce costs through sliding window subsampling training timesteps, but fundamentally compromise optimization, exhibiting severe instability and failing to reach full trajectory performance. We present Flash-GRPO, a single-step training framework that outperforms full trajectory training in alignment quality under low computational budgets while substantially improving training efficiency. Flash-GRPO addresses two critical challenges: iso-temporal grouping eliminates timestep-confounded variance by enforcing prompt-wise temporal consistency, decoupling policy performance from timestep difficulty; temporal gradient rectification neutralizes the time-dependent scaling factor that causes vastly inconsistent gradient magnitudes across timesteps. Experiments on 1.3B to 14B parameter models validate Flash-GRPO's effectiveness, demonstrating substantial training acceleration with consistent stability and state-of-the-art alignment quality.

Yuanrui Wang, Xingxuan Zhang, Han Yu, Mingchao Hao, Gang Ren, hao yuan, Li Mao, Yunjia Zhang, Chun Yuan, Peng Cui

Recent tabular foundation models routinely match or surpass strong tree ensembles and specialized deep architectures, yet their numeric embeddings remain a bottleneck. We diagnose a low-rank collapse induced by the prevalent linear+ID scheme and introduce RaBEL, a compact Radial Basis Embedding Layer that front-loads nonlinearity via localized RBF features. RaBEL increases shallow-layer effective rank and improves conditioning without deeper stacks; it is complementary to periodic mappings. We further identify a permutation-order pathology in bidirectional attention (feature$\rightarrow$sample) and propose a reordered stack: sample-attention $\rightarrow$ FFN $\rightarrow$ feature-attention, ensuring column-level context precedes feature mixing and that all attention computations influence the readout. Combining both ideas yields MiniX, a 2M-parameter model that surpasses 7M-parameter TabPFN-v2 and 27M-parameter TabICL baselines on popular benchmarks while reducing training and inference cost. Our results highlight principled nonlinear embeddings and attention-order redesign as key enablers of accuracy and efficiency gains in tabular foundation models.

Deep Learning · Large Language Models

Kejun Liu, Yuanyuan Liu, Ke Wang, Zhe Chen, Yibing Zhan, Wei Xiang, Hongyan Zhang

Multimodal Large Language Models (MLLMs) show promise for Multimodal Emotion Recognition (MER) but often remain unreliable because sparse emotional cues could be easily overwhelmed and affected by redundant context. While fine-tuning is effective, it is usually costly when using large models. Training-free methods like chain-of-thought reasoning provide a practical alternative, but they mostly rely on heuristic prompting to influence the model behaviors and do not explicitly focus on emotion relevant tokens internally, which would allow decision-relevant emotional tokens to be diluted by environmental noise, resulting in unstable predictions. To address this limitation without training, we rethink MER from a world-model perspective that treats emotion as a latent state inferred from noisy and redundant multimodal observations. Under frozen parameters, this view suggests that robustness depends on constraining why and how tokens contribute to inference. Based on this insight, we propose WETR (World-Model inspired Emotion-aware Token Refinement), a training-free, plug-and-play regulator that reshapes token usage through two mechanisms: Noise-suppressed Token Selection (NTS), which suppresses redundant intra-modal noise, and State-strengthened Token Reweighting (STR), which amplifies decision-relevant emotional tokens. Experiments on multiple MER benchmarks demonstrate that WETR consistently improves accuracy and stability under frozen parameters, which also improves token-level interpretability.

Applications · Computer Vision

Ke Wang, Yuanyuan Liu, Kejun Liu, Yuyang Xia, Chang Tang, Yibing Zhan, Zhe Chen

Dynamic Facial Expression Recognition (DFER) models the temporal evolution of facial expressions in videos. In real-world deployments, changing scenarios distort expression trajectories over time, making it difficult for existing methods to maintain performance. While most current approaches address this issue through passive feature alignment across scenarios or domain-incremental learning techniques that preserve previously learned representations, they do not explicitly model scenario evolution over time, limiting their ability to robustly capture expression dynamics under scenario-incremental changes. To end this, we propose **EmWorld**, an emotion world model for DFER that explicitly models latent emotion state evolution under scenario variations. Specifically, **EmWorld** formulates scenario-incremental DFER as a progressive Bayesian inference problem over latent world states with dual temporal scales. Slow-timescale component (**STS**) models scenario evolution using stochastic evolutionary priors, capturing long-term scenario effects and providing proactive guidance in new scenarios. Fast-timescale component (**FTS**) models frame-level expression dynamics with temporally consistent latent transitions, effectively decoupling expression dynamics from scenario influences. By jointly inferring latent states at both timescales, **EmWorld**, shifts DFER from a passive feature discrimination process to a active probabilistic state inference under evolving scenarios. Experiments on FERV39k, DFEW, and MAFW demonstrate that **EmWorld**, consistently outperforms state-of-the-art methods, achieving up to 3.84\% improvement while exhibiting strong cross-scenario stability and long-term robustness.

Applications · Chemistry, Physics, and Earth Sciences

Michael McCabe, Payel Mukhopadhyay, Tanya Marwah, Bruno Régaldo-Saint Blancard, François Rozet, Cristiana Diaconu, Lucas Meyer, Kaze Wong, Hadi Sotoudeh, Alberto Bietti 等

Foundation models have transformed machine learning for language and vision, but achieving comparable impact in physical simulation remains a challenge. Data heterogeneity and unstable long-term dynamics inhibit learning from sufficiently diverse dynamics, while varying resolutions and dimensionalities challenge efficient training on modern hardware. Through empirical and theoretical analysis, we incorporate new approaches to mitigate these obstacles, including a harmonic-analysis–based stabilization method, load-balanced distributed 2D-3D training strategies, and compute-adaptive tokenization. Using these tools, we develop \Walrus, a transformer-based foundation model developed primarily for fluid-like continuum dynamics. \Walrus\ is pretrained on nineteen diverse scenarios spanning astrophysics, geoscience, rheology, plasma physics, acoustics, and classical fluids. Experiments show that \Walrus\ outperforms prior foundation models on both short- and long-term prediction horizons on downstream tasks and across the breadth of pretraining data, while ablation studies confirm the value of our contributions to forecast stability, training throughput, and transfer performance over conventional approaches.

General Machine Learning · Online Learning, Active Learning and Bandits

Liangxiao Jiang, Liangxiao Jiang, Chaoqun Li, Shanshan Si

In crowdsourcing scenarios, to mitigate the impact of noisy labels assigned by non-expert workers, each instance is typically annotated multiple times by different workers. However, repeated annotation can introduce instance- or label-level redundancy, thereby inflating annotation costs. Despite its practical importance, research on repeated annotation strategies remains limited, and no existing strategy simultaneously avoids being offline, instance-unaware, and model-centric. In this paper, we propose a model-agnostic active annotation strategy, MA$^3$S, that addresses these limitations: (1) To reduce label redundancy caused by offline procedure, MA$^3$S estimates instance uncertainties with a general Beta distribution and updates them online as new labels arrive. (2) To prevent instance redundancy induced by instance-unaware designs, MA$^3$S constructs a nearest-neighbor graph to propagate instance uncertainties, reducing repeated annotations of similar instances. (3) To avoid being model-centric, MA$^3$S actively selects instances for annotation based solely on the estimated uncertainties, without relying on model feedback. Extensive experiments on synthetic and real-world datasets demonstrate that MA$^3$S consistently outperforms existing annotation strategies.

Linsong Shan, Laurence Yang, Zecan Yang, Fukai Guo, Honglu Zhao, Yixuan Geng

Video motion transfer aims to synthesize novel content videos that strictly follow the motion trajectories of a reference video. However, existing methods typically operate in Euclidean space, treating motion as unconstrained pixel displacements or linear phase shifts. This simplification frequently causes severe shearing artifacts and perspective collapse under complex camera and object motions. In this work, we present LieWarper, a geometry-aware motion transfer framework that reconceptualizes motion as coordinate evolution on a manifold rather than mere pixel displacement. Specifically, we derive an analytic solver on the $\text{Sim}(2)$ manifold to extract global evolution parameters from noisy optical flow. We then introduce a flow-guided phase modulation mechanism, enabling non-rigid dynamics to undergo coordinate transformation along the evolution path. This approach achieves accurate trajectory transfer while maintaining global geometric integrity. Extensive experiments show that LieWarper significantly outperforms state-of-the-art training-free baselines in both motion fidelity and geometric stability, while maintaining high generation quality.

Deep Learning · Large Language Models

Zexuan Wang, Chenghao Yang, Yingqi Que, Zhoufutu Wen, Zaiyuan Wang, Jiashuo Liu, Zhixin Yao, Zhenzhu Yang, Huaqing Yuan, Yiwen Wang 等

Real-world autonomous planning requires coordinating tightly coupled constraints where a single decision dictates the feasibility of all subsequent actions. However, existing benchmarks predominantly feature loosely coupled constraints solvable through local greedy decisions and rely on idealized data, failing to capture the complexity of extracting parameters from dynamic web environments. We introduce $\textbf{WorldTravel}$, a benchmark comprising 150 real-world travel scenarios across 5 cities that demand navigating an average of 15+ interdependent temporal and logical constraints. To evaluate agents in realistic deployments, we develop $\textbf{WorldTravel-Webscape}$, a multi-modal environment featuring over 2,000 rendered webpages where agents must perceive constraint parameters directly from visual layouts to inform their planning. Our evaluation of 10 frontier models reveals a significant performance collapse: even the state-of-the-art GPT-5.2 achieves only 28.0\% feasibility in text-only settings, which plummets to 3.4\% in multi-modal environments. We identify a critical Perception-Action Gap and a Planning Horizon threshold at approximately 10 constraints where model reasoning consistently fails, suggesting that perception and reasoning remain independent bottlenecks. These findings underscore the need for next-generation agents that unify high-fidelity visual perception with long-horizon reasoning to handle brittle real-world logistics.

Computer Vision · Image and Video Generation

Tianshuo Xu, Kai Wang, ZhiFei Chen, Leyi Wu, Tianshui Wen, Fei Chao, YINGCONG CHEN

Computational replication of Chinese calligraphy, a cornerstone of cultural heritage, remains challenging. Existing methods split into two flawed camps: some render high-quality isolated characters yet miss page-level aesthetics (ligatures, spacing, scale), while others attempt page/column synthesis but sacrifice calligraphic correctness. We introduce UniCalli, a unified diffusion framework for column-level recognition and generation. Training both tasks in one model is deliberate: recognition constrains the generator to preserve character identity and stroke structure, while generation supplies strong style/layout priors—together fostering concept-level abstractions (radicals, stroke configurations) that improve both tasks under long-tail, limited-label regimes. We curate a dataset of 8,000+ digitized pieces, with ~4,000 densely annotated (script labels, character boxes, transcriptions). UniCalli employs asymmetric noising and a rasterized box map to inject spatial priors, and is trained on a mix of synthetic, labeled, and unlabeled data. The model is robust to rare styles, better disentangles style from script, and attains state-of-the-art generative quality with clear gains in ligature continuity and layout fidelity, alongside stronger recognition. The framework extends to other ancient scripts, demonstrated by successful transfer to Oracle bone inscriptions and Egyptian hieroglyphs. Code and data will be released.

Applications · Neuroscience, Cognitive Science

Dehao Zhang, Fukai Guo, Shuai Wang, Jingya Wang, Jieyuan Zhang, Yimeng Shan, Malu Zhang, Yang Yang, Haizhou Li

Integrating Spiking Neural Networks (SNNs) with Transformer architectures offers a promising pathway to balance energy efficiency and performance, particularly for edge vision applications. However, existing Spiking Transformers face two critical challenges: (i) a substantial performance gap compared to their Artificial Neural Networks (ANNs) counterparts and (ii) high memory overhead during inference. Through theoretical analysis, we attribute both limitations to the Spiking Self-Attention (SSA) mechanism: the lack of locality bias and the need to store large attention matrices. Inspired by the localized receptive fields (LRF) and membrane-potential dynamics of biological visual neurons, we propose LRF-Dyn, which uses spiking neurons with localized receptive fields to compute attention while reducing memory requirements. Specifically, we introduce a LRF method into SSA to assign higher weights to neighboring regions, strengthening local modeling and improving performance. Building on this, we approximate the resulting attention computation via charge–fire–reset dynamics, eliminating explicit attention-matrix storage and reducing inference-time memory. Extensive experiments on visual tasks confirm that our method reduces memory overhead while delivering significant performance improvements. These results establish it as a key unit for achieving energy-efficient Spiking Transformers.

Ruibin Yuan, Hanfeng Lin, Shuyue Guo, Ge Zhang, Jiahao Pan, Yongyi Zang, Haohe Liu, Yiming Liang, Wenye Ma, Xingjian Du 等

We tackle the task of long-form music generation, particularly the challenging \textbf{lyrics-to-song} problem, by introducing \textbf{YuE (乐)}, a family of open-source music generation foundation models. Specifically, YuE scales to trillions of tokens and generates up to five minutes of music while maintaining lyrical alignment, coherent musical structure, and engaging vocal melodies with appropriate accompaniment. It achieves this through \textbf{track-decoupled next-token prediction} to overcome dense mixture signals, and \textbf{structural progressive conditioning} for long-context lyrical alignment. In addition, we redesign the \textbf{in-context learning} technique for music generation, enabling bidirectional content creation, style cloning, and improving musicality. Through extensive evaluation, we demonstrate that YuE matches or even surpasses some of the proprietary systems in musicality and vocal agility (as of 2025-01). We strongly encourage readers to \textbf{listen to our demo}\footnote{\url{https://map-yue.github.io/}}.