跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1112新增论文
+875其中 AI 相关
+133已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 05:42 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 06:14 — 2026-11-20 06:14(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-20 05:42最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

27,982 已收录论文23,249 AI 相关8,559 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 78 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 05:40(北京时间)
版本更新 · v4arXiv:2609.23466

RPMem:为LLM智能体学习跨会话的长期循环参数化记忆

RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents

Fanyu Zhao, Ruike Cao, Liang Dong, Fugen Yao, Jian Xu, Guanjun Jiang, Yinsheng Li, Yifei Zhao 等 9 位作者

AI 速读 基于摘要

RPMem提出两阶段架构,将每次会话编译为与模型无关的潜在记忆,并通过任务训练的循环门控选择性整合,再映射为骨干特定的LoRA参数,实现跨会话演化且可跨骨干复用的参数化记忆。

cs.CL · cs.AI

查看原文摘要

Long-running LLM agents require memory that persists and evolves across sessions. Text-based memory retrieves and reconstructs past interactions at every query, making long-horizon performance increasingly dependent on retrieval quality and contextual reasoning as histories grow. Parametric memory encodes experience directly into model computation, but existing approaches provide limited support for cross-session memory evolution. Their coupling to a specific backbone further restricts memory reuse after model replacement. We introduce RPMem, a two-stage architecture that compiles each session into a model-independent latent memory through forward computation and selectively integrates it with retained memory via a task-trained recurrent gate. The consolidated memory is then mapped to backbone-specific low-rank adaptation (LoRA) parameters, allowing the encoding capability to transfer when the backbone is replaced. Evaluation across three long-term memory benchmarks and five diverse backbones demonstrates broad generalization with near-constant update cost and memory footprint. With Qwen3-8B on PERMA, RPMem reaches 85.52%, outperforming the strongest parametric and text-based baselines by 5.32 and 12.98 percentage points, respectively. Ablations validate the complementary roles of session compilation and cross-session consolidation, while dynamics analyses reveal that the gate acquires task-specific memory integration strategies. These results establish RPMem as a lifecycle-independent parametric memory framework that maintains evolving cross-session memory that remains reusable across backbone replacements. Our code is available at https://github.com/Quark-Medical/rpmem/tree/main.

版本更新 · v2arXiv:2607.11012

EasyOPD: An Easy-to-use On-Policy Distillation Framework for Large Language Models

Jie Sun, Mao Zheng, Mingyang Song, Qiyong Zhong, Gengsheng Li, Zhepei Hong, Chang Wu, Pengfei Liu 等 10 位作者

原文摘要

Conventional language-model distillation often relies on fixed teacher-generated data, which may not cover the states encountered by an evolving student policy. On-policy distillation (OPD) instead collects teacher or evaluator supervision on student-generated rollouts. However, existing OPD methods differ substantially in supervision form, tokenizer compatibility, teacher access, and supervision granularity, leading to fragmented implementations that are difficult to reproduce and extend. We present \textsc{EasyOPD}, an on-policy distillation framework built on verl, a distributed reinforcement-learning framework for large language models. \textsc{EasyOPD} separates user-side configuration, method-specific supervision logic, and verl-based execution. Its method modules connect to the shared backend through extension boundaries for loss construction, rollout metadata, reward processing, tokenizer alignment, and teacher-side computation. We instantiate representative methods for three OPD settings -- cross-tokenizer OPD, on-policy self-distillation, and step-wise OPD. Experiments on reasoning, code-generation, scientific-knowledge, and tool-use benchmarks show that these implementations can be executed through the same verl-based backend while retaining their method-specific objectives and task-dependent performance profiles. We release \textsc{EasyOPD} with runnable YAML configurations, documentation, and an installable demonstration package and video.

cs.CL

版本更新 · v4arXiv:2609.23697

Distill What You Trust: Reliability-Aware Multi-Teacher On-Policy Distillation

Jie Sun, Mao Zheng, Mingyang Song, Zeyuan Liu, Gengsheng Li, Houcheng Jiang, Yilin Cheng, Bichuan Feng 等 11 位作者

原文摘要

Multi-teacher on-policy distillation allows a student to learn from complementary specialists on its own trajectories. Domain-routed approaches, however, select one teacher per example and keep it fixed throughout the response. This design both depends on domain labels that mixed training corpora often lack and cannot adapt teacher selection when the expertise required changes within a trajectory. We observe that each specialist deviates more from a shared reference on in-domain prompts than on out-of-domain prompts, on average. Based on this observation, we propose \textbf{TrustMOPD}, which replaces example-level teacher selection with label-free, token-level supervision allocation. At each student-generated prefix, TrustMOPD measures this displacement in next-token preferences, calibrates its magnitude across teachers, and uses the resulting scores as proxies for local reliability to weight teacher-specific distillation losses. Evaluated across mathematics, code, and instruction following, TrustMOPD closes 91.5\% and 98.0\% of the overall-score gap between the initial student and oracle-routed teachers when trained on \textsc{SingleCap} and \textsc{MultiCap}, respectively, compared with 54.4\% and 54.5\% for the strongest label-free baseline in each setting. On \textsc{SingleCap}, it approaches label-based MOPD without using domain labels. Our code is available at https://github.com/sunjie279/TrustMOPD-.

cs.CL · cs.LG

版本更新 · v2arXiv:2611.20349

Words Speak Louder? Exploring the Language Shortcut of LLM-Driven Incomplete Multimodal Learning

Qiangchang Wang, Chong Xiao, Xiaokun Bai, Rundong He, Zhuang Qi, Xusheng Liang, Zhibin Wu, Wenhao Li

原文摘要

Is a face or a voice still heard once the words are known? Incomplete multimodal learning increasingly uses large language models (LLMs) as fusion engines: modality features enter as token blocks and missing modalities become placeholders. We find that LLM-driven fusion can override non-verbal evidence it can read. Contrasting its full-input prediction with counterfactual views, the same model shown one modality or no content, we identify language shortcuts. We build MR-Bench: MR-Bench-A types every test sample of four sentiment benchmarks; MR-Bench-H contains 900 human-validated clips (620 language-shortcut, LS; 280 non-verbal-shortcut, NS) from seven sources, and every model is scored on all of them. Zero-shot MLLMs solve at most 32.7% of the LS clips; adding the transcript to the muted video lowers vision-language accuracy by 46.1-53.1 points. Yet inverting a text-only model's answers solves 94.4%, so LS accuracy alone cannot establish use of non-verbal evidence. Inside the fusion LLM, fused states align increasingly with the text view late in the decoder. Counterfactual-View Reliability learning (CoVeR) trains views as unimodal judges and withholds fused supervision where they disagree. It achieves state-of-the-art results on five benchmarks without extra inference cost in accuracy mode. On MR-Bench-H, it reaches 61.7% LS and 93.6% NS accuracy; robust mode raises LS accuracy to 63.0% while lowering NS accuracy to 84.8%. Among LS clips solved without text, adding text causes errors on 30.1% with CoVeR versus 32.2% with LLM-Fusion. Project page: https://peacelwh.github.io/CoVeR/.

cs.CV · cs.MM

版本更新 · v2arXiv:2610.36210

Diagnosing and Correcting Bias in MLLM for Long Video Understanding

Xusheng Liang, Jianqiao Sun, Hao Zhang, Yulei Niu, Hengshuang Zhao, Jiawei Ma

原文摘要

Long-video question answering is challenging since the answer often hinges on a few decisive moments scattered throughout the video, while memory constraints force Multimodal Large Language Models (MLLMs) to sample frames at extremely low rates, resulting in sparsity that risks omitting key evidence. Though aggressively enlarging the context size is intuitive, we argue that performance remains fundamentally constrained by the bias, i.e., the misleading cues caused by spurious linguistic correlations and salient yet irrelevant visual observations. In this paper, we first introduce S-MME, a benchmark designed to systematically diagnose shortcut-biased behavior in MLLMs. To mitigate this failure, we further propose a training-free framework, Counterfactual Long-video Evidence-Aware Reasoning (CLEAR). By treating the full video-question pair as a complete view, CLEAR estimates bias effects via augmented views by only keeping the question or locally salient visual clips. Then, we intervene hidden states to mitigate the discrepancy at inference such that the correct answer can be predicted confidently. With experimental studies across five benchmarks, we show that our method is generalizable and can be integrated in different MLLMs, yielding consistent gains in prediction and robustness. We hope CLEAR can offer a complementary direction in test-time scaling for long-video understanding.

cs.CV

新论文 · v1arXiv:2611.22652

OmniTongue: A Comprehensive MLLM Benchmark for Automated Tongue Diagnosis in Traditional Chinese Medicine

Liuyi Xu, Yun Guo, Shusheng Li, Xuewen Zhang, Yining Qian, An-Yang Lu

原文摘要

Multimodal Large Language Models (MLLMs) have excelled in Western medical imaging, yet their potential in Traditional Chinese Medicine (TCM) tongue diagnosis remains systematically unevaluated. Tongue diagnosis requires sophisticated global and local perception, serving as a rigorous touchstone for assessing the visual understanding depth of MLLMs. However, existing datasets are limited by single dimensions, coarse granularity, and ambiguous labels, hindering the evaluation of authentic clinical capabilities. To bridge this gap, we introduce OmniTongue, the first comprehensive, fine-grained Visual Question Answering benchmark for TCM tongue diagnosis. This benchmark integrates 1,351 expert-validated images and 21,616 instruction pairs. Its core design features 16 clinical dimensions for multidimensional evaluation, region-specific annotations for pathological localization, and 66 fine-grained labels for precise diagnostic representation. Extensive evaluations of existing MLLMs reveal significant performance gaps, demonstrating that medical-specific models lack domain advantages, while universally poor Macro-F1 scores expose a reliance on statistical shortcuts rather than genuine understanding of tongue pathology. These findings not only highlight the current limitations of MLLMs in interpreting regional medical features but also underscore OmniTongue's significance for developing robust automated tongue diagnosis models. The code and dataset will be made publicly available in a future release.

cs.CV

版本更新 · v2arXiv:2508.16569

A Disease-Centric Vision-Language Foundation Model for Precision Oncology in Kidney Cancer

Yuhui Tao, Zhongwei Zhao, Zilong Wang, Xufang Luo, Feng Chen, Kang Wang, Chuanfu Wu, Xue Zhang 等 20 位作者

原文摘要

The non-invasive assessment of renal masses remains a critical challenge in urologic oncology, where diagnostic uncertainty frequently causes overtreatment. Here, we develop RenalCLIP, a vision-language foundation model for precision oncology in kidney cancer. Utilizing 27,866 computed tomography scans from 8,809 patients across diverse multi-center cohorts, we employ a two-stage pre-training strategy to align domain-specific visual and textual representations. RenalCLIP achieves enhanced performance and generalizability across ten core clinical tasks, spanning anatomical assessment, diagnostic classification, and survival prediction, significantly outperforming state-of-the-art general-purpose foundation models. Furthermore, RenalCLIP demonstrates strong data efficiency in diagnostic classification, achieving peak baseline performance using only 20% of the training data. The model also exhibits robust zero-shot diagnostic capabilities, effective image-text retrieval, and high-quality medical report generation. Our findings establish RenalCLIP as a powerful, generalizable tool to enhance diagnostic precision, refine prognostic stratification, and personalize the management of renal masses.

eess.IV · cs.AI · cs.CV

新论文 · v1arXiv:2611.20771

Nemotron 3.5 Bolt E4B 4GB: An Open and Efficient Small Language Model for Fast Conversational Agents

NVIDIA, :, Adi Margolin, Aditya Malte, Aishwarya Chhabra, Alex Hodson, Ameya Sunil Mahabaleshwarkar, Ambrish Dantrey 等 113 位作者

原文摘要

We introduce Nemotron 3.5 Bolt E4B 4GB, an open and efficient small language model further post-trained from Gemma-4-E4B-it and optimized for speed and intelligence per GB of memory used for fast conversational agents. The model carries forward Gemma's strong conversational capabilities and further improves multi-turn tool use, instruction following, and input grounding for fast, local voice/device assistants, interactive personas, and embedded/Edge interfaces. The model combines natural conversation with multi-turn agentic capabilities to power voice/device assistants, interactive characters and robotic/IoT interfaces running on GeForce RTX, Jetson, and RTX/DGX Spark. Experiments on 21 benchmarks show that Nemotron 3.5 Bolt E4B 4GB achieves the highest average accuracy while generating the fewest output tokens in both reasoning and non-reasoning modes, compared with Gemma-4-E4B-it and Qwen3.5-4B. The model is released with a DFlash drafter. With DFlash, Bolt E4B achieves $2.74\times$ the per-user decode speed of inference without speculative decoding at concurrency~1, and $1.21\times$ the generation throughput of Gemma-4-E4B-it with MTP at batch size 1.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.20524

GaugeRoPE: RoPE-Compatible Executable Latent Attention

Yuanhang Gao, Xiangrui Yang, Lingyuan Meng, Yuanfeng Chen, Dongsheng Li

原文摘要

Latent KV cache compression reduces memory footprint by mapping historical keys and values into compact representations. However, generic compressed key states require reconstruction to native dimension before applying RoPE and computing attention scores, adding sequence-scaling overhead to the decode path. We characterize when a latent KV representation can serve directly as the execution state of pretrained RoPE. For RoPE-based transformers, exact static linear execution of the rotary key path requires the latent-to-native map to preserve the pretrained RoPE action through an intertwining relation, restricting exact mixing to coordinates that share the same RoPE frequency. Guided by this characterization, we build GaugeRoPE, a training-free executable latent KV representation. It combines a RoPE-compatible carrier that preserves the rotary action with an approximate position-independent residual key--value (RKV) correction for complementary key and value information, both evaluated without per-token dense historical K/V reconstruction. On Mistral-7B, GaugeRoPE achieves $5.85\times$ KV compression while maintaining quality close to the full-cache baseline. Additional MHA results validate the construction beyond GQA. GaugeRoPE achieves up to $2.48\times$ the decode throughput of the vanilla uncompressed baseline through direct latent execution.

cs.LG · cs.CL

版本更新 · v4arXiv:2610.21390

PriorityFEC: Deadline-Aware Streaming FEC for KV-Cache Handoff in Edge Multi-Agent Systems

Han Shen, Qifu Tyler Sun, Fanyang Meng, Ye Wang, Yongsheng Liang

原文摘要

Collaborative edge large language model (LLM) systems often require repeated prefill computation when task contexts are transferred between agents. Reusing previously computed key--value (KV) caches can eliminate this overhead, but requires KV-cache delivery before the receiving agent begins decoding. Under strict deadlines and unreliable edge links, complete KV cache transfer may be infeasible, making the timely delivery of useful KV information critical. This paper proposes PriorityFEC, a utility-aware KV-cache handoff scheme that combines prioritized source transmission with adaptive loss recovery. PriorityFEC first organizes KV blocks into a utility-aware source queue to prioritize important information. It then employs ACK-sliding Streaming FEC and a lightweight Double Deep Q-Network (Double-DQN) scheduler to dynamically balance source delivery and repair transmission under deadline constraints. We implement PriorityFEC in a distributed edge LLM-serving prototype and evaluate it using Qwen2.5-7B-Instruct and Llama-3.1-8B-Instruct across multiple workloads. Experimental results demonstrate that PriorityFEC preserves more useful KV information and achieves substantially higher task accuracy than competing transport schemes, particularly when the deadline is insufficient to deliver the complete KV cache.

cs.NI · cs.AI

新论文 · v1arXiv:2611.19976

CreaTrace: Video Creative Plagiarism Detection and Evidence Tracing

Chang Liu, Sheng Li, Zhenxing Qian, Xinpeng Zhang

原文摘要

Video creative plagiarism refers to the unauthorized reproduction of creative ideas across videos despite substantial differences in visual appearance, posing a new challenge to video copyright protection. However, existing video copy detection methods primarily focus on visual content similarity, struggling to capture abstract creative that are entangled with specific visual realizations. To address this issue, we introduce a novel task, named Video Creative Plagiarism Detection (VCPD), and propose an iterative creative evidence tracing framework, termed CreaTrace, to verify creative similarity and accurately localize the corresponding evidence segments. Specifically, we design a Multimodal Semantic Event Segmentation strategy to divide similar long videos into coherent narrative events, facilitating event-level dataset construction and retrieving similar segments. Based on these events, CreaTrace employs Coarse Creative Matching to identify candidate event pairs through narrative semantics and camera language. Then CreaTrace presents Creative Decoupling to disentangle abstract creative patterns from specific visual realizations. Meanwhile, Creative Swap Contrastive Learning is devised to enhance creative consistency through cross-realization feature swapping. Benefiting from the above designs, our CreaTrace enables accurate creative similarity detection and temporal localization, while providing interpretable evidence report. Extensive experiments demonstrate the effectiveness and robustness of CreaTrace across diverse creative plagiarism scenarios.

cs.CV · cs.AI

版本更新 · v2arXiv:2611.17048

Beyond Answering: Learning to Speak First and Act in Streaming Video

Shuhan Li, Huankang Guan, Xintong Guo, Yang Bo, Yuyang He, Dunyuan Xu, Jingyan Chen, Fang Liu 等 18 位作者

原文摘要

Most AI assistants respond only when prompted, remaining silent even when events in the video stream offer meaningful opportunities for conversation. To move beyond purely user-driven interaction, we present AURA 2.0, a streaming video large language model that introduces three core upgrades to AURA. The key advance is Model-Initiated Conversation (MIC), which enables the model to identify topics worth discussing in the evolving visual stream and initiate conversations at appropriate moments without a user query. Stream-Aware Tool Calling (SATC) lets the model act on what it sees by invoking external tools using the current visual and conversational context and incorporating returned information into the ongoing interaction. Interactive Visual Grounding (IVG) supports visual grounding in both user inputs and model outputs. The model can identify objects marked by users on video frames and produce frame-aligned bounding boxes to link its responses to specific objects and regions. To develop these capabilities, we construct a dedicated streaming interaction dataset and adopt a three-stage training scheme to integrate the new behaviors with AURA's existing streaming interaction abilities. We further incorporate Long-Horizon Interaction Memory (LHIM) to maintain contextual continuity over extended video streams. Evaluations on public streaming benchmarks show that AURA 2.0 achieves leading performance among open-source streaming models, while targeted evaluations further validate its new interaction capabilities.

cs.CV · cs.AI

版本更新 · v2arXiv:2611.16265

Rectified Looped Transformer

Musheng Li, Jiawei Zhang, Ziyuan Liu, Yuantao Gu

原文摘要

Looped Transformers increase effective depth by repeatedly applying a shared block, offering a parameter-efficient approach to language modeling. However, most existing works directly reuse each loop's output as the next's input, which can lead to hidden-state scale growth and perturbation amplification as recurrence deepens. We propose Rectified Looped Transformer (RLT), which redesigns feedback between loops using an interpolation schedule inspired by flow-based modeling. At each loop, RLT forms the next input by linearly interpolating between the current state and its prediction. Such interpolation distributes state changes across loops, encouraging a smoother trajectory from the initial input to the final output. Theoretical analysis proves that, under appropriate assumptions, RLT keeps state magnitudes uniformly bounded across loops and reduces the worst-case perturbation amplification. We evaluate RLT on language modeling corpora and downstream benchmarks. At matched training and inference depths, RLT consistently achieves lower perplexity than a standard looped Transformer, while exhibiting greater robustness to input perturbations and variance in inference depth. Consistent with the theoretical results, latent trajectory analysis shows that RLT maintains more stable hidden-state norms across loops, which also facilitates extrapolation-based decoding strategies. Notably, RLT achieves these gains without requiring additional trainable parameters or extra recurrent block evaluations, thus providing a simple yet more stable feedback mechanism for looped Transformers.

cs.LG · cs.AI

版本更新 · v3arXiv:2611.06700

PINR-ESI: Physics-Informed Self-Supervised Implicit Neural Representation Framework for EEG Extended-Source Imaging

Zhiyong Zhou, Sheng Liao, Xiaolin Li, Youshen Xiao, Bin Dai, Surui Liu, Yakang Dai

原文摘要

EEG extended-source imaging aims to localize active cortical regions and characterize their extent, yet supervised inverse networks typically depend on synthetic EEG-source pairs and may be sensitive to synthetic-to-real mismatch. We propose a physics-informed self-supervised implicit neural representation (INR) framework for spatial source reconstruction without paired source labels or simulation-based supervised pretraining. The lead-field matrix encodes the source-to-sensor volume-conduction model and constrains the INR through agreement between predicted and measured EEG. Cortical current density is represented as a continuous coordinate-based neural field. Forward EEG prediction samples the field at cortical vertices and applies local smoothing before lead-field mapping. A classical inverse estimate provides warm initialization and observation-specific spatial guidance through prior-guided support regularization. Simulations across varying SNRs, source extents, and source counts showed low spatial dispersion and good localization performance. Quantitative evaluation on clinical EEG recordings from epilepsy patients and qualitative analysis of scalp EEG during intracranial stimulation supported feasibility for real-world source imaging. These findings suggest the potential of physics-informed self-supervised INR for extended-source imaging.

cs.LG · q-bio.NC

新论文 · v1arXiv:2611.17784

Direction or Magnitude? Learning Scalars over Task-Calibrated Directions

Ziqing Wen, Xiaohui Song, Jiahuan Wang, Ping Luo, Junlin Zeng, Dongsheng Li, Kele Xu, Tao Sun

原文摘要

Parameter-efficient fine-tuning (PEFT) aims to preserve adaptation quality while reducing training costs. We propose SCALAR, which achieves performance comparable to LoRA with substantially fewer trainable parameters, lower peak training memory, and higher throughput. SCALAR constructs a fixed input basis from task activations and assigns a random output dictionary to each input direction. Fine-tuning learns only layer-specific scalar coefficients, reducing gradient and optimizer-state storage. Grouped computation aggregates output atoms before applying the adapter to token activations, while dictionary sharing across compatible layers reduces fixed-basis storage. Experiments on commonsense reasoning, mathematical reasoning, code generation, and knowledge evaluation after instruction tuning demonstrate effective adaptation at small trainable budgets. On commonsense reasoning, SCALAR achieves accuracy comparable to LoRA with about 4% of its trainable parameters. System measurements on Qwen2.5-7B show 20% lower peak training memory and 6% higher throughput than LoRA. The combination of adaptation quality, a compact trainable state, and training efficiency makes SCALAR a promising approach to resource-constrained fine-tuning.

cs.LG

新论文 · v1arXiv:2611.17781

TReC: Evaluating Move-Induced State Changes in Instruction-Conditioned Go

Zhuangsheng Li, Yunhan Zhang, Dailin Li, Qingxian Yu, Yu Wu, Youqi Song, Bangyuan He

原文摘要

When a Go model predicts a move different from the expert's, coordinate distance measures how far the prediction lands from the reference. We introduce Transition Representation Consistency (TReC) to compare how the two moves change a board-state embedding. Both moves are executed from the same position under the game rules, and TReC is the cosine similarity between the two resulting representation changes. In experiments with a frozen KataGo network on 680 mid-to-late-game positions from five games, the gap between the highest and lowest candidate per position has a median of 0.01 to 0.08 for the direct successor-state cosine and 0.88 to 1.33 for TReC, depending on the evaluator layer. TReC follows coordinate distance only weakly: the rank correlation between a candidate's distance to the reference and its TReC, computed within each position, has a median of -0.19 over these positions.

cs.AI

新论文 · v1arXiv:2611.17163

UAV-Flow++:面向语言引导无人机飞行的统一基准与学习套件

UAV-Flow++: A Unified Suite for Benchmarking and Learning Language-Guided UAV Flight

Donglin Yang, Xiangyu Wang, Yantong Zhong, Wenhao Zheng, Zihan Ding, Yue Liao, Hongsheng Li, Ke Xu 等 9 位作者

AI 速读 基于摘要

作者提出 Flying-on-a-Word(Flow)短程语言引导无人机飞行任务,并配套真实与仿真数据集、仿真评测环境及 FlowVLA 学习框架。

cs.RO · cs.CV

查看原文摘要

Language-guided UAV navigation has largely focused on long-horizon route planning, leaving short-range, object-relative flight maneuvers underexplored. To address this gap, we formulate Flying-on-a-Word (Flow), a task requiring a UAV to convert concise natural-language instruction, egocentric visual observation, and current state dynamics into continuous flight actions. Flow encompasses both primitive motion commands and complex object-interactive behaviors, assessing motion intent comprehension and spatial context grounding. To enable policy learning and closed-loop evaluation, we introduce UAV-Flow, a comprehensive dataset comprising 30,692 expert-piloted real-world trajectories across eight distinct motion categories, alongside 10,109 simulation trajectories in the UAV-Flow-Sim environment equipped with task-specific completion criteria. Furthermore, we develop FlowVLA, which undergoes imitation pretraining on mixed real-sim demonstrations and online post-training via Tail-Aware GRPO (TGRPO). By leveraging group reward distributions, TGRPO effectively reinforces high-reward action sequences. Evaluated on 273 held-out UAV-Flow-Sim episodes, pretrained FlowVLA achieves a mean success rate of 75.58%, outperforming the strongest baseline by 6.72 percentage points, which TGRPO post-training further elevates to 93.16% with superior sample efficiency. Physical UAV experiments demonstrate robust execution of object-relative commands in both indoor and outdoor real-world scenes. Together, Flow establishes a novel benchmark and learning framework for language-conditioned flight maneuvers.

新论文 · v1arXiv:2611.16317

Wanda-Guided Sparse Perturbations for Efficient Zeroth-Order Optimization

Ziqing Wen, Xiaohui Song, Jiahuan Wang, Ping Luo, Junlin Zeng, Dongsheng Li, Tao Sun

原文摘要

Zeroth-order (ZO) optimization enables memory-efficient fine-tuning of large language models through forward-only evaluations, but high-dimensional random perturbations can limit optimization efficiency. Sparse perturbations reduce the search dimension, making the selection of informative coordinates critical. We propose Wanda-Importance Sparsity-MeZO (WIS-MeZO), which uses Wanda weight--activation saliency to construct task-conditioned sparse perturbation masks while keeping the pretrained model dense. We analyze support quality through gradient energy capture and relate it to gradient estimation and convergence. Across 16 benchmarks with LLaMA and Qwen models ranging from 3B to 32B parameters, WIS-MeZO achieves higher aggregate scores than MeZO and reaches comparable validation losses in fewer optimization steps. Comparisons with random and magnitude-based sparse perturbations further highlight the importance of informative support selection.

cs.LG · cs.AI

新论文 · v1arXiv:2611.14953

RSLiveBench-UAV: A Continually Evolving Vision-Language Benchmark for Aerial Spatial Intelligence

Yue Zhou, Jiawei Liu, Jue Chen, Ziyang Gong, Haojia Wei, Jingxiang Li, Xue Jiang, Zhihang Zhong 等 12 位作者

原文摘要

Aerial spatial intelligence (ASI) requires models to understand objects and spatial relationships across changing viewpoints and scales. Evaluating these abilities as models evolve calls for fresh physical observations, yet producing new aerial spatial questions requires repeatedly establishing entity identities, geometric references, and cross-view correspondences. We introduce \textbf{RSLiveBench-UAV}, a continually evolving vision-language benchmark driven by recurring acquisition of real UAV imagery. Its update protocol admits images captured after the preceding release and delays answer disclosure. An entity-centered production workflow uses geometry-assisted association to link repeated observations of physical vehicles, reuse human-verified attributes, and combine them with view-specific annotations and spatial references for traceable question generation. All tasks use deterministic scoring without model judges. We evaluate 30 general-purpose, remote-sensing, and embodied models on 35,491 question records from ten scenes, covering 17 tasks across 2D perception, 3D perception, cross-view perception, and reasoning. All 18 tested embodied models outperform the three selected remote-sensing comparators in Overall, although the strongest embodied model scores 43.29 versus 59.88 for GPT-6-Astra. Fine-grained vehicle recognition remains challenging, and performance varies across heights and camera pitches. Retrospective scene-group comparisons and rolling-window replay characterize score-pattern consistency under scene renewal. RSLiveBench-UAV connects fresh physical observations, entity-centered answer production, and systematic model evaluation to support continual assessment of ASI. Benchmark will release at https://rslivebench.space

cs.CV

版本更新 · v2arXiv:2603.01478

Contract-Theoretic Semantic Abstraction for Covert Communication in LAENets

Yansheng Liu, Jinbo Wen, Kun Zhu, Hui Li, Yang Zhang, Jiawen Kang

原文摘要

In Low-Altitude Economy Networks (LAENets), Unmanned Aerial Vehicles (UAVs) transmit task-related information to the Base Station (BS) under stringent low-probability-of-detection constraints. These constraints limit transmission resources, hindering reliable information delivery through conventional bit-level communication. Semantic Communication (SemCom) addresses this challenge by prioritizing task-relevant information over bit-level accuracy. However, semantic abstraction must balance information loss and redundancy to preserve task reliability and transmission efficiency. Moreover, the BS cannot directly observe or reliably verify UAVs' semantic processing capabilities and abstraction-dependent transmission costs, leading to information asymmetry. We propose an incentive-aware semantic abstraction framework for covert communications in LAENets. Specifically, we adjust UAV-side semantic abstraction levels to provide differentiated covert semantic services under fixed-dimensional transmission payloads. To address information asymmetry, we develop a contract-theoretic model and adopt Prospect Theory (PT) to capture risk-sensitive semantic abstraction decisions under uncertainty. We further design a Regularized Diffusion-based Soft Actor-Critic (RDSAC) algorithm for optimal contract design under PT, incorporating diffusion entropy and action entropy regularization. Numerical results validate the proposed framework and show that RDSAC improves average rewards by 6.77% over SAC and 31.78% over proximal policy optimization.

cs.NI

版本更新 · v2arXiv:2610.23966

自适应人工智能实现可泛化的胎儿脑生物测量

Generalizable fetal brain biometry via adaptive artificial intelligence

Yijin Li, Mingxuan Liu, Yi Liao, Le Chang, Hongjia Yang, Kasidit Anmahapong, Xiaotian Hu, Ziang Wang 等 27 位作者

AI 速读 基于摘要

提出解剖引导的测试时自适应框架 BioTTA,从三维胎儿脑 MRI 自动测量 11 项生物指标,并在多中心异质数据上提升测量精度与异常检测能力。

cs.CV

查看原文摘要

Fetal brain biometry provides a quantitative basis for assessing prenatal growth and identifying congenital brain abnormalities. However, comprehensive assessment remains limited by labor-intensive manual measurements and automated models that lose accuracy across imaging sequences and institutions. We introduce BioTTA, an anatomically guided test-time adaptation framework that measures 11 fetal brain biometrics from reconstructed three-dimensional magnetic resonance images. BioTTA adapts pretrained models to individual unlabeled volumes using geometric consistency and atlas priors, without access to source images. In a retrospective study across five centers in China and Switzerland, BioTTA improved measurement accuracy across three out-of-distribution datasets and two network architectures. It reduced mean absolute measurement errors by 46-82% relative to the corresponding models without adaptation, achieving errors similar to those of supervised fine-tuning. Its measurements were mapped onto normative growth trajectories derived from expert annotations, enabling gestational-age-specific assessment through a web-based reporting platform. Across four disease cohorts, the platform achieved 82.1-95.0% accuracy in binary detection of ventriculomegaly or cerebellar abnormalities, with performance similar to that of a senior radiologist. BioTTA provides a practical foundation for standardized fetal brain biometry across heterogeneous imaging settings, supporting scalable prenatal growth assessment and quantitative evaluation of brain abnormalities.

版本更新 · v4arXiv:2606.24548

Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning

Jiayi Lei, Yuandong Pu, Xingyu Han, Rongpeng Zhu, Jing Xu, Jinyao Wang, Zijian Zhou, Bin Fu 等 11 位作者

原文摘要

Text-to-image (T2I) generation models have achieved remarkable progress in producing visually realistic images from natural language prompts. Yet it remains unclear whether their success reflects genuine causal understanding or sophisticated pattern matching over visual-textual correlations. Inspired by Russell's inductivist turkey, we introduce Counterfactual-World (CF-World), a counterfactual benchmark designed to investigate whether text-to-image models can generate images under rules that systematically contradict real-world priors. CF-World organizes each scenario into three progressive levels: factual generation under ordinary world knowledge, explicit counterfactual generation with direct visual instructions, and implicit counterfactual generation requiring causal deduction from altered rules. We evaluate open-source and closed-source text-to-image models using CF-Eval, a scoring pipeline based on vision-language models. We report the scores at each prompt level as the primary results and use Prior Resistance Rate (PRR) and Reasoning Retention Rate (RRR) as auxiliary descriptive indicators. All evaluated models score lower on counterfactual prompts than on factual prompts. Diagnostic experiments reveal difficulties in following altered rules and recombining rarely co-occurring visual attributes. The gains from rephrasing object and attribute names are consistent with a role for learned visual priors in counterfactual generation. Our benchmark and evaluation code are publicly available at https://jylei16.github.io/CF-World.github.io/.

cs.CV

版本更新 · v2arXiv:2605.07396

Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis

Zhepei Hong, Yukai Wang, Mao Zheng, Mingyang Song, Gengsheng Li, Houcheng Jiang, Dan Zhang, Haiyun Guo 等 10 位作者

原文摘要

On-policy distillation (OPD) is a powerful paradigm for LLM post-training, yet its reliance on teacher logits restricts it to white-box teachers. In this paper, we study whether rubric-based supervision can provide a text-only feedback interface for black-box OPD, and what makes it effective. Our instantiation, Rubric-based On-Policy Distillation (ROPD), induces rubrics by contrasting teacher responses with the student's current rollouts and uses them to score these rollouts for on-policy optimization. We find that, under matched settings, text-only ROPD outperforms logit-based OPD methods on four competition-math benchmarks, reaching the best AIME24 accuracy of standard logit-based OPD with 9.6x fewer training samples. Our analysis yields three findings: rubric rewards track correctness far better than teacher log-likelihood (AUC 0.90 vs. 0.35); training with them repairs more failed criteria and regresses fewer passed ones than logit-based supervision; and contrasting teacher responses with student rollouts is central to rubric quality. These results position rubric-based OPD as a flexible, black-box-compatible alternative to logit-based OPD. Our implementation is available at https://github.com/Peregrine123/ROPD_official.

cs.LG · cs.AI

新论文 · v1arXiv:2611.12791

大语言模型作为开放世界自动化机器学习的通用搜索器

Large Language Models as a Universal Searcher for Open-World Automated Machine Learning

Yuxuan Hu, Jihao Liu, Weikang Shi, Xijie Huang, Linda Wei, Mingjie Zhan, Aojun Zhou, Rui Liu 等 9 位作者

AI 速读 基于摘要

作者提出基于大语言模型的通用AutoML框架,用统一数值编码NCode将架构、超参数与数据配比联合优化重构为排序任务,并在多任务上报告了跨域泛化与可扩展性结果。

cs.CL

查看原文摘要

Developing effective machine learning models requires complex manual tuning, while current Automated Machine Learning (AutoML) frameworks remain domain-specific and isolate model architecture, training hyperparameter, and data ratio optimization. Here, we bridge this gap by proposing a universal, large language model (LLM)-based AutoML framework that jointly optimizes these configurations for the first time without the need for task-specific fine-tuning. We propose NCode, a unified numerical encoding scheme that translates diverse AutoML design choices into universal discrete sequences and effectively reframes the optimization process as a unified ranking task. Trained solely on optimization trajectories derived from a limited, single-domain vision task, the proposed LLM-based searcher demonstrates impressive cross-task, cross-modality and joint search-space optimization generalizability, achieving state-of-the-art performance across image classification, image segmentation, speaker verification and text-to-image benchmarks. Crucially, it exhibits superior scalability in the large-scale training and joint optimization of a billion-parameter Diffusion Transformer, requiring 896 GPU-days and attaining a state-of-the-art GenEval score of 0.91. By leveraging reinforcement learning to instill Chain-of-Thought reasoning, we provide a systematic way to interpret the LLM-based searcher's internal decision-making mechanisms, revealing its optimization strategy shifted from the early-stage diversity-driven exploration to the late-stage anchor exploitation. Our proposed framework provides a scalable, generalizable, and interpretable pathway toward general-purpose open-world machine learning optimization.

版本更新 · v3arXiv:2606.15912

On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents

Gengsheng Li, Mao Zheng, Mingyang Song, Ruiqi Liu, Tianyu Yang, Jie Sun, Qiyong Zhong, Haiyun Guo 等 11 位作者

原文摘要

Multi-turn agents that plan, invoke tools, and interact with environments offer a promising paradigm for solving complex tasks, yet their capabilities typically rely on very large models whose inference cost is prohibitive in practice. On-Policy Distillation (OPD) is a natural recipe for transferring such capabilities to smaller students, but we find that it suffers a characteristic failure mode in this setting: small student errors compound across turns and push the trajectory out of the teacher's familiar state distribution, so the teacher's supervision becomes least reliable precisely where the student needs it most. We propose Guided On-Policy Distillation (Guided-OPD), a simple yet effective algorithm that mixes teacher- and student-generated turns within each rollout and schedules the teacher's intervention probability along a curriculum that decays to zero. Strong guidance keeps early trajectories close to the teacher distribution and is then gradually withdrawn to recover the purely on-policy regime used at inference. On ALFWorld, ScienceWorld, and WebShop, distilling Qwen3 students from a Qwen3-30B-A3B teacher, Guided-OPD yields average relative gains of 21.1\% in Score and 25.5\% in Success Rate over vanilla OPD, with larger gains on smaller students.

cs.LG · cs.AI

新论文 · v1arXiv:2611.12057

AscendMOEA: An Ascend NPU-Accelerated Platform for Tensorized Multi-Objective Evolutionary Algorithms

Qianlong Dang, Zhiyang Zhang, Baosheng Li, Tianqing Zhu, Junhu Ruan

原文摘要

Multi-objective evolutionary optimization increasingly involves large populations, expensive problem evaluations, and diverse algorithmic structures. These workloads expose the limited parallelism of loop-based implementations, while rewrites for accelerator execution can alter selection order, tie handling, and population updates. AscendMOEA is presented as a scalable platform that executes multi-objective evolutionary algorithms (MOEAs) on Huawei Ascend neural processing units (NPUs) and conventional central processing units (CPUs). The platform represents the decision vectors, objectives, constraints, and auxiliary states as tensors and provides reusable interfaces for algorithms, problems, population operators, quality indicators, monitoring, and repeated experiments. Dense computations are executed in batches, such as dominance, distance, variation, and problem-evaluation calculations. Short recurrences with causal dependencies retain their prescribed order and consume precomputed tensor results, which preserves the behavior of the original algorithms. AscendMOEA contains 18 algorithms, 155 benchmark and application problems, 19 public operator interfaces, and 11 quality indicators. Experiments on eight Ascend NPUs and 192 physical CPU cores evaluate operator throughput, end-to-end runtime, memory consumption, numerical agreement, and implementation ablation. Tensorized operators obtain a median acceleration of 1.58 times on the NPU. At large population scales, complete algorithms achieve a median acceleration of 5.76 times while retaining the recorded quality indicators. Moreover, the results identify the workload scale and ordered computation that determine whether accelerator execution is beneficial. AscendMOEA is open-sourced at https://github.com/dqlme/AscendMOEA.

cs.NE

新论文 · v1arXiv:2611.11792

APO2CS: Advantage-Aware Preference Optimization for Two-Level Constructive Search in Combinatorial Optimization

Kaixi Yang, Linbo Qiao, Wei Shang, Yanqi Shi, Dongsheng Li

原文摘要

Preference optimization has emerged as a promising alternative to reward-based training for neural combinatorial optimization. However, existing methods typically rely on binary pairwise labels, which discard the magnitude of solution-quality differences and provide supervision only at the complete-solution level. We propose Advantage-aware Preference Optimization for Two-level Constructive Search (APO2CS), a preference-based training objective for constructive neural solvers that integrates both macro-level and micro-level supervision. At the macro level, APO2CS enriches pairwise preferences with an advantage term derived from objective-value differences. At the micro level, it compares partial trajectories, thereby providing denser supervision throughout the sequential construction process. The resulting objective can be used either to train a policy from scratch or to fine-tune a pretrained one. Experimental results show that APO2CS improves the expressiveness and search capability of preference learning for combinatorial optimization, while demonstrating strong effectiveness and adaptability across multiple combinatorial optimization tasks.

cs.LG

新论文 · v1arXiv:2611.11355

Attacking Slide Puzzle CAPTCHAs Based on Time and Space Generative Adversarial Networks

Rui Guo, Xuelian Xie, Botao Xu, Kesheng Liu, Wenxian Wang, Haizhou Wang

原文摘要

CAPTCHAs can protect websites from malicious attacks. As a typical representative of behavior CAPTCHAs, slide puzzle CAPTCHAs have become increasingly popular in recent years due to their user-friendliness and high security. Previous attack methods on slide puzzle CAPTCHA mainly face challenges in the following four aspects. (1) The defense mechanisms of previous slide puzzle CAPTCHAs were relatively simple. The current slide puzzle CAPTCHAs have added complex interferences, detected slide trajectory features in the two-dimensional space, and added other defense mechanisms. (2) The previous notch detection methods were difficult to accurately locate the notch positions. (3) Previous attack trajectories were limited to the horizontal dimension, making them impossible to pass the existing detection. (4) The previous attack trajectories were generated by fitting functions, which were relatively simple and could not well simulate the slide characteristics of human users. In response to the above challenges, firstly, we systematically analyze the defense strategies of six most popular slide puzzle CAPTCHAs: Capy, Dingxiang, Geetest, Kyger, Shumei and Tencent. Secondly, for each type of CAPTCHA, we construct a notch detection dataset and a slide trajectory dataset separately. Thirdly, we use advanced YOLOv11 to detect the notch positions and train generative adversarial networks (GAN) to generate attack trajectories. As far as we know, we are the first to generate attack trajectories by directly learning human slide trajectory characteristic. According to the experimental results, this method cracked six most popular slide puzzle CAPTCHAs with success rates of over 90\%, and the attack time is only about 5 seconds, indicating that the security of existing slide puzzle CAPTCHAs is facing challenge. At the same time, we propose various methods to enhance the security of slide puzzle CAPTCHAs.

cs.CR

新论文 · v1arXiv:2611.10811

STAR-VF: Spatio-Temporal Aware Representation Condensation for Data-Efficient Video Fusion

Yuchen Xian, Yunqiu Xu, Guosheng Lin, Yang He

原文摘要

Video fusion aims to integrate complementary cues from heterogeneous sources, producing visually informative videos with coherent spatio-temporal structures. Jointly learning cross-modal complementarity and temporal dependencies typically relies on large-scale, high-quality video datasets, whose storage and repeated use during optimization incur substantial costs, making data-efficient learning highly desirable. To address this challenge, we rethink video fusion from the perspective of dataset condensation and propose STAR-VF, the first framework that condenses spatio-temporal representations for data-efficient video fusion. STAR-VF condenses the original training set into a compact set of learnable spatio-temporal representations, which are decoded into synthetic video clips and optimized using feature-level supervision provided by a frozen proxy model. The resulting condensed data preserves fusion-relevant spatial and temporal cues without requiring ground-truth fused videos as supervision. To adapt fusion learning to condensed representations, we equip the final fusion model with flow-free inter-frame temporal modeling and query-driven intra-frame aggregation, enabling direct temporal interaction and adaptive selection of fusion-relevant information in representation space. Extensive experiments on infrared-visible, multi-exposure, multi-focus, and medical video fusion benchmarks demonstrate that STAR-VF, trained with only approximately 1/16 of the original temporal training set, achieves fusion quality comparable to methods trained on the full data. Further analyses validate the contributions of learned condensation and flow-free temporal modeling, and demonstrate the robustness of the condensed supervision across different proxy encoders and downstream fusion models. Project page: https://zju-xyc.github.io/STAR-VF-Project-Page/.

cs.CV

版本更新 · v2arXiv:2605.08354

Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria

Juanxi Tian, Fengyuan Liu, Jiaming Han, Yilei Jiang, Yongliang Wu, Yesheng Liu, Haodong Li, Furong Xu 等 9 位作者

原文摘要

Aligning multimodal generative models with human preferences demands reward signals that respect the compositional, multi-dimensional structure of human judgment. Prevailing RLHF approaches reduce this structure to scalar or pairwise labels, collapsing nuanced preferences into opaque parametric proxies and exposing vulnerabilities to reward hacking. While recent Rubrics-as-Reward (RaR) methods attempt to recover this structure through explicit criteria, generating rubrics that are simultaneously reliable, scalable, and data-efficient remains an open problem. We introduce Auto-Rubric as Reward (ARR), a framework that reframes reward modeling from implicit weight optimization to explicit, criteria-based decomposition. Before any pairwise comparison, ARR externalizes a VLM's internalized preference knowledge as prompt-specific rubrics, translating holistic intent into independently verifiable quality dimensions. This conversion of implicit preference structure into inspectable, interpretable constraints substantially suppresses evaluation biases including positional bias, enabling both zero-shot deployment and few-shot conditioning on minimal supervision. To extend these gains into generative training, we propose Rubric Policy Optimization (RPO), which distills ARR's structured multi-dimensional evaluation into a robust binary reward, replacing opaque scalar regression with rubric-conditioned preference decisions that stabilize policy gradients. On text-to-image generation and image editing benchmarks, ARR-RPO outperforms pairwise reward models and VLM judges, demonstrating that explicitly externalizing implicit preference knowledge into structured rubrics achieves more reliable, data-efficient multimodal alignment, revealing that the bottleneck is the absence of a factorized interface, not a deficit of knowledge.

cs.AI