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

+816新增论文
+642其中 AI 相关
+95已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 13:32 — 2026-11-21 13:32(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 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 24,181 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
版本更新 · v2arXiv:2608.01802

CoNav-UAV: Cooperative Dual-Altitude Aerial Navigation via Stackelberg Learning

Junru Song, Wenhao Zhang, Yang Yang, Xuekai Qiu, Feifei Wang, Weien Zhou, Tingsong Jiang, Ying Wen 等 10 位作者

原文摘要

Aerial search missions often require an unmanned aerial vehicle (UAV) to locate a target from only a brief description of its appearance and surroundings, a task known as target-oriented aerial vision-and-language navigation (VLN). The task demands city-scale exploration and grounding as well as collision-free close-range approach, two interleaved processes that are difficult to reconcile within a single agent. Most existing methods adapt the ground VLN paradigm to a single UAV and rely on external assistance to compensate for its inefficiency. A recent attempt deploys two UAVs at complementary altitudes but still depends on privileged sensing and trains the two agents independently, precluding any mutual adaptation. We propose CoNav-UAV, which models the task as a Stackelberg game between a high-altitude leader and a low-altitude follower to capture their sequential decisions and asymmetric observations and utilities, with both agents using only onboard sensing. We introduce Iterative Stackelberg Learning, which tailors optimization to each agent's role: the leader's high-level vision-language reasoning builds on pretrained capabilities and is refined through memory-based in-context learning, while the follower's precise motion control is fine-tuned through DAgger-style expert distillation. Alternating the two updates lets each agent continually adapt to the other's evolving behavior. CoNav-UAV outperforms single- and dual-agent baselines across three high-fidelity urban scenes from the AerialVLN benchmark. It improves success rate by up to 30.8 points on the learning scene and by up to 9.0 points under cross-scene transfer, where the leader reuses its learned memory and the follower is adapted with 2.6-3.7 times less target-scene data. Extensive ablations confirm the contributions of key components and the benefit of mutual adaptation, with consistent gains across VLM backbones.

cs.AI · cs.RO

版本更新 · v4arXiv:2602.11776

MUSE: Multi-Tenant Model Serving With Seamless Model Updates

Cláudio Correia, Alberto E. A. Ferreira, Lucas Martins, Miguel P. Bento, Sofia Guerreiro, Ricardo Ribeiro Pereira, Ana Sofia Gomes, Jacopo Bono 等 10 位作者

原文摘要

In binary classification systems, decision thresholds translate model scores into actions. Choosing suitable thresholds relies on the specific distribution of the underlying model scores but also on the specific business decisions of each client using that model. However, retraining models inevitably shifts score distributions, invalidating existing thresholds. In multi-tenant Score-as-a-Service environments, where decision boundaries reside in client-managed infrastructure, this creates a severe bottleneck: recalibration requires coordinating threshold updates across hundreds of clients, consuming excessive human hours and leading to model stagnation. We introduce MUSE, a model serving framework that enables seamless model updates by decoupling model scores from client decision boundaries. Designed for multi-tenancy, MUSE optimizes infrastructure re-use by sharing models via dynamic intent-based routing, combined with a two-level score transformation that maps model outputs to a stable, reference distribution. Deployed at scale by Feedzai, MUSE processes over 4 thousand events per second, and over 55 billion events in the last 12 months, across several dozens of tenants, while maintaining high-availability and low-latency guarantees. By reducing model lead time from weeks to minutes, MUSE promotes model resilience against shifting attacks, saving millions of dollars in fraud losses and operational costs.

cs.LG · cs.DC

版本更新 · v2arXiv:2611.11139

Graphene: A Lightweight Transformer with Ising Mean-Field Refinement for Image Super-Resolution

Seungki Hong, Taekwang Jang

原文摘要

This paper proposes Graphene, a lightweight image super-resolution architecture with two complementary feature refinement mechanisms: Ising-model-inspired local feature refinement using an Ising Refinement Block (IRB) and stage-history-based feature refinement using a History Attention (HistAttn) module. The IRB reuses attention output features and pre-softmax attention logits to construct signed pairwise token couplings within each local window, applies unrolled mean-field updates, and refines features through a gated residual correction. These signed couplings allow alignment and opposition between latent spins to modulate local feature refinement. HistAttn attends over the current stage output and earlier representations at the same token position and adaptively blends the current stage output with a history-weighted feature aggregate without adding spatial pairwise attention. On Urban100 at $\times4$, Graphene and Graphene-light improve over IET and IET-light by 0.24 dB and 0.38 dB, respectively, with 34.3%/13.7% fewer parameters, 44.8%/44.4% fewer FLOPs, 83.9%/95.9% lower latency, and 63.7%/92.0% lower peak memory. Real-world SR comparisons further show that Graphene recovers fine details and preserves textures across diverse degradations. Code and reference checkpoints are available at https://github.com/skethz/Graphene

cs.CV

版本更新 · v3arXiv:2611.18179

Explanations that Transfer: Interpreting Medical Retrieval with Sparse AutoEncoders

Diane Bouchacourt, Gaëtan Brison

原文摘要

Medical AI systems that answer users' queries rely on retrieving medical knowledge from large document collections. In this context, finetuning general models on medical datasets can improve retrieval relevance. Yet the dense embeddings underlying modern retrieval systems remain largely opaque, making it difficult to understand the mechanics behind their results. Moreover, adapting to a specific medical dataset risks losing transferability to new clinical corpora. In this work, we tackle these issues by applying Sparse Autoencoders (SAEs) to medical information retrieval, transforming dense text embeddings into semantically interpretable representations. To do so, our model combines a reconstruction objective with an InfoNCE contrastive loss that directly preserves query-document relevance. We evaluate three embedding models across six medical retrieval datasets, both in-domain and out-of-domain. Trained on a medical corpus, our sparse codes improve in-domain retrieval over the original embeddings, and lose less out-of-domain performance than their dense counterparts, especially when the target corpus is distant from the training one. Importantly, our experiments show that the method yields interpretable features whose semantic content can be inferred from the queries and documents that activate them most strongly. The interpretation of these features sheds light on why a particular document was retrieved, and transfers beyond the training distribution.

cs.IR · cs.LG

新论文 · v1arXiv:2611.24258

Towards Vacuum-Assisted Robotic Needle Interventions: From Fluid Aspiration to Tissue Biopsy

Sheena Shabana, Laxmi Nag Laxminarayan Nagesh, Marta Vallejo, Karen Donaldson, Maria Koskinopoulou

原文摘要

Robotic ultrasound-guided needle interventions have primarily focused on target localization and accurate needle placement, while the subsequent acquisition of diagnostic material remains comparatively underexplored. Moreover, pleural fluid aspiration and tissue biopsy are typically addressed as separate procedures, despite sharing common requirements for ultrasound guidance, safe access, and sample transport. This work presents a unified robotic framework for ultrasound-guided fluid and tissue extraction using a single vacuum-assisted end effector. The proposed system combines force controlled ultrasound scanning, semantic target identification, automated needle deployment, and procedure specific material acquisition. A coaxial needle assembly and shared pump assisted pathway enable direct pleural fluid aspiration, while controlled cannula actuation provides the additional cutting action required for solid-tissue acquisition. End-to-end evaluation using a Franka Emika Panda robot over 50 phantom trials achieved successful extraction in 23/25 pleural fluid aspiration trials (92\%) and 22/25 tissue acquisition trials (88\%). Following successful tissue-target access, acquisition and transport were completed in all 22 trials.

cs.RO

版本更新 · v2arXiv:2603.29765

Training-Free Dynamic Upcycling of Expert Language Models

Eros Fanì, Oğuzhan Ersoy

原文摘要

Large Language Models (LLMs) have achieved remarkable performance on a wide range of specialized tasks, exhibiting strong problem-solving capabilities. However, training these models is prohibitively expensive, and they often lack domain-specific expertise because they rely on general knowledge datasets. Expertise finetuning can address this issue; however, it often leads to overspecialization, and developing a single multi-domain expert remains difficult due to diverging objectives. Furthermore, multitask training is challenging due to interference and catastrophic forgetting. Existing work proposes combining the expertise of dense models within a Mixture of Experts (MoE) architecture, although this approach still requires multitask finetuning. To address these issues, we introduce Dynamic Upcycling MoE (DUME), a novel approach that reuses dense experts trained on different domains to construct a unified MoE model. Our method builds a single multitask model that preserves the capabilities of the original dense experts without requiring additional training. DUME is both cost-efficient and scalable: by leveraging the closed-form solution of ridge regression, it eliminates the need for further optimization and enables experts to be added or removed dynamically. Our extensive experiments on different tasks (in causal language modeling and reasoning settings) with several model sizes (between 115M and 9B parameters) and architectures demonstrate that DUME consistently outperforms baseline approaches. In particular, in a reasoning setting, DUME can also surpass the dense expert model's performance in its domain, achieving 104% of the dense expert's performance on average. Finally, we also show that the DUME model can be fine-tuned to further improve performance in complex reasoning scenarios. Our code is available at: github.com/gensyn-ai/dume.

cs.LG · cs.CL

新论文 · v1arXiv:2611.24257

TRESS: A Fixed-Size History Representation for Irregular Time Series Forecasting

Shusen Ma, Yangchun Xie, Xudong Zuo, Haizhou Liang, Yun-Bo Zhao

原文摘要

A fixed number of recent observations may span minutes for one variable and days for another. Earlier measurements can still reveal whether the latest value is unusual for that variable. We propose TRESS (Timestamped Recent Events and Statistical Summaries), a forecasting model that retains the latest observations at their original times and summarises the full history of each variable. For a given set of variables and event budget, this representation stays the same size as the record grows. Its query-conditioned event lifting module weights deviations from the latest value according to the age of each observation and the forecast horizon. A channel-specific decoder combines the resulting features with historical statistics and a summary shared across variables to predict a correction to the latest value. Retaining 8 to 16 observations per variable, TRESS records the lowest mean test MSE and MAE among the methods compared on all four benchmarks. Serving 32 successive query times from one encoded history reduces CPU inference time by a factor of 2.12--2.60 across the four datasets. The code is at https://github.com/SSMa913/NICLab-TRESS.

cs.LG · stat.ML

版本更新 · v2arXiv:2611.15062

Probabilistic State Space Enumeration in Neural Network Computation

Victor O. K. Li, Yang Han, Jacqueline C. K. Lam

原文摘要

Many methods for pruning neural networks rank weights or groups of weights by importance and retain a single subset. We study how channel groups contribute jointly to the output of multilayer perceptrons (MLPs) in Transformer language models. Inspired by network reliability analysis, probabilistic state space enumeration (PSSE) represents the dense MLP output as the expected importance-corrected masked output over $2^G$ joint states of $G$ channel groups. Summing the most probable states' probability-weighted outputs gives an approximation whose absolute error is bounded by the omitted probability mass times the maximum masked-output norm. NORDER-II adapts ORDER-II to enumerate states in decreasing probability without sorting the full space. Its first $B$ states maximize the probability mass captured at that budget. A weight-entropy scorer fixes each layer's ordering from pretrained weights. We evaluate all 168 MLP layers across six models from the Llama, Gemma, and Qwen families on two datasets with 8, 16, and 32 channel groups. In all 1,008 comparisons, the 95%-mass prefix yields lower mean relative error than uniform sampling at the same state count, with or without bias correction. At all three group counts, it also yields lower median and 99th-percentile relative error than a single top-$k$ mask. For downstream inference, we use the number of distinct channels in each prefix to set pruned MLP widths. With one validation-selected group count per model, PSSE achieves lower perplexity than both top-$k$ pruning baselines in all 36 matched-FLOP settings. Our pruned decoder MLPs achieve mean speedups of $1.11\times$, $1.23\times$, and $1.36\times$ over dense MLPs at 10%, 20%, and 30% target MLP projection FLOP savings, respectively. PSSE offers a principled path toward both probability-mass-controlled approximation and more efficient inference in pretrained language models.

cs.LG

新论文 · v1arXiv:2611.24256

Spark-H3: Adaptive Block Sparse Attention for Video Diffusion Models

Zecheng Tang, Jiaye Fu, Youtian Lin, Xinyao Rao, Liuxuan Sun, Jian Zhang, Yao Yao, Wei Li

原文摘要

Long video sequences make attention a substantial cost in video diffusion models. Block sparse attention (BSA) reduces this cost by computing selected blocks exactly while compressing the remaining blocks. However, fixed token grouping can place tokens with dissimilar attention preferences in the same group, while uniform key averaging can underestimate the attention mass of compressed blocks. We introduce Spark-Attn, a training-free BSA method comprising Spark-Reblock and Spark-Reweight. Spark-Reblock recursively groups tokens by attention preference while preserving regular block shapes for efficient GPU execution. Spark-Reweight uses the global mean query as an anchor to construct attention-weighted key-value representations and logit biases for the compressed blocks, calibrating their attention mass. We instantiate Spark-Attn in MiniMax-H3 as Spark-H3. At 10% exact-block density, Spark-H3 delivers a 2.49$\times$ DiT speedup and reaches 24.81 dB PSNR against the corresponding dense outputs on MiniMax-H3 (20 denoising steps, 345 frames, 1344$\times$768). Increasing the density to 20% further improves PSNR to 26.76 dB while still achieving a 2.26$\times$ DiT speedup. These results demonstrate that Spark-H3 achieves a state-of-the-art quality-efficiency trade-off for training-free BSA on video diffusion models.

cs.CV

新论文 · v1arXiv:2611.24253

One Shot, Any View: High-Fidelity Video Reshooting with Geometry Guidance and Visual References

Kai Huang, Runze Xu, Hui Ren, Taiyi Wu, Xinyuan Li, Xun Gao, Quande Liu, Dong Tang 等 11 位作者

原文摘要

Filming a scene from an additional angle after production usually requires a costly reshoot. We present One Shot Any View, a system that takes a recorded clip and generates a reshot video of the same performance along a user-specified camera trajectory. As in recent geometry-grounded methods, the system conditions generation on the source video and an explicit 3D prior, namely a point video rendered along the requested trajectory from a feed-forward reconstruction of the source video. We target human-centric cinematic videos, which are often shot with long lenses, shallow depth of field, and low-key lighting, all of which degrade feed-forward reconstruction. Existing geometry-grounded methods tend to inherit the degraded point video, and their output quality drops visibly. Two designs make such point videos usable. First, in addition to rendered videos of 3D assets, we train on real-world multi-camera videos, whose point videos are produced by the same reconstruction pipeline as at inference. This training-inference consistency enables the generator to take only the composition of people and scene elements from the point video, and their appearance from the source video. Second, a geometry-anchored RoPE offset keeps the generated video temporally synchronized with the source while largely preventing the output from copying the degraded appearance of the point video. Meanwhile, since the generator is a pretrained reference-to-video (R2V) model, the system also accepts optional character and scene reference images, which supply the appearance of regions that the source never shows. In both objective and human evaluations, One Shot Any View outperforms existing reshooting methods.

cs.CV

新论文 · v1arXiv:2611.24251

Analysis of the (1+1)-EA-ES-Bilevel on Mixed Discrete-Continuous Optimization Problems with Interactions

Timo Kötzing, Jurek Sander

原文摘要

Mixed discrete-continuous optimization problems can pose challenges -- especially for previous integrated approaches -- when interactions cause beneficial discrete changes to be rejected before sufficient continuous adjustment. We introduce ProximityOneMax as a simple benchmark with pairwise discrete-continuous interactions. On this function, we prove an exponential lower bound on the expected time for the (1+1)-EA-ES-Integrated to reach the target accuracy when initialized near a continuous optimum for a suboptimal discrete configuration with a sufficiently small step size. Experiments show frequent entries into such states from random initialization. We introduce the (1+1)-EA-ES-Bilevel, which uses an upper-level (1+1)-EA to optimize discrete variables and a lower-level (1+1)-ES to optimize continuous variables for each fixed discrete offspring before selection. For several interaction benchmarks and sufficiently small target values $ε> 0$ that require an optimal discrete configuration, using fixed continuous initialization and a suitable fixed budget per lower-level call, we prove that the expected number of fitness evaluations to reach objective value at most $ε$ is $Θ(n_d \cdot \log n_d \cdot n_c \cdot \log(R/\sqrtε))$, where $n_d$ is the number of discrete variables, $n_c$ is the number of continuous variables, and $R$ bounds the distances from the fixed continuous starting point to all relevant continuous optima for fixed discrete configurations.

cs.NE

新论文 · v1arXiv:2611.24249

From Points to Trajectories: Rethinking Multimodal Alignment for Physical Events

Yiyang Zhu, Guangyuan Liu, Jingdi Lei, Li Wei, Chau Yuen

原文摘要

Advancing physical artificial intelligence (Physical AI) requires moving beyond static object recognition to ground how real-world mechanics (e.g., impact, friction, and force transfer) unfold over time. While multimodal aligners seek to capture these interactions by matching multi-sensor streams, prevailing architectures compress each temporal sequence into a single pooled embedding. We show that this paradigm fails on twin events: distinct physical executions recorded under identical task conditions. Collapsing the temporal dimension averages out transient cross-modal dynamics, effectively reducing physical event alignment to static scene recognition. Formally, we prove that as sequence length increases, any temporally pooled representation converges to the stationary recording condition. Consequently, as windows grow, no choice of loss function or embedding geometry can disambiguate twin events from pooled features alone. Instead, we show that physical events are uniquely identified by the event gap, namely the instantaneous, synchronous co-fluctuations across modalities that are erased by pooling and accumulate only along unpooled trajectories. To recover this signal, we introduce CounterPoint, a lightweight plug-in module that strips out each modality's temporal mean to score frame-level cross-modal agreement. Integrated across four state-of-the-art (SOTA) multimodal aligners, CounterPoint shifts representations from coarse condition matching to fine-grained physical event alignment, consistently outperforming existing temporal alignment methods.

cs.AI · eess.SP

新论文 · v1arXiv:2611.24247

Allocentric Memory, Egocentric Acting: A Dual-Frame VLA for Urban Aerial Navigation

Haotian Xu, Yue Hu, Zhengqiu Zhu, Tuo Feng, Wenguan Wang, Quanjun Yin

原文摘要

Language-goal aerial navigation requires a UAV to reach a destination specified in natural language using observations collected during flight. A key challenge is linking changing egocentric perception with spatial evidence anchored to stable locations for long-range navigation. We propose CityNav-VLA, a dual-frame vision-language-action model for urban navigation integrating dynamic egocentric context with persistent allocentric spatial memory. The UAV incrementally accumulates visual observations on a fixed north-up map initialized with geographic and landmark priors, preserving evidence across viewpoint changes. A dynamic query conditioned on the instruction, current observations, UAV state, and motion history retrieves relevant memory evidence to predict a map-frame target. A deterministic controller converts this target into body-frame commands using the UAV's current pose, connecting global reasoning with egocentric execution. To reduce target fluctuations over long horizons, early goal commitment (EGC) fixes the execution target to the coordinate-wise median of the first $K$ predictions without extra trainable parameters. On Test Unseen, CityNav-VLA reduces NE by 21.2% and improves SR and SPL by 15.8% and 30.9%, respectively. It also reduces NE by 6.2% and improves SR and SPL by 5.6% and 23.2%, respectively, relative to the former SOTA after dataset refinement. Cumulative ablations show that navigation-map features yield the largest gains, while metric coordinates further improve endpoint accuracy. With a 4B-scale backbone, inference averages 0.68 s per decision with 8.6 GB peak memory on a single A100, presenting remarkable model efficiency.

cs.CV · cs.RO

新论文 · v1arXiv:2611.24244

CommDreamer: Radio-Geometric World Models for Mapless Cellular-Connected UAV Trajectory Planning

Yuqi Ping, Tianhao Liang, Tingting Zhang

原文摘要

Reliable cellular connectivity and collision-free flight are essential for unmanned aerial vehicle (UAV) operations in low-altitude urban canyons, where dense 3D buildings obstruct flight clearance, shadow serving base stations, and create strong co-channel interference at street intersections. Existing planners either require prior 3D city meshes and channel knowledge maps unavailable onboard, or rely on model-free reinforcement learning with low sample efficiency and poor cross-city generalization. We propose CommDreamer, a mapless radio-geometric world model that fuses raw onboard 3D LiDAR scans, multicell cellular reports, and shift-invariant relative kinematics to jointly infer local obstacle clearance and directional signal-to-interference-plus-noise ratio (SINR) dynamics. Using a categorical recurrent state-space model, CommDreamer compresses multimodal measurement histories into a coordinate-invariant latent belief, enabling the UAV to foresee deep shadow zones and train a lightweight online policy purely via multi-step latent imagination without prior maps or antenna patterns. Zero-shot evaluations across unseen urban morphologies in our open-source ray-tracing simulator, AeroCity-RT, show that CommDreamer converges within 150 episodes where model-free reinforcement learning fails to complete flights, achieving 100.0% mission success with zero collisions while lifting median route SINR to 8.02 dB and cutting effective SINR outage by over 50% relative to radio-blind world-model and reactive LiDAR baselines.

cs.RO · eess.SY

新论文 · v1arXiv:2611.24243

End-to-End Landsat Land Surface Temperature Reconstruction with AlphaEarth Embeddings

Shengjie Liu

原文摘要

Land surface temperature (LST) data at Landsat's 30 m resolution is important for many applications, but cloud contamination prevents its spatially continuous observations. Here, we propose A$^2$E$^2$, an end-to-end U-Net that integrates annual temperature cycle (ATC), coarse LST from Earth system modeling, and AlphaEarth embeddings for Landsat LST reconstruction. The ATC supplies a physics-guided thermal prior, the coarse LST provides a temporal background, and the U-Net converts the embedding field into day-specific fine-scale correction using observed pixels. Experimental results on four seasonally distributed Landsat 8/9 scenes over New York City in 2022 show that A$^2$E$^2$ achieves 0.78 K mean absolute error and 1.01 K root mean squared error, reducing error by 60.1% relative to baseline method without spatial correction and by 3.7% relative to the same U-Net guided by annual mean spectral reflectance. Sensitivity analysis shows stable performance regardless of distance to clear pixels and percentage of blocked pixels. Independent validation with ECOSTRESS LST shows that Earth foundation model embeddings have better performance than annual mean spectral bands for LST reconstruction.

cs.CV

新论文 · v1arXiv:2611.24242

Joint Image Denoising and Interpolation via Mixed Graph Filtering

Gene Cheung, Niruhan Viswarupan, Romisaa Elsaidy

原文摘要

Images often require both denoising and interpolation, yet treating the two tasks separately is suboptimal: interpolation introduces correlated noise that complicates subsequent denoising, while denoising may remove image details useful for interpolation. In this paper, we study joint image denoising and interpolation from a mixed graph filtering perspective, where denoising is modeled using undirected graph filters and interpolation using directed graph filters. We first establish that, under mild conditions, any (pseudo-)linear denoiser and interpolator can be interpreted as solution filters of maximum a posteriori (MAP) estimation problems regularized by undirected and directed graph smoothness priors, respectively. Guided by these results, we formulate graph-based joint denoising and interpolation problems using both directed and undirected graph structures. We characterize when joint denoising/interpolation reduces to a separable pipeline and when a genuinely coupled optimization is required. For the non-separable case, we recover sparse graph operators from given denoisers and interpolators, yielding an efficient linear-system formulation solvable via conjugate gradient. Experimental results demonstrate that our proposed joint framework consistently outperforms separate denoising and interpolation pipelines across multiple denoiser-interpolator combinations.

eess.IV · cs.CV · eess.SP

版本更新 · v2arXiv:2611.09493

FusionCLIP: Multimodal Contrastive Pretraining for Fusion Plasma Diagnostics

Qiang Chen, Xiao Wang, Qingquan Yang, Hao Si, Zikang Yan, Guosheng Xu, Jin Tang

原文摘要

Visible-light videos and multivariate diagnostic signals provide complementary observations of tokamak discharges. However, existing fusion pretraining methods primarily learn representations by reconstructing or predicting observations, leaving the correspondence between these modalities underexplored. Representation learning is further challenged by spatially localized plasma regions in video frames and substantial differences in diagnostic sampling rates. We propose FusionCLIP, a multimodal contrastive pretraining framework. A selective video encoder retains informative visual tokens, while a query-based time-series encoder integrates asynchronous diagnostic signals using their observation timestamps. Contrastive learning aligns representations of the two modalities. We construct the EAST Multimodal Diagnostics (EAST-MMD) dataset, comprising 1307 EAST discharges, and evaluate the model through independent fine-tuning on three tasks: disruption prediction, edge-localized mode (ELM) classification, and H98 regression. FusionCLIP achieves a Joint score of 89.07%, with absolute gains of 2.41% and 2.90% over the best competing baseline, and the in-domain contrastive pretraining baseline CLIP-Base, respectively. Ablations and attention visualizations further support the contributions of its key components.

cs.CV · cs.AI

版本更新 · v2arXiv:2611.06414

Twists and Turns: A Graph-Based Benchmark and Framework for Long-Term Memory in Exploration Tasks

Chongyuan Dai, Yaling Shen, Zirui Song, Junfeng Liao, Jinpeng Hu, Xiuying Chen

原文摘要

Long-term problem-solving processes, such as scientific research and software development, proceed along an evolving trial-and-error trajectory toward a central goal. We term these \textit{exploration tasks}, which require models to remember not only facts but also how solutions are tested against intermediate outcomes and early attempts are continually revised or revived. However, existing long-term memory research focuses on factual recall and updates, overlooking the interconnected nature of exploration. We observe that exploration processes naturally form graphs, with branching approaches linked by revisions and reconsiderations. Motivated by this, we propose \textsc{LExMem}, a graph-guided benchmark designed to evaluate \underline{\textsc{Mem}}ory in \underline{\textsc{L}}ong-term \underline{\textsc{Ex}}ploration tasks. We model exploration processes as graphs and introduce an evolutionary mechanism to increase their structural complexity, yielding 224 dialogues and 2,018 question-answer instances derived from graph structures. Building on the same insight, we propose \textsc{LExGraph}, a graph-based memory framework that incrementally organizes dialogues into interconnected memory nodes and retrieves evidence through hybrid retrieval and neighbor expansion. Extensive experiments demonstrate that \textsc{LExMem} poses a significant challenge to existing retrieval- and memory-based systems, whereas \textsc{LExGraph} achieves superior performance and generalizes effectively to external benchmarks. Codes and datasets are available at https://github.com/mbzuai-nlp/LExMem.

cs.CL

新论文 · v1arXiv:2611.24240

ViLFlow: Parallel Vision-Language Generation with Continuous Latent Flows

Kevin Zhai, Bian Sun, Zhenyi Wang, Song Wang

原文摘要

Vision-language generation has predominantly relied on autoregressive and discrete diffusion models. Autoregressive models generate tokens sequentially, while discrete diffusion models typically predict tokens independently within each denoising step. We propose ViLFlow (Vision-Language Flow), a continuous-flow vision-language model that combines joint modeling of output embeddings with parallel token decoding. ViLFlow adapts pretrained continuous language generation to visual question answering and image captioning through learned image guidance and prediction-aware token decoding. A visually adapted teacher provides image-guided predictions as additional denoising supervision. The denoiser learns to reproduce these predictions directly, retaining one image-conditioned prediction per generation step. We train the token decoder on denoiser predictions and paired reference text to improve the conversion of continuous outputs into words. The decoder can be adapted independently, improving answering and captioning without further denoiser training. For captioning, it also supplies text feedback during late denoising, allowing decoded words to inform subsequent refinement. ViLFlow outperforms autoregressive and masked-diffusion baselines by up to 8.46 percentage points on VQAv2 and 4.50 points on GQA without GQA training. On COCO Karpathy test, it improves CIDEr by 16.25 over masked diffusion and 17.81 over sampled autoregression.

cs.CV · cs.LG

版本更新 · v2arXiv:2604.15805

WorldComposer: Generative High-Fidelity Simulation with Digital Cousins for Generalizable Robot Learning and Evaluation

Jasper Lu, Zhenhao Shen, Yuanfei Wang, Shugao Liu, Shengqiang Xu, Shawn Xie, Jingkai Xu, Feng Jiang 等 11 位作者

原文摘要

Learning robust robot policies in real-world environments requires diverse data augmentation, yet scaling real-world data collection is costly due to the need for acquiring physical assets and reconfiguring environments. Therefore, augmenting real-world scenes into simulation has become a practical augmentation for efficient learning and evaluation. We present WorldComposer, an automated generative Real2Sim2Real framework that maps real-world panoramas into high-fidelity, task-ready simulation environments and further synthesizes diverse Digital Cousins through scene and object variations. Combined with high-quality physics engines and realistic assets, WorldComposer supports interactive manipulation across rigid, articulated, and deformable objects. Additionally, we incorporate multi-room stitching to construct consistent large-scale environments for long-horizon tasks. Experiments demonstrate a strong sim-to-real correlation validating our platform's fidelity, and show that extensively scaling up data generation leads to significantly better generalization to unseen scene and object variations, demonstrating the effectiveness of Digital Cousins for generalizable robot learning and evaluation.

cs.RO · cs.AI

新论文 · v1arXiv:2611.24236

From a finite subgroup of $SO(3)$:$C_2$ leads to a Holant dichotomy

Yuxuan Zhou

原文摘要

Counting complexity within the Holant framework has been extensively studied through complexity dichotomy theorems. While substantial progress has been achieved for various restricted settings, the general complex-valued even-arity case without auxiliary unary signatures remains largely open. This paper studies a fundamental case in this program where the binary signatures induce a group structure satisfying \(M(B(\mathcal{F}))\cong C_2\). It is observed that projective equivalence classes of binary signature matrices naturally embed into finite subgroups of \(SO(3)\), providing an algebraic viewpoint for structural classification. This paper further identifies two fundamentally different regimes for the \(C_2\) case, namely the normal and isotropic cases, and analyzes their complexity behavior separately. Combining gadget constructions, decomposition techniques, interpolation arguments, and a realnumberization approach that transforms the complex-valued setting into an equivalent real-structured framework, this paper establishes a complete dichotomy theorem: for every even-arity signature set \(\mathcal{F}\) satisfying \(M(\B(\mathcal{F}))\cong C_2\), the problem \(\mathrm{Holant}(\mathcal{F})\) is either polynomial-time computable or \#P-hard. A Pauli-basis representation for signatures is further introduced as an algebraically natural language for organizing realizable signatures and revealing structural relations that are less transparent in the standard basis.

cs.CC · cs.CL · cs.DM

新论文 · v1arXiv:2611.24233

Psychometrics-Inspired Coreset Selection for Image Quality Assessment

Susu Jiang, Xuelin Shen, Baoliang Chen

原文摘要

Collecting large-scale subjective annotations remains a critical bottleneck in training accurate image quality assessment (IQA) models. Coreset selection reduces this burden by selecting representative images before annotation. However, diversity in a visual feature space does not necessarily reflect diversity in perceptual quality, raising a fundamental question about which quality-related factors the representation should encode. We propose GRAM, a quality-aware representation learning framework inspired by the graded response model (GRM) from psychometrics. GRM describes how an individual's latent ability determines the probabilities of reaching successive assessment grades, with response sensitivity and grade thresholds governing this relationship. In this paper, we find that this principle naturally aligns with perceptual quality assessment, where the impact of image degradation depends on image content and distortion characteristics. Building on this connection, GRAM models quality judgments through three complementary factors: latent quality, content-dependent response sensitivity, and distortion-dependent grade thresholds. These factors jointly determine the probabilities of attaining different quality grades and the resulting expected quality score. The learned parameters provide a structured quality-aware representation that complements general visual features for coreset selection. Experiments on nine datasets demonstrate improvements across different selection strategies, downstream IQA models, and annotation budgets. The code will be made publicly available.

cs.CV

新论文 · v1arXiv:2611.24231

What Survives the Shift from Text to Pixels? Conditional Protection against Prompt Injection in Image-Rendered Documents

Haoyang Liu, Yinong Xu, Zhe Lang, Zhenyu Guan, Qianyun Zhang

原文摘要

Multimodal language models increasingly answer questions over external documents, exposing them to indirect prompt injection: commands planted in untrusted content to hijack the response. Rendering untrusted content as page images lowers attack success on average, leaving open which injected operations survive rendering, at what utility cost, and whether failed image attacks reflect unread commands or commands read but not followed. We pair text and page-image versions of 191 English question-answering sources across six models, measuring marker appending, answer formatting, and answer replacement alongside clean Question-Answering utility. Rendering reduces append and format execution for every model, yet Qwen3-VL-8B still executes image-borne replacement at 77.96\%. Protection also depends on target type, rendering settings, wording, and repetition, and a search over eight fixed attack candidates largely closes the image deficit in appending and formatting for Qwen and Gemini, though not for GPT-5-nano. Utility ratios on original questions range from 93.31\% to 101.61\%, but Qwen falls to 61.99\% when answers combine two evidence spans. Illegibility cannot explain all failed attacks: models often transcribe and identify image-borne commands they do not execute, and trusted user authorization raises execution on unchanged pages. Inside Qwen, patching early attack-region states induces all three operations, more weakly in images. Attention blocking suggests why: a text command acts through its own positions, whereas visual encoding spreads an image command and its target across the instruction page. Rendering thus offers conditional protection, motivating evaluations that report security by model, operation, and attack budget alongside utility.

cs.CR · cs.AI

版本更新 · v4arXiv:2504.09895

Reinforcement Learning with Reference-Based Rewards for Language Model Reasoning and Alignment

Shuai Zhao, Yunqiu Xu, Linchao Zhu, Ling Chen, Yi Yang

原文摘要

Reinforcement learning (RL) powers two major lines of large language model (LLM) post-training: reasoning, which elicits deliberate, verifiable problem solving, and alignment, which steers models toward helpful, harmless, and honest behavior. Both hinge on reward design. Reasoning relies on rule-based verification of final answers, whose binary feedback is blind to intermediate derivations, whereas process reward models (PRMs) require step-level annotations too costly to scale. Alignment depends on reward models (RMs) trained on binary preference pairs, making both data collection and model training resource-intensive. We propose RL2R, reinforcement learning with reference-based rewards, as a unified and inexpensive alternative. Using pre-existing or distilled references, RL2R measures semantic similarity with lightweight metrics such as BERTScore between a sampled generation and a reference answer or solution. Similarity preserves ordinal quality signals that binary feedback discards: responses closer to the reference earn higher rewards, and sound derivations receive credit even when the final conclusion is wrong. For mathematical reasoning, augmenting rule-based verification with answer- and step-level similarity provides low-cost process supervision and outperforms answer-only verification. For alignment, a critic-free REINFORCE-style instantiation covers general preference, safety, and confidence tasks on par with RM-based methods. Reference-based rewards thus offer a cost-effective, versatile reward source spanning reasoning and alignment.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.24229

ProbeShare: Probing a Few, Sharing Across Many for Fast World-Model Planning

Zejian Kang, Xiantao Lin, Zekai Chen, Boyang Shen, Mingyu Ma, Shengwen Zheng, Chengtai Guo, Xiangru Huang

原文摘要

Visual planning with a frozen joint-embedding world model supports robotic reaching and object manipulation by evaluating candidate action sequences against an image goal before execution. Standard cross-entropy method (CEM) planners roll out every candidate independently through a billion-parameter predictor, even when nearby actions induce similar scene changes. This redundant computation grows with population size and search rounds, slowing closed-loop replanning. We observe that candidates within a planning step share an observation history and thus a common action-to-feature map. Based on this insight, we propose ProbeShare, which measures local responses with a few representative probes and reconstructs each candidate's feature grid through scene-conditioned, geometry-aware weighting. When promising candidates move beyond existing probe coverage, ProbeShare evaluates a new probe to rescore nearby candidates. Across four RoboCasa tasks, ProbeShare accelerates episode planning by 43.8--128.9 times over dense RoboJEPA and at least $14.2\times$ over competitive baselines, with greater mean goal progress in a matched-time comparison.

cs.RO

新论文 · v1arXiv:2611.24228

Functional Principal Component Analysis: Minimax Optimality from Sparse to Dense Designs and Beyond

Shunxing Yan, Fang Yao

原文摘要

Functional principal component analysis (FPCA) plays a central role as a dimension-reduction and representation tool in functional data analysis, but its minimax theory for diverging spectral indices under noisy discrete observation has remained open for over two decades. To fill this gap, we consider a sieve-based FPCA framework that pools discrete measurements across subjects and accommodates sampling frequencies ranging from sparse to dense under random designs. We begin by establishing new minimax rates for covariance estimation over general bivariate function classes beyond tensor-product low-complexity structures, thereby identifying the intrinsically two-dimensional optimal rate. Our central theoretical contribution is to establish minimax optimal rates for both individually labelled eigenfunctions with diverging indices and leading principal subspaces of increasing dimensions, under explicit growth and regularity conditions. To establish these results, we develop a general framework for sharp minimax analysis of FPCA under discrete observation, separating spectral approximation from stochastic perturbations and exploiting their distinct structures, thereby offering a new approach to a broad class of nonparametric spectral estimation problems. For both spectral targets, the optimal rates reveal two distinct statistical mechanisms, spectral identification and nonparametric reconstruction, whose interplay gives rise to either four or two sampling regimes. This yields, for the first time, a precise characterization of the impact of discrete sampling across the full range from sparse to dense designs. Finally, as a downstream application, we analyze FPCA-based functional linear regression and show that the FPCA-based estimator attains the minimax-optimal rates.

math.ST · cs.LG · stat.ML

新论文 · v1arXiv:2611.24226

Neural Network-Based In-Contact Task Segmentation of Demonstrated Robot Motions via Hand Guiding

Johannes Hartwig, Marcello Kögler, Dominik Henrich

原文摘要

Intuitive robot programming approaches, such as Programming by Demonstration, enable non-experts to teach robots tasks through hand-guided demonstrations. However, for in-contact tasks requiring force control for parts of the motion, automated segmentation of motion types is crucial for improving usability. Considering the related work, this work proposes a neural network-based segmentation method categorizing motion into three fundamental types using input data of cartesian twists and wrenches at the end effector. We collect demonstration data using a 7-axis robot with a wrist-mounted force torque sensor and generate ground truth labeling by hand. While still in development, our research direction aims to enable non-experts to program in-contact tasks more intuitively.

cs.RO

版本更新 · v2arXiv:2611.23056

RFW-S: Everyday Deformable Objects with Independent Simulation Verification

Jiarui Guo, Saining Zhang, Jiaying Wan, Jiawei Weng, Junhao Chen, Rui Zhang, Yuanbo Lyu, Zhiheng Lee 等 18 位作者

原文摘要

Large-scale robotic simulation requires diverse deformable objects with executable physical properties and realistic interaction behaviors. However, existing 3D asset collections primarily emphasize visual diversity, while scalable physical construction and verification remain challenging. We introduce RFW-S, a large-scale dataset of 83,365 simulation-verified assets spanning 485 everyday categories across five structural families: soft solids, cloth sheets, shells, garments, and bags. We develop an automated pipeline integrating reference-guided 3D generation, structure-aware physical modeling, and LLM-assisted parameter estimation and calibration. To ensure physical reliability, we introduce an independent simulation verification framework that evaluates object behaviors under interactions distinct from those used for parameter calibration. Extensive experiments demonstrate the effectiveness of independent verification and characterize deformable responses under different physical configurations. We further evaluate robotic grasping in terms of both task success and object integrity, and demonstrate the physical realism of our simulated objects through sim-to-real replay of fragile-object manipulation. RFW-S provides a scalable foundation for physically grounded simulation and embodied robotic learning.

cs.RO · cs.CV

版本更新 · v2arXiv:2611.22669

Beyond the Camera: A Tri-Modal Driving World Model for Future RGB, Thermal, and LiDAR Forecasting in Adverse Weather

Faysal Mehrab Chowdhury, Md. Mahfuzur Rahman, Ahmed Rafi Hasan, Kishor Datta Gupta, Mohd Ariful Haque, Savannah Shannon

原文摘要

Driving world models forecast what a vehicle's sensors will record next. Most forecast camera video and some add LiDAR, but thermal cameras, which still see in darkness and some adverse weather, are rarely a forecast target, and to our knowledge no world model forecasts all three sensors. We study joint forecasting of RGB, thermal, and LiDAR on real adverse-weather sequences of the DSERT-RoLL dataset. We post-train a pretrained video world model for each sensor and represent LiDAR as a depth video aligned with the RGB camera, with densification and encoding chosen by what the model's video tokenizer can reconstruct. A tri-sensor model sees all three sensors as one video. We score LiDAR in meters against measured returns and compare against persistence baselines passed through the same tokenizer as the model. With this matching, an apparent loss of the thermal model to persistence in fog disappears. On all 58 validation sequences in six weather conditions, post-trained RGB and thermal forecasts beat compression-matched persistence. Joint training lowers the LiDAR error at 2s by 2.1m at a small cost in camera fidelity, and only the tri-sensor model's LiDAR forecasts beat persistence in mean error. Blanking one sensor degrades the forecasts of the others more in snow than in fog.

cs.CV

新论文 · v1arXiv:2611.24223

Training Denoising Models of Any Architecture Without Stored Images

Christos Koutlis, Ioannis Kompatsiaris, Symeon Papadopoulos

原文摘要

Can a pretrained denoising model replace the dataset used to train it? We investigate this question through teacher-supervised training, showing for the first time that continuous-time diffusion and flow models of any architecture and size can be trained from random initialization without stored images. Our students regress the teacher's velocity on a rolling pool of noisy samples, advanced along trajectories of random step counts to obtain independent, dense and approximately continuous noise levels. This saves considerable storage for large datasets and applies even when the data are unreleased or private. Our experiments include 12 teachers of 6 families and 6 datasets. Our method outperforms standard training of the same network on CIFAR-10 for students 4x smaller than the teacher, comes within 0.75 to 1.92 FID of it at the teacher's size and surpasses training on teacher-generated images and step reduction methods without teacher-based initialization. Our code is available at https://github.com/mever-team/ddm.

cs.CV