跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+1352新增论文
+1083其中 AI 相关
+143已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 15:04各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 16:27 — 2026-11-19 16:27(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:2026-11-19 06:59最近发现新增版本:2026-11-19 15:04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。

27,409 已收录论文22,787 AI 相关8,342 有修订112 HF 社区发现

论文修订列表

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 8,342 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
版本更新 · v5arXiv:2406.07243

MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs

Vera Neplenbroek, Arianna Bisazza, Raquel Fernández

原文摘要

Generative large language models (LLMs) have been shown to exhibit harmful biases and stereotypes. While safety fine-tuning typically takes place in English, if at all, these models are being used by speakers of many different languages. There is existing evidence that the performance of these models is inconsistent across languages and that they discriminate based on demographic factors of the user. Motivated by this, we investigate whether the social stereotypes exhibited by LLMs differ as a function of the language used to prompt them, while controlling for cultural differences and task accuracy. To this end, we present MBBQ (Multilingual Bias Benchmark for Question-answering), a carefully curated version of the English BBQ dataset extended to Dutch, Spanish, and Turkish, which measures stereotypes commonly held across these languages. We further complement MBBQ with a parallel control dataset to measure task performance on the question-answering task independently of bias. Our results based on several open-source and proprietary LLMs confirm that some non-English languages suffer from bias more than English, even when controlling for cultural shifts. Moreover, we observe significant cross-lingual differences in bias behaviour for all except the most accurate models. With the release of MBBQ, we hope to encourage further research on bias in multilingual settings. The dataset and code are available at https://github.com/Veranep/MBBQ.

cs.CL

版本更新 · v2arXiv:2606.25986

The Inference-Compute Frontier for Limit Order Book Prediction

C. Evans Hedges

原文摘要

We identify an empirical inference-compute frontier for limit order book prediction on FI-2010. A power law fitted to low- and mid-compute models extrapolates to an excluded MLPLOB-style mixer family whose work is $56$--$2{,}515$ times the largest budget in the corresponding fit. Across nine folds and five horizons, pooled $R^2$ is $0.934$ on the realized target frontier, with 59\% lower RMSE than constant endpoint extrapolation, and $0.731$ on all excluded operating points. Measured latency gives a weaker relationship and reorders model families. We therefore design FastBiNLOB to pack computation into dense temporal and feature mixing. H120 exceeds the published state-of-the-art macro-F1 on two of four horizons in every one of five seeds. Under our CPU/MPS protocol, H96 reduces median latency by 23.6\% relative to the W128 MLPLOB reference, and H120 by 60.2\% relative to a TLOB-inspired dual-axis attention reference.

cs.LG · q-fin.ST · q-fin.TR

版本更新 · v2arXiv:2606.05109

RePercENT: Scaling Disentangled Representation Learning Beyond Two Modalities

Vasiliki Rizou, Pascal Frossard, Dorina Thanou

原文摘要

To leverage the full potential of multimodal data, we need representations that go beyond the state-of-the-art alignment and fusion approaches and exploit all cross-modal interactions without sacrificing modality-specific information. Learning disentangled representations is a principled way to identify the underlying shared and unique factors that are hidden in observational data. However, while multimodal disentanglement is a compelling paradigm, existing methods are largely confined to the two-modality regime due to its inherent scalability bottleneck. To address this, we propose RePercENT, a self-supervised framework designed to surpass these limitations and unlocks scalable pairwise disentanglement beyond two modalities. Through a multimodal `plug-and-play' architecture, our approach operates directly on pre-extracted embeddings, eliminating the need for extensive joint pre-training while making no assumptions regarding the underlying modalities or foundation model backbones. Moreover, we introduce a joint optimization objective for simultaneously deriving the shared and unique components, and provide formal theoretical guarantees that characterize the optimality of our solution. Spanning modalities from images and videos to clinical reports and omics, and tasks from sentiment analysis to tumor classification, RePercENT successfully recovers disentangled components while maintaining competitive performance and significantly reducing computational complexity.

cs.LG

版本更新 · v2arXiv:2604.24325

Identification to Subclasses of Chordal Graphs

Petr A. Golovach, Laure Morelle, Daniël Paulusma

原文摘要

An identification of two vertices \(u\) and \(v\) in a graph replaces them with a new vertex that is made adjacent to every vertex of \(N(u)\cup N(v)\setminus \{u,v\}\). We study the \(\mathcal{H}\)-Identification problem, which is to decide whether a given graph \(G\) can be transformed (``identified'') to a graph in \(\mathcal{H}\) by applying at most \(k\) vertex identifications. We determine the classical and parameterized complexity of this problem for various subclasses \(\mathcal{H}\) of chordal graphs, obtaining an almost complete picture for two parameters: \(k\) and \(n-k\). We also consider the Identification problem, which is to test, for two given graphs \(G\) and \(H\), whether \(G\) can be identified to \(H\). We determine the parameterized complexity of this problem when \(H\) is a graph from one of our testbed classes, taking the number of simplicial vertices of \(H\) as the parameter.

cs.DS · cs.CC · math.CO

版本更新 · v2arXiv:2610.41275

TRACE: Target-State Risk-Aligned Conditional Execution for Embodied Tracking

Mingyang Lyu, Gongce Cao, Yiyang Jia, Lu Jia, Erliang Lin, Yuhao Zhang, Yinqian Sun, Pin Lyu 等 10 位作者

原文摘要

Embodied visual tracking requires a robot to follow a language-specified person under occlusion, look-alike distractors, and ambiguous instructions. We show that improving tracking persistence can simultaneously increase safety violations. Using a compact 0.6B vision-language-action (VLA) tracker with a frozen backbone, we update only the planner head with proximal policy optimization (PPO). PPO improves success and following rates across all three EVT-Bench settings, but increases the collision rate on distracted tracking because episodes that previously ended in target loss can instead end in contact. We introduce TRACE, an execution-time target-state risk gate that preserves the learned policy and intervenes selectively. A lightweight risk head processes 84 cues, including candidate boxes, identity margins, a learned range-and-bearing probe, and the policy's commands. When the calibrated risk exceeds a threshold, TRACE rescales the translational component of the next waypoint while leaving yaw unchanged. The executed action is identical to PPO's on more than 98% of steps. In paired evaluations on identical episodes, TRACE reduces the distracted-tracking collision rate by 3.96 percentage points, while further improving success and following rates. Matched slowdown controls without target-state timing do not reproduce this improvement. Concurrent evaluation reproduces a collision reduction of 3.77 points, compared with 0.29 points for identical-arm null pairs, indicating that the effect exceeds evaluation variability. These results show that target-state-aware execution can recover the safety cost of policy post-training with minimal intervention.

cs.RO

版本更新 · v14arXiv:2501.14941

On the Optimality of Gaussian Code-books for Signaling over a Two-Users Weak Gaussian Interference Channel

Amir K. Khandani

原文摘要

This article establishes that the capacity region of the two-users weak Gaussian interference channel can be achieved using Gaussian codebooks. It is further shown that the upper concave envelope of the achievable rate region can be attained using at most two time-sharing phases. In one phase, both users transmit simultaneously, while in the second phase, when present, only one user is active. Furthermore, the boundary of the capacity region can be traversed continuously through incremental reallocations of power between the two messages transmitted by each user. Finally, it is proven that the Han-Kobayashi achievable rate region with single-letter Gaussian codebooks attains the optimal boundary of the capacity region.

cs.IT · math.PR

版本更新 · v2arXiv:2610.41273

SPT-Flow: One Integration, Many Futures in Continuous-Time World Models

Mingyang Lyu, Yinqian Sun, Gongce Cao, Yuhao Zhang, Lu Jia, Qian Zhang, Bo Wang, Pin Lyu

原文摘要

Continuous-time world models generate a latent trajectory through a single ODE integration, but adding stochastic conditioning does not ensure that the model uses it. In our teacher-forced baseline, posterior means vary by only about 1% of the prior scale, and matched and swapped latents yield indistinguishable reconstruction PSNR at the reported precision. We study a supervision-shortcut hypothesis: ground-truth intermediate states can reduce the need for trajectory-associated latent information. We introduce SPT-Flow, which samples one latent per trajectory and matches a free-running ODE rollout to demonstration states at multiple readout times. Re-anchoring experiments support the proposed mechanism. On LIBERO, with both models trained for 30k optimizer steps, SPT-Flow improves best-of-10 PSNR over our retrained ODEWorld baseline by 2.0 and 2.4 dB at the mid-trajectory and final frames and reduces mean LPIPS by 23%, with comparable per-sample inference cost. The rollout control recovers most of the accuracy gain; learned latent conditioning adds diversity and best-of-K gains while reducing mean sample accuracy relative to this control. The diagnostics support trajectory-associated latent utilization; semantic mode coverage under matched conditions in the robotic setting remains unverified.

cs.LG

版本更新 · v2arXiv:2605.06014

Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven

Ran Ben-Basat, William Kuszmaul, Michael Mitzenmacher, Amit Portnoy, Shay Vargaftik

原文摘要

Uniform random rotations (URRs) are a common preprocessing step in modern quantization approaches used for gradient compression, inference acceleration, KV-cache compression, model weight quantization, and approximate nearest-neighbor search in vector databases. In practice, URRs are often replaced by randomized Hadamard transforms (RHTs), which preserve orthogonality while admitting fast implementations. The remaining issue is the performance for worst-case inputs. With a URR, each coordinate is distributed as a shifted beta distribution, which converges to a Gaussian distribution in high dimensions. Generally, one RHT is not suitable in the worst case, as individual coordinates can be far from these distributions. We show that after composing two RHTs on any $d$-sized input vector, the marginal distribution of every fixed coordinate of the normalized rotated vector is within $O(d^{-1/2})$ of a standard Gaussian both in Kolmogorov distance and in $1$-Wasserstein distance. We then plug these bounds into the analyses of modern compression schemes, namely DRIVE and QUIC-FL, and show that two RHTs achieve performance that asymptotically matches URRs. However, while two RHTs suffice for scalar quantization, they may be insufficient for Vector Quantization (VQ), which depends on the joint distribution across fixed-size blocks of coordinates (as opposed to only marginal distribution convergence for single coordinates). We prove that a composition of three RHTs leads to decaying coordinate covariance. This ensures that any fixed, bounded, multi-dimensional VQ codebook optimized for URRs has the same expected error when using three RHTs, up to an additive term that vanishes with the dimension. Finally, because practical inputs are rarely adversarial, we propose a linear-time $O(d)$ check on the input's moments to dynamically adapt the number of RHTs used at runtime to improve performance.

cs.LG · cs.AI · cs.DS · cs.NI

版本更新 · v2arXiv:2606.03203

MedCUA-Bench: A Screenshot-Only Benchmark for Clinical Computer-Use Agents

Jia Yu, Zilong Wang, Xinyang Jiang, Dongsheng Li, Shuo Wang

原文摘要

Computer-use agents could automate repetitive screen-based clinical work, but their reliability in medical graphical user interfaces remains largely unvalidated. Existing benchmarks focus on general web or desktop tasks and underrepresent medical software, which requires domain knowledge, exhibits markedly different UI design from mainstream applications, lacks public testing environments, and demands safety validation beyond task completion. We introduce MedCUA-Bench, an interactive benchmark for clinical computer-use agents. It covers 18 clinical scenarios across 10 medical domains, reconstructed from real product manuals and open-source medical systems to capture authentic clinical interfaces while avoiding licensing and privacy constraints. Each task ships with paired intent- and step-level goals to disentangle clinical reasoning from UI execution, and is evaluated by a deterministic checker over task completion and five clinical safety dimensions. Across 23 agents, the best closed-source model reaches 54.2% strict success, while all models remain below 9% on the real OpenEMR. Open-source agents average only 2.5%, with the best reaching 16.2%. MedCUA-Bench exposes the gap between current agents and reliable clinical software use, providing a reproducible testbed for future research.

cs.AI

版本更新 · v2arXiv:2610.18321

CoSMO: Conformal Semantic Mapping for Open-World Safe Robot Navigation

Shuqi Wang, Yiwei Zheng, Pingrui Zhang, Yue Gao, Xiang Yin

原文摘要

Safe autonomous navigation requires not only geometric obstacle avoidance but also semantic awareness. Different object categories demand different safety clearances, and the set of relevant categories may expand as the robot explores novel environments. Vision-language models (VLMs) offer rich semantic representations for building maps of unknown scenes, yet their confidence scores are poorly calibrated, making raw predictions unreliable for safety-critical planning. Conformal prediction (CP) can provide coverage guarantees, but existing methods assume a fixed label set and stationary data, limiting their use in open-world settings. We propose Conformal Semantic Mapping for Open-World Safe Robot Navigation (CoSMO), a semantic safety mapping framework that transforms VLM embeddings into online-calibrated coverage sets and safety-aware obstacle dilations under distribution shift. By calibrating directly in the embedding space, CoSMO avoids the score rescaling that arises in confidence calibration as the vocabulary expands. Experiments on the Matterport3D (MP3D) dataset show that CoSMO reduces semantic collisions by 61.6% relative to a geometry-only baseline, while maintaining formal coverage guarantees even under delayed expert feedback. Real-world experiments on a quadruped robot further demonstrate generalization by achieving long-run empirical coverage of 90.73% against the 90% target. Project website: https://yangming911.github.io/cosmo-page/.

cs.RO

版本更新 · v2arXiv:2605.02745

Bolek: A Multimodal Language Model for Molecular Reasoning

Frederic Grabowski, Jacek Szczerbiński, Maciej Jaśkowski, Kalina Jasińska-Kobus, Paweł Dąbrowski-Tumański, Tomasz Jetka, Bartosz Topolski

原文摘要

Molecular property models increasingly support high-stakes drug-discovery decisions, but their outputs are often difficult to audit: classical predictors return scores without rationale, while language models can produce fluent explanations weakly grounded in the input molecule. We introduce Bolek, a compact multimodal language model that grounds natural-language reasoning in molecular structure by injecting a Morgan fingerprint embedding into an instruction-tuned text decoder. Bolek is fine-tuned on molecular alignment tasks, including molecule description, RDKit descriptor prediction, and substructure detection, and on downstream reasoning over 15 TDC binary classification tasks using synthetic chains-of-thought anchored in concrete molecular features. Across these tasks, Bolek outperforms its Qwen3-4B-Instruct base on all endpoints in yes/no mode and on 13 of 15 in chain-of-thought mode, raising mean ROC/PR AUC from 0.55 to 0.76. It also outperforms TxGemma-9B-Chat on 13 of 15 binary classification tasks despite being less than half its size. Bolek's explanations are more grounded than those of the baseline LLMs: it cites numerical descriptors 10-100x more often per chain-of-thought, and the cited values agree strongly with RDKit for key descriptors such as TPSA, MolLogP, and MolWt (Spearman rho = 0.87-0.91). Generalisation extends beyond the training panel: on 15 unseen TDC classification endpoints, Bolek matches TxGemma on five, and it produces non-trivial rank correlations on three held-out regression endpoints despite never seeing downstream regression during training. These results suggest that targeted modality injection and reasoning supervision tied to verifiable molecular features can yield compact, auditable molecular reasoning models.

cs.LG · cs.AI · q-bio.BM

版本更新 · v10arXiv:2209.06865

Sketch of a novel approach to a neural model

Gabriele Scheler

原文摘要

We present an account of neuroplasticity with respect to cell-internal processing pathways in relation to membrane and synaptic plasticity. We think traditional synapse-centric, weight-based models of memorization are not sufficient or adequate to capture the complexity of neuroplasticity. In these accounts, the model is a network of neurons connected by adaptive transmission links. The adaptation of the transmission links relies on weight changes according to use of the transmission link (short-term and long-term potentiation/depression). In contrast, we propose a paradigm switch from a synapse-centric model (each synapse learns independently, based on its history of use) to a neuron-centric model (each neuron uses signal selection for intracellular pathways to express plasticity at the membrane). A neural model consists of (a) expression of parameters at the membrane, in particular dendritic synapses or spines, and axonal boutons (b) internal parameters in the sub-membrane zone and the cytoplasm with its protein signaling network and (c) core parameters in the nucleus for genetic and epigenetic information. In a neuron-centric model, each node (=neuron) in the network has its own internal memory. Neural transmission and information storage are separated, not automatically combined by coupling strength. There is filtering and selection of signals for storage. Not every transmission event leaves a trace. This represents an important conceptual advance over synaptic weight models. We present the neuron as a self-programming device, rather than as passively determined by ongoing input. We believe a new approach to neural modeling is necessary, because the experimental evidence is not well captured by traditional synapse-centric models. Ultimately, we are interested in the possibilities of a flexible memory system that processes external signals according to its inherent structure.

q-bio.NC · cond-mat.dis-nn · cs.AI · cs.NE · q-bio.MN

版本更新 · v7arXiv:2504.08509

The Complexity of Generalized HyperLTL with Stuttering and Contexts

Gaëtan Regaud, Martin Zimmermann

原文摘要

We settle the complexity of satisfiability, finite-state satisfiability, and model-checking for generalized HyperLTL with stuttering and contexts, an expressive logic for the specification of asynchronous hyperproperties. Such properties cannot be specified in HyperLTL, as it is restricted to synchronous hyperproperties. Nevertheless, we prove that satisfiability is $Σ_1^1$-complete and thus not harder than for HyperLTL. On the other hand, we prove that model-checking and finite-state satisfiability are equivalent to truth in second-order arithmetic, and thus much harder than the decidable HyperLTL model-checking problem and the $Σ_0^1$-complete HyperLTL finite-state satisfiability problem. The lower bounds for the model-checking and finite-state satisfiability problems hold even when only allowing stuttering or only allowing contexts.

cs.LO

版本更新 · v3arXiv:2609.03602

SV-WAM: An Efficient Surround-View World-Action Model for End-to-End Autonomous Driving

Jinyang Wang, Shiwei Li, Junjian Wang, Zhiqiang Deng, Jianbin Gao, Yihang Zhao, Liu Liu, Yongjia Zhao 等 15 位作者

原文摘要

World models (WMs) have demonstrated strong potential for end-to-end autonomous driving by learning predictive representations of future scene dynamics. However, generating future videos during inference introduces substantial computational overhead, leading many recent driving WMs to adopt a single front camera as input for efficient deployment. This design restricts spatial coverage in safety-critical maneuvers such as lane changes, merges, and turns. To address this limitation, we propose SV-WAM, a surround-view world-action model (WAM) that preserves full six-camera observations while maintaining efficient inference. SV-WAM leverages future-video prediction as dense training supervision for action learning within a shared generative model, rather than as an inference-time output. At the core of this design is an action-centered causal mask that prevents action tokens from attending to future-video tokens during joint action-video denoising. Consequently, the video branch can be discarded at deployment, enabling efficient action-only planning. Furthermore, we introduce a differentiable drivable-area compliance regularizer that penalizes vehicle-footprint corners approaching or crossing drivable boundaries, improving planning safety and boundary awareness. Extensive experiments on the closed-loop NAVSIMv2 benchmark and the open-loop nuScenes benchmark demonstrate that SV-WAM achieves state-of-the-art planning performance with low inference latency and competitive zero-shot transfer capability.

cs.CV · cs.RO

版本更新 · v3arXiv:2512.20177

NeuralCrop: Combining physics and machine learning for improved crop modelling

Yunan Lin, Sebastian Bathiany, Maha Badri, Maximilian Gelbrecht, Philipp Hess, Brian Groenke, Jens Heinke, Christoph Müller 等 9 位作者

原文摘要

Global gridded crop models (GGCMs) are crucial for projecting climate impacts on agricultural productivity and assessing associated risks to food security. However, state-of-the-art GGCMs are subject to substantial uncertainties arising from reduced representations of complex processes. Projected increases in the frequency and severity of climate extremes require more reliable agricultural yield simulations. Recent machine learning approaches trained on observational data provide alternatives to GGCMs, but remain under-constrained due to sparse observations and show poor out-of-distribution generalization. Here we introduce NeuralCrop, a differentiable hybrid GGCM that combines the strengths of an advanced process-based GGCM (LPJmL) with data-driven components. NeuralCrop is first trained to reproduce its underlying fully process-based version, before it is fine-tuned on observational flux data of physiological variables. Evaluation against held-out flux-tower observations from European wheat and US maize sites shows 32.6-45.2% reductions in mean normalized root-mean-square error for daily carbon and water fluxes. Although fine-tuned only on physiological variables, NeuralCrop improves temporal correlations with independent yield records across 71.4% of the cultivated area for European wheat and 84.0% for the US Corn Belt during 1981-2019. It performs highly competitively compared to GGCMI Phase~3 models. NeuralCrop reproduces yield anomalies more accurately across a range of soil-moisture conditions and especially for extreme drought conditions. For large-scale, long-term simulations, NeuralCrop runs nearly two orders of magnitude faster than the CPU-based LPJmL baseline model, mainly thanks to GPU acceleration. Our results highlight end-to-end hybrid crop modelling as a promising avenue for improving crop simulations and informing food security assessments under climate change.

cs.LG · physics.comp-ph

版本更新 · v2arXiv:2606.05261

NIV: Neural Axis Variations for Variable Font Generation

Nadav Benedek, Ariel Shamir, Ohad Fried

原文摘要

Variable fonts enable continuous variation of glyph geometry along semantic design axes such as weight, width, slant, and optical size. However, constructing a variable font from a static font remains a labor-intensive process requiring expert typographic design and manual specification of glyph variation data. We introduce NIV (Neural Axis Variations), a method that automatically converts a static font into a fully functional variable font. Given glyph outlines and a set of desired design axes, NIV predicts per-point displacements. The model operates directly on vector glyph geometry and employs a novel Property Embedding mechanism that captures interactions between multiple axes, enabling consistent multi-axis variation within a unified framework. We train NIV on a newly constructed dataset derived from variable Google Fonts, comprising over one million variation tuples. The resulting model generalizes across unseen code points, unseen font styles, high-complexity CJK glyphs, and even out-of-distribution handwriting inputs. The generated outputs are standard variable font files supporting continuous interpolation via existing rendering engines. To facilitate research, we release the dataset, the complete training and inference implementation, and trained models at https://github.com/ndvbd/NIV. Beyond typography, our approach demonstrates how structured geometric objects with continuous parametric variation can be synthesized using neural deformations.

cs.CV · cs.AI · cs.LG

版本更新 · v2arXiv:2403.10239

Do media narratives shape foreign ownership? Evidence from African regions

A. Fronzetti Colladon, R. Vestrelli, S. Bait, M. M. Schiraldi

原文摘要

Foreign investors rarely observe local business conditions directly, especially in developing economies where reliable subnational information is limited. In such contexts, media narratives may shape how investment locations are perceived by increasing their visibility and framing local risks and opportunities. This paper examines the relationship between media narratives and foreign ownership across African locations. We combine firm-level data from the World Bank Enterprise Surveys with a novel corpus of 167,746 English-language news articles on industrial investment in Africa published between 2014 and 2019. Using text mining and semantic network analysis, we construct investment-location measures of the semantic importance of business-related media themes through the Semantic Brand Score (SBS) and study their associations with firm-level foreign ownership. The results point to a significant association between how the media frames a location and the level of foreign presence there. This association varies across frames. It is predominantly positive, relates to both the intensive and extensive dimensions of foreign ownership depending on the theme, and may interact negatively with the investment climate. This paper contributes to research on the geography of foreign capital by identifying public narratives as a feature of the information environment associated with observed foreign-equity participation.

cs.CL · econ.EM · physics.soc-ph

版本更新 · v4arXiv:2506.18682

Multi-Scale Spectral Attention Module-based Hyperspectral Segmentation in Autonomous Driving Scenarios

Imad Ali Shah, Jiarong Li, Tim Brophy, Martin Glavin, Edward Jones, Enda Ward, Brian Deegan

原文摘要

Recent advances in autonomous driving (AD) have highlighted the potential of hyperspectral imaging (HSI) for enhanced environmental perception, particularly in challenging weather and lighting conditions. However, efficiently processing high-dimensional spectral data remains a significant challenge. This paper presents an empirical investigation of a Multi-Scale Attention Mechanism (MSAM) for enhanced spectral feature extraction through three parallel 1D convolutions with varying kernel sizes (1-11) and adaptive feature aggregation. By integrating MSAM into UNet's skip connections, we evaluate performance improvements in semantic segmentation across multiple HSI datasets for urban driving scenarios. Comprehensive ablation studies demonstrate that MSAM consistently outperforms baseline UNet-SC, achieving average improvements of 2.32% in mIoU and 2.88% in mF1, while maintaining competitive GPU performance against established attention mechanisms. Our findings reveal that optimal kernel combinations are dataset-specific, with configurations such as (1;5;11) and (3;7;11) demonstrating particularly strong performance. This empirical investigation advances understanding of HSI processing capabilities for AD applications and establishes a foundation for adaptive multi-scale spectral feature extraction in automotive deployment.

cs.CV · cs.AI

版本更新 · v2arXiv:2610.18541

Empathy Is Not the Scapegoat for Declines in Factuality and Reliability

Letian Shi, Kanwal Mehreen, Deheng Zhang, Yuxia Wang

原文摘要

Language models are increasingly expected to support users in stressful or uncertain situations, where warmth and empathy are desirable. While recent work associates warmer models with reduced reliability, we show that this conclusion is incomplete. Prior studies often train primarily on empathetic dialogue, making it difficult to separate tone effects from SFT-induced distribution shift. We revisit this issue at both the model and evaluation levels. We study prompting, SFT, and RL for inducing warm behavior, and comprehensively evaluate capability preservation using an 11-dataset benchmark suite and EMOFACT under emotional contexts. Across multiple model families, we find that warmth effects are task- and model-dependent, while task-aligned adaptive tone can improve empathy and targeted reliability, although some capability trade-offs remain. We further introduce human-validated empathy evaluators specifically developed to assess empathetic model responses. Our results suggest that models can be more supportive in social interactions while remaining reliable.

cs.CL

版本更新 · v2arXiv:2512.05511

Rethinking Infrared Small Target Detection: A Foundation-Driven Efficient Paradigm

Chuang Yu, Jinmiao Zhao, Yunpeng Liu, Yaokun Li, Xiujun Shu, Yuanhao Feng, Bo Wang, Xiangyu Yue

原文摘要

While large-scale visual foundation models (VFMs) exhibit strong generalization across diverse visual domains, their potential for single-frame infrared small target (SIRST) detection remains largely unexplored. To fill this gap, we first systematically introduce frozen VFM representations into the SIRST task and propose a Foundation-Driven Efficient Paradigm (FDEP), a general and efficient framework compatible with diverse VFMs and SIRST networks, which improves detection accuracy without additional VFM-related inference overhead. Specifically, a Semantic Alignment and Modulated Fusion (SAMF) module is designed to achieve dynamic alignment and deep fusion of the global semantic priors from VFMs with task-specific features. Meanwhile, to avoid the inference-time overhead introduced by VFMs, we propose a Collaborative Optimization-based Implicit Self-Distillation (CO-ISD) strategy, which enables implicit semantic transfer between the main and lightweight branches through parameter sharing and synchronized backpropagation. In addition, to unify the fragmented evaluation system, we construct a Holistic SIRST Evaluation (HSE) metric that performs multi-threshold integral evaluation at both pixel-level confidence and target-level robustness, providing a stable and comprehensive basis for fair model comparison. Extensive experiments demonstrate that the SIRST detection networks equipped with our FDEP framework achieve state-of-the-art (SOTA) performance on multiple public datasets. Our code is available at https://github.com/YuChuang1205/FDEP-Framework

cs.CV

版本更新 · v2arXiv:2412.11161

Why and How: Knowledge-Guided Learning for Cross-Spectral Image Patch Matching

Chuang Yu, Yunpeng Liu, Jinmiao Zhao, Ao Chen, Xiujun Shu, Bo Wang, Zelin Shi, Xiangyu Yue

原文摘要

Recently, cross-spectral image patch matching based on feature relation learning has attracted extensive attention. However, existing methods focus on mining richer feature relations by building complex relation extraction structures. Meanwhile, performance bottlenecks have gradually emerged. To address this, we make the first attempt to explore a stable and efficient bridge between descriptor learning and metric learning, and construct a Knowledge-Guided Learning Network (KGL-Net), which achieves significant performance improvements while abandoning complex network structures. Specifically, we find that there is feature extraction consistency between metric learning based on feature difference learning and descriptor learning based on Euclidean distance. This provides the foundation for bridge building. To ensure the stability and efficiency of the constructed bridge, on the one hand, we conduct an in-depth exploration of 20 combined network architectures. On the other hand, a feature-guided loss is constructed to achieve mutual guidance of features. In addition, unlike existing methods, we consider that the feature mapping ability of the metric branch should receive more attention. Therefore, a hard negative sample mining for metric learning (HNSM-M) strategy is constructed. To the best of our knowledge, this is the first time that hard negative sample mining for metric networks has been implemented and brings significant performance gains. Extensive experimental results show that our KGL-Net achieves SOTA performance in multiple cross-spectral image patch matching datasets. Our code is available at https://github.com/YuChuang1205/KGL-Net

cs.CV

版本更新 · v4arXiv:2403.11751

Relational Representation Learning Network for Cross-Spectral Image Patch Matching

Chuang Yu, Yunpeng Liu, Jinmiao Zhao, Dou Quan, Zelin Shi, Xiangyu Yue

原文摘要

Recently, feature relation learning has drawn widespread attention in cross-spectral image patch matching. However, existing related research focuses on capturing diverse feature relations between image patches and ignores sufficient intrinsic feature representations of individual image patches. To address this limitation, we propose an innovative relational representation learning that simultaneously focuses on sufficiently mining the intrinsic features of individual image patches and the feature relations between image patches. Based on this, we construct a Relational Representation Learning Network (RRL-Net). Specifically, we innovatively construct an autoencoder to effectively characterize the individual intrinsic features, and introduce a feature interaction learning (FIL) module to extract deep-level feature relations. Meanwhile, to further fully mine individual intrinsic features, a lightweight multi-dimensional global-to-local attention (MGLA) module is constructed to enhance the global feature extraction of individual image patches and capture local dependencies within global features. By combining the MGLA module, we further explore the feature extraction network and construct an attention-based lightweight feature extraction (ALFE) network. Furthermore, a multi-loss post-pruning (MLPP) optimization strategy is proposed, which can greatly facilitate network optimization while avoiding increases in parameters and inference time. Extensive experiments demonstrate that our RRL-Net achieves state-of-the-art (SOTA) performance on multiple public datasets. Our code is available at https://github.com/YuChuang1205/RRL-Net

cs.CV

版本更新 · v2arXiv:2609.15334

Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation

Xinyue Xu, Hongbin Lin, Juangui Xu, Hualiang Wang, Lehan Wang, Lijie Hu, Adrian Weller, Xiaomeng Li

原文摘要

Medical imaging modalities such as ultrasound and X-ray are widely used in clinical practice, where diagnosis follows a structured, evidence-driven workflow aligned with standardized criteria. While multimodal large language models (MLLMs) show promise for automated medical report generation, most existing systems rely on end-to-end multimodal fusion without modeling clinically defined intermediate attributes, leading to limited grounding and interpretability. To address this issue, we propose CORAL (COncept-grounded ReAsoning with Localization), a multimodal framework that integrates spatial grounding and concept-level supervision into a unified reasoning process. CORAL employs a prompt-driven medical segmentation model to localize lesions and predicts multi-class clinical attributes through a Concept Bottleneck module. The resulting textual concept tokens are combined with mask-modulated visual features within an MLLM to enable structured report generation and diagnostic prediction. Experiments on BUS-CoT and IU X-ray datasets demonstrate consistent improvements in diagnostic accuracy, concept consistency, and report quality over strong general-purpose and medical MLLMs, indicating that concept-grounded reasoning better aligns generation with clinical decision processes.

cs.CV · cs.AI · cs.LG

版本更新 · v4arXiv:2606.05506

Robust Scene Transfer for PointGoal Navigation via Privileged Sensor Guided Contrastive Learning

Amirhossein Zhalehmehrabi, Tiziano Tezze, Alberto Castellini, Alessandro Farinelli

原文摘要

We propose a sensor-guided adaptive contrastive learning framework for visual representation learning in PointGoal navigation. During training, privileged LiDAR sensing guides the contrastive objective through a geometry-aware similarity metric and adaptive temperature scaling, encouraging visual embeddings to capture navigation-relevant structure rather than scene-specific appearance. The resulting encoder is pretrained independently, frozen, and used as the perceptual backbone for reinforcement learning, decoupling representation learning from policy optimization. We further introduce a cross-stage domain mismatch between representation pretraining and policy learning to suppress environment-specific shortcuts and promote reliance on task-relevant features. Extensive experiments in high-fidelity simulation demonstrate that our approach significantly improves policy-level scene transfer across diverse indoor and outdoor environments. At deployment, the agent relies only on monocular RGB observations together with standard task-related inputs such as goal position and proprioceptive signals, without access to LiDAR or other privileged sensors. Our method outperforms large pretrained vision models and standard contrastive baselines under severe appearance and semantic shifts. We also release a multimodal dataset to support future research on privileged-guided visual representation learning for navigation. The code is available at:

cs.CV

版本更新 · v2arXiv:2609.01549

NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games

Tomáš Holeček, Viliam Lisý

原文摘要

Model-based reinforcement learning (MBRL) has achieved remarkable results in single-agent domains, yet its extension to competitive imperfect information games (IIGs) remains underexplored. In multi-agent settings, opponent-induced non-stationarity complicates the learning process, and decentralized model learning faces severe identifiability barriers, which we argue make centralized model learning a mathematical necessity. Building on this analysis, we propose NashDreamer, a principled MBRL framework for two-player zero-sum IIGs. It introduces a centralized Multi-Agent Recurrent State-Space Model (MARSSM) that decouples environment dynamics from the effect of players' strategies on their individual observations. NashDreamer is designed to use arbitrary policy gradient algorithms and inherits their convergence guarantees towards Nash equilibria under an idealized model. Empirical evaluations across five benchmark games demonstrate that NashDreamer substantially improves sample efficiency over model-free baselines early in the training. Finally, we theoretically analyze the architecture's optimization landscape, identifying the vulnerability of the Dreamer family of algorithms to posterior collapse in stochastic environments. We leave it as an open challenge.

cs.LG

版本更新 · v2arXiv:2610.25391

Rapid Mixing for Sampling Colorings of Random Graphs up to Tree Uniqueness Threshold

Zhidan Li, Kuan Yang

原文摘要

We study the mixing time of the single-site Glauber dynamics for sampling proper $q$-colorings on sparse Erdős-Rényi random graphs $\mathcal{G}(n, d/n)$. We prove that, whenever $q \ge (1 + o_d(1))d$, Glauber dynamics mixes in polynomial time with high probability over $\mathcal{G}(n, d/n)$ for all sufficiently large integers $n$. This improves the previous bound $q = (α^* + o_d(1))d$ where $α^* = 1.7632...$ is the unique solution of $x = \exp(1/x)$ on $[1, \infty)$ by Efthymiou, Hayes, Štefankovič, and Vigoda (SODA, 2018) and asymptotically matches the uniqueness threshold on infinite regular trees. Our proof has three main ingredients. First we establish logarithmic bounds on the spectral and coupling independence constants of the Gibbs distribution by extending the tree analysis of Chen, Liu, Mani, and Moitra (J. ACM, 2026). Second, we extend the entropy-factorization framework for two-spin systems on random graphs, developed by Bezáková, Galanis, Goldberg, and Štefankovič (TALG, 2024), to proper colorings by introducing a buffer around high-degree vertices. Finally, we compare the resulting heat-bath block dynamics with the single-site Glauber dynamics.

math.PR · cs.DM · cs.DS

版本更新 · v3arXiv:2502.04379

Can Large Language Models Capture Video Game Engagement?

David Melhart, Matthew Barthet, Georgios N. Yannakakis

原文摘要

Can out-of-the-box pretrained Large Language Models (LLMs) detect human affect successfully when observing a video? To address this question, for the first time, we evaluate comprehensively the capacity of popular LLMs for successfully predicting continuous affect annotations of videos when prompted by a sequence of text and video frames in a multimodal fashion. In this paper, we test LLMs' ability to correctly label changes of in-game engagement in 80 minutes of annotated videogame footage from 20 first-person shooter games of the GameVibe corpus. We run over 4,800 experiments to investigate the impact of LLM architecture, model size, input modality, prompting strategy, and ground truth processing method on engagement prediction. Our findings suggest that while LLMs rightfully claim human-like performance across multiple domains and able to outperform traditional machine learning baselines, they generally fall behind continuous experience annotations provided by humans. We examine some of the underlying causes for a fluctuating performance across games, highlight the cases where LLMs exceed expectations, and draw a roadmap for the further exploration of automated emotion labelling via LLMs.

cs.CV · cs.AI · cs.CL · cs.HC

版本更新 · v5arXiv:2605.05155

Aes3D: Aesthetic Assessment in 3D Gaussian Splatting

Chuanzhi Xu, Boyu Wei, Haoxian Zhou, Xuanhua Yin, Zihan Deng, Haodong Chen, Qiang Qu, Weidong Cai

原文摘要

As 3D Gaussian Splatting (3DGS) gains attention in immersive media and digital content creation, assessing the aesthetics of 3D scenes becomes important in helping creators build more visually compelling 3D content. However, existing evaluation methods for 3D scenes primarily emphasize reconstruction fidelity and perceptual realism, largely overlooking higher-level aesthetic attributes such as composition, harmony, and visual appeal. This limitation comes from two key challenges: (1) the absence of general 3DGS datasets with aesthetic annotations, and (2) the intrinsic nature of 3DGS as a low-level primitive representation, which makes it difficult to capture high-level aesthetic features. To address these challenges, we propose Aes3D, the first systematic framework for assessing the aesthetics of 3D neural rendering scenes. Aes3D includes Aesthetic3D, the first dataset dedicated to 3D scene aesthetic assessment, built on our proposed annotation strategy for 3D scene aesthetics. In addition, we present Aes3DGSNet, a lightweight model that directly predicts scene-level aesthetic scores from 3DGS representations. Notably, our model operates solely on 3D Gaussian primitives, eliminating the need for rendering multi-view images and thus reducing computational cost and hardware requirements. Through aesthetics-supervised learning on multi-view 3DGS scene representations, Aes3DGSNet effectively captures high-level aesthetic cues and accurately regresses aesthetic scores. Experimental results demonstrate that our approach achieves strong performance while maintaining a lightweight design, establishing a new benchmark for 3D scene aesthetic assessment.

cs.CV · cs.AI

版本更新 · v2arXiv:2606.15793

Proximal Policy Optimization for Amortized Discrete Sampling

Anna Zykova-Myzina, Timofei Gritsaev, Daniil Tiapkin, Nikita Morozov

原文摘要

This paper explores policy gradient algorithms for training stochastic policies to sample from structured discrete probability distributions under the Generative Flow Network (GFlowNet) framework. Building on extensive theoretical connections between GFlowNets and entropy-regularized reinforcement learning, we derive equivalents of standard policy gradient algorithms for training GFlowNets, as well as experimentally explore their various methodological aspects, including baseline training and advantage estimation. Most importantly, our work is the first to derive and successfully apply proximal policy optimization to GFlowNets, showing its improved convergence speed and data efficiency compared to standard GFlowNet training objectives on benchmarks ranging from synthetic energies to molecular graph generation.

cs.LG · cs.AI · stat.ML

版本更新 · v2arXiv:2610.38281

A Witnessing Duality for ReLU Network Depth

Dimitrios Myrisiotis

原文摘要

A depth lower bound for ReLU networks asserts that every sufficiently shallow network fails on some input. What does a proof of such a bound compute? We study this question for exact computation of the maximum of $n$ real inputs, with depth measured by the number of hidden layers. For every separately fixed prime $q$ and depth bound $K$, we give a uniform $\mathsf{TC}^0$ refuter for rational networks with at most $K$ hidden layers and more than $q^K$ inputs, provided that the reduced denominators of their nonbias weights are not divisible by $q$. Biases may be arbitrary rationals. The refuter finds a rational input on which the network fails, and its correctness is provable in $\mathbf{VTC}^0$, the bounded-arithmetic theory of uniform constant-depth threshold computation. The underlying numerical depth lower bound follows from Averkov, Hojny and Merkert (ICLR 2025), extending Haase, Hertrich and Loho (ICLR 2023); our contribution is an internal proof that makes its geometric argument into a feasible refuter. On the construction side, $\mathbf{VTC}^0$ verifies locally checkable certificates for the balanced integer-weight maximum network of depth $\lceil\log_2 n\rceil$. At $q=2$, the construction and refuter meet: for each fixed $K$, the theory verifies that integer-nonbias-weight networks with arbitrary rational biases can compute the maximum with at most $K$ hidden layers exactly when $n\le 2^K$. We also give certified rational constructions of polynomial encoding length and depth $O(\log n/\log\log n)$. These results instantiate a witnessing duality: bounded proofs of certified existence and of refutation correspond, respectively, to threshold-computable constructors and refuters whose guarantees the theory proves.

cs.CC · cs.LG · cs.LO