跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+367新增论文
+288其中 AI 相关
+33已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 10:18 · 全站最近入库：2026-11-09 10:17各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 10:55 — 2026-11-09 10:55（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：2026-11-09 10:18最近发现新增版本：2026-11-09 10:17库内论文最新更新时间：2026-11-06 12:44

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。

17,467 已收录论文14,949 AI 相关4,222 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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 17,467 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 10:16（北京时间）
新论文 · v1arXiv:2610.37962

Statistical Detection of Positional Bias in LLM-Based Recommender Systems: Methodologies and Empirical Evidence

Carlos Peláez-González, Francisco Herrera, Andrés Herrera-Poyatos

原文摘要

Large Language Models (LLMs) are increasingly used as recommendation generators in conversational recommender systems (RS) via retrieval-augmented generation (RAG). This flexible design introduces new sources of structural bias. This paper studies positional bias in top-1 and single-turn LLM-based RS: systematic dependence of the recommended item on the order in which candidates are presented in the prompt. We propose two complementary detection methodologies: (i) POB-ICM, based on contingency matrix analysis and Chi-square independence testing, and (ii) POB-UNBP, a sample-efficient approach derived from a uniformity null model under permutation-based evaluation, enabling stochastic decoding with formal statistical guarantees. Using a controlled RAG testbed for product recommendation, built on a real product catalog, a fixed prompt template and 2000 template-generated user queries with 20 permutations each (40,000 instances), both methodologies reject the null hypothesis of positional independence and uniformity in all evaluated state-of-the-art models. We introduce three complementary metrics -- permutation sensitivity, positional bias, and strong positional bias -- to quantify this effect, the latter targeting cases where the position displaces the recommendation towards clearly less relevant items rather than only choosing among comparably relevant ones. A robustness analysis across candidate-set size and decoding temperature shows that the bias is structural and model-dependent, not an artifact of deterministic decoding or candidate-set size. These results establish positional bias as a measurable, reproducible property of prompt-mediated recommendation pipelines in the evaluated setting and motivate routine auditing and governance controls (e.g., order randomization, standardized prompting) for deployed LLM-based RS. Source code is publicly released.

cs.IR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2509.20333

BBoE: Leveraging Bundle of Edges for Kinodynamic Bidirectional Motion Planning

Srikrishna Bangalore Raghu, Alessandro Roncone

原文摘要

In this work, we introduce BBoE, a bidirectional, kinodynamic, sampling-based motion planner that consistently and quickly finds solutions in environments with varying obstacle clutter. The algorithm combines exploration and exploitation while relying on precomputed robot motions, resulting in efficient convergence towards the goal. Our key contributions include: i) a strategy to quickly find solutions in obstacle-rich spaces by leveraging a bundle of precomputed robot motions (i.e., edges); and ii) BBoE, a robust bidirectional kinodynamic planner that utilizes this strategy to produce fast and feasible solutions. Across four systems spanning 3D to 6D state spaces, BBoE is the only planner to achieve $\geq96\%$ success on every system while attaining the lowest planning time on three of four.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2601.08024

A Highly Efficient Diversity-based Input Selection for DNN Improvement Using VLMs

Amin Abbasishahkoo, Mahboubeh Dadkhah, Lionel Briand

原文摘要

Maintaining or improving the performance of Deep Neural Networks (DNNs) through fine-tuning requires labeling newly collected inputs, a process that is often costly and time-consuming. To alleviate this problem, input selection approaches have been developed in recent years to identify small, yet highly informative subsets for labeling. Diversity-based selection is one of the most effective approaches for this purpose. However, they are often computationally intensive and lack scalability for large input sets, limiting their practical applicability. To address this challenge, we introduce Concept-Based Diversity (CBD), a novel and highly efficient diversity metric for image inputs that leverages Vision-Language Models (VLMs). Our results show that CBD exhibits a strong correlation with Geometric Diversity (GD), an established diversity metric, while requiring only a fraction of its computation time. Building on this finding, we propose a hybrid input selection approach that combines CBD with Margin, a simple uncertainty metric. We conduct a comprehensive evaluation across a diverse set of DNN models, input sets, selection budgets, and six most effective state-of-the-art selection baselines. The results demonstrate that the CBD-based selection consistently outperforms all baselines at guiding input selection to improve the DNN model. Furthermore, the CBD-based selection approach remains highly efficient, requiring selection times close to those of simple uncertainty-based methods such as Margin, even on larger input sets like ImageNet. These results confirm not only the effectiveness and computational advantage of the CBD-based approach, particularly compared to hybrid baselines, but also its scalability in repetitive and extensive input selection scenarios.

cs.CV · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.28195

Attractive Faces Skew Text-to-Image Reward Models and Leaderboards

Harvey Mannering, Zhiwu Huang, Adam Prügel-Bennett

原文摘要

Human preference is now central to the evaluation, guidance, finetuning, and ranking of text-to-image models. However, the susceptibility of human preferences to bias in image generation remains underexplored. We identify a key observation: for human faces, perceived attractiveness skews image quality judgments, even when comparing real photographs of comparable fidelity. In a controlled user study, annotators rank more attractive faces as higher quality, even when unattractive real faces are compared with attractive AI-generated ones. We examine the downstream consequences of this bias. Firstly, simulating Elo rankings from user study data shows attractiveness can distort a leaderboard's ranking, elevating synthetic attractive faces over real, unattractive ones. Secondly, the same bias reappears in the human preference models. Editing 40 annotated facial attributes in isolation, we find that attractiveness is the strongest correlate of score for four of five human preference models (PickScore, MPS, HPSv2.1, HPSv3), and the strongest predictor of score in regression analysis. We further show that preference aligned generation shifts faces toward younger, more feminine faces, and can override explicit prompts for unattractive faces, thereby limiting user control. Finally, we explore mitigation strategies, both for data collection and post training on human preference models. These findings highlight the need for preference models that disentangle image quality from human cognitive bias, enabling more reliable evaluation.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.09164

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks

Magdalena Trędowicz, Łukasz Struski, Arkadiusz Lewicki, Karolina Pachota, Andrzej Grudzień, Mateusz Jagła, Jacek Tabor

原文摘要

Saliency maps are most useful when they identify the image regions that are sufficient to preserve a model's behaviour. We introduce SEAMS, a sufficiency-based saliency method that directly optimises a soft mask using a preservation objective. Given a frozen differentiable model output, such as a class probability, CLS embedding, or token representation, SEAMS searches for a compact mask that preserves the selected output. The approach relies on a simple optimisation framework based on soft masks, a learnable budget, and a three-way image composite generated entirely from the query image. As a result, it requires no auxiliary distractor dataset, architecture-specific attribution mechanism, or differentiable top-k relaxation. Experiments with frozen ViT-S/16 and ConvNeXt models show that the same optimisation pipeline can generate object-level, class-conditioned, and token-level explanations by changing only the preserved target. The resulting masks are compact, interpretable, stable across random initialisations, and competitive on insertion and deletion benchmarks. Our results also indicate that different architectures often rely on different sufficient evidence while achieving similar preservation fidelity, highlighting the architecture-dependent nature of visual explanations.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37954

MesoCraft: a web-based tool for interactive procedural modeling of mesoscale biological structures

Donggang Jia, Alexandre Kouyoumdjian, Ondrej Strnad, Uros Smajdek, Ciril Bohak, Dilara Bayraktar, Alejandra Esparza, Peter Mindek 等 11 位作者

原文摘要

Biological models bring the molecular world of cells into view, enabling experts and the public to explore and understand biological discoveries. Building mesoscale models requires organizing many molecular components into spatial arrangements that can be revised as evidence and interpretations develop. We present MesoCraft, a browser-based tool for structural biologists centered on interactive procedural modeling. User-defined rules generate collections of molecular instances, while a geometry-node editor and visual feedback support authoring and revision of their spatial relationships. Beyond model construction, MesoCraft integrates exploration and communication, enabling researchers to inspect molecular organization and create guided animations that highlight key spatial relationships. By connecting modeling, exploration, and explanation in a unified workflow, MesoCraft allows insights gained during exploration and communication to inform iterative model refinement, supporting the development of mesoscale models into visual narratives of cellular organization. A demonstrative deployment of the tool is available at https://mesocraft.kaust.edu.sa/.

cs.GR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37952

SAG-Sep: Sparse Augmented Graphs and Onion-Guided Search for Rounded Capacity Cut Separation

Haoran Liu, Guanyi Wang, Yu Yang

原文摘要

Rounded capacity cuts (RCCs) are among the most effective cuts for capacitated vehicle-routing relaxations, but exact separation is computationally prohibitive at scale. Existing heuristic and neural separators can be fast, but often fail to produce sufficiently many effective cuts within practical separation budgets. We introduce SAG-Sep, a separator that scores node membership in RCC-inducing subsets across vehicle-count levels from a fractional LP solution in a single encoder forward pass, avoiding the iterative predict-and-coarsen inference used by NeuralSEP-style separators. SAG-Sep encodes the LP solution as a Sparse Augmented Graph (SAG), adding flow-informed multi-hop edges that expose long-range routing structure without densifying attention. Beyond LP-aware sparse encoding, we observe that high-value exact RCCs are typically nested, organizing into onion-like subset families, and SAG-Sep's node scores track subset nesting depth. This motivates Onion-Sweep (OS), a training-free decoder that ranks customers by their scores, evaluates the RCC violation of every prefix of the ranking in one vectorized pass, and emits the most violated prefix of each replica together with a cross-replica family of nested proposals, converting independent node scores into structurally coordinated RCC candidates without a tuned threshold or probing band. On the NeuralSEP benchmark with N=1000 customer instances, SAG-Sep with OS reduces the average root gap by 17.7% relative to the strongest NeuralSEP baseline, while the single-pass SAG-Sep separator achieves a roughly 30-fold per-iteration neural separation speedup. Our findings suggest that LP-aware sparse encoding and the nested structure of high-value cuts are structural patterns worth leveraging in neural separation more broadly.

cs.LG · cs.AI · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37951

Federated Learning for Semantic Communications over Multiple Access Channels

Yalin E. Sagduyu, Tugba Erpek, Yi Shi

原文摘要

This paper presents a federated learning (FL) framework for semantic communication (SemCom) over the multiple access channel (MAC), where multiple distributed transmitters simultaneously convey semantic information to a common receiver using end-to-end learned semantic representations. Semantic feature extraction, compression, wireless transmission, and semantic inference are jointly optimized through FL-based SemCom. Unlike conventional SemCom systems that train users independently, simultaneous semantic transmissions over the MAC enable concurrent training of multiple transmitters within the same transmission interval, thereby reducing training overhead and channel usage. Federated semantic aggregation is incorporated with shared and personalized encoder components, allowing transmitters with limited local training data to benefit from semantic representations learned from transmitters possessing larger datasets while preserving local adaptation. Evaluated using the CIFAR-10 dataset over fading channels, the proposed approach maintains high semantic inference accuracy under shared wireless access and significantly improves performance under severe data imbalance. In the meantime, simultaneous semantic transmissions can significantly reduce training overhead while preserving robust semantic performance across distributed transmitters with heterogeneous local datasets. These results highlight the potential of combining FL and SemCom to support scalable and communication-efficient edge intelligence in future wireless networks.

cs.IT · cs.DC · cs.LG · cs.NI · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37949

AI-Generated Non-Consensual Intimate Imagery is Configured, Not Built: How General-Purpose AI Technology Enables Sexual Violence

Julia B. Kieserman, Ashley Phoebe Ishoel, Damon McCoy, Elissa M. Redmiles, Lucy Qin, Jaron Mink

原文摘要

AI-generated non-consensual intimate imagery (AIG-NCII) is an increasingly prevalent form of online abuse, distinguished from AI-generated sexual content (AIG-SC) by the sexualized depiction of a real person's identity without their consent. To understand how offenders may benefit from the tools and resources shared across the broader AIG-SC community, we analyzed 139 R+ guides on CivitAI, a popular platform known to host a disproportionate amount of AIG-SC. We find that AIG-SC guides discuss how to create content generation workflows composed of sexual and identity concepts, the building blocks of AIG-NCII, including one guide that explicitly outlines an AIG-NCII workflow. We identify that ultimately AIG-NCII is enabled by configuration rather than a distinct set of technical tools. We map AIG-NCII threat models across basic and advanced AIG-SC workflows to demonstrate how multiple dual-use technical components can compose NCII outputs in an environment with little to no discussion of ethical implications or responsible use. We conclude by noting that, as most workflows rely on open-weight models, existing technical defenses against AIG-NCII are limited. However, our findings offer a starting point for evaluation of AI-based models and products against realistic attacker behavior required by new EU regulation and suggest that efforts to develop safeguards at the model- and product-levels should focus on generation of identity content.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37946

The Collaborative Critique: An Inspection Method for Expert Evaluation of User Interfaces

Wendy Lucas, Tamara Babaian

原文摘要

The development of the collaborative critique (CC) usability inspection method was driven by the need for systems, ranging from the simple to the complex, to lessen the workload on their users by being better collaborative partners. In the collaborative view of system-user interaction, the role of the system is expanded to that of a partner that must help its users achieve their goals. This perspective shifts the dynamic from focusing on the user's ability to make effective and efficient use of the system to the system's usefulness within a given task, user, and interaction context, thereby reducing the user's cognitive and physical efforts. The CC method consists of a walkthrough evaluation in which the questions answered at each step of the interaction assess the collaborative strength of the system. This method is further distinguished by the inclusion of questions that access the behavior of the system in error situations, which are known to be particularly burdensome to users of complex systems. In this paper, we provide a detailed description of the CC method and its application and demonstrate its usefulness in evaluating an interface. The results of a laboratory evaluation show that the method performed well in identifying the problems experienced by users across all severity levels and predicted almost all of the problems associated with error situations.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37944

Symmetric List Objects

Fiona Blackett, Vikraman Choudhury, Rin Liu

原文摘要

Cons-lists are fundamental to functional programming, and are well-understood as initial algebras, and as a concrete construction of free monoids. In category theory, such list objects can be axiomatised internal to any monoidal category, with nil and cons maps, and a recursion mechanism. When strengthened to support parametrised recursion, they can be shown to give the free monoid construction. We study a small variant on parametrised list objects called parametrised symmetric list objects, in a symmetric monoidal category, where the two frontmost elements are allowed to be permuted. We show that this gives a construction of free commutative monoids, and develop some related theory.

math.CT · cs.LO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37941

A Poisson Transition and Bias Law for KSG Mutual-Information Estimation

Abhiram Gorle, Tsachy Weissman

原文摘要

We quantify the error of the strict-radius Kraskov--Stögbauer--Grassberger (KSG-1) mutual-information estimator on a Gaussian channel as the sample size \(n\) grows and the channel becomes nearly deterministic. For fixed dimension \(p\) and neighbor index \(k\), we define the resolution parameter \(u_n=ne^{-I_n}\), where \(I_n\) is the true mutual information in nats. When \(u_n\to u\in(0,\infty)\), we prove that the estimation error converges in mean square to a computable deterministic bias \(B_{p,k}(u)\). Sampling fluctuations therefore vanish, while an additive bias can persist. We derive this bias from an explicit marked-Poisson law for the neighborhood counts, characterize its small-\(u\) asymptotics, and show that it tends to zero as \(u\to\infty\). The same law describes how often neighborhoods saturate, meaning that they make the largest possible contribution to the estimate. The limiting saturation probability decreases continuously and strictly from one to zero, allowing a Gaussian-model bias correction on fixed critical intervals. Finite-sample experiments show substantial bias even when the true information lies below the estimator's logarithmic ceiling and saturated neighborhoods are rare. Saturation-based correction reduces estimation error in these experiments, though recovering the resolution parameter from the observed saturation fraction can remain difficult when saturation is rare.

cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37940

Enumeration Complexity of Permutation Classes

Manuel Bodirsky, Mohamed Elsheikh

原文摘要

We study classes of permutations that are defined by avoidance of forbidden patterns. For each fixed finite set $B$ of forbidden patterns, we study the \emph{avoider enumeration problem}: given an integer $n$, output all $B$-avoiding permutations of length $n$. Avoider enumeration is output-polynomial for every fixed $B$. However, our main notion of efficiency is polynomial delay. We use the insert-maximum tree as a search tree, in which permutations are built by repeatedly inserting a new maximum while preserving pattern avoidance. This leads to the \emph{insert-maximum extension problem}, which asks if a given permutation has an avoiding descendant at a specified depth. An algorithm for this problem can prune branches that cannot reach the target length. Hence, if this problem is in P, we obtain polynomial-delay enumeration. To investigate this problem, we introduce and study \emph{pockets}, the maximal finite subtrees of the insert-maximum tree. For fixed $B$, if there is a polynomial $p$ such that every pocket rooted at $ρ$ has at most $p(|ρ|)$ nodes, then the extension problem is solvable in polynomial time and enumeration has polynomial delay. In particular, a bound on pocket depth depending only on $B$ suffices. We prove such a bound if the class is well-quasi-ordered, has a regular insertion encoding, or if $B$ omits one of the three maximum-position types: leftmost, interior, or rightmost. We also prove that extension is in NP for every fixed $B$, even with binary-encoded target depth. On the negative side, we construct a fixed set of $55$ forbidden patterns for which extension is NP-complete. Consequently, enumerating valid extensions from a given starting permutation cannot have polynomial delay unless P=NP. This also answers a question of Hanika by showing that the forbidden permutation constraint satisfaction problem can be NP-complete for a fixed forbidden set.

cs.CC · math.CO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37937

You Don't Need Aligned Representations: Knowledge Distillation via Random Prototype Spaces

Hamza Etcibasi, Ramazan Gokberk Cinbis

原文摘要

A widely held assumption in knowledge distillation is that teacher and student representations must occupy a compatible or explicitly aligned feature space. We propose RPKD (Random Prototype Knowledge Distillation), which discards this assumption by comparing both networks against a shared bank of randomly initialized, frozen prototype vectors. Alignment is therefore carried out in an external reference space rather than in the teacher's native feature coordinates: the teacher side is projected by fixed random maps that carry no trainable parameters, and only the student adapts. Two branches handle the transfer: a logit branch aligning global prototype similarity distributions and a feature branch matching spatially-resolved prototype activation maps. Both operate within the same fixed prototype space, which can be interpreted as a random feature embedding that approximately preserves inter-sample similarity structure, so the prototype bank and the distillation objective stay unchanged across teacher-student pairs while only the input projections are instantiated per architecture. In low-category settings, decoupling the prototype vocabulary from the task label space yields richer supervision than the label space alone, an advantage absent from logit-based methods, whose supervisory signal collapses as class count shrinks. This advantage is especially relevant in real-world scenarios where the label space is typically constrained. Extensive experiments demonstrate the effectiveness of RPKD, achieving a maximum gain of +7.98% over OFA on CIFAR-100, +12.44% on ImageNet-100, and +1.28% on ImageNet-1K. Source code is available at https://github.com/HamzaEtcibasi/RPKD

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37936

Finite-Step Geometry of Marginal-Preserving Velocity Fields in Generative Flows

Ewsey Obzherin, Valentin Khrulkov

原文摘要

Generative flows can admit different velocity fields that induce the same continuous marginal evolution but behave differently after numerical discretization. We study this finite-step non-equivalence while keeping the marginal path and numerical method fixed. Projected modified equations characterize the component of local integration error that changes the marginal law and give sufficient conditions for higher marginal convergence order. For affine fixed-shape distributions, we characterize exact finite-step reachability and derive spectral obstructions and sharp nearest-reachable Wasserstein errors. For diffusion probability-flow ODEs, we construct skew-score perturbations that preserve the exact marginal path under exact scores and quantify their leakage under score error. Controlled Gaussian and mixture experiments recover the predicted order, reachability, and obstruction phenomena.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37935

SkillMem: Compact External Skill Memory for Latent Multi-Agent Reasoning

Yuxuan Zhu, Mohammad Mohammadi Amiri, Pin-Yu Chen, Keerthiram Murugesan

原文摘要

Latent multi-agent systems reduce inference cost by keeping intermediate reasoning and inter-agent communication in continuous representations.\ Reusable skills, however, are commonly supplied as text or stored as layer-wise Key-Value states or skill-specific model parameters, introducing repeated processing or substantial per-skill storage.\ We introduce \textbf{SkillMem}, which represents each reusable skill as a small external latent memory and makes it directly available during latent multi-agent reasoning.\ A role-conditioned cross-attention reader allows the same memory to guide different agents according to their roles and current hidden states.\ We train the skill memories and shared reader through behavioral distillation, matching the change in token predictions induced by a textual skill while keeping the backbone frozen.\ For our experiments, we obtain textual skills from paired successful and failed multi-agent trajectories, although existing skills can also be compiled directly.\ Across six benchmarks and Qwen3 models ranging from 4B to 14B parameters, SkillMem provides strong gains for smaller backbones while preserving efficient latent multi-agent inference across model scales.\ We use the same $8\times256$ memory configuration across all evaluated model scales, requiring 9.6\,KB of skill-specific storage per skill, including its retrieval embedding.\ For a library of 100 skills, SkillMem reduces total storage by more than $38\times$ compared with alternative skill representations and achieves up to a $4.23\times$ end-to-end inference speedup.\ These results show that compact procedural memories can be reused without sacrificing the efficiency of latent multi-agent reasoning.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37934

Bi-Phase Training: Learning Efficiently From Scratch

Abel Gurung, Joseph Campbell

原文摘要

Pre-training foundational models is computationally expensive as models scale. In this work, we introduce Bi-Phase Training (BPT), a parameter-efficient pre-training method that preserves the high-rank learning dynamics observed in full-parameter optimization with substantially reduced trainable parameters. BPT parameterizes each weight update as a composition of constrained high-rank left/right transformations via trainable diagonal matrices and low-rank adapters whose updates are periodically merged into the frozen base weights, resulting in a compounding expansion of accessible directions during training. Across language-model pre-training from scratch (Qwen2.5 models from 100M to 1.5B parameters and OLMo-2-1B) on FineWeb-Edu (10B and 100B tokens), BPT achieves validation perplexity close to full-parameter baselines while using far fewer trainable parameters; e.g., at the 1.5B scale, BPT uses 66% fewer trainable parameters with only a small validation-perplexity gap. Additionally, a comprehensive evaluation across diverse downstream tasks shows that BPT preserves much of the full-parameterized model's downstream performance.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37933

NLP-based Message Prioritisation for Opportunistic Routing: A Case Study of Nepal Earthquake Emergency Communication

Yihang Cao, Milena Radenkovic

原文摘要

This dissertation investigates whether Natural Language Processing (NLP) based semantic message prioritisation can improve the treatment of urgent disaster messages in opportunistic emergency communication, using the 2015 Nepal earthquake as a case study. TF IDF with Logistic Regression and BERT are used to classify social media messages into nine humanitarian categories, which are mapped to four routing priorities from P1 to P4. These priorities are integrated into the ONE simulator within a controlled Kathmandu earthquake scenario using a modified Binary Spray and Wait router. BERT achieves higher priority accuracy and P1 recall than Logistic Regression, while reducing under prioritisation and severe priority errors. However, improved NLP performance does not produce uniform network gains. P1 delivery probability remains high and similar across routing conditions, and no consistent latency reduction is observed. The clearest difference appears under buffer pressure, where the BERT condition shows fewer observed ground truth P1 buffer losses than Logistic Regression. The results indicate that semantic prioritisation is most valuable when limited transmission and storage resources are contested, although it cannot overcome mobility and contact constraints in opportunistic networks.

cs.NI · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.36305

Bilinear World Models: Learning Representations with Structured Dynamics for Efficient Control

Antonio Pariente, Ignacio Boero, Nikolai Matni, Alejandro Ribeiro

原文摘要

World models jointly learn latent representations and dynamics that predict how high-dimensional observations evolve under actions. In this work, we propose a JEPA-style world model in which, rather than learning arbitrary latent dynamics, we restrict them to follow a bilinear parameterization. This structure enables efficient planning and control while shifting the modeling burden onto the encoder, encouraging richer representations that expose the controllable geometry of the system. In particular, this structured parameterization allows us to structurally enforce action recoverability, thereby preventing representation collapse by construction. Although prescribing a bilinear parametrization may appear restrictive, we show that a broad class of nonlinear dynamical systems admits a transformation under which the dynamics become bilinear. Empirically, we show across standard 2D and 3D control tasks that representations with bilinear-parameterized dynamics can be learned directly from high-dimensional observations, reducing planning time by nearly three orders of magnitude while retaining or even improving control accuracy. We also propose more demanding regimes of longer-horizon planning and real-time control, and demonstrate that our method succeeds in both, moving JEPA-style world models beyond short-horizon offline planning.

cs.RO · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37932

Understanding Large Language Models as Numerical Optimizers

Lingyun Guo, Ali Bereyhi

原文摘要

Large language models (LLMs) have emerged as potential tools for numerical optimization. Despite promising results, their intrinsic optimization capabilities and limitations remain poorly understood, particularly in high dimensions. This paper investigates the ability of LLMs to exploit mathematical problem structures and generate feasible, near-optimal solutions. We develop an evaluation framework that distinguishes solution quality from execution failures, including numerical inaccuracies, constraint violations, and output-format errors. Using representative problems from convex optimization, fractional programming, and constrained projection, we assess LLM performance against deterministic reference solvers across different dimensions. Our results reveal that LLMs can capture useful optimization structures and produce near-optimal solutions, even when their outputs fail to satisfy numerical or formatting requirements. However, reliability deteriorates with increasing problem dimension and depends strongly on the underlying optimization structure. To further investigate the limitations, we deploy an iterative refinement mechanism that provides targeted feedback on feasibility and solution quality. The results demonstrate that iterative refinement substantially improves reliability and extends the range of problem dimensions over which LLMs produce valid solutions. Nevertheless, persistent numerical and structural errors limit their applicability as standalone optimizers. These findings provide insights into the capacity and limits of LLM-based optimization and motivate hybrid approaches that combine LLM reasoning with deterministic numerical verification.

cs.AI · cs.LG · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37929

3D Occupancy-Language Fields from mmWave Radar

Haowen Lai, Zhiwei Zheng, Mingmin Zhao

原文摘要

Radar systems can recover scene geometry and recognize predefined categories, but these outputs do not provide a persistent spatial representation for open-ended language queries. Such queries require linking observations from different viewpoints to the same physical locations. We present TextRadar, a framework that constructs a scene-level 3D occupancy-language field from panoramic radar observations. The field combines occupancy with scale-dependent language features at surface locations, allowing the reconstructed scene to be queried with new descriptions. A single-frame radar distillation model predicts aligned ranges and language features from each radar observation. Using radar-estimated poses, we register these predictions to reconstruct the field from radar alone in a new scene. Experiments on approximately 20k synchronized observations across seven buildings demonstrate scene-level natural-language querying and prompt-free semantic visualization. Analysis of camera-to-radar concept transferability shows stronger agreement for structures, materials, and human poses than for colors and printed text.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.09560

Attention Geometry

Julio Candanedo

原文摘要

Attention normalizes learned scores into a Markov operator. In the continuum, the local sector becomes diffusion on a learned Riemannian manifold, but attention natively bonds distant points, creating nonlocal structure such that no tensor geometry can describe. The Bakry-Emery calculus, built directly from the transition operator, extends geometry to these potentially stratified spaces, giving a coordinate-free account of what vision and language transformers learn.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37927

Machine learning applications in the heliosphere

Vishal Upendran, Banafsheh Ferdousi

原文摘要

Space weather is the study of the near-Earth impact of the processes on the Sun. In a this era of technology, space weather emerges as a crucial area of study wherein the state of the near-Earth conditions need to be modeled and forecasted. Crucially, the advent of machine learning provides us with opportunities to study this subject in a rather comprehensive manner. In this chapter, we treat the the processes arising from Sun to the impact on the ground as a set of coupled systems, which can be studied in isolation or in a coupled manner. We define these individual systems in terms of their state vector $\vec{S}$, which provides us with an opportunity to define the physical variables determining the system. This also allows us to consider the systems in terms of their observables, obtained through the action of operators as $\vec{O}[\vec{S}]$. In such a formalism, the machine learning algorithms serve as {\it learned operators}, defined generally as inference ($\mathcal{I}$), propagation ($\mathcal{P}$), and emulation ($\mathcal{E}$). Through such a formalism, we present how machine learning helps advance our understanding of the physical systems under study, while also accelerating the development of operational models for space weather forecasting.

astro-ph.SR · cs.LG · physics.space-ph

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.12022

Simulation-Based Inference with Convolutional Maximum Mean Discrepancy for Noisy Data

Ritwik Vashistha, Jeff M. Phillips, Abhra Sarkar, Arya Farahi

原文摘要

Ignoring measurement noise degrades statistical inference. Existing correction techniques are often computationally costly and inefficient. Kernel methods based on maximum mean discrepancy have enabled efficient, likelihood-free inference, but they typically assume clean data. We introduce a framework for inference with samples corrupted by potentially heteroscedastic noise from a known distribution. Central to our method is the convolutional maximum mean discrepancy, which compares distributions after noise convolution and retains metric validity under standard kernel conditions. We establish finite-sample deviation bounds that are unaffected by measurement error and an equivalence between testing under noise and kernel smoothing. Based on this discrepancy, we propose an estimator, establish its consistency and asymptotic normality, and provide an efficient implementation using stochastic gradient descent. We demonstrate the practical effectiveness of our method through simulations and applications in astronomy, anthropometry, and the social sciences. Our method provides a unified, likelihood-free, simulation-based framework for efficient and robust inference for broad classes of problems in noisy data.

stat.ME · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37926

GARDEN: Generalist Autonomous Reward Design Through Evidence Navigation for Cooperative Multi-Agent Reinforcement Learning

Dogan Urgun

原文摘要

Cooperative multi-agent reinforcement learning (MARL) enables teams of agents, such as robots and autonomous vehicles, to learn coordinated behavior, but what such teams learn is largely determined by their reward function. Because task success alone provides too little guidance for learning, intermediate rewards are usually designed by hand, and this effort must often be repeated whenever the environment or the team changes. Large language models (LLMs) can automate the effort by writing reward functions as code, yet the resulting rewards are typically designed and tested in a single setting. To enable their reuse across settings, GARDEN (Generalist Autonomous Reward Design through Evidence Navigation) is proposed, in which one reward program is developed for a family of related scenarios and transferred, unchanged, to scenarios that were not available during its design. During development, environment code, training records, and agent behavior are investigated by an LLM reward engineer, and draft rewards are tested in trial training runs, while the learning algorithm and the rule for selecting the final reward are held fixed. On unseen scenarios of the Overcooked and SMAX benchmarks, task returns were increased by 58.2% and 52.5% over the default rewards on two kitchen layouts, and the mean win rate in two combat scenarios was raised from 51.0% to 89.9%. Under matched candidate and probe budgets, this exceeded the 84.2% and 79.2% obtained with fixed diagnostic feedback and Eureka-inspired reward reflection. These results show that a single autonomously engineered reward can be reused effectively across related cooperative scenarios.

cs.AI · cs.MA · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37923

VerifiedLab: Harnessing Knowns for Unknowns

Yu Yao, Jiayi Dong, Yang Yang, Shuiwang Ji, Ju Li

原文摘要

Across human history, knowledge has undergone several transitions, from orality to writing and then to digital archives. At each transition, humans established new conventions to preserve knowledge for the new era. Nowadays, as research agents are increasingly deployed for laboratory experiments, knowledge is crossing another boundary: from records written for humans to those for machines. In this work, we introduce VerifiedLab, a multi-agent harness framework for this human-to-machine transition of knowledge. VerifiedLab transforms research output from passive artifacts into active systems that accelerate downstream use, adoption and prediction of future trends. In VerifiedLab, a team of AI scientists with distinct roles reasons over records verified field by field: a principal investigator plans, a librarian computes the evidence directly from the records, specialists draft, and a gate and a critic check each claim against the measured reliability of its data before the harness decides whether to release or withhold it. We demonstrate the efficacy of VerifiedLab through extensive experiments on perovskite solar cells: VerifiedLab recovers known physical trends, anticipates devices reported a year later, and lets AI scientists inherit the literature together with a measure of how far it can be trusted. By scaling the inference-time verification compute, VerifiedLab introduces a new pathway for knowledge dissemination and machine harness for AI co-scientists.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.02620

Same Error, Different Function: The Optimizer as an Implicit Prior in Financial Time Series

Federico Vittorio Cortesi, Giuseppe Iannone, Giulia Crippa, Tomaso Poggio, Pierfrancesco Beneventano

原文摘要

Neural networks applied to financial time series operate in a regime of underspecification, where predictors achieve comparable out-of-sample error. Using large-scale volatility forecasting for S&P 500 stocks--twelve architecture-optimizer configurations, thirteen seeds each, evaluated on 564,795 held-out observations--we show that comparable test loss conceals measurably different predictors. In eleven of twelve comparisons, models trained from identical initialization and identical data order diverge $1.3$ to $7.8$ times further than repeated runs of either optimizer alone, ruling out initialization noise as the explanation. On a common scale, predictions differ by 5--17\% of the typical forecast error while the models' error magnitudes differ by less than 0.7\% of it. The divergence reshapes nonlinear response profiles, temporal dependence, and ultimately decisions: volatility-ranked portfolios trace a Sharpe-turnover frontier with up to 58\% turnover dispersion at comparable gross Sharpe ratios. In underspecified settings, optimization is a consequential source of inductive bias, and model evaluation must extend beyond scalar loss to functional and decision-level behavior.

cs.LG · q-fin.CP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37921

FAD-KV: Adaptive Dictionary KV Caching for Efficient Reasoning Decoding

Yuxuan Zhu, David H. Yang, Parisa Shiravani, Mohammad Mohammadi Amiri, Tejaswini Pedapati, Subhajit Chaudhury, Keerthiram Murugesan, Pin-Yu Chen

原文摘要

Key-value (KV) caching is a core mechanism in large language models, where intermediate key and value representations are stored to accelerate autoregressive decoding. As generation length increases, KV cache memory and computation grow linearly, making compression critical for efficient long-output reasoning. Dictionary-based sparse KV compression is appealing because it represents each token's KV states as a sparse combination of learned basis elements (atoms) in a dictionary, preserving token-level structure without enforcing a global low-rank constraint. However, existing dictionary-based methods face two practical limitations during decoding: iterative sparse coding methods such as Orthogonal Matching Pursuit add decoding-time overhead, and static dictionaries may mismatch evolving KV distributions under test-time generation. While adaptive dictionary updates can reduce this mismatch, naive append-only strategies lead to dictionary growth during generation. We propose FAD-KV, a \textbf{F}ast \textbf{A}daptive \textbf{D}ictionary KV caching framework for efficient reasoning decoding. FAD-KV integrates (i) a screening-based sparse coding scheme, where a one-shot Top-\(n\) selection identifies a small candidate pool followed by lightweight coefficient refinement, and (ii) a fixed-size dictionary adaptation mechanism that reuses inactive atoms instead of expanding the dictionary. By controlling both sparse coding cost and adaptive dictionary growth, FAD-KV provides a memory-bounded and computation-efficient KV compression framework for long reasoning workloads. Experiments on reasoning and long-context benchmarks show that FAD-KV achieves a strong quality-efficiency trade-off while avoiding unbounded dictionary growth during decoding.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37919

SciGame: Let Agents Play the Scientific Discovery Games in the Real and Counterfactual World

Yusheng Zhao, Bowei He, Xue Liu, Mingxiao Li

原文摘要

Large language model agents are increasingly used for scientific discovery. However, existing benchmarks mix law inference with programming, score data fitting instead of prediction on unseen inputs, and do not separate empirical evidence from pretrained priors. We introduce SciGame, a controlled benchmark that converts scientific literature into structured scientific cards. Each card yields a pair of Original and dimensionally consistent Counterfactual environments with the same task interface. SciGame contains a Historical collection of canonical laws and a live Temporal collection curated from papers published after model knowledge cutoffs. It evaluates agents in candidate-guided Identification and open-ended Discovery settings. Each setting runs under Prior-only, Fixed, and Adaptive protocols. Experiments on five frontier models yield three findings. First, familiar priors hurt performance once the governing relation is altered. Second, adaptive experimentation helps the strongest models but harms weaker ones under limited budgets. Third, good explanations can hide quantitative failures. Recovering the exact symbolic form remains the main bottleneck, even when agents interpret evidence correctly. Current agents can investigate systems actively, but inducing exact laws in unfamiliar settings remains an open challenge.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37917

What Actually Matters? A Paired Evaluation of Inference Settings for $π_{0.5}$ on BEHAVIOR-1K

Ruben Hammele, Samira Huber, Mohammad Nazeri, Amirreza Payandeh, Alexandyr T. Card, Aaron Nguyen, Anuj Pokhrel, Daeun Song 等 10 位作者

原文摘要

Vision-Language-Action (VLA) models offer a promising paradigm for general-purpose household robotics. However, inference and data-collection strategies that have been deployed in smaller-scale settings do not necessarily generalize to large-scale, diverse task suites. To address this gap, we conduct a systematic, paired evaluation of previously proposed inference and data-collection strategies across all 100 tasks. Our evaluation uses a fine-tuned $π_{0.5}$ model based on the 2025 BEHAVIOR Challenge winner, which achieves a Q-score of 0.39 on the public test set. These results show that proposed strategies do not transfer uniformly to new environments and tasks. Project page, videos, and detailed analysis: https://rubenhammele.github.io/behavior2026

cs.RO · cs.AI · cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗