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

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 06:41 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 06:56 — 2026-11-22 06:56(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:2026-11-22 06:41最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

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

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

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 8,992 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 06:39(北京时间)
版本更新 · v2arXiv:2610.34923

Attack logics, not outputs: Concept-based Property Attacks for Shortcut Elimination in Neural Networks

Raik Dankworth, Felix Mächtle, Thomas Eisenbarth, Gesina Schwalbe

原文摘要

Deep neural networks (NNs) for computer vision are vulnerable to adversarial attacks, such that minuscule malicious changes to inputs may induce unintuitive outputs. One key approach to verify and mitigate such robustness issues is to falsify expected output behavior, which enables local robustness guarantees and adversarial training. Due to the black-box nature of NNs, current attacks only falsify a class of the final output, such as flipping from $\text{stop_sign}$ to $\neg \text{stop_sign}$. In this work we argue that robustness analysis should focus more generally on logical inconsistencies in concept-level reasoning rather than solely on output misclassification. We formalize this perspective through concept-based properties, i.e., constraints over human-interpretable concepts such as $\text{red} \land \text{octogonal} \implies \text{stop_sign}$ and study the falsification of such properties as a principled form of adversarial attack. Furthermore, an implementation of concept-based properties on already trained NNs is proposed using techniques from concept-based explainable artificial intelligence (C-XAI). For that we formally prove that attacks on concept-based properties are expected to have a reduced search space compared to simple class falsification, whilst arguably be more aligned with intuitive robustness targets. The practical effectiveness of our approach for logically informed adversarial training is shown in an empirical study across multiple models and datasets, including both vision and a security-relevant code processing task. Our results demonstrate that concept-level falsification generalizes classical adversarial attacks: Retraining on our novel attacks maintains robustness gains as compared to classical adversarial retraining whilst better eliminating semantic biases.

cs.CR · cs.LG

版本更新 · v2arXiv:2609.32732

Plan-to-Synthesis: Cross-City Human Mobility Generation via Semantic Latent Flow Matching

Zhoufu Wang, Baoshen Guo, Zhiqing Hong, Junyi Li, Kailai Sun, Heye Huang, Alok Prakash, Shenhao Wang 等 9 位作者

原文摘要

Human mobility generation aims to synthesize realistic point-of-interest (POI) visitation trajectories and has become an important tool for travel behavior modeling, transportation management, and urban planning. Existing diffusion-based methods achieve high fidelity but require per-city generation, given the inherent heterogeneity of geospatial locations and POI categories, while large language model-based methods generalize across cities but remain too costly at scale, especially for long-horizon trajectory generation. To address this, we propose SeMoFlow, a Semantic human Mobility generation framework based on latent Flow matching. We first encode heterogeneous POIs from different cities into a shared cross-city representation space via hierarchical Semantic IDs, where shared prefixes capture transferable semantics, and successive codes progressively refine the representation toward individual POIs. Building on the semantic IDs, SeMoFlow follows a plan-to-synthesis hierarchical generation paradigm, in which an autoregressive planner generates coarse-grained semantic and recurrence patterns, and a flow matching realizer synthesizes fine-grained suffix latents. The generated latents are subsequently decoded and grounded to concrete POIs. Extensive experiments on large-scale multi-city datasets show that SeMoFlow achieves higher trajectory fidelity than existing baselines, preserves city-specific mobility motifs, and supports both joint multi-city generation and effective cross-city transfer. The code is available at \href{https://github.com/urban-mobility-generation/SeMoFlow}{https://github.com/urban-mobility-generation/SeMoFlow}.

cs.SI · cs.LG

版本更新 · v2arXiv:2606.19350

Pruning via Causal Attribution Preserves Reasoning Performance in Large Language Models

Amogh Sheth, Andrew Lin, Biruk Assefa, Yi Wen Huang, Yuhao Ge

原文摘要

Large language models (LLMs) excel at multi-step reasoning but incur substantial inference cost. We introduce Causal Attribution Pruning (CAP), a training-free method that identifies critical attention heads by measuring their causal impact on reasoning tasks and uses these head-level scores to guide fine-grained weight pruning. For each attention head, CAP estimates the expected performance degradation when the head is masked during forward passes on a small calibration set of reasoning problems. These causal scores are then converted into weight-level importance values for the corresponding projection matrices. Unlike magnitude-only or activation-based criteria, CAP's interventional measurement directly captures each head's functional contribution, yielding relative accuracy gains of up to 61% over Wanda on ARC-Challenge at 20% sparsity. We evaluate CAP on GSM8K, StrategyQA, and ARC-Challenge using Llama-3-8B-Instruct and Mistral-7B-Instruct at 10%, 20%, and 50% sparsity. At moderate sparsity (10-20%), CAP improves over Wanda in most model-benchmark configurations. with especially large gains on ARC-Challenge for Llama-3. Our results suggest that attention-head-level causal attribution can better preserve reasoning performance on downstream benchmarks than correlational pruning criteria at equivalent sparsity, while remaining limited by coarse MLP attribution at 50% sparsity.

cs.CL

版本更新 · v2arXiv:2606.25435

Kom8ndor: An IEEE 802.11bn-Oriented Simulator for Wi-Fi 8 and Beyond

Francesc Wilhelmi, Sergio Barrachina-Muñoz, Boris Bellalta

原文摘要

The upcoming IEEE 802.11bn amendment marks a paradigm shift in Wi-Fi, which will pose ambitious performance targets under the paradigm of Ultra-High Reliability (UHR). To understand the implications of such a new technology and to support early research and protocol design for Wi-Fi 8, we present Kom8ndor. This discrete-event network simulator extends the open-source Komondor platform (a simulator validated against ns-3 and other analytical tools) with 802.11bn features. Among the newly added functionalities, we highlight Multi-Access Point Coordination (MAPC)-including Coordinated Time-Division Multiple Access (Co-TDMA), Coordinated Spatial Reuse (Co-SR), and Coordinated Beamforming (Co-BF)-, Non-Primary Channel Access (NPCA), and Dynamic Subband Operation (DSO). Beyond Wi-Fi 8 implementations, Kom8ndor introduces novel functionalities (e.g., a machine learning wrapper for building AI-based protocols) and a modular design to boost the prototyping and research of future Wi-Fi technologies. Kom8ndor is open-source (GNU GPLv3) and available at https://github.com/wn-upf/Komondor.

cs.NI

版本更新 · v3arXiv:2610.07853

Lost in the bf16 Cast: Exporting Ternary Language Models Can Revert Most Low-Learning-Rate Code Changes

Avichal Sahai, Nishant Raj, Animesh Srivastava

原文摘要

Ternary language models such as BitNet b1.58, Falcon-E and BitCPM are fine-tuned through higher-precision latents and deployed as ternary codes by an export that, in the labs' documented pipelines, first casts latents to bf16. We audit releases from three labs. In released checkpoints, fp32 quantization of the shipped latents disagrees with deployed codes on 0.83-1.77% of codes (Falcon-E, BitCPM) and 1.530% (2B-4T); most Falcon-E and BitCPM disagreements are bf16 products exactly on the threshold, which ties-to-even maps to zero, and the unmodified onebitllms exporter reproduces all four Falcon-E releases byte for byte. At fine-tuned endpoints with ULP-matched rates, the documented export lowers greedy GSM8K strict accuracy from 58.79% to 0.78% (Falcon-E-1B-Base) and 36.13% to 0.39% (BitCPM-CANN-0.5B), and a bf16 save and reload lowers 2B-4T's by 27.54 points while its last-number accuracy rises at that endpoint. The strict decrease recurs at each of three new seeds in all three models and has the same direction on 607 reserve test rows, but it is recipe-dependent: at Falcon-E's online-loss-selected rate the export was non-inferior, and after a longer recipe no difference was detected. Two remedies, writing the trained codes directly or adjusting bf16 inputs so unchanged tools emit them, met an inherited 4-point strict-accuracy non-inferiority criterion in all three models, also for the pooled mean over three fixed new trajectories per model and, separately, on the reserve rows. In a frozen study of bf16 latents in fine-tuning (one task, one trajectory per arm), native bf16 writes left 2B-4T's endpoint codes unchanged and changed one Falcon-E code; emulated stochastic-rounding and compensated writers changed codes and were non-inferior to fp32 training at that margin. In two model families, randomized threshold-distance interventions support distance-dependent selection of changed codes.

cs.LG · cs.CL

版本更新 · v3arXiv:2502.09254

AnomalyGFM: Graph Foundation Model for Zero/Few-shot Anomaly Detection

Hezhe Qiao, Chaoxi Niu, Ling Chen, Guansong Pang

原文摘要

Graph anomaly detection (GAD) aims to identify abnormal nodes that differ from the majority of the nodes in a graph, which has been attracting significant attention in recent years. Existing generalist graph models have achieved remarkable success in different graph tasks but struggle to generalize to the GAD task. This limitation arises from their difficulty in learning generalized knowledge for capturing the inherently infrequent, irregular and heterogeneous abnormality patterns in graphs from different domains. To address this challenge, we propose AnomalyGFM, a GAD-oriented graph foundation model that supports zero-shot inference and few-shot prompt tuning for GAD in diverse graph datasets. One key insight is that graph-agnostic representations for normal and abnormal classes are required to support effective zero/few-shot GAD across different graphs. Motivated by this, AnomalyGFM is pre-trained to align data-independent, learnable normal and abnormal class prototypes with node representation residuals (i.e., representation deviation of a node from its neighbors). The residual features essentially project the node information into a unified feature space where we can effectively measure the abnormality of nodes from different graphs in a consistent way. This provides a driving force for the learning of graph-agnostic, discriminative prototypes for the normal and abnormal classes, which can be used to enable zero-shot GAD on new graphs, including very large-scale graphs. If there are few-shot labeled normal nodes available in the new graphs, AnomalyGFM can further support prompt tuning to leverage these nodes for better adaptation. Comprehensive experiments on 11 widely-used GAD datasets with real anomalies, demonstrate that AnomalyGFM significantly outperforms state-of-the-art competing methods under both zero- and few-shot GAD settings.

cs.LG · cs.AI

版本更新 · v4arXiv:2609.11115

Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation

Koutian Wu, Wenjun Zhang, Junjie Zhou, Pengqian Han, Qiming Bao, Ergan Shang, Jiayu Wang, Junkai Wang 等 16 位作者

原文摘要

Benchmark researchers and developers of large language models (LLMs) and other AI systems need to find relevant evaluations, locate their benchmark datasets and code, and understand the settings behind reported scores. We present Benchmark Radar, a living database and search engine for retrieval and discovery of AI benchmarks, covering LLM evaluation, agentic and tool-use benchmarks, coding, reasoning, safety, and domain-specific evaluations. The system combines daily discovery of benchmark papers, repositories, datasets, and releases with a searchable benchmark catalog, mentions in model cards and technical reports, and score histories. It retains source identities and citations so readers can inspect candidate benchmarks and their evaluation evidence. Daily discovery draws on 37 sources: 13 direct connectors and 24 first-party research and engineering feeds. The catalog contains 1,283 source records drawn from 4 benchmark catalogs and 12,916 numeric observations on 790 records. We describe collection and retrieval, audit the full catalog, and examine benchmark saturation, adoption trends, and the limits of score comparisons. A worked example walks through a complete prior-art search, showing how to query the catalog and inspect benchmark evidence when designing a new evaluation. We release the web dashboard with a benchmark leaderboard, a Pareto frontier view of score against measured use, saturation and trend views, daily feeds, downloadable evidence, a command-line interface (CLI) for offline queries, and reproducible analysis.

cs.AI · cs.IR

版本更新 · v8arXiv:2402.11887

Generative Semi-supervised Graph Anomaly Detection

Hezhe Qiao, Qingsong Wen, Xiaoli Li, Ee-Peng Lim, Guansong Pang

原文摘要

This work considers a practical semi-supervised graph anomaly detection (GAD) scenario, where part of the nodes in a graph are known to be normal, contrasting to the extensively explored unsupervised setting with a fully unlabeled graph. We reveal that having access to the normal nodes, even just a small percentage of normal nodes, helps enhance the detection performance of existing unsupervised GAD methods when they are adapted to the semi-supervised setting. However, their utilization of these normal nodes is limited. In this paper, we propose a novel Generative GAD approach (namely GGAD) for the semi-supervised scenario to better exploit the normal nodes. The key idea is to generate pseudo anomaly nodes, referred to as 'outlier nodes', for providing effective negative node samples in training a discriminative one-class classifier. The main challenge here lies in the lack of ground truth information about real anomaly nodes. To address this challenge, GGAD is designed to leverage two important priors about the anomaly nodes -- asymmetric local affinity and egocentric closeness -- to generate reliable outlier nodes that assimilate anomaly nodes in both graph structure and feature representations. Comprehensive experiments on six real-world GAD datasets are performed to establish a benchmark for semi-supervised GAD and show that GGAD substantially outperforms state-of-the-art unsupervised and semi-supervised GAD methods with varying numbers of training normal nodes. Code will be made available at https://github.com/mala-lab/GGAD.

cs.LG

版本更新 · v2arXiv:2308.01463

SemDiff: Binary Similarity Detection by Diffing Key-Semantics Graphs

Zian Liu, Xiaoxi Meng, Viet Vo, Siqi Ma, Chao Chen, Dongxi Liu, Jun Zhang, Shigang Liu 等 10 位作者

原文摘要

Binary similarity detection is a critical technique that has been applied in many real-world scenarios where source code is not available, e.g., bug search, malware analysis, and code plagiarism detection. Existing works are ineffective in detecting similar binaries in cases where different compiling optimizations, compilers, source code versions, or obfuscation are deployed. We observe that all the cases do not change a binary's key code behaviors although they significantly modify its syntax and structure. With this key observation, we extract a set of key instructions from a binary to capture its key code behaviors. By detecting the similarity between two binaries' key instructions, we can address well the ineffectiveness limitation of existing works. Specifically, we translate each extracted key instruction into a self-defined key expression, generating a key-semantics graph based on the binary's control flow. Each node in the key-semantics graph denotes a key instruction, and the node attribute is the key expression. To quantify the similarity between two given key-semantics graphs, we first serialize each graph into a sequence of key expressions by topological sort. Then, we tokenize and concatenate key expressions to generate token lists. We calculate the locality-sensitive hash value for all token lists and quantify their similarity. %We implement a prototype, called SemDiff, consisting of two modules: graph generation and graph diffing. The first module generates a pair of key-semantics graphs and the second module diffs the graphs. Our evaluation results show that overall, SemDiff outperforms state-of-the-art tools when detecting the similarity of binaries generated from different optimization levels, compilers, and obfuscations. SemDiff is also effective for library version search and finding similar vulnerabilities in firmware.

cs.CR

版本更新 · v2arXiv:2608.20822

Interaction Effects Between Learner Characteristics and Dialogue Format in LLM- and TTS-Generated Dialogue-Based Lessons

Fumie Watanabe, Gendo Kumoi, Tota Suko, Takashi Ishida, Yuko Kuma, Manabu Kobayashi, Shigeichi Hirasawa

原文摘要

Large language models and text-to-speech technology enable low-cost production of dialogue-based lessons: videos in which two speakers converse. The speakers' roles can vary, but little is known about whether all learners respond alike to such differences. In a repeated-measures design, 222 first-year high school students viewed lessons in three formats: a teacher and a student (TS), two students (SS), and two teachers (TT). Within the aptitude-treatment interaction framework, linear mixed-effects models tested whether associations between learner characteristics and outcomes differed by format. The learner characteristics were experiential learning style - seeking challenging, new experiences (CE factor) and learning by reflecting on experience (RCE factor) - and critical thinking disposition; the outcomes were motivation based on the ARCS model, self-reported learning outcomes, and overall evaluation. For motivation, both factors interacted with format: the CE factor's association differed between TS and TT, and the RCE factor's slope was significantly positive in TS and SS and significantly larger in TS than TT. For learning outcomes, no interaction was detected, but critical thinking disposition was positively associated with them. For overall evaluation, again no interaction was detected, but TT was rated lowest. Given small-to-medium interaction effects, these findings are preliminary evidence to inform personalized learning design.

cs.CY

版本更新 · v2arXiv:2610.32118

Beyond Correctness: How Novice Software Engineering Students Exercise Oversight of Generative AI

Ali Shakiba, Thomas Chaffey

原文摘要

Generative AI (GenAI) is shifting software engineering students' work from producing artefacts towards evaluating and supervising AI-generated outputs. However, little is known about what characteristics students identify in outputs when reporting interventions, or how they exercise oversight during authentic software engineering work. We analysed 962 student-AI interaction turns documented by 145 first-year software engineering students through structured AI Journals, including 172 student-declared interventions. Using a multi-dimensional coding framework, we characterised the output characteristics identified in these reported interventions, students' reasons for intervening, the actions they took, and how those actions were enacted. Fitness problems were identified in 74.4% of interventions, compared with 16.9% involving correctness problems, indicating that oversight more often concerned whether plausible AI outputs were suitable for the engineering task than whether they contained explicit errors. Among classifiable interventions, students most frequently modified generated outputs (51.0%) or refined their prompts (28.2%), with both response types commonly associated with engineering fit. Within-student analysis further showed that outputs perceived as containing minor flaws were associated with lower evaluation confidence than outputs perceived as perfect. Taken together, these findings characterise novice AI oversight as a process that extends beyond error detection to encompass both judgement of fitness for purpose and active intervention in AI-assisted engineering work.

cs.SE · cs.HC

版本更新 · v2arXiv:2601.12701

RPT*: Global Planning with Probabilistic Terminals for Target Search in Complex Environments

Yunpeng Lyu, Chao Cao, Ji Zhang, Howie Choset, Zhongqiang Ren

原文摘要

Routing problems such as Hamiltonian Path Problem (HPP), seek a path to visit all the vertices in a graph while minimizing the path cost. This paper studies a variant, HPP with Probabilistic Terminals (HPP-PT), where each vertex has a probability representing the likelihood that the robot's path terminates there, and the objective is to minimize the expected path cost. HPP-PT arises in target object search, where a mobile robot must visit all candidate locations to find an object, and prior knowledge of the object's location is expressed as vertex probabilities. While routing problems have been studied for decades, few of them consider uncertainty as required in this work. The challenge lies not only in optimality ordering the vertices, as in standard HPP, but also in handling history dependency: the expected path cost depends on the order in which vertices were previously visited. This makes many existing methods inefficient or inapplicable. To address the challenge, we propose a search-based approach RPT* with solution optimality guarantees, which leverages dynamic programming in a new state space to bypass the history dependency and novel heuristics to speed up the computation. Building on RPT*, we design a Hierarchical Autonomous Target Search (HATS) system that combines RPT* with either Bayesian filtering for lifelong target search with noisy sensors, or autonomous exploration to find targets in unknown environments. Experiments in both simulation and real robot show that our approach can naturally balance between exploitation and exploration, thereby finding targets more quickly on average than baseline methods.

cs.RO · cs.CG

版本更新 · v3arXiv:2512.16074

In-Context Multi-Operator Learning with DeepOSets

Shao-Ting Chiu, Aditya Nambiar, Ali Syed, Jonathan W. Siegel, Ulisses Braga-Neto

原文摘要

An important application of neural networks in scientific computing is non-linear operator learning. In this framework, a neural network is trained to fit a non-linear map between infinite dimensional spaces, for example, the solution operator of ordinary and partial differential equations. Recently, inspired by the discovery of in-context learning for large language models, an even more ambitious paradigm has been explored, called multi-operator learning. In this approach, a neural network is trained to learn many different operators at the same time. At inference time, the network is passed a small number of example input and output pairs to disambiguate the desired operator. In this work, we provide a precise mathematical formulation of the multi-operator learning problem, propose a parameter-efficient, attention-free architecture, called DeepOSets, and prove its universality in the in-context multi-operator learning task. We perform experiments demonstrating the efficacy of DeepOSets on several benchmarks, including Burgers' equation, 1D and 2D Darcy flow, and a variety of initial-value and boundary-value differential equations. In a comparison with the transformer-based ICON model on the 1D Darcy problem, under a small training budget (10k steps), DeepOSets attained lower error at every context size with 19% of the parameters, while with an extended budget (100k steps), ICON attains 26-41% lower error, but at the cost of roughly 218$\times$ more training time, 12$\times$ higher inference latency, and 5.3$\times$ more parameters.

cs.LG

版本更新 · v3arXiv:2608.18577

Online Service with Per-Batch Maximum Delays

Tianhang Lu, Runtian Ren, Shengcai Liu, Ke Tang

原文摘要

We study online service with per-batch maximum delays on a finite metric space. Requests arrive over time, and a server serves each batch by following a walk visiting its requests' locations. Movement is instantaneous. The objective is to minimize the total distance traveled by the server plus the sum, over all batches, of the maximum waiting time in each batch. We give deterministic polynomial-time algorithms with competitive ratios $10$ on finite lines, $12$ on weighted trees, and $20$ on arbitrary finite metrics. Unlike additive delay, maximum delay allows younger requests to join a batch without increasing its delay charge. Our algorithms coordinate service using a common waiting clock and a threshold determined by the metric. The analysis uses certificates for groups of requests to compare this policy with any offline schedule, even one that serves different batches and follows different walks. This comparison shows that coordinating service in this way loses only a constant factor. The bounds hold whether the server must serve requests it visits or may leave them unserved; the two rules also have equal offline optimal costs. Offline optimization is polynomial on lines and explicitly represented weighted trees, and NP hard on general metrics. When arrivals are announced but locations are hidden until visited, we give an $84$-competitive algorithm on a known finite line under either rule.

cs.DS

版本更新 · v2arXiv:2407.18524

She Works, He Works: A Curious Exploration of Gender Bias in AI-Generated Imagery

Amalia Foka

原文摘要

She Works, He Works is an interdisciplinary project that combines feminist visual theory, AI critique, and artistic practice to examine gender representation in AI-generated imagery. By juxtaposing text-to-image outputs of male and female construction workers, it reveals how societal biases manifest in generative AI systems. The study employs critically crafted prompts that blend traditionally gendered traits with unconventional contexts, exposing disparities in representation-emphasizing aesthetics and agility for women versus authority and professionalism for men. Grounded in Griselda Pollock's feminist insights on visual culture, the project positions AI as both a technological and cultural actor, capable of perpetuating stereotypes and enabling critique. As both a study and an artwork, the project underscores the transformative potential of AI to reimagine gender norms and inspire equitable narratives. It highlights the ethical implications of AI in creative industries, calling for transparent practices, diverse datasets, and reflexive engagement with AI's cultural impact. Through its integration of critical analysis and artistic exploration, She Works, He Works contributes to broader discussions on inclusive AI development and the role of art in fostering societal change. This dual approach showcases the power of AI as a medium for critique and a tool for envisioning more just and inclusive futures.

cs.CY · cs.AI · cs.CV

版本更新 · v2arXiv:2608.04484

Even more properties of parity based bit-counting complexity classes

Tayfun Pay

原文摘要

We investigate several additional properties of parity based bit-counting complexity classes ${\bf B_{|0|\oplus}P}$ and ${\bf B_{|1|\oplus}P}$. We first prove that ${\bf C_=P}={\bf ES}={\bf MNS}\subseteq{\bf P}^{{\bf B_{|1|\oplus}P}}={\bf P}^{{\bf B_{|0|\oplus}P}}$. We then build upon the four consecutive value theorem from \cite{P26b} and develop a bit recovery procedure that reconstructs the binary representation of a ${\bf \#P}$ value one bit at a time by querying appropriately padded and shifted versions of that value. Using this procedure, we prove that ${\bf PP}\subseteq{\bf P}^{{\bf B_{|1|\oplus}P}}$ and ${\bf PP}\subseteq{\bf P}^{{\bf B_{|0|\oplus}P}}$, which consequently yields ${\bf P}^{\bf PP}={\bf P}^{\bf B_{|0|\oplus}P}={\bf P}^{\bf B_{|1|\oplus}P}$. Furthermore, since this procedure recovers the complete numerical output of a ${\bf \#P}$ function, it also establishes the functional containments of ${\bf \#P}\subseteq{\bf FP}^{{\bf B_{|1|\oplus}P}}$ and ${\bf \#P}\subseteq{\bf FP}^{{\bf B_{|0|\oplus}P}}$. We additionally demonstrate that caching repeated oracle queries reduces the number of distinct queries required for the bit recovery procedure from $4n$ to $2n+2$. Finally, we prove that parity based bit-counting hierarchies ${\bf ΣB_{|0|\oplus}H}$, ${\bf ΣB_{|1|\oplus}H}$, ${\bf ΔB_{|0|\oplus}H}$ and ${\bf ΔB_{|1|\oplus}H}$ contain ${\bf CH}$. As a result, these hierarchies coincide with ${\bf CH}$ since the reverse containments were already established in \cite{P26b}.

cs.CC

版本更新 · v2arXiv:2610.35866

Auto-Research Arena: Benchmarking and Advancing Auto-Research in Language Modeling

Xi Chen, Chongjian Ge, Yiran Xu, Yiqun Mei, Henrik I. Christensen, Hao Tan, Ziwen Chen, Hanwen Jiang

原文摘要

As autonomous research systems become more capable, benchmarks must both evaluate their performance and support meaningful research progress. We introduce Auto-Research Arena, a multi-target benchmark for evaluating autonomous research systems and discovering ideas in language modeling. Arena supports diverse research objectives within a shared experimental environment by separating admissibility from improvement: model quality and resource constraints determine whether a result qualifies, while the selected target measures progress among admissible results. We instantiate Arena in language model pretraining with nine targets spanning model, data, training, and inference efficiency, and evaluate seven research harnesses using two foundation models. Arena clearly differentiates existing harnesses across research objectives, with several sophisticated methods outperformed by our simple sequential search baseline, indicating substantial headroom in current auto-research systems. Beyond evaluation, Arena reveals a substantially broader frontier of model and system ideas aligned with active research directions. Reusing these discoveries in a new quality-driven search yields lower training loss under matched data and FLOPs and lower held-out BPB at the same model size. Together, Arena provides a common framework for benchmarking autonomous research and expanding its scope in language modeling. The code is available at https://github.com/Auto-Research-Arena/auto-research-arena

cs.LG

版本更新 · v3arXiv:2603.29924

Abstraction in Style: Beyond Texture and Color

Min Lu, Yuanfeng He, Anthony Chen, Jianhuang He, Pu Wang, Daniel Cohen-Or, Hui Huang

原文摘要

Artistic styles often embed abstraction beyond surface appearance, involving deliberate reinterpretation of structure rather than mere changes in texture or color. Conventional style transfer methods typically preserve the input geometry and therefore struggle to capture this deeper abstraction behavior, especially for illustrative and nonphotorealistic styles. In this work, we introduce Abstraction in Style (AiS), a generative framework that separates structural abstraction from visual stylization. Given a target image and a small set of style exemplars, AiS first derives an intermediate abstraction proxy that reinterprets the target's structure in accordance with the abstraction logic exhibited by the style. The proxy captures semantic structure while relaxing geometric fidelity, enabling subsequent stylization to operate on an abstracted representation rather than the original image. In a second stage, the abstraction proxy is rendered to produce the final stylized output, preserving visual coherence with the reference style. Both stages are implemented using a shared image space analogy, enabling transformations to be learned from visual exemplars without explicit geometric supervision. By decoupling abstraction from appearance and treating abstraction as an explicit, transferable process, AiS supports a wider range of stylistic transformations, improves controllability, and enables more expressive stylization.

cs.CV

版本更新 · v2arXiv:2610.18420

Agaram 2.5B: The First Tamil-First Language Model Trained from Scratch with Tool Calling. A Playbook for Under-Represented Languages

Ramchand Kumaresan, Madhusudhanan G, Kaushik Kezendirane

原文摘要

We present Agaram 2.5B, a Tamil-first language model trained from scratch that converses in Tamil script, romanized Tanglish and English, and calls tools. Our first model, Agaram 1.5B, guided the new base, tokenizer and fine-tuning recipe: we pretrained a new 2.53B-parameter base on 50 billion tokens, 58% of them Tamil, with a tokenizer that needs 1.55 tokens per Tamil word where Qwen2.5's needs 9.44. A four-day public preview of our first 2.5B chat model showed where it fell short with real users, and we rebuilt supervised fine-tuning around what we saw, on 222,662 records. The released model scores above Sarvam-1 in all six translation directions we measured (FLORES chrF 56.9 into Tamil and 55.4 into English), chooses the expected tool on all 25 prompts of a tool set that was used during checkpoint selection and whose schemas appear in training, with exact arguments on 16, and was preferred over the preview model by an LLM judge on 100 sealed human-written prompts (net preference +30 points, 95% interval +14.5 to +45.0). On FLORES it also scores above Google's Gemma 4 E4B-it and our fine-tuned variant of it in both directions, with 2.53B parameters against E4B's 4.5B effective parameters. Factual knowledge and reliable refusal of harmful requests remain open problems, which we set out as future work. The base and chat weights and GGUF files are released under Apache-2.0, and this report gives a full account of the data, training and evaluation as a playbook for building language models for under-represented languages.

cs.CL · cs.AI · cs.LG

版本更新 · v2arXiv:2009.02815

Optimal Inapproximability of Satisfiable $k$-LIN over Non-Abelian Groups

Amey Bhangale, Subhash Khot

原文摘要

A seminal result of Håstad [J. ACM, 48(4):798--859, 2001] shows that it is NP-hard to find an assignment that satisfies $\frac{1}{|G|}+\varepsilon$ fraction of the constraints of a given $k$-LIN instance over an abelian group, even if there is an assignment that satisfies $(1-\varepsilon)$ fraction of the constraints, for any constant $\varepsilon>0$. Engebretsen et al. [Theoretical Computer Science, 312(1):17--45, 2004] later showed that the same hardness result holds for $k$-LIN instances over any finite non-abelian group. Unlike the abelian case, where we can efficiently find a solution if the instance is satisfiable, in the non-abelian case, it is NP-complete to decide if a given system of linear equations is satisfiable or not, as shown by Goldmann and Russell [Information and Computation, 178(1):253--262. 2002]. Surprisingly, for certain non-abelian groups $G$, given a satisfiable $k$-LIN instance over $G$, one can in fact do better than just outputting a random assignment using a simple but clever algorithm. The approximation factor achieved by this algorithm varies with the underlying group. In this paper, we show that this algorithm is {\em optimal} by proving a tight hardness of approximation of satisfiable $k$-LIN instance over {\em any} non-abelian $G$, assuming $P \neq NP$. As a corollary, we also get $3$-query probabilistically checkable proofs with perfect completeness over large alphabets with improved soundness. Our proof crucially uses structural properties captured by Gowers' notion of {\em quasi-randomness} for non-abelian groups [Combinatorics, Probability and Computing, 17(3):363--387, 2008].

cs.CC

版本更新 · v2arXiv:2605.11225

PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement

Tuo Zhang, Alin-Ionut Popa, Yan Xu, Rui Song, Dimitrios Dimitriadis

原文摘要

Large language model (LLM)-based agents frequently generate seemingly coherent plans that fail upon execution due to infeasible actions, constraint violations, and compounding errors over extended horizons. PIVOT (Plan-Inspect-eVOlve Trajectories) addresses this plan-execution misalignment through a self-supervised framework that treats trajectories as optimizable objects iteratively refined via environment interaction. The framework comprises four stages: PLAN generates candidate trajectories; INSPECT executes them and computes structured losses with textual gradients encoding plan-execution discrepancies; EVOLVE applies these signals to produce improved trajectories; and VERIFY performs a final global check against task constraints. A monotonic acceptance process ensures a non-decreasing solution quality. Empirical evaluations on DeepPlanning and GAIA demonstrate state-of-the-art performance: with human-in-the-loop (HITL) feedback, PIVOT establishes a strong upper bound up to 94% relative improvement in constraint satisfaction, while its fully autonomous variant retains substantial gains, showing that the core trajectory-refinement mechanism remains effective without external supervision. At the same time, PIVOT remains computationally efficient, requiring up to 3x to 5x fewer tokens than competing refinement methods. These findings establish that (self- or human-supervised) feedback-based trajectory optimization is a principled methodology for mitigating plan-execution gaps in autonomous agent systems.

cs.AI · cs.LG · cs.MA

版本更新 · v2arXiv:2606.16602

PhysGuard: Fisher-Guided Gradient Projection for Sim-to-Real Neural PDE Surrogates

Changjian Zhou, Junfeng Fang, Negin Yousefpour, Peng Wu, Bin Yan, Guillermo A. Narsilio

原文摘要

Neural operator models trained on simulation data often lose accuracy when applied to experimental measurements due to the sim-to-real gap. Standard fine-tuning with limited real data can reduce this gap, but it may also damage the core physics-relevant representations learned during pretraining. Although knowledge-preserving adaptation has been widely investigated in vision or language tasks, it remains unclear whether these methods are suitable for neural operators whose architectures and protected knowledge are fundamentally different. Neural operators need to preserve core-scale physical structures rather than semantic or visual features. We propose PhysGuard, a physics-preserving framework for accurate sim-to-real adaptation of neural operators. Specifically, PhysGuard uses the empirical Fisher Information Matrix computed on simulation data to identify physics-critical parameter directions, then restricts fine-tuning updates to directions that do not interfere with them. A layer-wise Gram-matrix formulation makes this efficient for models with millions of parameters, while an adaptive threshold automatically determines the protected subspace size. A spectral probe experiment shows that the dominant Fisher directions are strongly associated with low-frequency output structures. Experiments on benchmark across four neural operator architectures and different physical systems show that PhysGuard performs strongly on most evaluation metrics compared to baselines. The benefits are most evident under severe domain shift, where it reduces low-frequency error by up to 32% compared to standard fine-tuning while maintaining adaptability. Our code is available at https://github.com/Data-Driven-Computational-Geotechnics/PhysGuard.

cs.LG · math.NA

版本更新 · v2arXiv:2610.35219

Multi-Agent Relay Thinking

Xu Liu, Jungang Qiao, Guikun Chen, Xiaojuan Qi, Wenguan Wang

原文摘要

Existing multi-agent collaboration (MAC) methods have primarily explored a group thinking collaboration topology, where agents independently generate solutions and aggregate their outputs. In this work, we investigate an alternative relay thinking topology, where reasoning ownership is dynamically transferred across agents, allowing subsequent agents to inherit and refine an evolving reasoning trajectory. We introduce Multi-Agent Confidence-guided Relay (MACR), a framework that enables dynamical relay collaboration among agents. The key challenge is determining when reasoning should be relayed and which agent should continue the process. method addresses this challenge through confidence-guided relay triggering and a bidding mechanism that selects the next agent based on its confidence. Experiments on four benchmarks show that method outperforms the strongest single-model strategies in accuracy, e.g., +3.3% on MathVista and +3.9% on MMStar, and remains on par with multi-agent strategies while consuming 6.0x less token overhead on HallusionBench and MMStar. Further analysis demonstrates that relay collaboration enables heterogeneous agents to progressively integrate complementary insights, combining heterogeneous capabilities across reasoning stages. Our source code is available at https://github.com/67L1/MACR.

cs.CV

版本更新 · v2arXiv:2610.35313

CoPE-CGL: Community-aware Prototype Extraction for Replay-Free Continual Graph Learning

Bo-Young Lim, Seokhwan Kim, Kisung Lee, Hyuk-Yoon Kwon

原文摘要

Continual graph learning (CGL) maintains models as graphs evolve without retraining from scratch, while mitigating catastrophic forgetting. Existing methods typically target either transductive or inductive settings and often store past subgraphs or require task identifiers at inference. We propose Community-aware Prototype Extraction for Continual Graph Learning (CoPE-CGL), a replay-free framework that uses a parameter-free structural prior, precomputed by multi-hop Laplacian smoothing, to anchor learning, memory, and inference. CoPE-CGL combines topology-infused bottleneck adaptation, community-level prototypes, and dynamic routing by majority vote over node-to-prototype matches. The default protocol assumes each test graph comes from one learned task; a node-level variant handles mixed-task graphs. Each task adds at most a constant amount of storage, with no past graph data retained. At equal storage and without task identifiers, CoPE-CGL matches the strongest replay baseline even when it receives true task identifiers: average performance (AP) is 95.17% and 95.72% versus 94.28% and 95.82% on Arxiv and CoraFull, respectively, with 5.9-14.0 times faster runtime and zero forgetting. Across four transductive and three inductive benchmarks and mixed streams, CoPE-CGL exceeds the second-best of up to eleven baselines by up to 1.41, 6.32, and 9.33 AP percentage points, respectively. It runs 1.3-7.9 times faster end-to-end than the most accurate competitor on each benchmark and scales to the largest benchmark graph. On graphs mixing two tasks, its node-level variant achieves the best AP among CGL methods. The design targets homophilic graphs with community structure.

cs.LG · cs.DB

版本更新 · v11arXiv:1911.10116

Aggregative Efficiency of Bayesian Learning in Networks

Krishna Dasaratha, Kevin He

原文摘要

When individuals in a social network learn about an unknown state from private signals and neighbors' actions, the network structure often causes information loss. We consider rational agents and Gaussian signals in the canonical sequential social-learning problem and ask how the network changes the efficiency of signal aggregation. Rational actions in our model are log-linear functions of observations and admit a signal-counting interpretation of accuracy. Networks where agents observe multiple neighbors but not their common predecessors confound information, and even a small amount of confounding can lead to much lower accuracy. In a class of networks where agents move in generations and observe the previous generations, we quantify the information loss with an aggregative efficiency index. Aggregative efficiency is a simple function of network parameters: increasing in observations and decreasing in confounding. Later generations contribute little additional information, even when generations are arbitrarily large and agents observe arbitrarily far into the past.

econ.TH · cs.SI · econ.GN

版本更新 · v2arXiv:2610.33367

Pinching Antenna and Relay Assisted Joint Indoor Outdoor NOMA Communications with SWIPT

Amit Agarwal, Susmita Sain, Keshav Singh, Sudip Biswas

原文摘要

This paper presents a unified downlink architec- ture for serving indoor and outdoor users from a shared multi-antenna rooftop base station (BS). To overcome severe building-penetration loss, the BS transfers information and radio- frequency (RF) energy to an indoor access point (AP) using simultaneous wireless information and power transfer (SWIPT). The AP harvests this energy and performs amplify-and-forward (AF) relaying, enabling self-sustained indoor communication. A movable waveguide-mounted pinching antenna (PA) further improves indoor coverage by adapting its position to the prop- agation environment. For outdoor transmission, zero-forcing (ZF) beamforming suppresses inter-group interference, while power-domain non-orthogonal multiple access (NOMA) supports multiple users within each group. We maximize the outdoor weighted sum rate (WSR) while satisfying stringent indoor and outdoor quality-of-service (QoS) requirements. The resulting nonconvex problem jointly optimizes the BS power fraction, SWIPT power-splitting ratio, PA position, and NOMA power allocation. To obtain an efficient solution, we develop a two-stage method based on alternating optimization (AO) and sequential quadratic programming (SQP). Numerical results show that the proposed architecture improves outdoor spectral efficiency while maintaining reliable, energy-sustainable indoor coverage. Increasing the BS array size further raises the indoor QoS- satisfaction probability toward unity, even under demanding rate targets.

cs.IT

版本更新 · v3arXiv:2606.01621

Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation

Muyi Bao, Yuxin Cai, Hang Xu, Zongtai Li, Jinxi He, Jingfan Tang, Chen Lv, Ji Zhang 等 10 位作者

原文摘要

Vision-language models (VLMs) have become a common foundation for vision-and-language navigation in continuous environments (VLN-CE). Yet most VLM-based methods cast navigation as low-level action prediction, an interface that is ambiguous, tied to short-horizon motion primitives, and inefficient due to repeated VLM querying. We propose Goal2Pixel, a pure pixel-based paradigm that reformulates VLN-CE as navigable pixel grounding. Rather than predicting actions, Goal2Pixel uses the image plane as a unified spatial interface between VLM reasoning and robot motion: the model predicts a visible navigable pixel, which is back-projected into a 3D waypoint for forward navigation. Non-forward actions are encoded by auxiliary left/right/bottom regions for turning and stopping. To support long-horizon navigation, we propose ViKeyMem, a visibility-aware keyframe memory, achieving a favorable performance-efficiency trade-off while reducing training cost by over 50%. To adapt pretrained VLMs to navigable pixel grounding, we introduce semantic embeddings and coordinate-aware auxiliary losses. Among methods trained without external data, Goal2Pixel achieves competitive state-of-the-art performance on R2R-CE and RxR-CE. On R2R-CE Val-Unseen, it achieves 54.1% SR and 52.5% SPL with only 7.75 VLM calls per episode. Compared with direct action prediction, Goal2Pixel improves SR by 21.2 percentage points while requiring 6 times fewer VLM calls. Project Page: https://baobao0926.github.io/Goal2Pixel/.

cs.CV · cs.RO

版本更新 · v3arXiv:2602.10528

A swap-adversarial framework for domain generalization in pre- and post-stimulation Parkinsonian state classification

Seongwon Jin, Hanseul Choi, Sunggu Yang, Sungho Park, Jibum Kim

原文摘要

We propose a novel swap-adversarial framework that mitigates high inter-subject variability and the high-dimensional low-sample-size problem in electrocorticography (ECoG) data. It achieves robust domain generalization across ECoG and electroencephalography (EEG)-based brain-computer interface datasets. Our framework integrates (1) robust preprocessing, (2) inter-subject balanced channel swap (ISBCS) for cross-subject augmentation, and (3) domain-adversarial learning (DAL) to suppress subject-specific bias. The ISBCS method is a bio-inspired channel swapping strategy that exchanges only functionally corresponding channels across subjects, guided by a brain map, to mitigate inter-subject distribution differences. The DAL strategy encourages the model to learn task-relevant shared features. In addition, we introduce a new ECoG dataset, the first reproducible benchmark, which is constructed from long-term ECoG recordings of 6-hydroxydopamine-induced rat models and annotated with neural responses measured before and after electrical stimulation. We validate the effectiveness of this framework through extensive experiments under cross-subject, cross-session, and cross-dataset settings. Our results show that the proposed framework exhibits the best and robust generalization performance both for our newly constructed ECoG and public EEG datasets.

cs.LG · cs.AI

版本更新 · v3arXiv:2608.29249

Validating FKG.in: Soundness Assessment in LLM-Augmented Indian Food Knowledge

Saransh Kumar Gupta, Armaan Shah, Lipika Dey, Partha Pratim Das, Ramesh Jain

原文摘要

The online culinary ecosystem is increasingly populated by recipe content generated, modified, or summarized by LLMs. Although often convincing, such outputs may contain hallucinated ingredients, misrepresented quantities, or culturally implausible combinations, limiting their suitability for downstream applications and knowledge graph construction. In this paper, we present a semi-automated soundness assessment workflow for validating structured recipe data extracted from informal culinary sources and augmented by LLMs. Developed as part of FKG(.in), a knowledge graph of Indian food, the pipeline identifies and addresses common failure modes, including structural inconsistencies, semantic and logical incoherence, and deviations from the source text, through a multi-stage process combining formal grammars, vocabulary-based checks, statistical heuristics, Set Transformer-based coherence modeling, and retrieval-based verification. Although evaluated on Indian recipes, the proposed methods are applicable to broader multilingual and multicultural culinary domains. We provide a practical, auditable, and application-agnostic approach to improving the reliability of machine-readable food knowledge infrastructures in the era of LLM-generated content.

cs.AI · cs.CL · cs.IR · cs.LG

版本更新 · v2arXiv:2610.16914

FOCUS: A Subspecialty Foundation Model for Intraoperative Central Nervous System Pathology

Xing Liu, Yifan Guo, Hongtai Lv, Lei Lou, Yuyi Tan, Jiang Du, Xijia Zhang, Ming Zhang 等 21 位作者

原文摘要

Intraoperative frozen-section diagnosis of central nervous system (CNS) lesions guides surgical decisions but is challenged by artefacts, diagnostic complexity and time constraints. Most pathology foundation models have limited exposure to CNS frozen tissue. Here we present FOCUS, a subspecialty foundation model pretrained on 27,930 frozen-section whole-slide images enriched for CNS tissue. FOCUS ranked first across all 11 diagnostic and 12 biomarker-prediction tasks in the internal test cohort, achieving mean AUCs of 0.969 and 0.877, respectively. This advantage was retained in the temporal and external test cohorts. We further organized a WHO-aligned diagnostic hierarchy, where FOCUS also outperformed comparator models. In a reader study, FOCUS assistance enabled junior readers to approach or exceed unassisted senior readers in hierarchical diagnostic accuracy and granularity. More importantly, FOCUS assistance enabled readers to correctly identify a mean of 63.0% of initially missed lymphoma cases (73.2% among junior readers), potentially avoiding unnecessary extensive resection. These findings highlight the potential of FOCUS to provide clinically actionable support for intraoperative CNS pathology and inform surgical decisions.

cs.CV