paperlist.ai

AI 顶会论文

AI 顶会论文库

检索 30+ 个顶会的论文，包括 NeurIPS、ICLR、ICML、CVPR、ACL、AAAI 等。输入关键词筛选，打开任意一篇查看摘要、作者和链接。

arXiv

Sensor-Driven Mission Synthesis for UAV/UGV Swarms: A TB-CSPN Coordination Architecture with Hardware-Enforced Safety

Uwe M. Borghoff, Paolo Bottoni, Remo Pareschi

This paper presents a coordination architecture for heterogeneous UAV/UGV swarms that synthesises mission actions from uncertain, multi-modal sensor evidence while preserving hardware-enforced safety at the actuation boundary. The approach combines radar, RF, acoustic, and visual observations with Topic-Based Communication Space Petri Net (TB-CSPN) orchestration to support incremental mission formation under partial and evolving information. Consultant agents transform sensor outputs into temporally bounded semantic tokens, while supervisor agents provide authorisation and policy-governed release of mission transitions. This separation between interpretation, coordination, and execution yields auditable decision paths, constrains non-determinism within the coordination layer through guards and synchronisation, and enables bounded-time integration of heterogeneous evidence. To improve resilience in contested environments, including cyber compromise, spoofing, jamming, and communication loss, the digital coordination layer is complemented by independent analogue safety envelopes that clamp or veto unsafe actuator commands issued to individual vehicles. A coastal-surveillance case study illustrates how the proposed architecture enables dependable, governed, and physically safe swarm coordination under operational uncertainty.

arXiv

M-LINKX: Multiview Graph Learning for Brain Cognitive Disease Detection

An Phan, Yufei Jin, Xingquan Zhu

Electroencephalogram (EEG) is a non-invasive and relatively low-cost procedure that measures brain electricity for the detection of cognitive diseases. EEG-based classification of dementia-related conditions, including Alzheimer's disease (AD), mild cognitive impairment (MCI), and frontotemporal dementia (FTD), remains challenging because EEG signals are noisy, non-stationary, and vary across subjects. Segment-based learning provides a practical way to model long EEG recordings by converting them into fixed-length inputs. For each segment, discriminative information may be explored by using signals within each channel (i.e. electrode), as well as interactions between EEG channels. In this paper, we propose M-LINKX, a multi-view graph learning framework for EEG-based dementia classification. For each segment, we extract channel-level node features and construct multiple functional-connectivity (FC) graph views, where each view is defined by a specific combination of connectivity metric, frequency band, and topology filter, respectively. Instead of relying on message passing over the constructed graphs, M-LINKX follows a simple design in modeling node features and adjacency-based connectivity representations. The graph-view representations are fused using global trainable view weights, and subject-level prediction is obtained by averaging segment-level probabilities. Experiments on two three-class EEG datasets with different diagnostic groups, CAUEEG (HC/MCI/Dementia) and AHEAP (HC/AD/FTD), show that M-LINKX achieves the best subject-level performance under the main experimental settings. Our study suggests that multi-view functional connectivity can improve EEG-based dementia classification when integrated with an appropriate graph-learning architecture. Code and data are available at https://github.com/anphantt/MLINKX.

arXiv

Explainability Boosted Anomaly Detection Framework for O-RAN based NextG Networks

Nurullah Aksu, Ali Fuat Sahin, Semiha Tedik Başaran

The wireless networks have historically faced significant security vulnerabilities, necessitating advanced anomaly detection mechanisms, especially as networks evolve towards 6G and beyond. This study introduces an advanced anomaly detection framework that leverages explainable artificial intelligence to enhance the security of next-generation (NextG) cellular networks. By implementing and evaluating a variety of artificial intelligence models, the framework demonstrates high accuracy and efficient runtime performance in identifying malicious traffic within a realistic Open Radio Access Network (O-RAN) testbed. A key innovation of this work is the integration of post-hoc explainability methods to identify the most critical key performance metrics (KPMs), which enables a significant 80% reduction in dataset complexity without compromising detection accuracy. Additionally, explainability analyses identify several critical attack traffic characteristics, such as protocol type, bandwidth, interval, and duration, to prevent upcoming network attacks. The resulting framework effectively balances computational efficiency, accuracy, and explainability, underscoring its practical applicability for enhancing security in next-generation cellular networks.

arXiv

Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning

Kai Chen, Jifeng Ding, Ning Ding, Jiaye Ge, Lixin Gu, Yicheng Gu, Qipeng Guo, Ermo Hua, Haian Huang, Haozheng Hou, Jie Hou, Xiangyu Hong, Che Jiang, Minxi Jin, Cheng Liang, Dahua Lin, Dawei Liu, Kuikun Liu, Chengqi Lv, Haijun Lv, Han Lv, Ningsheng Ma, Biqing Qi, Jianmin Qian, Shiya Su, Youbang Sun, Huanze Tang, Zhongbo Tian, Hanjing Wang, Rui Wang, Ting Wang, Yi Wang, Baiting Wu, Jun Xu, Bowen Yang, Hui Wang, Weida Wang, Haochen Ye, Jiashuo Yu, Shan Yu, Xiaoyi Yu, Qirui Zeng, Qi Zhang, Ming Zhang, Wenwei Zhang, Bowen Zhou, Xinyu Zhou

We introduce Mobius-v0, an architecture that comprises a globally shared Memory (FFN) that stores knowledge vectors and multiple Reasoners (Self-Attn) that iteratively achieve compositional reasoning. Using hidden states as cache and carrier, reasoners repeatedly query memory for required knowledge-vectors, while the knowledge is transmitted back to reasoning operators. Through this knowledge-reasoning-separation architecture, Mobius achieves better knowledge compression and reasoning efficiency. Built upon Mobius-v0 architecture: 1) Our 7B model trained-from-scratch achieves similar downstream score as a 7B Transformer baseline with 62.6% of baseline's training data. 2) Our Intern-S2-Mobius, continually-pretrained from Qwen3.5-35B, achieves similar downstream score while delivering nearly 4x end-to-end inference speedup.

arXiv

A Parameter-Free Few-Shot Evaluation for Elephant Vocalisation Classification

Christiaan M. Geldenhuys, Thomas R. Niesler

We present a parameter-free episodic evaluation of nearest-centroid classification for elephant vocalisations on fixed pretrained acoustic embeddings, across the Elephant Voices (EV) and Linguistic Data Consortium (LDC) datasets. Rather than asking which embedding yields the best classifier when trained on all available labelled data, we ask how the simplest classifier performs as labelled exemplars per class are varied. Each class is represented by the mean of its support-set embeddings, and each query is assigned to the nearest centroid under squared Euclidean distance. We evaluate this centroid classifier on the Perch (ver. 1), Perch (ver. 2), and HuBERT (base, layer 2) embeddings, together with mel frequency cepstral coefficient (MFCC) features, in an N-way k-shot manner under the same cross-validation protocol as the trained baselines. A bootstrap over 100 resampled support sets quantifies the sampling noise. On the smaller, low-resource EV dataset, the centroid classifier using the stronger Perch (ver. 1) and Perch (ver. 2) embeddings overtakes the fully-trained logistic regression classifier from a single exemplar per class and the stronger recurrent classifier from two. Over the reduced set of call types on which the strongly-supervised end-to-end baseline was trained, the centroid classifier matches and then surpasses that baseline in mean average precision (mAP), from a few exemplars per class. On the larger LDC dataset, where labelled exemplars are abundant, the trained baselines retain their advantage at every k considered. At five exemplars per class, the centroid classifier using the strongest embedding, Perch (ver. 2), attains a mAP of 0.542 on the EV dataset and 0.368 on the LDC dataset. Parameter-free nearest-centroid classification is the stronger choice when labelled exemplars are few and the fixed embedding already encodes the features that separate the call types.

arXiv

Disentangling Homophily and Rarity: Explaining Failure in Graph Neural Networks

Preben M. Ness, Fariz Ikhwantri, Dusica Marijan

Are heterophilic nodes in a graph harder to classify because they are heterophilic or because they are rare? Some existing work frames classification of such nodes as a subgroup generalisation problem, where a model performs well on the majority group at the expense of the rare group. Others explain this as a problem of neighbourhood aggregation in graph neural networks (GNNs). We assess these two viewpoints through a detailed evaluation of six GNNs on five datasets of varying homophily, and find that homophilic nodes tend to be easier to classify, even when they are rare---challenging the subgroup framing. However, our findings also nuance existing beliefs about how GNNs misrepresent heterophilic nodes. We demonstrate that the information needed to classify heterophilic nodes correctly is often recoverable by retraining the classification head of a model, or even just the final linear classification layer.

arXiv

What Makes a Good Layer? Assessing the Layer-Wise Intrinsic Properties of Music Foundation Models

Angelos-Nikolaos Kanatas, Yuexuan Kong, Pablo Alonso-Jiménez, Xavier Serra, Dmitry Bogdanov

Music foundation models are commonly used as frozen audio feature extractors, yet selecting which layer to extract from remains largely heuristic. Current practice defaults to fixed depths or multi-layer fusion, with limited understanding of why certain layers transfer better across downstream tasks or how representation quality varies with depth and pre-training paradigm. We conduct a systematic layer-wise analysis of 12 music foundation models spanning three pre-training paradigms (masked modeling, autoregressive modeling, and contrastive learning), characterizing their hidden representations through intrinsic geometric and transformation-based properties. Correlating label-free representation-quality metrics with layer-wise performance across 15 downstream tasks, we find that several metrics track layer quality for genre classification, emotion recognition, automatic tagging, and beat tracking, albeit with varying strength across tasks and pre-training paradigms. However, all metrics fail on tonal tasks such as key estimation and chord recognition, indicating that no single property serves as a general proxy for representation quality across music information retrieval tasks. To address this gap, we introduce a pitch-transposition equivariance measure that captures properties missed by these standard metrics, providing a consistent indicator of tonal quality across model families. Finally, we show that intrinsic metrics can serve as effective proxies for layer selection, matching or outperforming trainable multi-layer fusion methods, particularly in limited-data settings.

arXiv

TimeSage-EV: A Live Benchmark for Agentic Time Series Analysis in Evolving Environments

Qingren Yao, Yaxuan Kong, Yuqi Nie, Yichen Li, Stefan Zohren, Anna Vettoruzzo, Qingsong Wen, Ming Jin, Joaquin Vanschoren

Time series analysis in high-stakes domains relies on recurring data releases, where new observations can alter the evidence base and the validity of later conclusions. Existing time series QA benchmarks mostly rely on fixed snapshots, leaving temporal validity and cutoff-aware evidence use unevaluated. We introduce TimeSage-EV, a live benchmark for agentic time series analysis in evolving environments. It tracks 60 real institutional scenarios across 6 domains, comprising 1,485 scenario-period QA pairs from Feb 2023 to May 2026 and spanning monthly, weekly, daily, and irregular release cadences. At each period, large language model (LLM) agents receive time series data and source reports, while the withheld target release provides ground truth. TimeSage-EV evaluates state identification, data summarization, and outlook reasoning. Experiments with frontier LLM agents and TimeSage-1.0, a novel self-evolving agent with a reusable analytical skill library, reveal significant performance gaps across model tiers and recurring failures in temporal validity, exogenous context use, and adaptation. We release TimeSage-EV as a research resource with monthly updates, code, a leaderboard, and failure-mode analyses.

arXiv

Is Grokking a Loss of Normal Hyperbolicity of the Interpolation Manifold?

Suvinava Basak

A recent line of work recasts the post-memorization phase of grokking as constrained optimization: once a network interpolates the training set, weight decay drives a slow drift along the zero-loss manifold toward lower norm. In the language of dynamical systems, this is a fast-slow system in which the interpolation manifold plays the role of a slow manifold. We ask a question that this framing makes natural but the existing literature does not address: is the sharp generalization transition a loss of normal hyperbolicity of that manifold: a fold- or bifurcation-like event in which a normal restoring direction goes flat? Or does the manifold stay uniformly attracting while generalization happens by smooth drift? We propose a simple, optimizer-agnostic diagnostic: the smallest nonzero singular value $σ_{\min}^{+}(\mathbf J)$ of the residual Jacobian, which, for the squared loss, equals the slowest normal restoring rate of the manifold. On a two-layer ReLU network trained to grok modular addition under squared loss, $σ_{\min}^{+}(\mathbf J)$ does not collapse at the transition; it is near zero only before memorization and attains its largest values during the transition. The result holds across five seeds, and the six smallest singular values behave identically; there is no subspace-local collapse either. This is preliminary evidence against the bifurcation hypothesis and in favor of the smooth-contraction picture. We are explicit that a single-setting, gradual-transition experiment under Adam optimizer does not prove the absence of a bifurcation; it constrains where one could hide.

arXiv

Polaris : Multi Agentic System for Conversational Enterprise Analytics

Varuni H K, Soham Sarkar, Jay Kumar, Goutham Krishnan, Tanvi Johari, Avinash Bharadwaj, Santosh Hegde

In today's fast-paced environment, the ability to swiftly access, understand, and act on data is no longer optional; it is essential. Yet most organizations remain data-rich but insight-poor, constrained by the complexity of querying, interpreting, and explaining enterprise-scale information. We present Polaris, a supervisor-led multi-agent framework for conversational enterprise analytics that bridges this gap. Polaris introduces Dynamic Task Coordination (DTC), a decision-theoretic orchestration layer that models agent-task assignment as adaptive bipartite matching, enabling real-time coordination, recovery, and optimization across specialized agents for querying, visualization, and reasoning. By coupling DTC with reason-first, ReAct-style agents, Polaris transforms natural-language queries into coherent analytical workflows that not only retrieve and visualize data but also explain the underlying "why." Evaluation on structured enterprise datasets demonstrates high semantic fidelity and answer relevancy, underscoring the potential of multi-agent orchestration to deliver trustworthy, end-to-end business intelligence at scale.

arXiv

A Generalized Parallelogram Rule for Proportional Analogies on Riemannian Manifolds

Pierre-Alexandre Murena, Marcelo Hartmann

Analogies are quaternary relations of the form "a is to b as c is to d", usually denoted a : b :: c : d. This notion is formalized in particular with the notion of proportional analogy, which imposes some constraints on the valid analogies. Whereas proportional analogies have been studied mostly in symbolic domains and in vector spaces, their use is limited in non-Euclidean spaces. In this paper, we introduce a proportional analogy relation in Riemannian domains, extending the parallelogram rule used for arithmetic analogies in Euclidean spaces. We illustrate the introduced analogy on various manifolds, such as the sphere, shape spaces and manifolds of probability distributions.

arXiv

p-Spin Glass Network Efficient Single-Batch Continual Learning

Vladimer Khasia

Modern sequence models heavily rely on massive memory footprints and large-batch stochastic optimization, barriers that restrict sample efficiency and continual learning. We introduce the $p$-Spin Glass Network, a novel architecture that overcomes these limitations, structurally manages optimization variance and yields four noticeable capabilities: 1. It enforces memory efficiency: native ternary quantization compresses internal parameters by $8\times$, while exact implicit gradients strictly bound activation memory to $\mathcal{O}(B \cdot T \cdot D)$. 2. it demonstrates sample efficiency, matching the asymptotic performance of a Transformer baseline while utilizing $8\times$ fewer training sequences. 3. Method enables single-batch stability and smooth, monotonic convergence at a stochastic micro-batch size of $1$. 4. Finally, this stability proves modality-agnostic, maintaining robust temporal credit assignment across both discrete subword and long horizon uncompressed raw byte streams. Ultimately, this work removes large batch requirement for stable deep learning, establishing a foundation for continuous learning and edge AI.

arXiv

APTER: Adaptive Post-Training with Expert-Grounded Rubrics

Xukai Wang, Liangqi Li, Zhiyue Xu, Jingang Zhou, Xiaoyu Shi, Jiansheng Cai, Bo Zhang, Zhe Li, Xu-Yao Zhang

As large language models enter professional domains, they must satisfy domain constraints, include critical evidence, and provide complete reasoning rather than merely produce fluent responses. Existing post-training methods often rely on holistic preferences or outcome-level verification, while recent rubric-based methods usually generate rubrics independently for each query. In specialized domains, such unconstrained rubrics may omit critical requirements and vary across samples, hindering the diagnosis and targeted repair of persistent capability deficiencies. We propose APTER (Adaptive Post-Training with Expert-Grounded Rubrics), a framework that integrates structured domain knowledge into fine-grained evaluation, optimization, and diagnosis for specialized complex reasoning. First, expert-grounded rubric construction starts from an expert criteria framework built by domain experts, where each criterion represents a stable professional capability. For each query, APTER selects relevant criteria and instantiates them into query-level rubrics linked to their source criteria, turning reusable expert criteria into executable query-level supervision without reference answers. Second, adaptive post-training uses rubric verdicts as both optimization and criterion-level diagnostic signals. Aggregating low-scoring verdicts by criterion ID reveals persistent deficiencies and triggers targeted supervised fine-tuning updates during reinforcement learning. Experiments on mathematical reasoning and medical question answering show consistent gains across both domains. Across three model generations, APTER improves the mathematics and medical averages over the corresponding base models by up to 15.86 and 8.04 points, respectively. Code and rubric datasets are available at https://github.com/AntDT-APTER/APTER.

arXiv

Real-Time State-of-Health Estimation and Online Degradation Prognosis from Partial Battery Discharge Using Physics-Informed Neural Networks

Begoña Ispizua, Serio Gil-López, Leire Arrizabalaga, Ibai Laña

With the increasing integration of renewable energy sources, energy storage systems have become essential, making the accurate estimation of their State of Health (SOH) and degradation behavior critical. In this work, we propose a physics-informed deep learning approach for lithium-ion battery SOH prediction using incomplete discharge curves extracted from arbitrary voltage ranges, thereby reflecting realistic and heterogeneous operating conditions. The proposed method combines data-driven learning with physically motivated degradation dynamics to ensure consistent and reliable SOH estimation from partial discharge information, achieving a MAPE below 4$\%$. In addition, a real-time degradation trend estimation strategy is introduced to detect key aging transitions without requiring prior knowledge or historical data, making it applicable to a wide range of batteries. Overall, our approach enables SOH estimation from arbitrary discharge segments and a real-time degradation forecast that continuously integrates all usage, overcoming previous methods that rely on fixed protocols or early, non-adaptive predictions.

arXiv

CFR without Unbiasedness: Deterministic Guarantees for Persistent Public-Chance Schedules

Jiaxing Guo, Lei Ye

At a finite public-chance cut, counterfactual regret minimization (CFR) must choose how many outcomes to evaluate before each regret update. Exact evaluation processes the full cut at one strategy profile; persistent partial evaluation processes a fixed without-replacement order across evolving profiles. The latter covers every outcome once per epoch, yet its feedback is generally conditionally biased because earlier batches influence the profiles seen by later batches. We establish a deterministic target-transfer theorem for uniform, nonnested additive public cuts. The theorem bounds full-cut exploitability by regret on the delivered feedback and a public-debit term that couples prefix coverage discrepancy with motion along the realized strategy path. Consecutively balanced schedules consequently converge for additive signed regret matching (RM) and RM+ under predetermined averaging weights, while a fixed RM+ construction proves that the discrepancy--path product is necessary in general. A component-resolved form of the theorem converts an execution trace into a numerical exploitability certificate. On two released heads-up no-limit hold'em turn endgames, persistent order improves substantially over fresh reshuffling despite identical epochwise coverage, and partial coverage wins every registered shallow matched-budget comparison. A depth study locates a crossover between 32 and 64 full-cut outcome budgets, after which complete coverage dominates. These results characterize public-chance width and order as learning variables and provide a deterministic basis for designing and auditing persistent CFR schedules.

arXiv

Can Language Models Understand mmWave Data? Benchmarking Large Language Models for mmWave Radar-Based Human Understanding

Jeongwan Shin, Jaehyeon Kim, Donguk Ko, Jaeho Choi

Large language models (LLMs) have shown remarkable reasoning and generative capabilities, motivating their use as universal reasoning engines for perception. While modern approaches such as vision-language models (VLMs) have attempted to incorporate reasoning capabilities into visual sensing, the integration of LLMs with the millimeter-wave (mmWave) modality-despite its unique advantages under low light and occlusion-remains largely unexplored. The principal bottlenecks stem from the scarcity of radar language pairs, severe cross-dataset heterogeneity, and the absence of a foundational mmWave encoder. We address this gap through a minimal textualization interface that serializes each mmWave point cloud into concise natural language, allowing off-the-shelf LLMs to operate in a question answering (QA) setting. Building on this, we present mmWave-QA, the first benchmark for language-conditioned mmWave human perception. mmWave-QA aggregates heterogeneous public mmWave datasets and harmonizes them via calibration-aware preprocessing and global taxonomy alignment, while providing natural language QA. Spanning six scenarios and five QA tasks, the benchmark enables standardized evaluation across diverse mmWave hardware and experimental conditions, establishing a foundation for scalable research on mmWave-LLM integration. We further evaluate and analyze LLMs on our mmWave-QA, highlighting their zero-shot reasoning potential for radar perception, as well as their robustness under visual degradation.

arXiv

BiasTrace: Linking Reasoning Behaviours to Biased Outputs in LLMs

Varsha Ramineni, Hossein A. Rahmani, Jerome Ramos, Karin Sevegnani, Emine Yilmaz

LLMs exhibit social biases that can produce inaccurate and discriminatory inferences, posing risks in high-stakes applications. While prior work has made progress in measuring and mitigating bias, it largely focuses on final outputs of models, with limited understanding of the mechanisms that produce biased outcomes. Recent advances in LLM reasoning offers a new lens for investigating bias, yet the link between reasoning and bias remains poorly understood. Existing approaches focus primarily on final answer correctness or explicitly biased language, overlooking different behaviours in reasoning that can drive biased outcomes. We introduce BiasTrace, an annotation scheme for labelling reasoning behaviours in model-generated traces and linking them to biased outcomes. BiasTrace captures bias-specific behaviours (e.g., unsupported demographic assumptions) as well as general reasoning patterns that may implicitly contribute to bias (e.g. overthinking). We apply BiasTrace to reasoning traces in bias-sensitive contexts, scaled using validated LLM-as-a-judge methods, producing a large annotated dataset. Our analysis shows that biased outputs often stem from subtle reasoning behaviours rather than explicitly biased language, and that reasoning-level annotations improve bias detection. We further show that BiasTrace behaviours can be exploited for inference-time mitigation. These findings underscore the importance of examining a broader range of reasoning patterns to better understand bias in LLMs.

arXiv

The Note-Chord-Voice Framework: Structured Source Separation and Causal Inference for EV Charging Data

Jiajie Chen, Jinfeng Li

Real-world EV charging data exhibit three interlocking pathologies: hardware fragmentation (network timeouts and billing resets split sessions), physical violations (independent energy/duration models produce impossible states like 50 kWh in 10 min on a 7 kW charger), and collider bias (clustering on post-treatment outcomes opens backdoor paths for price elasticity). We propose the Note-Chord-Voice framework, a music-inspired, axiom-driven pipeline that separates data cleaning (Repair Chords), structural pattern discovery (Harmonic Chords), descriptive source separation (NMF Voices), and causal inference into distinct, falsifiable stages. Key innovations: (i) falsification gates (A1-A5, G3, G10) that test data suitability before modeling; (ii) Gamma-initialized NMF with input rescaling for convergence stability from STL decomposition; (iii) tag-based coupon grading (A/B/C/D) to isolate quasi-random treatment from night-time confounders and targeted promotions; (iv) separate per-voice OLS to avoid simplex collinearity; (v) Foote novelty curves for structural regime detection. Applied to the Jiangmen dataset (495,707 sessions, 20 stations, from July 2024 to March 2025), all core axioms pass except G3 (no strong 168 h cycle). NMF achieves R^2=0.9921; the physically constrained duration model yields aggregate R^2=0.5409. Two voices are price-sensitive (beta = -11 to -14 min, p<0.001), of which one is stable (Voice 3, beta=-14.16) and one treatment-driven (Voice 1, beta=-11.10); only the stable voice supports causal claims. Counterfactual simulation shows targeting discounts to price-sensitive voices recovers 52.8% of discount expenditures (~0.85M CNY/year); restricting to the single stable price-sensitive voice yields a more conservative estimate.

arXiv

WANDR: A Benchmark for Wide and Deep Research

Vitaliy Polshkov, Marcin Pitera, Jeremy Yang, Kirill Priemko, Maksim Gaiduk, Aleksandr Nikolenko, Denis Bykov, Clare Southern, Denis Yarats, Jerry Ma

WANDR (Wide ANd Deep Research) is a benchmark of 500 realistic, challenging data-collection tasks for research agents. Each task requires a system to discover a large set of entities that satisfy specified criteria (breadth), investigate each entity through multiple coordinated web searches (depth), and return independently verifiable records with supporting sources and excerpts. Tasks are represented as qualification key hierarchies that specify the entities, relationships, evidence, and required count at each level; a hierarchy with n companies, m employees per company, and k sources per employee requires n x m x k records. This structure supports diverse workflows such as market mapping, due diligence, literature review, product comparison, and talent sourcing, with targets ranging from dozens to thousands of records. WANDR replaces static gold answer sets with task-specific judges that refetch cited pages and verify each record against its evidence, allowing evaluation of current and changing facts. Record verdicts are aggregated into soft and hard precision, recall, and F1 scores that distinguish factual quality, coverage, and hierarchical completeness. The tasks are derived from de-identified product-usage logs and produced through a semi-automated pipeline with automated checks, empirical audits, and human review where needed. We evaluate six production research systems and find that the benchmark is far from saturated: at high effort, the strongest system reaches only 0.363 soft F1 and 0.133 hard F1. Performance degrades as target volume and hierarchy depth increase, with incomplete discovery, missing enrichment, and incomplete evidence construction remaining major bottlenecks. The benchmark and evaluation harness are available at https://github.com/perplexityai/wandr.

arXiv

Towards Efficient Multimodal and Multilingual Opinion Extraction for STI: A QLoRA-Based Fine-Tuning Approach

Sheng Hong, Xuanqi Wang, Jiacheng Wang, Yuwei Wang

Recent advances in large language models (LLMs) have reshaped semantic analysis. Opinion Extraction (OE) for Science and Technology Intelligence (STI) requires concise core opinions from large information streams. Off-the-shelf models struggle to filter noise from these streams and show limited structured-output reliability in zero-shot multilingual and multi-modal settings. To address information overload and extraction defocus, this study proposes a multimodal core-opinion extraction framework in which visual evidence serves as a contextual anchor for textual judgment. Using VideoLLaMA2 (VL2) and VideoLLaMA2.1 (VL2.1) as the base models, we apply Quantized Low-Rank Adaptation (QLoRA) fine-tuning on a curated dataset of 2,194 multilingual and multimodal samples. Under the selected Image-Augmented setting, fine-tuned VL2.1 generates structured JSON core-opinion outputs, achieving 64.98% Precision, 42.15% Recall, 51.14% F1-score, and 74.00% sample-level accuracy. Relative to the zero-shot VL2.1 setting, it raises the F1-scores of Spanish and Russian from 4.83% and 0.45% to 46.05% and 51.93%, respectively. The framework further incorporates a Fuzzy Cumulative Prospect Theory-based post-extraction triage module for case-level value assessment, providing a case-level value signal for downstream STI screening.

继续浏览

更多 AI 顶会论文

30+ 个顶会，按会议、年份和主题浏览。

浏览全部会议

进入任一会议和年份，查看完整论文列表。

全部会议 →

搜索论文

按标题、作者或关键词，在 21 万+ 篇论文里搜索。

搜索论文 →