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

+1085新增论文
+884其中 AI 相关
+130已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-18 19:45各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 23:25 — 2026-11-18 23:25(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:2026-11-18 04:28最近发现新增版本:2026-11-18 19:45库内论文最新更新时间:2026-11-18 08:00

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。

26,870 已收录论文22,374 AI 相关8,156 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 8,156 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
版本更新 · v2arXiv:2602.05339

Consistency-Preserving Concept Erasure via Unsafe-Safe Pairing and Directional Fisher-Weighted Adaptation

Yongwoo Kim, Sungmin Cha, Hyunsoo Kim, Jaewon Lee, Donghyun Kim

原文摘要

With the increasing versatility of text-to-image diffusion models, the ability to selectively erase undesirable concepts (e.g., harmful content) has become indispensable. However, existing concept erasure approaches primarily focus on removing unsafe concepts without providing guidance toward corresponding safe alternatives, which often leads to failure in preserving the structural and semantic consistency between the original and erased generations. In this paper, we propose a novel framework, PAIRed Erasing (PAIR), which reframes concept erasure from simple removal to consistency-preserving semantic realignment using unsafe-safe pairs. We first generate safe counterparts from unsafe inputs while preserving structural and semantic fidelity, forming paired unsafe-safe multimodal data. Leveraging these pairs, we introduce two key components: (1) Paired Semantic Realignment, a guided objective that uses unsafe-safe pairs to explicitly map target concepts to semantically aligned safe anchors; and (2) Fisher-Weighted Initialization for DoRA, which initializes parameter-efficient low-rank adaptation matrices using unsafe-safe pairs, encouraging the generation of safe alternatives while selectively suppressing unsafe concepts. Together, these components enable fine-grained erasure that removes only the targeted concepts while maintaining overall semantic consistency. Extensive experiments demonstrate that our approach achieves the best overall trade-off among baselines, providing effective concept erasure while preserving structural integrity, semantic coherence, and generation quality.

cs.CV · cs.LG

版本更新 · v3arXiv:2608.22007

The Communication Map of a Transformer

Richard Zhe Wang

原文摘要

The components of a transformer communicate by writing to and reading from a shared residual stream, and the mechanistic interpretability literature has mapped these connections by hand, one circuit at a time. We present the communication map, which charts every potential communication channel from the geometry of the model's weights alone. Its unit of analysis is the whole transformer rather than the individual head or circuit. Every ordered writer-reader pair, across all 18 connection classes from head-to-head to neuron-to-neuron, receives a coupling coefficient that generalizes the composition score of Elhage et al. (2021), with an exact chance level. The census finds that 70-89% of head pairs are oriented far from chance, some coupled strongly and others actively avoiding each other. The map recovers the known induction circuits blind from the strongest head-to-head couplings and groups the heads into communities, and ablating one such community destroys the model's in-context copying. As an application, we pool the coupling coefficients of every head to identify a two-dimensional residual stream subspace, distinct from those found by activation PCA or outlier dimensions, whose deletion abolishes induction in six models up to Pythia-6.9B. We release the map, the statistical machinery, and the intervention suite.

cs.LG · cs.CL

版本更新 · v2arXiv:2605.31463

PithTrain: A Compact and Agent-Native MoE Training System

Ruihang Lai, Hao Kang, Haozhan Tang, Akaash R. Parthasarathy, Zichun Yu, Junru Shao, Todd C. Mowry, Chenyan Xiong 等 9 位作者

原文摘要

Mixture-of-Experts (MoE) has become the dominant architecture for frontier language models. To meet this demand, production frameworks have built optimized MoE training stacks over years of engineering effort. Yet evolving these stacks for new architectures and system optimizations remains expensive. With the rise of AI coding agents, they could automate parts of training-framework development and accelerate this evolution. But applying them to these existing frameworks carries hidden costs, invisible to today's throughput-only evaluations. We name this missing dimension agent-task efficiency (ATE): the cost of using coding agents to understand, operate, and extend a framework. Grounded in four agent-native design principles, we build PithTrain, a compact, agent-native MoE training framework supporting pretraining, supervised fine-tuning, and reinforcement learning. We further introduce ATE-Bench, covering real-world training-framework tasks. Our evaluation shows PithTrain achieves throughput competitive with production frameworks and higher agent-task efficiency on ATE-Bench. On new-feature tasks, PithTrain uses up to 62% fewer Agent Turns than Megatron-LM, and up to 44% and 64% less Active GPU Time than Megatron-LM and TorchTitan, respectively.

cs.LG · cs.AI · cs.CL · cs.DC

版本更新 · v2arXiv:2610.10520

Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs

Zhewei Chen, Hao Zhu, Jiaojiao Jiang, Ahad N. Zehmakan

原文摘要

GNN-to-MLP distillation aims to retain the predictive accuracy of a message-passing teacher while deploying a graph-free MLP at inference. Existing methods mainly transfer node-wise predictions or use confidence-based reweighting, but they do not specify where the student should preserve the teacher's graph-induced geometry. We show that this omission leads to two spectral failure modes in the student's representation space. On sparse graphs, the student suffers from spectral underfit, missing high-energy teacher directions induced by aggregation. On dense graphs, it suffers from spectral overfit, retaining spurious directions that the teacher has collapsed through aggregation. Motivated by an energy-weighted teacher-student alignment objective, we propose Graph Geometry-aware MLP (G^2MLP), a training-time distillation framework guided by Ollivier-Ricci curvature. Curvature acts as a local proxy for allocating supervision between prediction-level and representation-level alignment. The deployed model is a standard MLP with no graph access at inference. Across node-classification benchmarks, G^2MLP improves over graph-free distillation baselines in most settings, reduces the teacher-student rank gap in both regimes, and transfers to Graph Transformer teachers and link prediction.

cs.LG

版本更新 · v3arXiv:2507.03617

EMERGE: A Benchmark for Updating Knowledge Graphs with Emerging Textual Knowledge

Klim Zaporojets, Daniel Daza, Edoardo Barba, Ira Assent, Roberto Navigli, Paul Groth

原文摘要

Knowledge Graphs (KGs) are structured knowledge repositories containing entities and relations between them. In this paper, we study the problem of automatically updating KGs over time in response to evolving knowledge in unstructured textual sources. Addressing this problem requires identifying a wide range of update operations based on the state of an existing KG at a given time and the information extracted from text. This contrasts with traditional information extraction pipelines, which extract knowledge from text independently of the current state of a KG. To address this challenge, we propose a generic and extensible pipeline that pairs textual passages with the KG edit operations they induce on a given KG snapshot. We instantiate this pipeline on the Wikidata knowledge graph and the English Wikipedia corpus to create EMERGE, a dataset of 233K Wikipedia passages associated with a total of 1.19 million KG edits across seven yearly Wikidata snapshots from 2019 to 2025. Our experimental results highlight key challenges in updating KG snapshots based on emerging textual knowledge, particularly in integrating knowledge expressed in text with the existing KG structure. We further show that KG access substantially improves executable updates and enables triple deprecation. These findings position EMERGE as a benchmark for developing methods that keep KGs up to date with emerging textual knowledge. The dataset (https://huggingface.co/datasets/klimzaporojets/emerge-benchmark) and code (https://github.com/klimzaporojets/emerge) are publicly available.

cs.CL

版本更新 · v3arXiv:2606.14095

Lyapunov-Based Sample Complexity Analysis for Weakly-Coupled MDPs

Tianhao Wu, Matthew Zurek, Weina Wang, Qiaomin Xie

原文摘要

We study the sample complexity of learning in average-reward weakly-coupled Markov decision processes (WCMDPs) and Restless Bandits (RBs) under a generative model. Naive reduction to a tabular MDP leads to high complexity bounds as the state-action space is exponentially large in the number of arms $N$. By exploiting the weakly coupled structure, we show that near-optimal policies can be learned with sample and computational complexities that are polynomial in $N$. Specifically, we analyze the plug-in approach, which applies an efficient planning algorithm to an empirical model estimated from data. For fully heterogeneous WCMDPs, we establish the first finite-sample PAC guarantee with polynomial complexity and an $O(1/\sqrt{N})$ optimality gap. For homogeneous RBs, we further prove that a smaller optimality gap is achievable under mild structural assumptions. A primary technical contribution is a novel Lyapunov-based analysis framework. Unlike classical approaches that rely on the difficult-to-control bias function, our framework uses an explicitly constructed Lyapunov function along with a drift transfer technique between the true and empirical models. A key step of independent interest in our framework is a fine-grained perturbation analysis for the underlying linear programming (LP) relaxation, which provides a general tool for analyzing LP-based policies and weakly-coupled systems.

cs.LG · math.OC · math.PR · stat.ML

版本更新 · v2arXiv:2605.19919

Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learning

Dongjie Yu, Kun Lei, Zhennan Jiang, Jia Pan, Huazhe Xu

原文摘要

Pretrained imitation policies have become a strong foundation for robot manipulation, but online adaptation can further improve policy performance within their pretrained behavioral support. A central question is therefore how reinforcement learning (RL) should adapt policies after offline pretraining. Existing lightweight methods commonly apply residual corrections directly in action space. We investigate how the steering interface affects online RL. In this work, we propose Z-Perturbation Reinforcement Learning (ZPRL), an approach that steers pretrained policies through a compact bottleneck latent rather than through policy weights or output actions. Building on an offline-learned bottleneck policy interface introduced by previous work, ZPRL turns this representation into an online RL control space through reward-driven residual perturbations while freezing the pretrained policy. We instantiate ZPRL on flow-matching policies and evaluate it on eight simulation tasks and four real-world tasks. Across diverse manipulation settings, ZPRL improves sample efficiency with competitive or better final performance. In the real world, ZPRL improves the average success rate on four tasks by 33.7 percentage points over imitation base policies. Our qualitative and quantitative results also indicate that ZPRL combines task success with smooth actions without explicit temporal filtering or smoothness regularization. These results suggest that a compact, task-aligned bottleneck latent provides an effective interface for online RL adaptation. Videos and code can be found at https://manutdmoon.github.io/ZPRL/.

cs.RO

版本更新 · v3arXiv:2602.11042

Characterizing the Trainability of Instantaneous Quantum Polynomial Circuit Born Machines

Kevin Shen, Susanne Pielawa, Vedran Dunjko, Hao Wang

原文摘要

Instantaneous Quantum Polynomial Circuit Born Machines (IQP-QCBMs) have been proposed as quantum generative models that combine a classically tractable training objective - based on the maximum mean discrepancy (MMD) - with a potential quantum advantage motivated by sampling-complexity arguments. While recent works have explored this model across various application domains, fundamental questions remain: does the model suffer from exponentially vanishing loss gradients, known as the barren plateau problem - a pervasive obstacle in quantum machine learning - and how do regimes of trainability relate to regimes of possible quantum advantage? Here, we address both questions analytically. To study trainability, we derive closed-form expressions for the variances of the partial derivatives of the MMD loss function and establish general upper and lower bounds. We explicitly characterize how trainability depends on the generator set and the spectrum of the chosen kernel, identifying regimes in which low Hamming-weight kernels avoid exponential gradient suppression under structured topologies. Regarding potential quantum advantage, we reformulate the anti-concentration property in terms of the same generator-set quantities that govern trainability, enabling a unified analysis. We show that sparse IQP architectures can produce classically intractable output distributions while simultaneously remaining trainable, at least at lower-weight frequencies. Our analytical results corroborate the numerical observations of prior work and provide principled guidelines for designing scalable IQP-QCBM architectures.

quant-ph · cs.LG

版本更新 · v3arXiv:2510.04532

More Than Meets the Eye? Uncovering the Reasoning-Planning Disconnect in Training Vision-Language Driving Models

Xurui Song, Shuo Huai, JingJing Jiang, Jiayi Kong, Jun Luo

原文摘要

Vision-Language Model (VLM) driving agents promise explainable end-to-end autonomy by first producing natural-language reasoning and then predicting trajectory planning. However, whether planning is causally driven by this reasoning remains a critical but unverified assumption. To investigate this, we build DriveMind, a large-scale driving Visual Question Answering corpus with plan-aligned Chain-of-Thought (CoT), automatically generated from nuPlan. Our data generation process converts sensors and annotations into structured inputs and, crucially, separates priors from to-be-reasoned signals, enabling clean information ablations. Using DriveMind, we train representative VLM agents with Supervised Fine-Tuning and Group Relative Policy Optimization and evaluate them with nuPlan's metrics. Our results, unfortunately, indicate a consistent causal disconnect in reasoning-planning: removing ego/navigation priors causes large drops in planning scores, whereas removing CoT produces only minor changes. Attention analysis further shows that planning primarily focuses on priors rather than the CoT. Based on this evidence, we propose the Reasoning-Planning Decoupling Hypothesis, positing that the training-yielded reasoning is an ancillary byproduct rather than a causal mediator. To enable efficient diagnosis, we introduce a novel, training-free probe that measures an agent's reliance on priors by evaluating its planning robustness against minor input perturbations. In summary, we provide the community with a new dataset and a diagnostic tool to evaluate the causal fidelity of future models.

cs.AI · cs.CL · cs.RO

版本更新 · v4arXiv:2505.05848

RefRef: A Dataset and Benchmark for Reconstructing Refractive and Reflective Objects

Yue Yin, Enze Tao, Weijian Deng, Dylan Campbell

原文摘要

Modern 3D reconstruction and novel view synthesis approaches have demonstrated strong performance on scenes with opaque, non-refractive objects. However, most assume straight light paths and therefore cannot properly handle refractive and reflective materials. The lack of datasets specialized for these effects has impeded efforts to fairly and thoroughly evaluate performance and thereby make progress in this domain. Most existing datasets focus on opaque scenes, while those targeting refractive objects are often limited to thin glass with negligible ray bending, untinted single-material objects, or backgrounds treated as infinitely-distant, leaving key failure modes under strong refraction untested. To address this gap, we introduce the RefRef dataset. It contains 150 synthetic and 60 real scenes spanning varying levels of geometric complexity and diverse background types that expose the limitations of existing methods. For the purpose of benchmarking, we also provide an oracle method that, given the object geometry and refractive indices, calculates accurate light paths for neural rendering, and a simple two-stage baseline that relaxes these assumptions. We evaluate these against state-of-the-art methods and show that the task is far from solved.

cs.CV

版本更新 · v5arXiv:2510.13068

NeuroRVQ: Multi-Scale Biosignal Tokenization for Generative Foundation Models

Konstantinos Barmpas, Na Lee, Dimitrios Chalatsis, William Raftery, Yannis Panagakis, Dimitrios A. Adamos, Nikolaos Laskaris, Alexandros Koliousis 等 10 位作者

原文摘要

Biosignals such as electroencephalography (EEG), electrocardiography (ECG), and electromyography (EMG) encode physiological activity across multiple temporal and spectral scales, yielding representations that are rich but challenging for machine learning. Foundation models trained to predict masked signal tokens have shown promise in learning generalizable biosignal representations, yet their performance depends on the tokenizer's ability to preserve high-frequency dynamics and reconstruct signals with high fidelity. We introduce NeuroRVQ, a modality-adaptive biosignal tokenizer family designed for high-fidelity signal reconstruction. To capture the full frequency spectrum, NeuroRVQ decomposes biosignals into frequency-specific representations via multi-scale temporal convolutions, each encoded into hierarchical RVQ codebooks to preserve high-frequency detail, combined with a novel phase-aware training loss that respects the circular topology of Fourier phase. By tuning the temporal resolution, number and size of temporal kernels and RVQ depth, this design adapts to the spectro-temporal characteristics of each biosignal modality. To validate that tokenizer quality drives downstream performance, we train a simple masked-token foundation model for each modality (NeuroRVQ-FM) using the corresponding NeuroRVQ tokenizer. The NeuroRVQ-FM family achieves competitive or superior downstream performance compared to existing modality-specific foundation models, demonstrating that high-fidelity tokenization is a critical factor for effective biosignal modeling.

cs.LG · cs.AI · cs.HC

版本更新 · v2arXiv:2606.17478

From Hidden States to Confessions: Auditing Deception in Reasoning Models

Kexin Chen, Dongxia Wang, Haonan Zhang, Yanhui Li, Xinyu Deng, Yi Liu

原文摘要

As LLMs acquire stronger reasoning capabilities, deceptive behavior becomes an increasingly serious safety concern. Existing deception monitors typically either score visible transcripts or derive scalar probe scores from representation vectors, leaving little inspectable evidence about why a response is suspicious. We introduce StateWitness, an audit decoder for deception monitoring. It reads a target model's hidden states to answer audit queries and produce confession-style reports of potential failures or violations. We evaluate generalization beyond the decoder's audit training data across two target reasoning models and seven deception datasets. StateWitness achieves 0.916 mean AUROC, with relative gains of 11.6% and 25.0% over the best black-box and activation-probe baselines, respectively, under the same evaluation protocol. When combined with existing monitors, StateWitness reduces missed deceptive examples in simple threshold ensembles. Beyond scalar detection, the decoder returns query-level answers, schema reports, and token- or sentence-level evidence traces for human inspection. We envision StateWitness as one monitoring layer in a broader defense-in-depth strategy.

cs.CL · cs.AI

版本更新 · v4arXiv:2607.24743

ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding

Hangjie Yuan, Yichen Qian, Zhiwei Tang, Xianzhe Xu, Sicheng Yang, Lirong Wu, Jinwang Wang, Pengju Wang 等 25 位作者

原文摘要

Multimodal large language models (MLLMs) hold immense potential to revolutionize clinical practice, yet deploying them in the medical domain is fundamentally a vision-centric challenge: models must absorb knowledge from heterogeneous 2D and 3D medical images, and evaluation protocols must align with radiologists' clinical practice and provide an accurate, fine-grained and factualness-driven assessment. In this paper, we introduce ClinFusion, a vision-centric MLLM designed for holistic medical understanding that systematically addresses these limitations. We propose a compositional and cascaded vision encoder architecture featuring a Cascade Spatial-Aware Locality Fusion operator that unifies diverse 2D and native 3D medical image understanding within a fused encoder. We further introduce a vision-grounded evaluation framework, including MedIF-Bench for instruction-following assessment and a region-of-interest-grounded method for clinically aligned and factualness-driven report generation evaluation. We show that ClinFusion sets a new state-of-the-art across a comprehensive suite of 2D and 3D multimodal medical benchmarks---spanning visual question answering, report generation, and instruction following---as well as textual medical tasks, outperforming leading open-source medical MLLMs (\textit{e.g.}, Hulu-Med, Lingshu) on 20 out of 24 benchmarks and demonstrating multimodal capabilities better than powerful proprietary models such as GPT-5.2 and Gemini-3-Flash on 13 out of 16 benchmarks, and can be further augmented with agentic tool use for retrieval-augmented and tool-assisted clinical workflows. A blinded evaluation by board-certified radiologists confirms that ClinFusion produces the highest-ranked reports, and validates our RoI-grounded metric as achieving the strongest correlation with expert judgment among all automatic evaluation metrics examined.

cs.CV · cs.AI · cs.CL

版本更新 · v4arXiv:2610.05900

Sub-Voxel Displacement and Ipsilateral Territory Decoupling for 3D Bilateral Coronary Artery Tree Reconstruction in Cardiac CT Angiography

Zeyu Jia, Xin Ming

原文摘要

Reconstructing topologically complete, sub-voxel-accurate 3D bilateral coronary artery trees from cardiac CT angiography (CCTA) requires simultaneously recovering continuous centerline trajectories and separating dense left/right coronary territories without cross-ostial collisions. We present a five-stage tubular drift and ipsilateral territory decoupling framework (M1-M5). Stage M1 pairs a 398,843-parameter multi-scale 3D pyramid encoder with a four-head tubular field network predicting vesselness probability, signed tubular boundary distance, unit tangent vectors, and continuous 3D centripetal displacement vectors. Stage M2 introduces recall-preserving multi-task optimization with 7-group AdamW parameter decoupling, L2-SP backbone regularization, and per-step anchor shrinkage. Stage M3 calibrates cylindrical Valsalva-sinotubular-junction wall coordinates and native-resolution orifice contact expectations for robust left and right ostial rooting. Stage M4 constructs a scalar-potential-weighted minimum-cost arborescence followed by normal-plane cross-sectional pullback and centripetal trajectory pruning. Stage M5 enforces coverage-guarded ipsilateral-field-coupled bilateral collision reduction and subtree handover. Across a 14-case held-out development cohort (Dev-14, 17-arm forward incremental build and 9-arm leave-one-out ablation) and an independent 50-case out-of-sample evaluation cohort (OOS-50) benchmarked against seven external architectures (nnU-Net, 3D UX-Net, Swin-UNETR, MedNeXt, CS2-Net, clDice-UNet, and Point-UNet), M1-M5 reduces bilateral chamfer distance on Dev-14 from 3.4381 mm to 2.2759 mm and achieves 2.7671 mm on OOS-50 with 7.11% bilateral collision rate and 79.7% distal branch completeness.

cs.CV · q-bio.TO

版本更新 · v6arXiv:2610.00329

Non-Commutative Lie-Algebraic State-Space Models: Finite-Division Variety Laws, Semidirect Cascades, and Gradient Saddle Escape

Zeyu Jia

原文摘要

Structured state-space sequence models (SSMs) achieve linear-time inference and logarithmic-time parallel training via associative scans, yet diagonal transitions generate solvable semigroups unable to track non-solvable group words or 3D rigid-body manifolds. We present Non-Commutative Lie-Algebraic State-Space Models (Lie-SSMs), parameterizing recurrent updates on Lie algebra tangent spaces via the matrix exponential. First, using an o-minimal cylindrical flag collar, we establish an unconditional single-layer finite-division criterion for contracting $SO(3)$ and $SU(2)$ heads, proving odd-prime Sylow abelianity, odd-$p$-core centrality, and exponent-30 commutator obstructions excluding $S_5$ in $SO(3)^m, SU(2)^m,$ and $SO(4)^m$ while identifying the sharp threshold $d^*(S_5)=d^*(A_6)=5$ in $SO(5)$. Second, Depth-2 semidirect and Schreier $2$-cocycle cascades resolve $S_5$, $2I\cong SL_2(F_5)$, and $\mathrm{Heis}(F_p)$ in $O(\log T)$ scan depth, whereas unnormalized contracting coupling collapses exponentially without Directional RMSNorm. Third, we characterize the $Θ(\varepsilon^{c-1})$ Chen--Magnus--Hall--Witt commutator saddle and $1/|[G,G]|$ coset-centroid dilution, proving generic first-order symmetry breaking at $\varepsilon=0$ and teacher-forced local Polyak--Łojasiewicz convergence under dense prefix supervision and factored readouts ($99.90\%/99.40\%$ on $S_5$ at $T=128$; $100.00\%$ on $D_{16}$). Across $SE_2(3)$ Left-Jacobian odometry, Hillis--Steele/Blelloch GPU scans ($48.24\times$ forward, $20.27\times/10.28\times$ full-layer speedup at $T=2048$), and three 3D IMU benchmarks (UCI HAR, UCI HAPT-PT, and 17-subject REALDISP), Lie-$SO(3)$ models reach $95.69\%\pm 0.14\%$ on HAR, $88.44\%\pm 0.83\%$ episode logit-vote ($83.97\%\pm 1.20\%$ C3 window in 30-subject 5-fold CV; $87.16\%\pm 0.64\%$ 9-subject split) on HAPT-PT, and $84.23\%\pm 1.00\%$ on REALDISP.

cs.LG

版本更新 · v4arXiv:2601.23258

Agnostic Language Identification and Generation

Mikael Møller Høgsgaard, Chirag Pabbaraju

原文摘要

Recent works on language identification and generation have established tight statistical rates at which these tasks can be achieved. These works typically operate under a strong realizability assumption: that the input data is drawn from an unknown distribution necessarily supported on some language in a given collection. In this work, we relax this assumption of realizability entirely, and impose no restrictions on the distribution of the input data. We propose objectives to study both language identification and generation in this more general "agnostic" setup. Across both problems, we obtain novel interesting characterizations and nearly tight rates.

cs.LG · cs.AI · cs.CL

版本更新 · v2arXiv:2609.37351

Typed Edge-Tensor Non-Reciprocal Port-Hamiltonian Deliberation for Counterfactual Open-World Deductive Reasoning

Zeyu Jia

原文摘要

Scaling test-time computation in continuous latent spaces offers an attractive alternative to verbose token-by-token generation for multi-step deductive reasoning. However, unregularized recurrent latent updates suffer from a deliberation drift cliff when rolled out beyond training horizons, while strictly energy-conserving or symmetric message-passing dynamics cannot break parent-to-child causal symmetry or suppress cyclic modus-ponens amplification on cyclic distraction graphs. We introduce Typed Edge-Tensor Non-Reciprocal Port-Hamiltonian Deliberation (TE-BPHD), a neuro-symbolic continuous-time latent reasoning architecture that couples skew-symmetric port-Hamiltonian conservation with relation-typed non-reciprocal directional transport and monotone dissipative damping on a semantic entity-state manifold. We prove (i) unconditional input-to-state stability and exponential contraction of autonomous rollouts across arbitrary inference depths without external norm projection, (ii) strict directional DAG reachability separation over symmetric message passing, and (iii) exact cycle-suppression margins under finite cyclic horn perturbations. Across counterfactual open-world deductive benchmarks (PrOntoQA-OOD up to depth 15, ProofWriter-OWA Cyclic at depths 5-10, FOLIO-Symbolic, and Cluttr-Relational), TE-BPHD eliminates the deep-horizon drift cliff, improves depth-10 cyclic reasoning accuracy to 90.0% (+/- 0.8%) over symmetric port-Hamiltonian and standard Transformer baselines, and supports zero-retraining adaptive Lyapunov halting that reduces average solver evaluations by 44% with negligible accuracy loss.

cs.LG · cs.AI · cs.CL

版本更新 · v3arXiv:2510.22969

Multi-Agent Conditional Diffusion Planning for Decentralized Wireless Resource Allocation

Kechen Meng, Sinuo Zhang, Rongpeng Li, Yansha Deng, Chan Wang, Zhifeng Zhao

原文摘要

In wireless communication systems, efficient and adaptive resource allocation is essential for enhancing overall Quality of Service (QoS). Compared with conventional Model-Free Reinforcement Learning (MFRL), Model-Based RL (MBRL) first learns a generative world model for subsequent planning, enabling more stable training through the reuse of historical experience. However, deploying MBRL in large-scale wireless networks remains challenging due to high-dimensional stochastic dynamics, strong inter-agent cooperation, and stringent communication constraints. To overcome these challenges, we propose a Multi-Agent Conditional Diffusion Model Planner (MA-CDMP) for decentralized communication resource management. Following the Decentralized Training with Decentralized Execution (DTDE) paradigm, MA-CDMP models each communication node as an autonomous agent and employs Diffusion Models (DMs) to capture environment dynamics. An inverse dynamics model is further incorporated to guide action generation, improving sample efficiency and policy scalability. Moreover, to efficiently approximate large-scale agent interactions, we introduce a Mean Field (MF) mechanism to assist the classifier in conditional DMs. This mitigates inter-agent non-stationarity and enhances cooperation with minimal communication overhead. We further establish an upper bound on the distributional approximation error induced by MF-based diffusion generation, guaranteeing convergence stability and reliable modeling of multi-agent stochastic dynamics. Extensive experiments demonstrate that MA-CDMP consistently outperforms existing MARL baselines in terms of average reward and QoS metrics, showcasing its scalability and practicality for real-world wireless network optimization.

cs.AI · cs.MA

版本更新 · v2arXiv:2609.13481

A Hybrid Hierarchical 1D-CNN-BiLSTM Framework for Extractive Summarization of Biomedical and Clinical Text

Saad Bin Ather, Muhammad Saif, Ali Hassan Khan, Manzer Abbas, Hajra Waheed

原文摘要

Large language models have made abstractive summarization remarkably fluent, but fluency has come at a cost. Models trained to generate freely over long documents may hallucinate, producing summaries that read well but drift from what the source actually says. This risk is especially serious in biomedical and clinical text, where fabricated details can have serious consequences. We address this by removing free-form generation from the pipeline rather than trying to constrain it. Our Hybrid Hierarchical CNN-LSTM Summarizer reframes summarization as extractive sentence selection: a stacked, multi-kernel convolutional network progressively refines contextual representations, while a bidirectional LSTM models long-range dependencies across the document. A lightweight scoring head predicts sentence importance using binary cross-entropy supervision. For PubMed, a document-adaptive mean-plus-standard-deviation threshold with a Top-3 fallback determines extraction; clinical evaluations instead use a fixed top-30\% sentence-selection policy. Because output sentences are copied verbatim, the framework prevents source-external generation, although omissions and contextual inaccuracies remain possible. Evaluated on PubMed and transferred without clinical fine-tuning to MIMIC-CXR and MIMIC-IV BHC, the model demonstrates competitive extractive summarization performance, with threshold and component ablations supporting adaptive extraction and the combined CNN--BiLSTM architecture. Clinical factuality analysis further highlights limitations in preserving important findings and negations. These results suggest that structural constraints offer a promising direction for source-grounded biomedical summarization, while emphasizing the importance of clinical completeness and contextual fidelity.

cs.CL

版本更新 · v3arXiv:2610.13314

NEAR: Neighborhood-Aware Residuals for Memory Retrieval

Han Luo, Zhan Zhuang, Xu He, Jujia Zhao, Yu Li, Suqin Yuan, Dong Li, Lei Feng

原文摘要

Memory retrieval aims to identify evidence from stored records to answer a query. Stored records with different factual details may share topics, entities, or events. Such shared contents would make records without the required evidence more likely to receive high similarity scores and outrank the correct evidence. In this paper, we use the information shared by these records to construct local references for query-memory matching. We propose NEighborhood-Aware Residuals (NEAR), a training-free framework that uses these references to construct residual representations that complement the original embeddings. Specifically, each memory derives a reference direction from its neighbors, and each query obtains its reference from a precomputed table. Using these references, NEAR constructs projection residuals for both queries and memories. These residuals are combined with the original embeddings for a single approximate nearest-neighbor search over a fixed memory index. Experiments on eight long-context retrieval benchmarks show consistent improvements across nine embedding models. Downstream evaluations show that NEAR improves question-answering performance.

cs.IR

版本更新 · v2arXiv:2605.11178

Oversmoothing as Representation Degeneracy in Neural Sheaf Diffusion

Arif Dönmez, Axel Mosig, Ellen Fritsche, Katharina Koch

原文摘要

Neural Sheaf Diffusion (NSD) learns a task-adapted sheaf geometry for node classification. We connect the study of these learned geometries with Geometric Invariant Theory (GIT) to analyse their representation-theoretic structure and develop mechanisms for geometric control during training. Identifying cellular sheaves with representations of the incidence quiver connects direct-sum decompositions to the harmonic space and motivates the study of trivial or low-complexity summands as potential degeneration modes. We make this perspective concrete by focusing on the trivial representation: on an embedded copy, the sheaf Dirichlet energy reduces to weighted scalar graph energy. The GIT stability framework provides a criterion for excluding such copies within the semistable class. Using its moment-map characterisation of polystability, we construct differentiable surrogates that encourage the corresponding balance conditions. We identify an equal-stalk obstruction to assigning a destabilising weight to the trivial representation and show how nonuniform stalk dimensions remove it. Controlled energy-minimisation experiments reproduce trivial-component formation, while native feature-conditioned NSD experiments on heterophilic graphs show how moment-map regularisation changes the balance and Dirichlet-energy trajectories of learned geometries during training, alongside their classification behaviour.

cs.LG · cs.AI · math.RT

版本更新 · v2arXiv:2606.02956

The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset

Richard Schwarzkopf, Fabian Immel, Alexander Blumberg, Jonas Merkert, Nils Rack, Kaiwen Wang, Fabian Konstantinidis, Julian Truetsch 等 24 位作者

原文摘要

Existing autonomous driving datasets have enabled major progress, but fall short in sensor fidelity, map completeness, or geographic diversity. We present KITScenes Multimodal, a European dataset built around high-fidelity sensors and maps. Our fully synchronized sensor suite combines high-resolution global-shutter cameras, long-range lidar beyond 400 m, 4D imaging radar, and redundant GNSS/INS localization. Our HD maps are, to our knowledge, the most complete of any sensor dataset, validated through autonomous driving trials on open-source software. For the first time in a public dataset, all driving-relevant traffic elements, such as traffic lights, are mapped in 3D to a reprojection-accurate level with full topological connectivity. Recorded in cities with irregular street layouts and mixed traffic modes, our dataset complements existing datasets by broadening the available geographic diversity. We also introduce four benchmarks, each advancing spatial learning for embodied AI: online HD map construction, long-range depth estimation, novel view synthesis, and end-to-end driving. Project page: https://kitscenes.com/multimodal/

cs.CV · cs.LG · cs.RO

版本更新 · v2arXiv:2605.04618

Constructions of locally repairable codes via concatenated codes

Hengfeng Jin, Fang-Wei Fu

原文摘要

Locally repairable codes (LRCs) have attracted considerable attention owing to their pivotal role in distributed storage systems. Since binary linear LRCs can significantly reduce the complexity of both encoding and decoding, the construction of binary LRCs has drawn extensive research interest. In this paper, we construct binary LRCs with locality $r=2$ and disjoint local repair groups via classical concatenation, where the outer codes are linear codes over $\mathbb{F}_4$ and the inner code is the binary $[3,2,2]$ linear code. We present a systematic approach for selecting outer codes to obtain LRCs attaining specified bounds, and show that the weight distributions of the resulting binary LRCs are determined by those of the selected outer codes. Under certain sufficient conditions, we construct several classes of optimal binary LRCs, including those attaining Griesmer-type bounds and binary perfect LRCs. Furthermore, we sharpen the Johnson-like bounds of Ma and Ge for binary LRCs with locality $r=2$ and disjoint local repair groups, and define nearly perfect binary LRCs and $k$-optimal binary LRCs with respect to the improved bounds. We show that nearly perfect binary LRCs can be constructed via concatenation when the outer codes are nearly perfect linear codes over $\mathbb{F}_4$. Finally, we present several examples of such nearly perfect and $k$-optimal binary LRCs.

cs.IT

版本更新 · v3arXiv:2602.14344

Zero-Shot Instruction Following in RL via Structured LTL Representations

Mathias Jackermeier, Mattia Giuri, Jacques Cloete, Alessandro Abate

原文摘要

We study instruction following in multi-task reinforcement learning, where an agent must zero-shot execute novel tasks not seen during training. In this setting, linear temporal logic (LTL) has recently been adopted as a powerful framework for specifying structured, temporally extended tasks. While existing approaches successfully train generalist policies, they often struggle to effectively capture the rich logical and temporal structure inherent in LTL specifications. In this work, we address these concerns with a novel approach to learn structured task representations that facilitate training and generalisation. Our method conditions the policy on sequences of Boolean formulae constructed from a finite automaton of the task. We propose a hierarchical neural architecture to encode the logical structure of these formulae, and introduce an attention mechanism that enables the policy to reason about future subgoals. Experiments in a variety of complex environments demonstrate the strong generalisation capabilities and superior performance of our approach.

cs.LG · cs.AI

版本更新 · v3arXiv:2605.14068

CurveBench: A Benchmark for Exact Topological Reasoning over Nested Jordan Curves

Amirreza Mohseni, Mona Mohammadi, Morteza Saghafian, Naser Talebizadeh Sardari

原文摘要

We introduce CurveBench, a benchmark for visual topological reasoning. Given an image of disjoint closed curves, a model must recover the tree of adjacent regions rooted at the exterior. The benchmark contains 756 hand-drawn images, ranging from simple configurations to maze-like and densely packed arrangements. Each image has a manually verified reference tree. We evaluate predictions by exact tree matching with the exterior root fixed. Gemini 3.1 Pro, the strongest model in our evaluation, achieves 71.1% exact-match accuracy on CurveBench-Easy and 28.7% on CurveBench-Hard. A Qwen3-VL-8B checkpoint trained using reinforcement learning with verifiable rewards reaches 31.7% on Easy, compared with 21.7% for its Thinking base model at a 16,384-token generation budget. The same comparison yields a gain of 1.1 percentage points on Hard.

cs.CV · cs.LG

版本更新 · v3arXiv:2601.03910

An Algebraic Representation Theorem for Linear GENEOs in Machine Learning

Francesco Conti, Patrizio Frosini, Nicola Quercioli

原文摘要

Geometric and Topological Deep Learning enhance machine learning by exploiting geometric and topological structures in data. In this context, Group Equivariant Non-Expansive Operators (GENEOs) provide a principled framework for encoding symmetries and designing efficient, interpretable neural architectures. Originally introduced in Topological Data Analysis and later adopted in Deep Learning, GENEOs unify geometric and topological approaches and include, as a special case, the operator computing persistence diagrams. Their theoretical foundations rely on group actions, equivariance, and compactness properties of operator spaces. GENEOs are defined between data spaces endowed with transformation groups, referred to as perception pairs. While previous representation results characterized linear GENEOs acting on identical perception pairs, many applications require operators between heterogeneous ones. In this work, we introduce and prove a new algebraic representation theorem for linear GENEOs acting between different perception pairs. Under mild assumptions on data domains and group actions, this result provides a complete characterization of such operators and implicitly yields a computational method to generate all linear GENEOs between two perception pairs. The proof combines tools from the theory of stochastic matrices, group actions, and invariant measures. In our paper, we also show that the space of linear GENEOs is compact and convex, making easier their use for learning and optimization. Our new theorem enlarges the applicability of GENEOs, and allows for their composition with a broader class of current architectures. We show this with an application in image reconstruction.

math.RT · cs.AI · cs.LG

版本更新 · v2arXiv:2605.10516

Consistency as a Testable Property: Statistical Methods to Evaluate AI Agent Reliability

Harsh Raj, Niranjan Orkat, Suvrorup Mukherjee, Aritra Guha, Cheryl Flynn, Subhabrata Majumdar

原文摘要

This paper establishes a rigorous measurement science for AI agent reliability, providing a foundational framework for quantifying consistency under semantically preserving perturbations. By leveraging $U$-statistics for output-level reliability and kernel-based metrics for trajectory-level stability, we offer a principled approach to evaluating agents across diverse operating conditions. Our proposal highlights the important distinction between the core capability and execution robustness of an agent, showing that minor task-level variations can induce complete strategy breakdowns despite the agent possessing the requisite knowledge for the task. We validate our framework through extensive experiments on three agentic benchmarks, demonstrating that trajectory-level consistency metrics provide far greater diagnostic sensitivity than traditional pass@1 rates. By providing the mathematical tools to isolate where and why agents deviate, we enable the identification and rectification of architectural concerns that hinder the deployment of agents in high-stakes, real-world environments.

cs.AI

版本更新 · v2arXiv:2609.34427

LLMs as Adaptive Meta-Solvers: Strategy-Diverse RL for Industrial-Scale Optimization

Shihao Zhang, Weiting Liu, Siyu Shao, Yitian Chen, Jianfeng Feng, Dongdong Ge, Yinyu Ye

原文摘要

Scaling LLM-based optimization from textbook-scale instances to real-world, industrial tasks remains a critical open challenge. Existing approaches are predominantly evaluated on small, self-contained textual problems and often commit to a solver-integrated paradigm, limiting their ability to handle the scale and structural diversity of practical optimization workloads. In this work, we propose a practical framework for training open-source LLMs to tackle real-world, industrial-scale optimization. We first show empirically that solver-integrated reasoning, exact combinatorial algorithm, and heuristic search exhibit complementary strengths across different problem structures and scales. Motivated by this, we introduce Strategy-Diverse Reinforcement Learning (SDRL), which trains LLMs as adaptive optimization meta-solvers. SDRL leverages this complementarity through a correctness-gated hierarchical diversity reward that promotes robust exploration across varying strategies and within each strategy, effectively preventing premature strategy collapse. We further introduce a mixed-format training scheme that jointly supports both self-contained textual problems and file-grounded instances. Across comprehensive evaluations, our framework outperforms existing fine-tuned methods and frontier models including DeepSeek-V4-Pro and GPT-5.5, both on average across benchmarks and on industrial-scale optimization tasks. We release our code and training data to facilitate future research https://github.com/tokentideAI/LLMMetaSolver.

cs.LG · cs.CL

版本更新 · v3arXiv:2610.13277

Beyond the Final Embedding: Retrieving Memories from Token-Level Evidence

Han Luo, Zhan Zhuang, Xu He, Jujia Zhao, Yu Li, Suqin Yuan, Dong Li, Lei Feng

原文摘要

Memory-augmented assistants retrieve evidence from stored conversations and documents to answer queries. Most embedding-based retrievers compare single-vector representations of queries and memories, even when relevance depends on a small part of the content. Such local evidence can be matched to queries using the contextual token representations already computed by the same embedding models. Our method uses sparse token matching to improve retrieval without additional training. Each query token retrieves a small set of matching tokens across candidate memories. The matching scores are aggregated for each memory and combined with whole-memory similarity to rank memories. An optional low-rank query adapter can be trained with supervision while keeping the encoder and stored memory representations fixed. Our method improves retrieval across eight benchmarks and multiple model families without additional training. Query adaptation further increases the gains to 13.3 and 14.3 percentage points in average Recall@10 and NDCG@10 on Qwen3-Embedding-4B. These retrieval gains translate into higher question-answering accuracy on long-term memory benchmarks.

cs.IR · cs.CL

版本更新 · v2arXiv:2610.32740

Strongly Adaptive Online Learning with Time-Varying Movement Costs

Andrew Jacobsen, Emmanuel Esposito, Hao Qiu, Mengxiao Zhang

原文摘要

We study online convex optimization (OCO) with time-varying movement costs, where the learner incurs both a loss and a time-dependent penalty for changing its decisions. While previous work has established dynamic regret guarantees for this setting, obtaining strongly adaptive guarantees that hold simultaneously over arbitrary intervals remains an open challenge. We address this by developing a new algorithm which, for every interval $[a,b]\subseteq[T]$ and arbitrary comparator sequence, achieves a data-dependent regret bound of $ \widetilde{\mathcal{O}}\left( \sqrt{(D^2+DP_{[a,b]})\sum_{t \in [a,b]}(\|g_t\|^2+λ_t\|g_t\|)} \right) $, where $D$ is the diameter of the decision domain, $P_{[a,b]}$ is the path length of the comparator sequence over $[a,b]$, $g_t$ is the gradient of the loss, and $λ_t$ is the movement-cost coefficient at round~$t$. Key to our approach is a novel reduction to sleeping experts with movement costs, a previously unexplored variant that is of independent interest. As a result of our development, we further obtain strongly-adaptive dynamic regret guarantees under arbitrary delayed feedback with a refined dependence on interval-restricted cumulative delays. Our approach also naturally extends to OCO with time-varying memory, where we obtain strongly-adaptive guarantees which improve the best-known bounds.

cs.LG · stat.ML