跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1111新增论文
+874其中 AI 相关
+133已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 08:57 — 2026-11-20 08:57(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:2026-11-20 08:48最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 02:59

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

27,982 已收录论文23,249 AI 相关8,559 有修订112 HF 社区发现

浏览论文库

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 23,249 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
新论文 · v1arXiv:2611.23563

Learning the Dynamics of Deformable Linear Objects Through Coupled Oscillators for Bimanual Robotic Manipulation

Iván López-Broceño, Maximilian Stölzle, Daniel Feliu-Talegon, Daniela Rus, Cosimo Della Santina

原文摘要

Many learning-based approaches for deformable linear objects (DLOs) rely on simplified deformation models that neglect dynamic effects and the mechanical response of the objects, limiting their applicability to lightweight, compliant objects and slow motions. Inspired by recent advances in learning physically structured dynamics with coupled oscillator networks (CONs), we propose $Φ$-CON for learning force-driven DLO dynamics. The model combines a floating-base coupled oscillator network (FBCON), whose latent potential energy depends only on the DLO's shape, with a learned affine diffeomorphism $Φ$ between observed positions along the DLO and latent coordinates. Its shape dynamics are stable by construction, and its Lagrangian structure yields explicit expressions for kinetic and potential energy. We exploit this structure to design a model-based proportional-derivative (PD) controller that compensates for the learned potential forces, thereby establishing closed-loop stability guarantees and ensuring convergence. We evaluate the approach on four simulated DLOs and a real bimanual robot setup. In simulation, $Φ$-CON achieves prediction accuracy comparable to neural ordinary differential equation (NODE) models and Lagrangian neural networks (LNNs), with $97.2\%$ and $90.2\%$ fewer parameters, respectively. Relative to a model-free PD baseline, the proposed controller reduces mean endpoint regulation error by $97.5$-$99.7\%$ in simulation and achieves a mean per-target reduction of $27.9\%$ across both endpoints in real-world experiments, demonstrating the importance of explicitly accounting for the mechanical response of stiff and heavy objects.

cs.RO

版本更新 · v2arXiv:2605.06906

TraXion: Rethinking Pre-training Frameworks for Mobility and Beyond

Shang-Ling Hsu, Mark Tenzer, Cyrus Shahabi, Khurram Shafique

原文摘要

Human mobility differs from text and from generic time series in three structural ways: visits are tuple-valued events whose meaning depends on the joint distribution over location, time, and activity; users carry persistent signatures across trajectories; and visits are not independent across users, since co-location at shared places is a primary signal. Existing pre-training recipes for mobility import objectives from language modeling, treating trajectories as sentences and visits as tokens, an analogy that fails against each of the three properties above. These properties define a broader class, multi-entity spatiotemporal event streams (MESES), spanning enterprise authentication logs, electronic health records, and other event-stream domains where entities share infrastructure, schedules, or contexts. We make the properties precise as three axioms that any pre-training framework for MESES should satisfy, and introduce TraXion, whose objectives and architecture are jointly designed to meet them. A single TraXion checkpoint per dataset leads task-specific baselines on every location-ranking and detection metric across six public mobility datasets covering anomaly detection, next-POI recommendation, next-visit prediction, and social-link prediction. The same recipe, applied unchanged to enterprise authentication logs and ICU mortality prediction, matches or exceeds prior work on both, showing that event streams from domains as different as mobility, security, and healthcare can be modeled under a single framework.

cs.LG

新论文 · v1arXiv:2611.23560

FACET - Facet Aware Contrastive Embeddings for Traits- Big Five Estimation from Life Narratives

Balakrishnan Arumugam, Priyen Parekh, Mehak Gupta, Joshua Oltmanns

原文摘要

Personality is only weakly and inconsistently signaled by written language, and existing text-based methods typically combine language-model and psycholinguistic representations at the input or decision level. It remains open whether a more deliberate combination of the two views, and a decomposition of the prediction target, can recover more of the signal. We present a three-phase framework for estimating Big Five personality domain scores from life-narrative interview text. It encodes text and psycholinguistic features separately and combines them by concatenation or by a learned weighting, decomposes each domain into contrastively trained facet embeddings instead of predicting the domain directly, and pools the facet embeddings by attention into a domain-level prediction. We compare end-to-end with staged training and ablate the input modalities, their combination, and the facet-pooling strategy. On 1,332 participants from the St. Louis Personality and Aging Network (SPAN) study, facet embeddings reach AUC up to 0.740, and domain-level R2 reaches 0.328, highest for Openness. End-to-end training gives lower error than staged training in every domain, and attention pooling gives the lowest error in every domain. Combining the two views lowers error relative to text alone for Conscientiousness and Agreeableness, whereas a learned weighting of the views shows no consistent advantage over concatenation. The framework provides facet- level predictions that a domain-only model cannot, and it improves modestly on a regression from the raw features in four of the five domains.

cs.AI

新论文 · v1arXiv:2611.23554

Layer-Matched Sparse Attention for Low-Redundancy 3D Reconstruction

Sammam Mahdi, Fariha Binta Salim, K. M. Jubair Sami, Rakin Bin Rabbani

原文摘要

VGGT reconstructs cameras and geometry from unposed images in one pass, but its global attention grows quadratically with the number of views. Training-free accelerators thin this attention and work well on redundant video, but lose pose accuracy when views share little geometry. This paper traces these losses to two kinds of cross-view information that a uniform sparse approximation can fail to preserve together: diffuse layers aggregate distributed context, whereas matching layers depend on query-specific interactions that carry little attention mass. A per-layer statistic measures the log-mass missed by a mean token. Its row-free proxy is the logit variance, and it selects the estimator for each layer. Diffuse layers use shared, importance-sampled hub keys, with log-weights that make the softmax numerator and denominator unbiased. Matching layers stay exact: every aggressive thinning tested cost accuracy. At equal cost, the selected layers outperform the four shifted windows tested. On 13 unseen low-redundancy scenes with 32 views, LMSA stays within 1.4 AUC@5 of dense attention, compared with 10.3 for AVGGT and 4.5 for SAF3R; its difference from contemporaneous GPA-VGGT is not significant, and only its gains over AVGGT pass both scene-level tests. With 100 views, it stays within 1.9 AUC@5 while its aggregator runs $2.0\times$ faster. Used post hoc to choose the layers GPA-VGGT protects, the statistic improves it by 1.2 AUC@5 for 5% more FLOPs. Applied untuned to $π^3$, it beats AVGGT but remains further from dense accuracy.

cs.CV

版本更新 · v3arXiv:2602.06104

Pragmatic Curiosity: A Unified Framework for Hybrid Learning and Optimization via Active Inference

Yingke Li, Anjali Parashar, Enlu Zhou, Chuchu Fan

原文摘要

Many engineering and scientific workflows rely on expensive black-box evaluations, requiring sequential decisions that must both improve task performance and reduce uncertainty. Bayesian optimization (BO) and Bayesian experimental design (BED) provide powerful but largely separate treatments of goal-directed optimization and information-seeking experimentation, leaving limited guidance for hybrid settings in which learning and optimization are intrinsically coupled. We propose Pragmatic Curiosity (PraC), a unified framework for hybrid learning and optimization via active inference. PraC evaluates candidate queries by trading information gain about a task-relevant latent symbol against an expected regret-based potential over outcomes. This formulation foregrounds three operational design choices: which latent quantity should be clarified, how task value is encoded as regret, and how strongly information gain should be exchanged against pragmatic regret. We instantiate PraC across three regimes of increasing complexity: decision-oriented monitoring with fixed global symbols and known downstream losses, targeted active search with induced local symbols and evolving coverage goals, and composite Bayesian optimization with hierarchical regret learning under unknown preferences. Across these regimes, PraC reduces downstream decision risk, improves coverage of critical outcome regions, and jointly learns predictive and preference structures without relying on task-specific staging rules.

cs.LG · stat.ML

版本更新 · v3arXiv:2603.13669

SHAMISA: SHAped Modeling of Implicit Structural Associations for Self-supervised No-Reference Image Quality Assessment

Mahdi Naseri, Zhou Wang

原文摘要

No-Reference Image Quality Assessment (NR-IQA) aims to estimate perceptual quality without access to a pristine reference. Learning an NR-IQA model faces a fundamental bottleneck because it requires many costly human perceptual labels. We propose SHAMISA, a non-contrastive self-supervised framework that learns from unlabeled distorted images through explicitly structured relational supervision. Unlike prior methods that impose rigid binary similarity constraints, SHAMISA shapes soft, controllable implicit structural associations that are both distortion-aware and content-sensitive. A key innovation is its compositional distortion engine, which generates an uncountable family of degradations from continuous parameter spaces and groups the resulting images so that exactly one distortion factor varies at a time. This construction enables fine-grained control over representational similarity during training. Images with shared distortion patterns are pulled together in the embedding space, while severity variations produce structured shifts. Dual-source relation graphs integrate known degradation profiles with emergent structural affinities throughout pre-training. The learned encoder is then frozen and paired with a linear regressor. Extensive experiments on synthetic, authentic, and cross-dataset NR-IQA benchmarks demonstrate strong overall performance, improved transfer in the reported cross-dataset comparisons, and favorable qualitative robustness diagnostics. Self-supervised pre-training requires no IQA opinion-score annotations or contrastive loss.

cs.CV · cs.AI · cs.LG

版本更新 · v6arXiv:2505.06787

Digital-physical testbed for ship autonomy studies in the Marine Cybernetics Laboratory basin

Emir Cem Gezer, Mael Korentin Ivan Moreau, Anders Sandneseng Høgden, Dong Trong Nguyen, Roger Skjetne, Asgeir Sørensen

原文摘要

The algorithms developed for Maritime Autonomous Surface Ships (MASS) are often challenging to test on actual vessels due to high operational costs and safety considerations. Simulations offer a cost-effective alternative and eliminate risks, but they may not accurately represent real-world dynamics for the given tasks. Utilizing small-scale model ships and robotic vessels in conjunction with a laboratory basin provides an accessible testing environment for the early stages of validation processes. However, designing and developing a model vessel for a single test can be costly and cumbersome, and researchers often lack access to such infrastructure. To address these challenges and enable streamlined testing, we have developed an in-house testbed that facilitates the development, testing, verification, and validation of MASS algorithms in a digital-physical laboratory. This infrastructure includes a set of small-scale model vessels, a simulation environment for each vessel, a comprehensive testbed environment, and a digital twin in Unity for visualization and remote control. With this, we aim to establish a design and verification pipeline that progresses from low-fidelity simulations, through potential-flow-based simulations of each vessel, to model-scale testing in the laboratory basin. Further advancement allows moving towards half-scale validation with R/V milliAmpere1 and full-scale validation with R/V Gunnerus. In this work, we present the testbed and its components and demonstrate its use for early-stage development of ship autonomy guidance, navigation, and control (GNC) algorithms. Model-scale hydrodynamic scaling, thruster characterization, and uncertainty propagation remain limitations for later-stage validation.

cs.RO · eess.SY

新论文 · v1arXiv:2611.23547

Bounded-Order Non-Identifiability in Latent Structure Block Models: The Fiber in Closed Form

Sie Hendrata Dharmawan, Peter Chin

原文摘要

A graphon is determined by all of its homomorphism densities, but motif-based methods use finitely many. We compute exactly what that truncation costs in a natural family: latent structure block models whose positions lie on $K$ rays, equivalently degree-corrected block models of rank two. For a given radial law, the configurations that agree on every graph with fewer than $2K-1$ vertices form a one-dimensional fiber, which we give in closed form with explicit endpoints; the friendship graph $F_{K-1}$ is its unique edge-minimal separator, so no fixed motif order serves every $K$. The separating signal is suppressed by a factor of at most $m_1^{2(K-1)}$, where $m_1$ is the mean squared slope, about $10^{-4}$ at $K=4$: detecting it from motif counts would take about $10^{15}$ nodes in a single graph, at any edge density. The information is nonetheless in the graph; the fiber belongs to the statistic, not the model. Common spectral pipelines, which count no motifs, still slide along the fiber by more than a third of its length at ordinary densities, with confidence regions that almost never contain the truth, while model-based fits of the same embedding do not. We give practitioners four checks: whether a fit is at risk, what to run instead, why a confidence interval will not warn, and how wide the remaining ambiguity is.

stat.ML · cs.LG · math.ST

新论文 · v1arXiv:2611.23546

Language Models Make New Research Sound Old

Guy Zyskind

原文摘要

Researchers are increasingly using large language models (LLMs) to validate research questions. We find that LLMs make open research questions sound partly studied and overstate what related papers establish. Models recognize most of these overstatements when asked to check the papers' full texts separately. On 40 questions drawn from newly accepted papers, GPT-6-Astra correctly judges 98% to be unstudied, but states that status plainly in only 8% of ordinary answers. All six frontier systems show reporting gaps of 30-90 percentage points. Across 22 models given identical papers, higher capability is associated with more accurate judgments and larger reporting gaps. This reporting failure is asymmetric: models correctly identify studied questions in 88-100% of ordinary answers when we supply the answering papers. To correct this, we build a fixed answer from each model's judgment and separate checks of cited papers. This raises Astra's clear reporting of open status from 8% to 95%, with improvements in all six systems. Finally, we predict reviewers' novelty grades by combining several models' written ratings with a rule learned from graded examples, reaching the performance range reported by Think-Probe-Respond. Unlike TPR, our approach needs no access to model weights or internal activations, so it also works with closed-weight frontier models.

cs.CL · cs.AI

新论文 · v1arXiv:2611.23543

Stability of Parallel Transport Convolution under Riemannian Metric Perturbations

Hongnian Huang, Andrew Stump

原文摘要

Geometric convolutions on Riemannian manifolds depend on the geometry of the underlying domain, making stability under metric perturbations a fundamental question in geometric deep learning. This paper studies this question for parallel transport convolution through methods from differential geometry and analysis. On a fixed compact manifold, we establish that, for a continuous input signal and a continuous reference kernel supported in a sufficiently small normal neighborhood, the convolution output depends continuously in $L^2$ on the Riemannian metric in the $C^2$-topology, under the specified localization and transport-path conventions. The analysis develops perturbation estimates for geodesics, parallel transport, Jacobi fields, and exponential maps, and uses these estimates to compare the transported kernels. A central difficulty is the cut locus, which obstructs uniform comparison of the transport construction over the entire manifold. We address this difficulty by combining uniform estimates away from the cut locus with integral bounds on neighborhoods of arbitrarily small volume, while also controlling the change in the Riemannian volume measure. The resulting qualitative stability theorem connects perturbation theory for Riemannian geometric constructions with the analysis of spatial convolution operators in geometric deep learning.

cs.LG · cs.CV · math.DG · stat.ML

新论文 · v1arXiv:2611.23537

From Docket Minutes to Case Trajectories: Building Analysis-Ready Criminal Court Data

Erfan Hosseini Sereshgi, Kory Rosen, Jaya Dhariwal, Nicholas Mattei, Aron Culotta

原文摘要

Criminal court records are often fragmented, noisy, and siloed, making it challenging for both legal experts and community stakeholders to access and analyze court data to identify trends and provide public oversight. In this paper, we introduce a system for data ingestion, harmonization, and dashboard visualization designed for New Orleans criminal court proceedings data, aimed at both expert and lay audiences. Our system collects and harmonizes disparate data, generates case trajectories, and provides intuitive visualization techniques based on community feedback to analyze demographics, temporal trends, and specific case events. We demonstrate the system through an exploratory analysis of recent short-term trends and policy impacts within New Orleans, illustrating how it can support the investigation of anomalies, policy changes, and procedural irregularities. We also present feedback from a small formative study of community stakeholders who have helped co-design and use the system, suggesting that it may improve access to and interpretation of local court data.

cs.IR

版本更新 · v2arXiv:2609.22226

Swiss-Knife: A Framework for Reconfigurable Externalised Multi-Objective Alignment at Decode Time

Agnibh Karmakar, Mayur Parvatikar, Shreyash Dhoot, Amit Dhanda, Aman Chadha, Kapil Wanaskar, Vinija Jain, Amitava Das

原文摘要

Decode-time alignment methods steer a frozen language model by scoring candidate continuations with an external reward and selecting the maximiser. We argue that this shared design is a single degenerate point in a much larger space. We introduce Swiss-Knife, a framework for externalised multi-objective alignment in which the alignment specification is a first-class runtime object: hot-swappable scoring blades, a batch normaliser, a pairwise aggregation operator, and a selection rule. Six axioms characterise the admissible aggregation operators, and we prove a representation theorem: every operator satisfying them has the form $R_i = \sum_{j \neq i} g((μ_i - μ_j)/s(σ_i,σ_j))$, a two-parameter family containing probit and logistic comparison rules and pointwise argmax as named coordinates. Within it, pairwise aggregation is Lipschitz-stable under adversarial reward contamination while argmax is not, and Candidate-Batch Normalization (CBN) makes the weight simplex invariant to the rescalings under which reward models are only ever identified. Our reference instantiation pairs DPO-LoRA blades with an uncertainty-aware pairwise tournament. Sweeping the helpfulness/honesty/harmlessness simplex, it attains the best balanced frontier of six decode-time methods (harmonic $F_1$ 0.797 vs. 0.750 for the strongest baseline, $p < 10^{-14}$) with the lowest refusal rate and highest helpfulness of any arm, and reconfigures its objectives in 0.05 ms with no gradient computation. Ablating CBN costs 0.217 $F_1$, and the metadata confirms the predicted mechanism: the lowest-variance blade retains 9% of its nominal 33% influence, and the collapse follows the predicted ordering.

cs.CL · cs.LG · stat.ML

版本更新 · v2arXiv:2611.10502

Distinguishing Extraction Failures and Clinical Discordance with LLM Uncertainty on Radiology Reports

Jerjes Aguirre-Chavez, Shant Malkasian, Roshun Sankaran, Brendan Crabb, Albert Hsiao

原文摘要

Large language models (LLMs) are increasingly used to structure data from unstructured text, but extraction errors remain inevitable. We evaluated whether LLM uncertainty could distinguish extraction failure from true clinical discordance. In 5{,}225 vessels from 1{,}045 patients undergoing coronary CT angiography (CCTA) for suspected coronary artery disease (CAD), we evaluated token-level and self-reported LLM uncertainty during extraction of vessel-level stenosis severity. Extraction failure was defined as disagreement between LLM-extracted stenosis and expert annotations. Clinical discordance was defined as disagreement in obstructive CAD status between CCTA and subsequent invasive coronary angiography (ICA). Incremental discrimination was assessed after adjustment for stenosis severity, calcium burden, and coronary vessel. Extraction failure was evaluated in 1{,}077 vessels from 253 patients with expert annotations, and clinical discordance in 1{,}641 vessels from 729 patients undergoing ICA within 90 days. Token-level Stenosis Margin showed the strongest association with extraction failure (adjusted OR, 4.15 [95\% CI, 2.57--6.69]; $P<0.001$) and clinical discordance (adjusted OR, 1.22 [95\% CI, 1.04--1.43]; $P=0.118$). Stenosis Margin significantly improved discrimination of extraction failure ($Δ$AUC, +0.06 [95\% CI, +0.03 to +0.09]; $P=0.001$), but not clinical discordance ($Δ$AUC, +0.01 [95\% CI, $-0.00$ to +0.02]; $P=0.245$). In a nested cohort of 138 vessels from 57 patients, 38 of 42 clinically discordant vessels (90\%) were extracted correctly. LLM uncertainty improved identification of extraction failure but not clinical discordance, suggesting that uncertainty may identify errors introduced during data extraction but may not generalize to discordance in underlying clinical data.

cs.CL

新论文 · v1arXiv:2611.23533

Can LLMs Understand What They Predict? Evaluating Latent Causal Structure Inference in Financial Markets

Yixiang Zheng, Yuechen Jiang, Zhiwei Liu, Jimin Huang, Yuyan Wang, Sophia Ananiadou

原文摘要

Large language models (LLMs) are increasingly evaluated through their ability to predict future outcomes, implicitly assuming that predictive success reflects an understanding of the underlying system. However, accurate predictions can often be achieved without recovering the latent mechanisms that generate observable outcomes. To examine this assumption, we introduce LUCID, a benchmark that evaluates whether models can infer latent market structures from event descriptions and historical financial observations. Models generate event-induced causal graphs representing inferred market structure and are evaluated through a reconstruction-based framework. Our evaluation of 6 open-weight and proprietary LLMs shows that adding their generated graphs generally reduces reconstruction quality compared with using historical observations alone, although a few metrics improve. These findings suggest that inferring informative, event-specific market structures from observable evidence remains challenging for the evaluated LLMs.

cs.CL · cs.LG

版本更新 · v2arXiv:2610.34747

Query-Driven Learning for Lifted Reasoning

Luise Ge, Brendan Juba

原文摘要

Learning and reasoning are both essential to intelligent agents, but have traditionally been treated as two separate stages: first learning a knowledge base from data (or taking one as given), and then verifying queries as if the knowledge base were complete. This separation has been shown to be inefficient when the downstream goal is to verify only a small set of queries. Moreover, it neglects the possibility that data and a knowledge base contain partial yet complementary information, requiring an agent to combine both sources to justify or refute a query. Motivated by the need to integrate learning and reasoning more tightly, we study the problem of query-driven learning for reasoning. More specifically, we extend prior work to the first-order setting, which is critical for practical applications as the number of ground atoms typically grows rapidly. We begin by asking when validating or refuting a universal query given partial data and knowledge base is even possible, and identify a necessary and sufficient condition called bounded concealment. We then propose a quasi-polynomial-time algorithm that solves the task at the lifted level. Finally, we establish soundness and completeness guarantees relative to space-bounded lifted proofs, along with quasipolynomial sample and runtime bounds, demonstrating that lifted query-driven reasoning can be efficient even when unrestricted knowledge-base learning is not.

cs.AI

版本更新 · v3arXiv:2611.18267

TetraCoder: Adaptive Tetrahedral Encoding for Neural Fields

Daniele Della Pietra, Antonella Rech, Nicola Conci, Nicola Garau

原文摘要

Implicit and explicit representations of geometry are central in computer graphics applications and come with their pros and cons. With surface sampling being faster on explicit representations and spatial queries being faster on implicit representations, finding efficient conversions between them is a highly desirable property. We present TetraCoder, a single resolution hash-free adaptive tetrahedral encoding that links an explicit tetrahedral spatial encoder with an underlying implicit signed distance field (SDF). The resulting hybrid implicit-explicit space is continuous piecewise affine (CPWA) by design, allowing to obtain an exact correspondence between the implicit SDF and the explicit analytic mesh. TetraCoder's design comes with additional perks, in particular: (a) it scales better than multi-resolution encoding methods due to its single resolution optimizable grid, (b) unlike hash-based methods, it is not affected by collisions, (c) it enables fast tetrahedral ray-tracing, geometry and appearance editing, directly through its adaptive tetrahedral scaffold. We demonstrate the versatility of TetraCoder by showing an improvement over state-of-the-art methods on multiple tasks: 2D/3D fitting from images and point clouds, 3D novel view synthesis, 3D reconstruction, and geometry/appearance editing.

cs.GR · cs.CV

新论文 · v1arXiv:2611.23531

RESCUE Jumper: A Centimeter-Scale Rolling and Jumping Robot for Search and Rescue

Kiran Marques, Shashwat Singh, Ben D'Ambrosia, Zeynep Temel, Melisa Orta Martinez

原文摘要

Centimeter-scale robots are promising for urban search and rescue because they can enter confined spaces that are inaccessible or unsafe for humans. However, their small size limits obstacle traversal after deployment. This paper presents the RESCUE Jumper, a 125 g mobile robot with a 6.2 cm width and 6.2 cm diameter wheels that combines ground rolling with jumping to traverse steps and gaps that exceeds its rolling capability. The RESCUE Jumper uses its two actuators for both rolling mode and jumping by reversing the direction of wheel motion. Forward wheel motion enables rolling, while reverse wheel motion winds a spring steel tail to store elastic potential energy and release it for jumping. The RESCUE Jumper varies tail winding speed to control jump direction, transitioning from backward to forward jumps as winding speed increases from 0.75 rad/s to 8.73 rad/s. The launch angle of the jumps ranges from 45 degree to -11 degree with respect to the vertical axis, reaching a maximum height of 9.2 cm and a maximum lateral displacement of 11.2 cm. We model the winding speed-dependent jumping behavior in three phases: tail release to determine the contact point and robot orientation, tail straightening until liftoff, and ballistic flight to predict jump height and lateral displacement. Finally, qualitative tests highlight the robot's locomotion in cluttered, real-world environments. The model and experiments presented in this work can inform future designs of space-constrained jump mechanisms in centimeter-scale robots for search and rescue and inspection in unstructured environments.

cs.RO

新论文 · v1arXiv:2611.23530

Dreaming Up Authors: Factual Prevalence and LLM Hallucinations in Academic Authorship Attribution

Sijia Zhong, Tamir Yirga, Yijia Ma, Thai Le, Yifan Hu

原文摘要

Large Language Models (LLMs) are widely used for question answering but are prone to hallucinations, yet the underlying causes, particularly the role of factual prevalence in training data, remain underexplored. In this work, we study this through academic authorship attribution, hypothesizing that hallucinations are more likely for less prevalent papers. Using citation count as a proxy for factual prevalence, we curate a dataset of 1.92 million papers across eight scientific disciplines with stratified samples by citation level. Experiments on three state-of-the-art LLMs confirm our hypothesis, revealing a robust inverse relationship between hallucination rate and citation count across all models and disciplines, with hallucination rates exceeding 98% for rarely cited papers and falling below 37% for highly cited ones. Our in-depth analysis further shows that these failures primarily reflect retrieval limitations rather than knowledge absence, and hidden-state probing of open-source models shows that factual prevalence is encoded in pre-generation representations, providing convergent mechanistic evidence for the prevalence-hallucination relationship. The code and data are available at https://github.com/quinnzhong1/dreaming-up-authors.

cs.CL

新论文 · v1arXiv:2611.23529

ORGANIC3D: Grounding 3D CT Vision Language Models in Organ Level Image Text Coupling

Zelong Liu, Hamza Ahmed, Wynn Wingyi Lee, Mickael Torjman, Alexander Dimitrakakis, Jiahua Lu, Timothy Deyer, Bachir Taouli 等 10 位作者

原文摘要

Vision language models (VLMs) have achieved strong performance in 3D computed tomography (CT) classification, but high accuracy does not reflect whether their predictions rely on the correct anatomical evidence. We introduce ORGANIC3D, a framework for evaluating and improving organ level image text alignment through controlled anatomical interventions. Our benchmark assesses 12 vision encoder checkpoints and 7 generative VLMs using matched patient comparisons, organ erasure, lesion replacement, and laterality perturbations, revealing substantial alignment failures even among top performing models. To learn organ level image text correspondence, ORGANIC3D aligns each finding sentence with the anatomy aware image features and trains on edited scans to anchor this alignment in the organ's image evidence. We further extend this framework to generative VLMs, promoting evidence dependent question answering and report generation. Trained exclusively on public data, ORGANIC3D achieves SOTA classification AUROC on CTRATE, Merlin, and the heldout RADChestCT dataset and reaches 77% laterality accuracy, compared with at most 66% for prior models. Its generative VLM matches or exceeds all evaluated publicly released VLMs on visual question answering, achieves the highest report accuracy, and retracts 96 to 99% of target organ findings after organ removal, versus a maximum of 69% for other models. Together, these results establish ORGANIC3D as a framework for testing whether 3D CT vision language models ground their predictions in anatomical evidence and for improving organ level alignment alongside predictive accuracy.

cs.CV

版本更新 · v2arXiv:2610.04874

When the noncommutative AM-GM inequality holds

Yimin Zhong

原文摘要

In this note, we prove that the noncommutative AM-GM inequality holds if $n\ge 2\lceil m/2 \rceil^2$. The motivation comes from counterexamples constructed in [De Sa, Random reshuffling is not always better, NeurIPS2020]. The proof constructs a vertex measure based on the Chebyshev nodes on the Boolean cube to extract the distinct indices. The main difficulty is that the measure is not positive on non-integer nodes. The key technique comes from [Grigoriev, Complexity of Positivstellensatz proofs for the knapsack, Computational Complexity (2001)] and eventually transforms the problem into a quadrature estimate.

math.PR · cs.LG · math.OC

新论文 · v1arXiv:2611.23524

Balancing Partition Forest for Causal Weighting

Felipe Angelim, Alessandro Leite

原文摘要

Balancing weights are used in observational causal inference to construct a population in which the treatment is independent of observed pretreatment covariates. The ideal weight is the ratio between the product of the covariate and treatment marginals and their joint distribution, for binary and continuous treatments alike. We propose Balancing Partition Tree (BPT) and Balancing Partition Forest (BPF), which estimate this ratio on a learned rectangular partition of covariate--treatment space. Each split maximizes the gain in a Bregman divergence computed from joint and marginal counts. Two choices of divergence yield criteria that maximize the mutual information captured by the partition or reduce the squared error of the weights. We show that the population residual of either criterion bounds the bias of inverse-probability-weighted and doubly robust response estimators that use the population partition weights. Across 17 synthetic and semi-synthetic settings and three response estimators, BPF obtains the lowest mean RMSE rank among seven weight estimators, and a single tree fits in 0.14 seconds on 16,512 observations.

stat.ME · cs.LG

版本更新 · v2arXiv:2609.02083

XMerge: Cross-Axis Selection and Reconstructive Layer Merging for LLM Depth Compression

Jundong Hu, Shekar Ramachandran

原文摘要

Removing complete transformer layers preserves a standard serving architecture, but existing depth-compression methods can lose substantial quality, and the loss varies unpredictably across models. We introduce XMerge, a post-training method with two components. Cross-axis selection identifies a block with low relative-magnitude and angular hidden-state change, and local boundary reconstruction re-fits the adjacent surviving block to match the original two-block output. XMerge uses no task labels or end-to-end fine-tuning, and it introduces neither architectural changes nor additional inference-time parameters. Across seven Llama and Qwen backbones (0.5B-8B), five published baselines, and three layer-reduction levels, its advantage over baselines is largest at the most aggressive removal: at k=4 it ranks first on six of seven backbones on CORE (a 22-task aggregate) and, separately, on six of seven on MMLU (five of seven on both at once), while avoiding the large perplexity increases of several competing operators. In a task-level bootstrap, the 95% confidence intervals for the three largest CORE margins exclude zero; the remaining margins are consistent with ties. Across the 14 (model, regime) cells it is also the only evaluated operator that never collapses, ranking top-2 in both zero-shot and in-context regimes; on a first calibration probe (one backbone) it is the best-calibrated operator. Ablations show that local reconstruction provides most of the gain, while cross-axis fusion helps when the two selection axes disagree. The additional construction cost is recovered through per-token decode savings after roughly tens of thousands of requests.

cs.LG · cs.CL

版本更新 · v2arXiv:2608.25903

MetaSieve: Faster Relational Deep Learning through SQL-Based Metapath Selection

Fahim Shahriar Khan, Ashraf Aboulnaga

原文摘要

Relational Deep Learning (RDL) is an effective approach to machine learning over multi-table relational databases. In RDL, a database is modeled as a graph in which each row is a node and each foreign-key relation is an edge, and a graph neural network (GNN) is trained on this graph. Training a GNN requires sampling a subgraph around every seed node in the training set, and the cost of training is largely determined by the size of these subgraphs. This paper aims to reduce subgraph size by leveraging the join and aggregation capabilities of relational database systems. We observe that sampled subgraphs are obtained by following metapaths composed of foreign-key links, and that many of these metapaths can be pruned without loss of accuracy. We present MetaSieve, a metapath selection layer that determines which metapaths to retain and which to prune. For each candidate metapath extension, MetaSieve computes statistics via SQL join and aggregation queries and evaluates the extension based on a novel scoring function that prefers lightweight but informative candidates. Metapaths whose scores fall below a threshold are deemed uninformative and pruned. Metapath selection in MetaSieve is lightweight since it relies only on database statistics and task labels, and it is independent of GNN parameters, so it integrates with diverse GNN architectures for classification and regression. Our evaluation on the RelBench benchmark with multiple GNN backbones shows that MetaSieve consistently reduces per-epoch training time by large margins while maintaining and often improving accuracy.

cs.DB · cs.LG

版本更新 · v2arXiv:2605.07058

MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments

Yicheng Gao, Xiaolin Zhou, Yahan Li, Yue Zhao, Ruishan Liu

原文摘要

Real-world clinical diagnosis is a complex process in which the doctor is required to obtain information from both interaction with the patient and conducting medical exams. Additionally, the doctor needs to adapt to different patient personas, as well as noisy and incomplete information that can happen at any time during the process. However, existing benchmarks for medical LLMs and methods for automatic diagnosis largely simplify this process by reducing it to single-turn question answering, noise-free conversations, or sequential exam making, etc., ignoring the interactive and uncertain nature of clinical diagnosis. In this paper, we aim to address this gap by formalizing clinical diagnosis as a Partially Observable Markov Decision Process (POMDP) with three action types: questioning the patient, ordering medical exams as tool calls, and issuing a diagnosis. We also introduce a systematic noise model comprising seven patient noise types and three exam noise types. Using our proposed environment, we train an effective diagnosis agent, \textbf{MedExAgent}, through a two-stage pipeline that first performs supervised finetuning on synthetic conversations structured after the Calgary-Cambridge model for clinical interviews, and then applies DAPO to optimize a composite reward capturing diagnostic accuracy, tool call quality, and exam cost including financial cost and patient discomfort. Through extensive experiments and ablation studies, we demonstrate that MedExAgent achieves diagnostic performance comparable to larger models while maintaining cost-efficient examination strategies.

cs.CL · cs.AI

版本更新 · v2arXiv:2608.02841

Localize, Don't Beautify: Client-Side Control of Image-Editing APIs for Cosmetic Surgery Previews

Sukhrobbek Ilyosbekov

原文摘要

Ask a commercial image editor to preview a cosmetic procedure and it will often change more of the face than the request names: a jawline edit can also smooth the forehead or alter the eyes. Existing methods for confining an edit to one region require access to the model's internals, which a public editing API does not expose. We ask how much control is possible from the client side alone. In a pilot benchmark, five current commercial editing configurations perform facelift-style jaw-neck and rhinoplasty edits on synthetic faces under two levels of client-side control: the prompt alone, and a masked composite that cuts the edited region out of the response and pastes it back onto the original photograph through a landmark-derived mask. Of 162 attempted edits, 151 could be scored. ArcFace cosine measures identity preservation; a CIELAB pixel-change ratio measures how much change lands inside the requested region rather than a protected facial zone. On 15 faces, the masked composite improved localization over the paired prompt-only output by a median of 0.315 (95% face-clustered bootstrap interval 0.279-0.366) while retaining most of the target-region change. Editors differed in edit strength and identity retention, and one returned near-copies for the facelift request. This is a study of control, not clinical accuracy: the faces are synthetic, no surgeons rated the outputs, and each condition was generated once. Within that scope, keeping a surgical preview inside its intended region needs no access to the model; a mask and composite on the client enforce it across every editor tested, at low provider cost.

cs.CV

版本更新 · v2arXiv:2610.26325

Typed Decision Models under Prevalence Shift and Label Budgets: Decision Training, Calibration, and Implicit Priors

Abdul Rahman Iqbal, Muhammad Fawad Nasim, Amir Saleem

原文摘要

Typed decision models (TDMs) return probabilities over caller-defined options, and Jev's vendor describes it as calibrated. We ask whether vendor decision training improves a model over its backbone, whether a TDM's calibration and thresholds withstand prevalence (label) shift like a fine-tuned classifier's, and how many labels a trained model needs to overtake a TDM. We compare three TDMs (Jev, Tev1-4B, Nimble-9B), their base models and trained classifiers on identical candidate-set decisions from five public datasets (on intent datasets, within the gold label's intent group) under simulated shift, with 35 paired tests frozen before the confirmatory analysis (earlier test-data checks disclosed), and estimate label-budget curves. First, decision training is not always beneficial: Nimble-9B, which differs from Qwen3.5-9B only by a LoRA adapter, is better calibrated on intent tasks but 12 Macro-F1 points worse on financial sentiment, a loss that persists across prompt formats; Tev1-4B's largest gain over its backbone is a prompt-format effect. Second, on 50 fixed moderate shifts, Jev's top-label calibration error and threshold risk grow significantly more than a fine-tuned DeBERTa's only on financial sentiment, sensitive to the prior set; averaged over 2,000 shifts the gap is at most one point. Third, label-free EM correction with the model's implicit prior lowers Jev's shifted calibration error where it is highest, but labelled recalibration lowers it far more. Fourth, DeBERTa needs 100-250 labels to overtake Jev on hate speech and does not clearly overtake it on CLINC150 at any budget; a QLoRA adapter on Qwen3.5-4B overtakes Jev with at most 2,500 labels on every dataset, on CLINC150 only marginally and not under in-budget selection. The TDMs tested are neither uniformly better than their backbones nor uniquely fragile under shift; their lead over trained models depends on the task.

cs.LG · cs.CL

新论文 · v1arXiv:2611.23520

BeFit: Shifting Complexity from Weights to Bernstein Activations for Resource-Constrained Sensing

Malak Gamal El-Din, Yasser Shoukry, Salma Elmalaki

原文摘要

Time-series sensing increasingly relies on neural networks, yet deployment on resource-constrained microcontrollers remains challenging. Aggressive model compression can reduce accuracy, while restricting weights to multiplication-free representations introduces further losses. We present BeFit, an end-to-end framework that shifts model capacity from weights to learnable Bernstein polynomial activations. BeFit (i) finds compact Bernstein-activated convolutional neural networks (BeCNNs) through hardware-aware neural architecture search and trains them via knowledge distillation; (ii) projects their weights to multiplication-free codes, freezes the codes, and recovers the resulting accuracy loss through the learnable activations; and (iii) generates model-specific kernels that exploit the projected weights for multiplication-free convolutions. On human activity recognition, BeCNNs are 2.75 percentage points (pp) more accurate on average than ReLU CNNs of identical architecture. On a TI CC3220SF (Cortex-M4), weight projection speeds BeCNNs up by 2.2x on average while losing 0.8 pp, compared with 2.4 pp for ReLU CNNs. Against the MLPerf Tiny DS-CNN reference model running on TensorFlow Lite Micro with CMSIS-NN, the unprojected BeCNN achieves 1.0 pp higher accuracy, 2.2x lower latency, and 6.4x lower flash, while the projected model remains within 1.0 pp of the reference accuracy and runs 5.9x faster. In emulation on a RISC-V core without a hardware multiplier, the instruction-count reduction relative to the DS-CNN increases from 5.2x on the Cortex-M4 to 147x. BeFit also extends to transformers and MLPs, and across all tasks the final models stay within 1.56 pp of their float32 teachers on average.

cs.AI · cs.AR

新论文 · v1arXiv:2611.23518

From Arraignment to Resolution: Transformer Models of Court Cases

Kory Rosen, Aron Culotta

原文摘要

The criminal legal system is composed of many complex decision points, such as which charges are pursued, how bond is determined, plea deal negotiations, and sentencing. Given the profound impact of such decisions, there is a growing need to increase the transparency within this system. While prior machine learning approaches have focused on modeling single decisions (e.g., recidivism), this paper proposes a transformer-based time series model to forecast the outcome of the next proceeding in a case (e.g., charges accepted, bond set, plea deal made, etc.). By modeling a case as an event sequence, we enable a more nuanced analysis to support better oversight and understanding of decision making. We conduct an empirical analysis of thousands of cases using a newly constructed dataset derived from publicly available court records of a mid-sized U.S. city. We fit models that combine textual data from clerk notes with structured information about the defendant, prior charges, and courtroom. Our transformer model achieves $.57$ micro-F1 on a 20-class multi-label task, a significant improvement over several baselines and comparable to a GRU trained on the same input. We demonstrate how the model can be used to provide insights into decision-making and help court observers identify emerging issues within the jurisdiction studied.

cs.CL · cs.CY · cs.LG

新论文 · v1arXiv:2611.23517

RageVLA: Augmentation-Trained Perception and Action for State-of-the-Art Robustness on LIBERO

Amrit Lal Singh, Smarak Kanjilal

原文摘要

Vision-language-action (VLA) models look saturated on LIBERO, yet most of them fall apart on LIBERO-PRO as soon as an object moves or the instruction asks for something new. We argue that what is missing is not scale but decoupling. In these policies, what to do is tied to where things were during training, to the scene around them and to the wording of the instruction. We cut these ties in two places. In the data, LIBERO demonstrations are re-arranged by general rules: every object and fixture is moved and rotated, tasks are carried into other environments and onto other surfaces, and every instruction is paraphrased. In the policy, a perception engine on frozen DINOv3 features, trained on this augmented data, hands the action model the scene in decoupled form: a list of objects with their positions, and a compact code of what the gripper is looking at, next to image and instruction embeddings from TinyCLIP. A flow-matching diffusion transformer, trained from scratch, acts on this view. We call this combination of Robust Augmentation and Grounded Encoding RageVLA. With 0.21 billion parameters, RageVLA sets a new state of the art on LIBERO-PRO among VLA policies, scoring 0.72 against 0.53 for the best published model, and a larger variant reaches 0.73. Two further tests on LIBERO-Object show that the policy acts on what it perceives. When the object positions it is given are shuffled while the camera images stay correct, its success falls from 0.965 to 0.215. When the target object is displaced by 28 cm, it still succeeds in 0.865 of the episodes, where $π_{0.5}$, run through the same harness, succeeds in 0.105.

cs.RO · cs.CV

新论文 · v1arXiv:2611.23516

Beyond the Sink Token: Sink-Guided Key Editing in Vision-Language Models

Hui Zhu, Saleh Zare Zade, Rafi Ibn Sultan, Xiangyu Zhou, Dongxiao Zhu

原文摘要

In vision-language models (VLMs), a few sink tokens attract a disproportionate share of attention. While previous studies have examined why these tokens attract attention, we investigate how the sink-key direction affects attention to image and question tokens. Across four probed VLMs, boosting the magnitude of positive sink-aligned components increases attention on average, whereas boosting negative components decreases it; these responses persist through later layers. This identifies the native sink key as a reference for controlling attention beyond its own position. Motivated by this finding, we propose SHRINK, a training-free method that partially reduces sink-aligned components across visible keys during generation. On nine benchmarks under sampled reasoning, it improves mean accuracy by 5.1 and 2.7 percentage points on LLaVA-OneVision-7B and Qwen2.5-VL-3B, with smaller gains on the other two main models, Qwen2.5-VL-7B and Gemma-3-4B. Beyond SHRINK, rescaling sink-aligned key components can replace the attention operations of two existing attention-steering methods, GIFT and ACG, with comparable accuracy on hallucination benchmarks.

cs.CV · cs.AI