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

+479新增论文
+361其中 AI 相关
+63已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 14:02 — 2026-11-16 14:02(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:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44库内论文最新更新时间:2026-11-14 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。

23,827 已收录论文19,941 AI 相关6,921 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 13,072 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
版本更新 · v2arXiv:2611.17332

ArchSpace: Recording, Reviewing, and Referencing LLM Architecture Research

Jie Wang, Tong Zhu, Jiahao Kuang, Zhe Xu, Mowen Ruan, Yunkai Chai, Yuliang Liu, Dehong Zheng 等 14 位作者

原文摘要

Model architecture shapes the scaling behavior, training efficiency, and inference cost of LLMs, making it a central focus of both industry and academia. In industry, teams such as those behind DeepSeek, Qwen, and Kimi routinely introduce architectural innovations, yet public reports rarely document which ideas succeeded, which were abandoned, and why. In academia, limited compute and inconsistent baselines often restrict evaluations to small-scale, single-point comparisons, making it difficult to establish whether improvements hold at larger scales or translate into broader impact. ArchSpace addresses both gaps as a public platform for Recording, Reviewing, and Referencing Architecture Research: each proposal is recorded with its experiments and reasoning, reviewed by the community, and referenced by later work. To evaluate ideas before costly large-scale training, ArchSpace leverages scaling laws to predict model loss at larger scales from smaller experiments, a practice widely adopted in industry. We provide initial references that make the platform usable: Qwen3.5 and OLMo3 baselines, fitted scaling laws, and a reusable training recipe. Ideas validated through this review can in turn become new baselines, and ArchSpace thereby aims to broaden the range of ideas that shape the next generation of models.

cs.CL · cs.LG

新论文 · v1arXiv:2611.18553

WeightBench: Evaluating Language Models as Weight-Space Programmers

Aayush Marasini, Barsat Khadka, Nick Rahimi

原文摘要

Recent work shows that large language models (LLMs) can operate directly on the parameters of other neural networks. They can read what a network was trained to do, fix a network that fails, and write working networks from scratch, all without gradient descent. This capability has been termed Weight-Space Programming (WSP). Exploring this new paradigm systematically requires a robust benchmark. We introduce WEIGHTBENCH, a benchmark that evaluates LLMs of increasing capability on 42 WSP tasks across five tracks: reading, fixing and writing weights, recognizing edits that are impossible, and data-free compression. The networks whose weights the LLMs read and edit range from 2K-parameter control policies to 7B-parameter language models. Experimental benchmark results show that frontier agents can already read small networks and write working control policies without ever running them, but cannot yet patch language models, compress them without data, or tell an impossible edit from a hard one. On all 42 tasks, Claude Opus 5.5 reaches a macro score of 0.535 (Sonnet 5.5 0.466, Haiku 5.5 0.402, DeepSeek v4-flash 0.215); on the 38 tasks it was run on, GPT-6.1-sol reaches 0.568 against Opus's 0.546. Code, the task registry, our OS-level sandbox harness, and the live leaderboard are publicly available at https://github.com/Aayush-Marasini/WeightBench.

cs.LG · cs.AI

版本更新 · v2arXiv:2609.06383

From Reading Code to Reading Spec: A Verified Layer for LLM-Driven Codebase Maintenance

Xinhao Zhang, Jingjie Lu, Kunpeng Liu, Fei Xie

原文摘要

The rapid growth of LLM-generated code increases software complexity and the maintenance burden on engineers. While LLMs offer a potential automated alternative, this structural complexity hinders their ability to manage codebases directly. We introduce the Provable Representation Of Original Functionality (PROOF), which manages codebases indirectly via structured specifications. To enable full-lifecycle codebase management strictly through these specifications, PROOF abstracts codebase topology into a hierarchical natural-language representation. To establish absolute trust, the system proves semantic equivalence by reconstructing source code exclusively from this specification. This verified foundation drives maintenance requests, executing code modifications while synchronously updating itself to prevent semantic drift. Experiments on real-world repositories confirm the effectiveness of these specifications.

cs.SE · cs.CL

新论文 · v1arXiv:2611.18549

JVT: Just Video Transformer makes pixel-space video diffusion simple

Jianjun Zhou, Hua Geng, Haoyu Guo

原文摘要

Direct diffusion modeling of high-dimensional raw video data is challenging, and existing pixel-space methods often rely on specialized architectures. We introduce JVT (Just Video Transformer), a simple large-patch DiT-style Transformer for pixel-space video diffusion, without a pretrained autoencoder, auxiliary detailers, cascaded stages, or U-Net-style skip connections. We systematically examine video patch embeddings, register tokens, and adaptive layer normalization to identify design choices that balance generation quality and computational efficiency. The resulting JVT design achieves generation quality competitive with latent diffusion baselines in both class-conditioned and unconditional settings. The pixel-space formulation of JVT also naturally supports joint generation of pixel-aligned modalities. We demonstrate this capability through camera-conditioned RGB-disparity generation, which improves camera following relative to RGB-only baselines and yields explicit scene geometry without an additional reconstruction model at inference. These results highlight the potential of simple DiT-style Transformers for pixel-space video diffusion, and we hope our findings offer useful insights and practical guidance for future research.

cs.CV

版本更新 · v4arXiv:2505.11294

Bidirectional Information Flow (BIF) - A Sample Efficient Hierarchical Gaussian Process for Bayesian Optimization

Juan D. Guerra, Thomas Garbay, Numa Dancause, Guillaume Lajoie, Marco Bonizzato

原文摘要

Hierarchical Gaussian Process (H-GP) models divide problems into different subtasks, allowing for different components to address each part, making them well-suited for problems with inherent compositional structure. However, existing H-GP frameworks typically employ one-way information sharing - either top-down or bottom-up - which limits sample efficiency and slows convergence. We propose Bidirectional Information Flow (BIF), which establishes continuous two-way communication. BIF retains the modular structure of hierarchical models - the parent conditions its own posterior on child summaries, treating them as structured priors - while introducing top-down feedback to softly decompose environment observations from the parent into sub-responses. This mutual exchange improves sample efficiency, enables robust training, and allows modular reuse of learned subtask models. We prove analytically the regret of a GP with a learned kernel scales linearly with the mismatch to the true kernel, tightening in the hierarchical case to the sum of child-level errors. Ablation shows removing the downward pathway collapses child $R^2$ by up to 58%. Across synthetic, neurostimulation, and HPO benchmarks, BIF achieves up to $4\times$ higher parent $R^2$ and roughly 100% AUC improvement over vanilla GPBO, and outperforms or is the runner-up in 38/40 tests compared to the state-of-the-art baselines while supporting modular child transfer to novel composite tasks.

cs.LG

版本更新 · v5arXiv:2601.15235

Tracing 3D Anatomy in 2D Strokes: Can Projection-Derived Masks Replace 3D Segmentation for Cervical Spine Fracture Recognition?

Fabi Nahian Madhurja, Rusab Sarmun, Muhammad E. H. Chowdhury, Adam Mushtak, Israa Al-Hashimi, Sohaib Bassam Zoghoul

原文摘要

Cervical spine fractures require rapid and accurate diagnosis, yet automatic CT interpretation remains challenging as subtle injuries must be assessed across large 3D volumes. We ask whether full 3D vertebra segmentation is necessary for fracture recognition, or whether vertebra masks approximated from 2D projections preserve sufficient diagnostic context. In the proposed multi-stage pipeline, a YOLOv8 detector localizes the cervical spine from multi-view variance projections (3D mean Intersection over Union 94.45%). Multi-label vertebra segmentation is performed with a DenseNet121-Unet on energy-based sagittal and coronal projections (mean Dice 87.86%). The predicted 2D masks are back-projected and fused into approximate 3D masks per vertebra to extract volumes of interest from the original CT, which are analyzed by an ensemble of 2.5D spatio-sequential CNN-Transformer models. On the full RSNA 2022 cohort at native prevalence (2,019 patients, five-fold cross-validation), the pipeline yields vertebra-level and patient-level F1-scores of 68.15% and 82.28%, area under the receiver operating characteristic curve of 91.63% and 90.95%, and area under the precision-recall curve (AUPRC) of 75.64% and 92.00%. With the classifier architecture fixed, replacing 3D-segmentation masks by projection-derived masks changed vertebra-level and patient-level AUPRC by +1.03 and +0.65 points, and the pipeline differed from the reproduced RSNA 2022 winning solution by -0.55 and +0.15 points. No AUPRC difference was statistically significant, and fold-wise 95% confidence intervals excluded vertebra-level losses larger than 1.46 and 2.81 points, respectively. Explainability and interobserver analyses examine reliability. Projection-based mask approximation is therefore a viable proxy for 3D vertebra segmentation in cervical fracture recognition.

cs.CV · cs.AI · cs.LG

版本更新 · v2arXiv:2605.13340

Shortcut Mitigation via Spurious-Positive Samples

Phuong Quynh Le, Jörg Schlötterer, Sari Sadiya, Gemma Roig, Christin Seifert

原文摘要

Shortcut mitigation strategies commonly rely on training data annotations, group-balanced held-out data or the presence of all groups, i.e., all combinations of (spurious) attributes and classes, in the training data. However, these requirements are rarely met in practice. We instead propose a method for targeted model analysis to identify a small set of instances in which the model relies on spurious attributes. Using that set and following ``this feature should not be used for prediction'' reasoning, we identify highly relevant neurons in an intermediate layer and regularize their impact. This ensures that models learn to depend on informative features rather than being right for the wrong reasons, thereby improving robustness without requiring additional balanced held-out data or annotations.

cs.LG

新论文 · v1arXiv:2611.18545

From smoothed analysis to backward error: The power of adaptive perturbations

Michał Dereziński, Michael W. Mahoney, Raphael A. Meyer, Christopher Musco

原文摘要

Smoothed analysis has become a central tool in theoretical computer science, often allowing for significant improvements to worst-case running times if we settle for a solution to a small random perturbation of the problem instance. This is closely related to the classical concept of backward error in numerical analysis, which allows an algorithm to return a solution to an arbitrary perturbation of the problem. Despite the qualitative similarity of these concepts, we show that they can exhibit large quantitative differences. Notably, we prove that, while a linear system with any $n \times n$ matrix $A$ can be solved to backward error $ε$ using $O(\log(n) / ε)$ matrix-vector products with $A$, any algorithm that solves a random $ε$-sized perturbation of $A$ requires $Ω(n)$ matrix-vector products. This means that a useful perturbation for solving a linear system in backward error must be adaptive to the input. Interestingly, however, randomness is still essential: we show that any deterministic method that attains small backward error for all linear systems provably requires $Ω(n)$ matrix-vector products, resulting in the first separation between randomized and deterministic algorithms in a natural computational model for solving linear systems. Finally, we show that matrix structure can significantly affect backward error complexity. For example, we show a deterministic $O(1/ε)$ matrix-vector product algorithm for symmetric linear systems.

cs.DS · math.NA

新论文 · v1arXiv:2611.18533

ModHarness-RL: Recasting Harnesses as Learnable and Evolving Programs for Agentic RL

Zelin He, Siyu Zhu, Jacob Helwig, Yujian Liu, Li An, Rohit Jain, Shiyu Chang, Alborz Geramifard

原文摘要

Agentic reinforcement learning (RL) increasingly relies on a harness, the scaffold around the model that decides what it sees of its own interaction and what guidance it receives. Most existing approaches train under a hand-written harness that stays fixed throughout. However, an effective harness depends on the domain, the data and the model, and keeps changing as the model trains. We introduce ModHarness-RL, which recasts the harness as programs that are learned from data and evolve as the model trains with RL. ModHarness-RL records the interaction as structured State, a set of typed blocks, and two core components of the harness are programs over these blocks, a Compression program that assembles the accumulated history into the model's context and a Steering program that supplies guidance when behavior deviates. During RL training, candidate programs are proposed from recent trajectories, verified by execution, and replayed over past trajectories, so the harness tracks how the model's behavior shifts. We study CodeSearch in depth and further analyze ALFWorld and BIRD SQL, with models from 1.5B to 8B. The proposed Compression and Steering mechanisms improve held-out performance over the fixed-harness baseline in most settings. These results suggest that a harness for agentic RL can be learned from the task's data and evolved with the model.

cs.AI · cs.CL · cs.LG

版本更新 · v2arXiv:2611.09724

Evaluating Anterior Cruciate Ligament Risk of Injury Using a Graph Convolutional Autoencoder

Athanasios Babouras, Paul A. Martineau, Thomas Fevens

原文摘要

Current solutions for assessing the risk of anterior cruciate ligament (ACL) injury typically rely on expensive motion-capture labs that require substantial resource investment or subjective evaluations of specific athletic stress tests by experts. The Drop Vertical Jump (DVJ) and the Single Leg Hop (SLH) are two examples of such tests typically used to track progress in ACL rehabilitation. In this paper, we develop an unsupervised learning model that runs entirely on a smartphone for two tasks, based on an autoencoder architecture with multiple layers of graph convolutional networks, which utilizes pose estimation data to determine a person's injury risk status. Our model accurately predicts athletes at high risk of injury for both athletic stress tests, with average sensitivities and specificities of 78% and 78% for the DVJ, and 75% and 74% for the SLH. Our findings support the development of a widely accessible smartphone solution for real-time screening of ACL injury risk.

cs.CV

新论文 · v1arXiv:2611.18530

Understanding Contextual Bias in Agricultural CNNs Through Hidden-Neuron Concept Induction

Abhilekha Dalal, Avishek Das, Samatha Ereshi Akkamahadevi

原文摘要

Convolutional Neural Networks (CNNs) can classify images using background-dominated patches that contain little or none of the target object, showing that they exploit contextual information. Previous studies detected this behavior through classification accuracy but say little about what CNN hidden layers represent. We investigate whether Concept Induction can reveal interpretable visual properties associated with hidden-neuron activations on contextual image patches. Using five agricultural datasets with high, moderate, and low contextual bias, we analyze four CNN architectures at three network depths and five patch locations. Quantitative image descriptors of each patch are encoded in a knowledge graph and used as background knowledge for Concept Induction, which derives logical expressions characterizing neuron activation. These expressions are tested on held-out images using the Mann-Whitney U test and Cliff's delta. Of 48,013 tested neuron-feature pairs, 13,164 (27.4%) were validated. Validation was most frequent at intermediate depths (mean 40.2% at mid layers versus 12.0% at deep layers), and no patch location dominated across datasets. Among the tested descriptors, edge, Gabor, and Tamura texture features had the highest validation rates. Stronger contextual bias did not correspond to higher neuron-feature validation rates: moderately biased Sugarcane had the highest rate (40.5%) and highly biased Cassava the lowest (19.2%). These results suggest that behavioral context dependence and the semantic interpretability of hidden neurons capture different aspects of CNN behavior, and that Concept Induction can complement patch-based bias detection.

cs.CV · cs.LG

版本更新 · v2arXiv:2504.16150

Evaluating the Generalizability and Explainability of Firn Image Classification with Topological Features

Jesse Dimino, Matt Jester, Kaitlin Keegan, Thomas Weighill, Sarah Day

原文摘要

In this paper we evaluate the performance of topological features for generalizable and explainable classification of firn image data, with the broader goal of understanding the advantages, pitfalls, and trade-offs in topological featurization. Firn refers to layers of granular snow within glaciers that haven't yet been compressed into ice. This compaction process imposes distinct topological and geometric structure on firn that varies with depth within the firn column. However, the limited and highly correlated training data available results in naive classifiers (such as convolutional neural networks) overfitting to orientation-dependent features. This motivates us to evaluate topological data analysis (TDA) as a way to design features which capture the shape of the firn data while retaining a large degree of invariance. We evaluate two classes of topological features, sublevel set features and distance transform features, together with persistence curves, to predict sample depth from firn images. A range of challenging training-test scenarios reveals that no one choice of method dominates in all categories. In particular, we see a tradeoff between accuracy on the one hand, and generalizability and explainability (via feature importance) on the other.

cs.CV · math.AT

新论文 · v1arXiv:2611.18523

Mutable Inference: Architecting LLM Accelerators for Inference-Time Learning

Yimin Gao, Liangtao Dai, Melika Morsali, Junting Huo, Mircea Stan

原文摘要

Long-context LLMs must retain growing histories, but full attention makes each new token increasingly expensive. Inference-time learning (ITL) offers another approach. The model keeps training on the context during inference, retaining what it learns in its weights. Recent work shows that ITL can match full-context attention quality while attending only to a recent fixed-size window. This bounds attention costs but adds Learning (backward computation and weight updates) alongside Prediction (the forward pass) costs. Inference accelerators assume fixed weights, while training accelerators target complete training steps. This work identifies two opportunities. Attention's non-matrix operations leave enough idle matrix capacity for Learning, while selected layers can tolerate delayed weight updates with little quality loss. We exploit both with Learning While Serving (LWS), an inference accelerator architecture that shares compute hardware between latency-critical Prediction and deadline-flexible Learning. Hardware-managed per-layer weight versioning allows Learning to publish updates while in-flight computations read older versions. Resumable reduction blocks let Learning kernels span fragmented idle windows and yield to Prediction, while dedicated softmax-gradient units relieve vector contention. On modeled datacenter and edge NPUs, LWS hides Learning within Prediction, sustaining Prediction-only throughput while preserving 99.3% of fully fresh Learning's quality benefit for TTT-E2E 3B at 128K tokens. Across nine models, LWS achieves 1.6x the throughput of serial execution and 1.3x that of the best prior co-execution architecture. RTL synthesis shows that LWS adds 1.5% to NPU core area without another MAC array. By efficiently turning idle inference capacity into learning capacity, LWS establishes inference-time learning as a first-class workload for future LLM accelerators.

cs.AR

新论文 · v1arXiv:2611.18519

Box-conditional Hypothesis Testing for Out-of-Distribution Object Detection

Donghoon Lee, Jusung Park, Shinjin Kang

原文摘要

Detecting out-of-distribution (OOD) objects is essential for ensuring the reliability and safety of object detectors in real-world deployment. We treat the decision on a detected box as a hypothesis test with the null hypothesis that the box covers an object of an in-distribution (ID) class. The null distribution changes with the size of the box and its contact with the image border, and the detector observes both. The test can therefore rank a box only against ID boxes of the same size and border contact, which gives a distribution-free bound on the false-alarm rate for each of them and uncovers the separation that one null distribution hides. The power of the test also rests on the layer it reads. Layers built only for the ID classes have no reason to keep what sets an unknown object apart, so the test reads the features before them. We propose \textbf{PLUM}, a training-free score that pools the last backbone stage inside the box and ranks its distance to the ID classes among ID boxes of the same size and border contact. On the standard benchmark, PLUM reaches the highest AUROC among the compared methods without external models, with 91.5 and 94.5 on PASCAL-VOC and 95.1 and 97.5 on BDD100K. Code: https://github.com/DDOZMI/PLUM

cs.CV

新论文 · v1arXiv:2611.18517

OpenLayout: An Open and Agentic-Driven Platform for Holistic VLSI Physical Design and Benchmarking

Qiufeng Li, Sizhe Tang, Quan Cheng, Zirui Wang, Wantong Li, Tian Lan, Weidong Cao

原文摘要

Physical design automation of very large-scale integrated circuits (VLSI) has made significant strides, progressing from single-stage placement and routing toward increasingly integrated full-flow implementation. Yet, existing approaches struggle with the vast design space optimization (DSO) arising from diverse technology nodes, circuit designs, and varied constraints. The substantial runtime of physical-design tools further exacerbates this challenge, leaving industrial workflows heavily dependent on experienced engineers to navigate the design space and achieve power, performance, and area (PPA) targets, incurring significant engineering effort. We argue that large language models (LLMs) with strong reasoning capabilities, enriched with distilled human design expertise, offer a promising path toward efficient and automated DSO. Unlike traditional algorithms, LLMs can interpret complex design contexts and naturally incorporate human expertise expressed in natural language for reasoning, acting, observing, and adapting throughout the design process, a capability that conventional optimization methods cannot exploit. To this end, we present OpenLayout, an agentic platform that leverages multi-agent collaboration with embedded design knowledge to enable self-iterative DSO. We further introduce OpenLayout-Bench, a benchmark targeting advanced technology nodes with commercial EDA tools to systematically evaluate physical design automation capabilities of LLMs. Experimental results demonstrate that OpenLayout achieves state-of-the-art performance, with approximately 20% accuracy improvement over baseline methods. Our work is open-sourced at https://github.com/fenggev56/OpenLayout

cs.AR

新论文 · v1arXiv:2611.18516

StreamEmbed: Real-Time Indexing from Pixels for Screenshot Retrieval

Dayoon Ko, Yichuan Wang, Soyeong Jeong, Joseph E. Gonzalez, Gunhee Kim, Sewon Min

原文摘要

Screen history can serve as searchable visual memory for people and agents, but unlike an offline corpus, it must be encoded and indexed as each screenshot arrives. OCR-based indexing is fast but loses visual information; visual encoding takes over two seconds. Yet screens change incrementally: most pixels repeat within and across screenshots. This raises a question: do visual encoders need to recompute their representations from scratch for every new screenshot? We present StreamEmbed, a system for incremental visual embedding that exploits this redundancy. Guided solely by pixel differences, it combines spatial token pruning, which skips blocks that repeat a neighbor, with temporal KV reuse, which reuses cached keys and values for blocks unchanged across screenshots. A small learned adapter compensates for pruning and reuse to preserve fidelity to full-screenshot embeddings. On ScreenMemEval, our benchmark of 10,426 questions over 184 hours of screen histories from two humans and a computer-use agent, StreamEmbed sets a new accuracy-latency Pareto frontier on an M2 Pro GPU: it encodes up to 3.7x faster than full-screenshot encoding without sacrificing accuracy and improves accuracy over OCR-based indexing by up to 6.3 Recall@10 points at matched latency. A memory-efficient vector index stores a simulated year of screenshots in 0.13 GB of RAM. Together, these results make real-time indexing of screen history in its native visual form practical, laying a foundation for fully local visual assistants.

cs.CV · cs.IR · cs.LG

版本更新 · v2arXiv:2611.17238

HEIR: Harness Egocentric Intent for Human-Robot Interactions

Yichi Zhang, Bo Wang, Zhenghan Zhu, Yutong Han, Jiayin Zou, Gao Kejun, Chang Liu, Shaoxuan Xie 等 14 位作者

原文摘要

For robots to assist, serve, and collaborate with humans, they must not only interpret human requests conveyed through language and multimodal intentional cues, but also execute long-horizon tasks that interleave navigation and manipulation. In this paper, we introduce HEIR, a resource for studying how to Harness Egocentric Intent for Human-Robot Interaction. HEIR pairs human speech, measured gaze, and egocentric video with robot observations and teleoperated navigation-manipulation trajectories, while each session preserves successive episodes, with each request fulfilled through multiple execution subtasks. The captured data, together with human-authored annotations, support the study of intent grounding, execution planning, and task completion within a unified interaction setting. To demonstrate the value of HEIR, we conduct extensive offline experiments to evaluate how models benefit from additional human-centric context across these tasks, together with real-robot experiments that assess execution task completion. HEIR thus provides a valuable resource for studying user-centric robot interaction in naturalistic household environments. Our demo and dataset are available online.

cs.RO

新论文 · v1arXiv:2611.18514

Can Mechanistic Interpretability Help Explain LLM Agent Failures? A Case Study on Web Element Hallucination

Mohamed Aghzal, Mor Geva, Gregory J. Stein, Ziyu Yao

原文摘要

Mechanistic Interpretability (MI) has made significant progress in explaining the internal computations of Large Language Models (LLMs); however, these advances have yet to demonstrate comparable success in explaining the decision-making processes of LLM-based agents. This paper examines the challenges MI tools face when applied to realistic agentic failures. We focus on one such failure: web agents hallucinating actions that are not available on a website. We apply a series of mechanistic analyzes to Qwen2.5-7B-Instruct as it interacts with live websites. We find that a linear probe trained on the last prompt token can predict hallucinations before generation begins (0.80 AUC) and steering along a probe direction corrects 85\% of hallucinations, but disrupts 7\% of valid actions. However, these results only provide a partial explanation of why the agent hallucinates. The probe direction is sensitive to prompt formatting, losing much of its steering effect after a minor change to how actions are represented. Additionally, circuit identification can be difficult as the computation is distributed across multiple components and positions, and the information the agent relies on varies across examples. We discuss how these observations challenge the assumptions underlying standard MI methods for circuit discovery and feature identification, and outline future directions for making these methods better suited to explain failures in LLM-based agents.

cs.AI · cs.CL

版本更新 · v2arXiv:2601.08732

ISLA: Ensemble learning and domain adaptation for generalizable acute ischemic stroke lesion segmentation in diffusion MRI with clinical validation

Vincent Roca, Hakim Daouairi, Sevak Yepremian, Hilde Henon, Nicolas Martinage, Laurent Puy, Grégory Kuchcinski, Martin Bretzner 等 9 位作者

原文摘要

Accurate segmentation of acute ischemic stroke (AIS) lesions on MRI is essential for clinical decision-making. Deep learning methods offer a promising approach to automating this task. However, they often generalize poorly to unseen clinical sites, and few AIS lesion segmentation methods have been externally validated. In this study, we propose $\mathit{ISLA}$ (Ischemic Stroke Lesion Analyzer), a framework for AIS lesion segmentation built on the design principles of $\mathit{nnU\text{-}Net}$. $\mathit{ISLA}$ combines attention modules, deep supervision, and ensemble learning across different input resolutions, convolutional block types, and loss functions. We also introduce $\mathit{ISLA\text{-}MT}$, a variant that leverages unlabeled target-domain images through semi-supervised learning. We trained both approaches on the SOOP and ISLES 2022 datasets and evaluated on a held-out internal validation set of 253 cases, as well as on 590 cases from an independent multicenter clinical cohort. We compared them with three state-of-the-art pre-trained models and with $\mathit{nnU\text{-}Net}$ trained on the same data. $\mathit{ISLA}$ outperformed the pre-trained models on the internal validation set, while both $\mathit{ISLA}$ and $\mathit{ISLA\text{-}MT}$ outperformed them on the external cohort. Although $\mathit{nnU\text{-}Net}$ performed slightly better than $\mathit{ISLA}$ internally, both $\mathit{ISLA}$ variants demonstrated better generalization to the external cohort. Furthermore, $\mathit{ISLA\text{-}MT}$ significantly improved performance over $\mathit{ISLA}$ on the external cohort. The proposed models performed particularly well on low-contrast lesions, and qualitative error analyses suggested greater robustness to acquisition artifacts. Both models are fast ($\sim$ 5 s per case), and their code and weights are publicly available at https://github.com/RocaVincent/isla_segmentation.

cs.CV · cs.AI

版本更新 · v2arXiv:2609.00518

Learning Task-Specific Antibody Representations via Function-Aware Masking

Ayan Goel, Thomas A. Walton, Amirali Aghazadeh

原文摘要

Antibody-specific language models pretrained via masked language modeling (MLM) learn representations that are critical for downstream sequence design and property prediction tasks. Yet, the corruption process itself is rarely leveraged as a source of inductive bias during pretraining. While preferentially masking complementarity-determining regions (CDRs) improves binding-related predictions, antibodies possess diverse biological priors over a variety of functions. Herein, we introduce function-aware masking, a family of pretraining algorithms that align mask placement with specific functional priors (e.g., from IMGT annotations or structure predictions) to shape the learned representation space. We show that these specialist masking strategies significantly improve performance on their respective objectives, yielding up to a 14% gain on structure-related tasks and up to a 5.9x improvement on CDR-related tasks. To further improve performance across multiple functional axes, we develop hybrid masking strategies that integrate multiple priors, balancing reconstruction over binding, structural, and biophysical objectives. Our results demonstrate that informed mask placement provides a parameter-free mechanism for imposing functional inductive biases in antibody language model training.

cs.LG · q-bio.BM

新论文 · v1arXiv:2611.18506

Agentic induction of common data elements and information extraction from sarcoma case report abstracts

Daniel Reichenpfader, Kwaku Appiagyei, Manovah Nadarajah, Ahmed Reda Bahr, Irina Filchenko, Fabio Dennstädt

原文摘要

Common data elements (CDEs) support clinical data comparability but are usually defined manually. We investigated whether large language model agents could derive a CDE schema from sarcoma case report abstracts and apply it at scale. An agent proposed 72,909 candidate CDEs from 24,588 PubMed abstracts; agentic consolidation yielded 1,570 CDEs. We retained 53 supported by at least 50 abstracts and attempted evidence-linked extraction across the corpus. Processing succeeded for all retained CDEs in 79.2% of abstracts, including responses indicating non-mention. Two human reviewers approved 83.0% of retained CDEs for relevance, 67.9% for clarity, and 56.6% for correctness. In 100 sampled abstracts, exact agreement with the value extracted by the LLM was 94.9% among 1,116 pairs with a non-empty answer (abstract-level bootstrap 95% CI, 93.0-96.4%). Errors concentrated in anatomical and temporal fields. These findings support agent-assisted schema drafting followed by expert curation before large-scale extraction.

cs.CL

版本更新 · v3arXiv:2611.00482

A Straight Line Is Not a Camera Pose: Auditing Short-Clip Pose Benchmarks

Xinyi Shi

原文摘要

Many vision benchmarks align a prediction to the ground truth before scoring it. If the alignment minimises the error, an input-free template scores the truth's distance from everything the alignment can reach, so the ground truth alone fixes how well a template can score, before any model runs. Camera pose is our central case. The absolute trajectory error (ATE), the standard camera-motion measure, aligns camera positions by a similarity transform. On the common Sintel protocol, an image-free constant-velocity line has a lower mean ATE than 10 of 11 recent models and 85 of 110 published methods, and on Lightspeed than 5 of 9 models and 10 of 11 published methods. The straightness of the true paths separates these two from TUM, ScanNet, DyCheck and ADT, where every model beats the line. A residual signal-to-noise criterion with the alignment's first-order refit predicts when straightening a prediction lowers ATE in all but one of 4010 model-clip evaluations, including all 504 on three benchmarks registered in advance. The alignment also ignores where cameras look: rotating a trajectory by 30 degrees against its orientations leaves ATE unchanged yet worsens the static-point reprojection of every model on Sintel, TUM and ScanNet. Fitting the alignment's rotation to the predicted orientations gives pose-anchored ATE (PA-ATE), a one-function change at about ATE's cost (37 vs. 34 microseconds per clip). It is never below ATE, ranks every image-free reference below every model on Sintel, tracks the reprojection error under controlled rotation and straightening, largely preserves the models' order, and exposes Lightspeed ground-truth orientations that the images contradict. Beyond poses, templates beat some published methods on KITTI video depth, SSP-3D body shape and NoW faces, and in video depth this distance sets KITTI apart from Sintel and Bonn.

cs.CV · cs.RO

新论文 · v1arXiv:2611.18504

Agentic AI for Discovering Fault-Tolerant Quantum Circuits

Aritra Lahiri, Florian Marquardt

原文摘要

Scaling quantum computing toward practical quantum advantage is currently limited by the efficiency of circuits that operate on information encoded by quantum error-correcting codes. The full stack of quantum computing encompasses several tasks: preparation of logical code states, implementation of logical gates, logical routines on encoded qubits, etc. Yet, these circuits are largely designed by hand for individual cases, with some recent works incorporating machine learning for certain aspects. We formulate this problem as agentic evolutionary program synthesis, wherein a large language model, leveraging its pretraining knowledge and tool-use proficiency, and guided by a circuit verifier, evolves a program that defines a Clifford circuit for a wide range of curated tasks such as logical state preparation, logical gate design, and logical routines such as code-switching, code growth, etc. Our approach consistently finds fault-tolerant circuits for all of these tasks, each verified by an exhaustive check over faults.

quant-ph · cs.AI

版本更新 · v2arXiv:2610.02288

AdaptViT: Runtime-Adaptive Vision Transformer Deployment on Custom RISC-V

Vishnu PS, Ajay Kumar M, Yike Li, Robert Bogdan Staszewski, Deepu John

原文摘要

Deploying Vision Transformers (ViTs) on low-power edge devices is challenging due to high computational demands. Conventional pruning frameworks require a separate compiled binary for each sparsity level, increasing storage overhead and limiting runtime adaptability. This paper presents an end-to-end deployment pipeline that transforms pretrained ViTs into a single runtime-configurable binary, enabling dynamic compute-budget switching on embedded CPUs. This is achieved by restructuring generated C kernels with modified loop bounds and binary-mask control logic, allowing execution to switch across discrete sparsity levels via compact external configuration files. Compared to multi-binary deployment, the proposed runtime-adaptive approach reduces on-device storage by up to 4.86x, requiring only 163 MB for ViT-Base instead of nearly 800 MB. To maximize pruning efficiency, we introduce a hardware-aligned block pruning strategy for Multi-Layer Perceptron (MLP) layers. In addition, a custom ISA extension is proposed to exploit input-reuse patterns in linear projection kernels. On a Synopsys TRV32P3FX RISC-V processor, the full system achieves up to 2.8x speedup at 65% MLP and 50% attention-head pruning for ViT-Base. The ISA extension alone provides a 1.56x speedup and 33% lower inference energy, with a 24.7% area overhead in a TSMC 28 nm implementation.

cs.AR

新论文 · v1arXiv:2611.18485

Interactive Program Induction with Language Model Priors

Robin Shing Moon Chan, Ryan Cotterell

原文摘要

Program induction refers to the process in which a learner aims to recover a program from a few given input-output examples. This paradigm broadens programming access by letting users demonstrate the rule-based behavior they want to apply to unseen data, instead of having to implement it themselves. However, recovering a program from finite input-output examples is fundamentally ambiguous, as a finite set of input-output examples is theoretically consistent with infinitely many programs whose output diverges on unseen inputs. We view this problem from a Bayesian perspective, where, given a prior $p^0$ over programs, identifying the target program means concentrating posterior probability mass on it by observing additional input-output examples. In the interactive program induction setting, the learner chooses maximally informative inputs and queries an oracle, such as the user, for their outputs. We derive a greedy query-selection algorithm and show that it terminates after $\mathcal{O}(\frac{1}γ\log 1/p^0(f^\star))$ informative oracle queries, and returns the target program $f^\star$ up to approximate equivalence when no other class outweighs it under the prior. The algorithm uses a language model as the prior under a PAC-style relaxation of program equivalence, where the query-selection objective is estimated using importance sampling. On the CodeARC benchmark, the algorithm improves accuracy over the LM only agent by up to 22 percentage points while observing up to 10.5 fewer input-output examples.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.18484

From AI-Enabled Remote Patient Monitoring Toward Agentic Robotics: Embodiment, Governance, and Care Integration

Ivana Ragusa, Lorenzo Guiducci, Filippo Cavallo

原文摘要

AI-enabled remote patient monitoring is evolving beyond passive data collection toward agentic AI systems that interpret patient states, coordinate care, and initiate action across domestic and clinical settings. This structured scoping review finds that mature agentic care has not yet emerged: Most systems remain human led, while stronger decision-action coupling and embodied AI remain largely confined to prototypes and pilots. Healthcare robotics makes the transition from monitoring to action especially visible by translating AI-generated recommendations and decisions into speech, movement, prompting, physical assistance, escalation, and care coordination, making embodiment, clinical integration, human oversight, and governance fundamental design requirements. Further progress requires safe and interoperable care architectures in which intelligent components operate through clinically validated and accountable workflows. We propose agentic robotics as a future direction for supervised systems embedded in the care ecosystem, connecting AI agents and robots with clinicians, caregivers, and patients through auditable workflows that can be interrupted and remain subject to human oversight and explicit AI governance.

cs.RO · cs.AI · cs.MA · cs.SE · eess.SY

版本更新 · v2arXiv:2609.04141

Efficient Test-Time Adaptation through Human-Agent Interaction

Zora Zhiruo Wang, Apurva Gandhi, Rulin Shao, Aspen Chen, Jonas Mueller, Zhiqi Liang, Jett Chen, Michael Ryan 等 25 位作者

原文摘要

AI agents are trained on population-scale data to encode broad capabilities spanning those of many practitioners. Yet the artifacts they produce rarely meet the personal bar professionals need to stake their reputation on. On realistic, open-ended tasks where success criteria are heterogeneous and insufficiently documented, individual expertise lives precisely in the elevation and departure from the average. In practice, iterative human-agent interaction surfaces criteria that users cannot fully specify up front, yet apply repeatedly across tasks. We argue this cross-session interaction data is a rich, underused signal for closing the gap to individual expertise. In this work, we propose test-time adaptation through human-agent interaction (TAHI), which integrates these signals into agent context and weights, and crystallizes each user's training and evaluation criteria via an evolving rubric module. We adapt agents to 30 individuals in two high-utility domains, writing and visual creation, on a total of 600 tasks. Our agents improve solo task success by 4.5-20.9% within only tens of tasks. Meanwhile, our evolving rubric module serves as a scalable annotation tool, creating evaluation rubrics that catch 16.0-22.3% more failures than those from LMs or humans alone. While agents are adapted towards individuals, we show these personalized agents also produce improvements in success of up to 8.8% that generalize across users.

cs.AI

版本更新 · v2arXiv:2606.05373

Evidence-Guided Neural Architecture Selection under Uncertainty for Subject-Specific Blood Glucose Forecasting

Md Azharul Islam, Dwyer Deighan, Tarunraj Singha, Danial Faghihi

原文摘要

Reliable neural architecture selection is an open challenge in time-series forecasting under limited, noisy, and heterogeneous data, where standard heuristic architecture design and validation approaches fail to ensure accurate and reliable prediction and generalization. We propose EVIDENT (EVidence-based IDEntification of Neural archiTectures), a framework for architecture selection that integrates Bayesian training, evidence-based ranking, and task-specific validation under uncertainty. The framework explores the candidate architecture pool and identifies the lowest-capacity model that satisfies a prescribed validation criterion. We demonstrate this method using temporal convolutional networks (TCNs) for individualized blood glucose forecasting in type 1 diabetes patients. The results show that EVIDENT systematically rejects both under- and over-parameterized TCN architectures on population-level diabetes data, while identifying models that generalize reliably to unseen patients. When multiple architectures are competitive, the framework further supports plausibility-weighted ensemble predictions that enhance predictive performance. Compared with a random-search baseline, EVIDENT identified smaller architectures with more consistent forecasting performance on unseen patients. These findings establish EVIDENT as a strategy to neural architecture discovery, enabling reliable model selection for high-consequence forecasting in data-limited and heterogeneous settings.

cs.LG · physics.bio-ph

版本更新 · v3arXiv:2401.13712

Engineering Yeast Cells to Facilitate Information Exchange

Nikolaos Ntetsikas, Styliana Kyriakoudi, Antonis Kirmizis, Bige Deniz Unluturk, Andreas Pitsillides, Ian F. Akyildiz, Marios Lestas

原文摘要

Although continuous advances in theoretical modelling of Molecular Communications (MC) are observed, there is still an insuperable gap between theory and experimental testbeds, especially at the microscale. In this paper, the development of the first testbed incorporating engineered yeast cells is reported. Different from the existing literature, eukaryotic yeast cells are considered for both the sender and the receiver, with α-factor molecules facilitating the information transfer. The use of such cells is motivated mainly by the well understood biological mechanism of yeast mating, together with their genetic amenability. In addition, recent advances in yeast biosensing establish yeast as a suitable detector and a neat interface to in-body sensor networks. The system under consideration is presented first, and the mathematical models of the underlying biological processes leading to an end-to-end (E2E) system are given. The experimental setup is then described and used to obtain experimental results which validate the developed mathematical models. Beyond that, the ability of the system to effectively generate output pulses in response to repeated stimuli is demonstrated, reporting one event per two hours. However, fast RNA fluctuations indicate cell responses in less than three minutes, demonstrating the potential for much higher rates in the future.

cs.ET · cs.IT · q-bio.MN

新论文 · v1arXiv:2611.18471

Do Verifier Judgments Survive Abstraction? Measuring Verification Transport for LLM Agent Evaluation

Disha Sheshanarayana, Sai Linisha Reddy Goli

原文摘要

LLM-based verifiers are increasingly used to evaluate agent executions, but their reliability is typically measured under a single representation of the trajectory. In deployed agent systems, the same execution may be exposed through composed tools, delegation boundaries, or compacted histories, changing what execution evidence is directly observable to the verifier. It therefore remains unclear whether correct verifier judgments persist across such abstraction boundaries. We introduce Verification Transport, a reliability test that measures judgment stability under abstraction-induced changes in execution observability. We construct matched native, abstracted, and restored views of the same frozen executions while holding the task, realized trajectory, outcome, ground truth, evaluation criterion, and verifier fixed. Across four agent-evaluation benchmarks, seven verifier backbones, four verification protocols, and three abstraction boundaries, we find substantial transport failure, reaching about 31% under macro abstraction and delegation. Verification protocols exhibit distinct failure modes: direct verification more often produces incorrect verdicts, whereas evidence-grounded and deliberative protocols tend to abstain under limited observability. This suggests that lower transport failure rates do not necessarily imply greater reliability. Restoring the corresponding execution provenance recovers 85.5% of transport failures, while recovery is lower when provenance is lossy or unavailable. These results show that native-view accuracy alone is insufficient to characterize verifier reliability when execution evidence crosses abstraction boundaries.

cs.CL · cs.AI