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

+0新增论文
+0其中 AI 相关
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-15 10:52 · 全站最近入库：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-14 12:18 — 2026-11-15 12:18（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：2026-11-15 10:52最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,729 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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 17,362 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-15 10:50（北京时间）
新论文 · v1arXiv:2611.16307

DEDCA: Test-Time Adaptation for Generalized AI-Generated Image Detection

Hao Tan, Qimin Zhang, Lihuang Fang, Kebing Jin, Jinghui Qin

原文摘要

AI-generated image detectors face significant challenges when deployed in real-world environments, particularly when test samples are produced by unseen generators that deviate from the source training distribution. Existing detectors often rely on a single type of evidence, such as semantic representations or low-level generation traces, making them vulnerable when the corresponding cue becomes unreliable. Moreover, adapting detectors to newly emerging generators usually requires target labels or retraining, which is costly and impractical. To address these challenges, we propose Dual-Evidence Disagreement-Constrained Adaptation (DEDCA), a test-time adaptation framework for generalized AI-generated image detection. DEDCA constructs a dual-evidence detector by combining CLIP-based semantic evidence with trace evidence extracted from shuffled entropy and residual statistics, and introduces a reliability-aware gate to perform sample-specific adaptive fusion. Our key idea is to exploit the disagreement between the two evidence streams as an unlabeled adaptation signal, enabling the detector to adjust to target-domain shifts without relying on target labels or blindly trusting a single prediction stream. Experiments show that DEDCA achieves superior performance on the GenImage benchmark by outperforming state-of-the-art AI-generated image detectors and test-time adaptation methods with 92.0\% average accuracy.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16304

StateAlign: Internalizing State-Aware Decision-Making for Reliable Multi-Turn Tool Agents via Reinforcement Learning

Zhexi Lu, Subhajit Chaudhury, Tejaswini Pedapati, Keerthiram Murugesan, Lei Yu

原文摘要

Reinforcement learning has improved the tool-use capabilities of large language models. However, better task performance can coincide with increased tool hallucination. Reliable tool use requires decisions to follow the current task state: available information, tool capabilities, and task progress. Our analysis shows that agents sometimes execute when they should ask for information, retrieve it, or decline an infeasible request, even when reasoning identifies missing information. We introduce StateAlign, combining task-state construction with state-contrastive reinforcement learning. The data cover five task conditions and pair states with different action requirements. Outcome rewards guide task completion; token-level contrasts compare the same generated reasoning and actions under paired states to train outputs that fit the current state. Experiments across five base models from three families show improvements on BFCL v4 multi-turn, ToolSandbox, and When2Call. Ablations show that state construction improves performance and reliability under different reward designs. The complete method further reduces tool hallucination across three Qwen3 sizes. On Qwen3-8B, StateAlign improves BFCL v4 multi-turn accuracy from 45.5% to 55.2% and reduces no-tool hallucination on SimpleToolHalluBench from 62.2% under outcome-only training to 56.1%. Behavioral analyses show more consistent decisions, more complete multi-call execution, and stronger recovery after tool errors.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.24969

Rare Event Estimation via Iterative Unalignment

Hanming Yang, Daksh Mittal, Jing Dong, Hongseok Namkoong

原文摘要

As agents are deployed with increased autonomy, even extremely rare events along their stochastic output trajectories can occur and prove catastrophic. Safe deployment therefore does not depend on whether these events can occur, but on how often they might. We study the problem of estimating the probability of rare events that arise from stochastic variation in the agent's own actions. Estimating this type of risk requires searching over the combinatorially vast space of trajectories. Naive Monte Carlo is computationally prohibitive in this regime, and constructing effective importance sampling (IS) proposals requires coordinated changes to a context-dependent chain of conditional distributions. We develop a new IS method that perturbs the original model's weights to construct the proposal. The proposal is itself a differentiably parameterized language model, enabling gradient-based search over weight space. We formulate an objective that combines a differentiable surrogate for event amplification and an adaptive regularization scheme that dynamically balances amplification against estimator stability. We evaluate our approach on $\sim$120M and $\sim$2.6B models across three event families spanning 300+ rare events as rare as $10^{-9}$, all with independently estimated reference probabilities. In our most verifiable settings, we observe that our IS estimator achieves over $800\times$ compute-weighted efficiency gains on average over naive Monte Carlo for events with probabilities lower than $10^{-7}$. Our implementation is available at https://github.com/namkoong-lab/iterative-unalignment.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.13987

Communication-Learning Co-Design for Pinching-Antenna-Assisted Federated Learning in Heterogeneous Wireless Networks

Shuai Wang, Wenxuan Sun, Mingjie Shao, Wantao Jiang, Yanqing Xu, Lingxiang Li, Zhi Chen

原文摘要

Wireless federated learning (FL) suffers from two coupled bottlenecks: statistical heterogeneity across clients and communication-constrained model synchronization over unreliable wireless links. Instead of focusing on algorithmic design and/or wireless resource optimization, this paper provides a systematic study of pinching antenna (PA)-empowered FL for heterogeneous wireless networks and develops a unified communication-and-learning framework. Specifically, we integrate a segmented waveguide-enabled pinching antenna (SWAN) architecture with a heterogeneity-robust FL algorithm based on client variance reduction and dual quantization, so as to jointly mitigate communication bottlenecks and client drift. On this basis, we further develop a two-stage SWAN-assisted downlink protocol and formulate fairness-oriented uplink optimization problems for PA positioning, bandwidth allocation, and quantization design. Efficient solution frameworks are then derived for the resulting downlink and uplink optimization problems. Experimental results show the superiority of the proposed design in convergence speed and final accuracy under non-independent and identically distributed data and communication bottlenecks.

cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16301

LoCoJAX: Host-Local Coordination for Small-Model RL on TPUs

Loki Chen, Gregory B. Rehm, Yang Song, Hongye Xie, Ming Lei, Chongyang Bai, Bob Kamma, Mingfu Liang 等 16 位作者

原文摘要

Reinforcement learning (RL) increasingly targets small language models, and executing these workloads efficiently across multiple accelerators requires effective coordination. On TPUs, Pathways-based RL uses a single controller to coordinate computation across hosts. This execution model is effective for large models, but its coordination computational costs are harder to amortize when small models repeatedly invoke short computations. To characterize these computational costs, we sweep dense models from 0.6B to 405B parameters on TPU v7x under a decode-heavy workload and measure how host and network computational overhead vary with model size. At 0.6B, host orchestration occupies 36% of step time and network communication 2%, whereas for large models, estimated network computational costs dominate the non-compute time. Motivated by these findings, we present Local Coordination JAX (LoCoJAX), which implements local rollout and reward processing on each TPU host with synchronous global training. In controlled comparisons against a tuned and optimized Pathways baseline on Qwen3-0.6B across three workloads and 8-64 TPU v7x chips, its colocated mode (LoCoJAX-CO) is 1.3-3.6x faster per step; on GSM8K, it completes a step faster on 8 chips than Pathways does on 64. Finally, a Ray-managed disaggregated mode (LoCoJAX-DA) overlaps rollout and training on separate hosts, and placement experiments establish when this overlap compensates for dividing devices and transferring weights: only when rollout dominates the step and receives most of the hosts. On NuminaMath-CoT at 256 chips, giving rollout 75% of hosts cuts step time by about 15% compared with LoCoJAX-CO.

cs.LG · cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02627

Recovering Missing Degrees of Freedom in Simulation-Trained Field-Level Generative Models

Masato Shirasaki, Shiro Ikeda

原文摘要

Simulation-trained generative models are emerging as a powerful framework for field-level inference in cosmology, particularly in strongly nonlinear regimes where analytical approaches become intractable. However, the finite size of training datasets often leads to variance shrinkage, indicating that part of the realization-level variability of the underlying physical process is not captured by the learned generative dynamics. In this paper, we interpret variance shrinkage as a diagnostic of missing effective degrees of freedom and introduce physics-informed latent modifications to the generative dynamics of a continuous normalizing flow. We show that these latent corrections recover a substantial fraction of the missing variability without requiring additional training simulations. Using weak-lensing field-level inference as a representative cosmological application, we further demonstrate through posterior analysis that the learned latent directions are actively exploited during inference and behave as effective nuisance parameters that absorb part of the mismatch between the training and target distributions. As a result, the model exhibits improved robustness to out-of-distribution shifts in field-level inference. Our work establishes variance shrinkage as a practical diagnostic for identifying missing degrees of freedom in simulation-trained generative models and provides a framework for recovering them through physics-informed modifications of generative dynamics.

astro-ph.CO · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.13535

Joint Communication-Control Strategy Optimization with Partially Nested Information Structures: The Linear-Quadratic Case

Haoyi You, Kaiqing Zhang

原文摘要

In this paper, we formalize a joint communication-control strategy optimization (JCCO) problem in multi-agent linear systems with quadratic costs, under the common-information-based (CIB) framework from decentralized stochastic control. For computational tractability, we focus on such JCCO problems with partially nested (PN) information structures (ISs). In particular, with a baseline communication protocol that leads to a PN IS, we establish a series of conditions under which the partial nestedness is preserved under the (additional) communication strategies to be optimized, while violating them may cause nonlinearity or non-existence of the optimal control strategies, with open-loop communication strategies. Under these conditions, we then develop a dynamic-programming-based approach to compute the optimal control strategies of JCCO with open-loop communication strategies, which yields a set of closed-form Riccati Equations. As a byproduct of independent interest, such an approach also offers a new way to solve decentralized linear-quadratic control with PN ISs and output feedback, under the CIB framework and the aforementioned conditions. Finally, we extend such an approach to JCCOs with closed-loop communication strategies, yielding a more tractable dynamic program than an infinite-dimensional CIB-belief-based one.

eess.SY · cs.MA · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16290

Parallel Computing Systems for the Optimal Selection of Process Equipment

Andrey B. Borisenko

原文摘要

This monograph addresses the optimal selection of equipment for chemical-engineering systems of multiproduct batch plants, a large-scale NP-hard discrete optimization problem in which, for each processing stage, a unit of standard size must be chosen so that the total capital cost of the equipment is minimized while the system remains operable and produces the required products within a given time horizon. We present the mathematical model of system operation and analyze its computational properties. We then develop a sequential branch-and-bound algorithm and its parallel versions for shared-memory systems (OpenMP), distributed-memory clusters (MPI, master-worker), and graphics processing units (CUDA), including recursive and iterative tree traversal, shared-memory optimization, and branch-divergence reduction. To overcome the exponential growth of the run time, we propose a hybrid metaheuristic in which Ant Colony Optimization finds a feasible initial solution and Simulated Annealing improves it, and we implement it on GPUs with thousands of independent threads. Finally, we propose random, constant, and multi-constant approaches to tuning the parameters of the ant colony algorithm based on statistical analysis of many parallel runs, and we study the program on GPUs of three generations and on nodes with several GPUs. Computational experiments on multi-core processors, clusters, and GPUs show that the parallel hybrid algorithm finds solutions within 0.01% of the branch-and-bound optimum in tens of seconds instead of tens of hours.

cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16289

Eliciting and Mitigating Specification Satisficing in Coding Agents

Ruixin Wang, Tianyi Zhang

原文摘要

Coding agents often fail to meet all requirements in the task description. In some of these failures, the agent considers an implementation choice that meets a requirement, but later decides to commit to another one that does not meet the requirement for a reason it finds acceptable. We call this specification satisficing. It is challenging to identify and mitigate specification satisficing because the agent accepts such choices for its own reasons, and existing self-correction methods are biased toward them. We propose SatisFix, which guides a coding agent to report these choices and their reasons, and then check each choice against the task description. We evaluate SatisFix on DeepSWE and SWE-bench Pro with five LLMs as backbones and two different agent frameworks, and compare it with three self-correction methods. SatisFix improves the pass@1 of the base agent by an average of 5.09% on DeepSWE and 7.06% on the hard subset of SWE-bench Pro. On DeepSWE, it outperforms the best baseline by 3.98%. Our ablation study shows that both steps of SatisFix contribute to the improvement.

cs.SE · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16287

RiskLens: Human-Informed Incident Transfer for AI Risk Evaluation

Yiliu Tang, Hangyue Zhang, Yun Huang

原文摘要

As AI capabilities advance, early-stage teams need better ways to judge whether historical incidents transfer to new products, demanding support beyond static risk checklists or one-off ideation tools. We present RiskLens, a human-AI workflow with an interactive system built around a live crawl, refreshable ranker, and extensible, human-informed schema. RiskLens analyzes 2,034 AI incidents and 10,443 AI products to rank transferable incidents using a feature schema spanning technical, operational, and user-facing attributes and supports an interface that presents ranked incident evidence, generated scenarios, risk metrics, and mitigation suggestions. In a study with 21 AI-familiar participants, users surfaced evaluation criteria that we added as 13 human-informed dimensions, including harm categories, failure mechanisms, and vulnerable groups. The feature-based model outperformed a generic baseline with an 86.2% win rate, and remained stable on a twenty-month future holdout; after human-informed schema expansion, the updated model outperformed the same baseline on 91.4% of pairs.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16285

Scaling Pêlagos: Multi-GPU Orchestration for Relay Belief-Propagation Decoding

Xulong Tang, Dionysios Diamantopoulos, Tristan Müller, Apo Kayi, Nelson Mimura Gonzalez, Muhammad Osama, Seetharami Seelam, Haralampos Pozidis 等 10 位作者

原文摘要

Fault-tolerant quantum computing requires quantum error-correction (QEC) decoders that achieve low logical error rates under real-time operating constraints. These constraints motivate heuristic decoding algorithms whose error-correction performance must be evaluated through large-scale simulation. High-throughput decoding accelerates this evaluation and the exploration of decoder parameters. Using multiple graphics processing units (GPUs) is a natural way to scale these simulations, but naively distributing syndrome batches introduces host-side preprocessing and output-collection overheads that limit scaling. To address these limitations, we extend the Pêlagos relay belief-propagation (Relay-BP) decoder with process-isolated orchestration, parallel host preprocessing, and shared-memory output. We evaluate both one-gross ($[[144,12,12]]$) and two-gross ($[[288,12,18]]$) codes in a multi-GPU environment. Specifically, for the one-gross circuit at $R=50$, eight AMD Instinct MI300X GPUs and eight AMD Instinct MI355X GPUs achieve optimized end-to-end speedups of $5.68\times$ and $6.23\times$, respectively. For the two-gross circuit, the corresponding speedups are $6.92\times$ and $7.01\times$. When throughput is calculated using GPU decoding time, the corresponding two-gross speedups are $7.58\times$ and $7.45\times$, indicating near-linear GPU scaling. We deploy Pêlagos on Lux, Oak Ridge National Laboratory's AMD Instinct MI355X-based supercomputer, as a pathfinding application for high-throughput QEC simulation. This deployment provides a concrete quantum-computing use case for the AI + HPC infrastructure supporting the Genesis Mission's scientific-discovery goals. These end-to-end measurements demonstrate a practical path to accelerating large-scale QEC simulation through efficient multi-GPU decoding.

quant-ph · cs.ET

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16284

Decisions at the end of the world

Casper van Elteren

原文摘要

International treaties are often described as tigers without teeth, failing to secure compliance or change outcomes. Cooperation also depends on how states maintain the rules they have already made -- especially where no sovereign stands above the states. Here we map more than six decades of decision-making under the Antarctic Treaty, linking submitted proposals to recorded responses and tracing how instruments act on earlier ones. Shared references tie decisions together across the agenda. Recurring revision concentrates in specialised histories, above all the management of protected areas, beyond what activity, popularity and reference age predict. Periodic administrative reviews retire outdated instruments in bulk, joining otherwise separate histories without coordinating policy across subjects. Binding Measures build overwhelmingly on earlier Measures, with little direct succession from non-binding Resolutions. Distinguishing these layers shows how a shared rule system is sustained by consensus, and provides a basis for comparing cooperation across global commons.

physics.soc-ph · cs.SI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16275

Demo: Matter-Based IoMT Telemetry and Security Analysis

Muhammad Hassan, Masooda Bashir, Carl Gunter

原文摘要

Connected health devices increasingly support health monitoring outside clinical settings, making secure and accessible physiological data important for patients and caregivers. However, device-specific applications and interfaces complicate the integration of readings from different devices. The Matter standard provides standardized device commissioning and protected communication, but its cluster library does not represent the health attribute measurement. We present a preliminary demo study of a Matter-based IoMT testbed with a specific HealthVitals cluster. Implemented in the connectedhomeip SDK on a Raspberry~Pi~5, the cluster exposes simulated heart rate, blood oxygen saturation, and body temperature. We examine commissioning, attribute retrieval, communication under simulated packet loss, and operational traffic through a reference controller. The study demonstrates that this custom telemetry model can operate within the tested Matter configuration without modifying commissioning or secure-session mechanisms. The resulting testbed gives researchers and device developers a concrete platform for investigating health-oriented extensions. It also supports exploration of local telemetry integration that could help patients and caregivers access readings across connected devices.

cs.AR · cs.ET · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16274

Distribution-First Framework for Learning Risk-Sensitive Individualized Treatment Rules

Zhen Fang, Guanting Chen, Yufeng Liu

原文摘要

Learning a risk-sensitive individualized treatment rule (ITR) with patient covariates is challenging when the treatment criterion depends on the full conditional outcome distribution rather than only its conditional mean. Existing methods are largely criterion-specific, making it difficult to compare multiple treatment criteria within a common pipeline, such as quantiles, conditional value-at-risk (CVaR), and complex preference-based objectives such as cumulative prospect theory. We propose a distribution-first framework for risk-sensitive ITR learning that first estimates treatment-specific conditional outcome distributions and then constructs the target ITR by plug-in criterion evaluation. The proposed framework unifies treatment rule learning across multiple criteria and accommodates hard-to-optimize objectives within the same estimation pipeline. On the theoretical side, it yields a general error propagation result for locally Hölder-stable criteria, linking first-stage distribution estimation error to downstream criterion estimation and treatment regret, together with sharper regret bounds under standard margin conditions. Empirically, we show that the proposed framework outperforms direct criterion-specific methods in multiple settings and further evaluate it on the ACTG175 HIV clinical trial, a randomized study comparing several antiretroviral regimens in HIV-infected adults.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.12125

CARE-PO: Controllable Tool-Call Efficiency for LLM Agents

Xiaoyang Ye, Xiao Yao, Hairui Zhu, Yiying Yang, Bei Gan, Jinliang Lu, Tengjin Weng, Yuan Yao 等 9 位作者

原文摘要

External tool calls are a major running cost of an LLM agent, while its training objectives align almost exclusively with task completion. In a step-level diagnosis of Qwen3.5 trajectories at two model sizes on GAIA, a long-horizon tool-use benchmark, we find that most contain removable calls, at a similar rate at both sizes. Some methods add an efficiency reward to the objective to reduce the call count, but introduce problems of their own: the anchor they price calls against is computed from the policy's own rollouts (e.g., the group's shortest correct rollout) and so moves with the policy; training can drift toward a collapsed policy that issues no tool call at all, a degeneracy seen in published reports and in our 27B baseline; and a training run delivers a single operating point, so the user cannot trade efficiency against capability. We present CARE-PO (Controllable Anchored Relative Efficiency Policy Optimization) to mitigate these problems. The efficiency reward prices calls against a reference budget anchored to the task's own difficulty and fixed before training. Injecting a successful trajectory from the training data into each online GRPO rollout group and charging for evidence a trajectory never gathers ease the drift toward a collapsed call count. Shaping the cost curve by an effort tag in the prompt yields an efficiency and a capability operating point from a single training run. On GAIA, five of the six operating points across three model sizes improve on their base model in success rate and call count at once. On four held-out multi-hop benchmarks the result is size-dependent: at 27B and 4B success rate is held or raised at a lower call count, while at 9B both operating points trade success rate for fewer calls. The call count remains well above zero throughout training at all three sizes.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16272

A Binary Search Tree with the Unified Bound

Yang Cao, Haoran Qi, Hanzhi Wang

原文摘要

We give a deterministic online binary search tree (BST) that satisfies the unified bound of Iacono [SODA 2001], which subsumes the working-set and dynamic-finger bounds: it serves every sequence $X$ of $m$ searches on $n$ keys at total cost $O(m+\mathrm{UB}(X))$, and every single search at cost $O(\log n)$. Previously, no BST was known to satisfy the unified bound, even offline. As a consequence, the dynamic optimality conjecture implies Iacono's conjecture that splay trees satisfy the unified bound. We also show that the unified bound is $O((m+n)(1+\log c_σ))$ on every sequence of searches that avoids a fixed permutation $σ$, where $c_σ$ is the Füredi-Hajnal limit of $σ$. Hence every BST that satisfies the unified bound, including ours, serves such sequences at this cost. For permutations this bound is tight, and it improves the previous upper bound $O(nc_σ^2)$ on the optimal cost, due to Berendsohn, Kozma and Opler [STOC 2024]. Finally, we extend the tree to support insertions and deletions: a sequence $X$ of $m$ operations, starting from $n_0$ keys, costs $O(n_0+m+\mathrm{UB}(X))$ in total, where $\mathrm{UB}$ is now the extension of the unified bound to insertions and deletions by Bădoiu, Cole, Demaine and Iacono [TCS 2007]. Hence, if splay trees are dynamically optimal for searches, insertions and deletions, then they serve every such sequence at this total cost as well.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16271

Hierarchical Decoding for Quantum Error Correction

Xulong Tang, Narges Alavisamani, Joan Camps, Matthew Cha, Elise Jennings, Jack O'Connor, Humberto Munoz Bauza, Josh Izaac 等 21 位作者

原文摘要

Fault-tolerant quantum computing requires classical decoders that can keep up with syndrome data streams and supply correction information and logical measurement outcomes to the quantum control system. Meeting these requirements at scale requires high throughput while controlling the end-to-end latency from readout to usable correction. In this paper, we organize decoding algorithms, execution strategies, and code constructions using common classifications and examine their performance and trade-offs under the reported evaluation conditions. We distinguish decoder-level hierarchy, where multiple decoding stages or resources cooperate to decode a single code, from code-level hierarchy, where the code construction itself introduces multiple decoding levels. We first review single-code hierarchical decoders and their cascaded predecoding and windowed, streaming, and distributed implementations. We then study hierarchical and concatenated codes, focusing on how decoding is coordinated across code levels through hard decisions, soft reliability information, or syndrome information. We also examine how qubit modalities shape decoding workloads and timing requirements, and review how different decoding platforms meet these requirements, including central processing units (CPUs), graphics processing units (GPUs), field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), and cryogenic platforms. By assessing design trade-offs, this paper clarifies connections across the literature and provides a shared foundation for QEC design exploration. It also identifies gaps in performance reporting and system integration to guide future research toward practical quantum error correction.

quant-ph · cs.ET

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16270

SMIC: Shared Multiscale Input-Reference Conditioning across Transformer Layers for Natural Language Inference

Xin Zhang, Victor S. Sheng

原文摘要

Natural Language Inference models can be sensitive to localized lexical changes. We introduce Shared Multiscale Input-Reference Conditioning (SMIC), which constructs a single input-dependent multiscale reference and reuses it across Transformer layers. Each layer applies its own multiscale transformation to the shared reference and injects the resulting conditioning feature before the attention update. We instantiate SMIC in a token--context Transformer (TCT) and conduct from-scratch comparisons against decoder-based and Multi-Layer Perceptron (MLP) baselines across all three ANLI rounds. TCT-SMIC attains the highest observed ten-seed mean accuracy on all three ANLI rounds. The ablations further support the contribution of SMIC. We evaluate a real-valued Llama-style plug-in and extend deletion/insertion diagnostics to pretrained ModernBERT encoder and Llama decoder models with and without SMIC. Across the evaluated perturbation protocols, TCT-SMIC exhibits comparatively low pooled-attention redistribution and smaller signed accuracy changes. We further establish a finite-sample bound on average subset-mass redistribution in terms of the mean Jensen--Shannon divergence between the restricted and renormalized attention distributions.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16267

Causals: An Open Knowledge Graph for Research on Causal Reasoning

Miaozhe Lin, Qiongzheng Lin, Zhongwei Liang, Zijun Liu

原文摘要

Applying causal knowledge to a new event requires connecting the event to relevant entities and the relationships through which its consequences may unfold. We present Causals, an open knowledge graph for research on this form of reasoning. Its initial release, constructed from news reports, contains 369,184 nodes and 1,272,418 edges linking reported events, organizations, commodities, financial instruments, and other entities. Structural relationships, observations, and attributed causal claims retain distinct semantics and links to source records. We describe the construction and representation of the resource and characterize its connectivity and multi-hop retrieval properties. Causals provides shared relational knowledge for studying how language models retrieve relevant context and apply mechanisms to particular events. The dataset is available under CC BY 4.0 at https://causals.org/, and we invite contributions to its ontology, records, and evidence.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.19858

Online Test-Time Adaptation for Generalizable Dynamic Graph Anomaly Detection

Jialun Zheng, Hanchen Yang, Jiannong Cao, Yankai Chen, Yuanjing Feng, Philip S. Yu

原文摘要

Generalizable dynamic graph anomaly detection (DGAD) enables pretrained detectors to identify anomalies in unseen target domains without costly retraining. However, existing methods often fail for two reasons. First, they mainly rely on domain-agnostic patterns and miss domain-specific patterns that keep evolving. Second, they assume access to the full target domain data, whereas in more practical online test-time adaptation settings, target data arrive sequentially in unlabeled chunks. To address these limitations, we formulate online test-time adaptation for generalizable DGAD and propose OTTA-DGAD. OTTA-DGAD first extracts dynamic prototypes, i.e., evolving representations of normal and anomalous patterns, from temporal ego-graphs and stores them in a memory buffer. The buffer selectively retains general patterns shared across the source domains used for pretraining while incorporating new patterns from the target domain. An anomaly scorer then compares incoming edge representations against these prototypes to identify both general and domain-specific anomalies. During adaptation, OTTA-DGAD updates the memory buffer using reliable pseudo-labels identified through confidence-based detection. It further enriches each target chunk with relevant representations retained from previous chunks, compensating for information loss resulting from the sequential arrival of data. Extensive experiments under strict test-then-adapt OTTA settings demonstrate state-of-the-art performance on ten real-world datasets from diverse domains.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.10498

EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution

Python Song, Zhixuan Liang, Kelsey Fu, Mengdi Wang, Junfeng Yang, Shilong Liu

原文摘要

Robot foundation models provide strong visuomotor control, yet their performance can degrade when object positions or task instructions change. Further improvements often require post-training on substantial robot data, which can be costly to collect through methods such as teleoperation. Agentic harnesses can adapt around the model, but current self-evolving harnesses use robot trials inefficiently when deciding which code and skill changes to pursue. We introduce EmbodiedRSI, a self-evolving agentic harness that autonomously decides where to explore next and turns the resulting physical interaction into improved code and skills. EmbodiedRSI realizes this through a Fast-Slow Dual-System Architecture, in which competing code and skill hypotheses are maintained in a Hypothesis Graph. Value-of-Information Experiment Selection chooses physical experiments that can distinguish these hypotheses. Their outcomes guide Code-Skill Co-Evolution. The Slow System builds Hierarchical Memory, and Reward-Grounded Memory Learning selects effective memory according to their value for later Fast-System improvement. On RoboCasa365, EmbodiedRSI reaches 77.0% overall success and 71.3% on Composite-Unseen, compared with 40.1% for the best baseline. EmbodiedRSI also reaches 86.8% overall success on LIBERO-Pro. Beyond benchmark performance, EmbodiedRSI transfers zero-shot to real-world robot, achieving 71.3% overall success across multiple challenging tasks.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16265

Rectified Looped Transformer

Musheng Li, Jiawei Zhang, Ziyuan Liu, Yuantao Gu

原文摘要

Looped Transformers increase effective depth by repeatedly applying a shared block, offering a parameter-efficient approach to language modeling. However, most existing works directly reuse each loop's output as the next's input, which can lead to hidden-state scale growth and perturbation amplification as recurrence deepens. We propose Rectified Looped Transformer (RLT), which redesigns feedback between loops using an interpolation schedule inspired by flow-based modeling. At each loop, RLT forms the next input by linearly interpolating between the current state and its prediction. Such interpolation distributes state changes across loops, encouraging a smoother trajectory from the initial input to the final output. Theoretical analysis proves that, under appropriate assumptions, RLT keeps state magnitudes uniformly bounded across loops and reduces the worst-case perturbation amplification. We evaluate RLT on language modeling corpora and downstream benchmarks. At matched training and inference depths, RLT consistently achieves lower perplexity than a standard looped Transformer, while exhibiting greater robustness to input perturbations and variance in inference depth. Consistent with the theoretical results, latent trajectory analysis shows that RLT maintains more stable hidden-state norms across loops, which also facilitates extrapolation-based decoding strategies. Notably, RLT achieves these gains without requiring additional trainable parameters or extra recurrent block evaluations, thus providing a simple yet more stable feedback mechanism for looped Transformers.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16264

Label-Efficient Document-Grounded Factuality Detection via Cross-Paraphrastic Invariance Learning

Chao Chen, Shanshan Lin, Dongsheng Hong, Sibo Ju, Wenjie Yang, Sihong Xie, Xiangwen Liao

原文摘要

Large language models (LLMs) can generate fluent claims that are unsupported by a given source document, motivating accurate and efficient document-grounded factuality detection. Existing LLM-based evaluators often require repeated inference and incur high computational cost, whereas compact factuality detectors are efficient at inference time but commonly rely on large labeled or synthetically generated corpora. We propose CPIL (Cross-Paraphrastic Invariance Learning), a two-stage Siamese framework that converts a small labeled set into relational supervision without acquiring additional factuality labels. CPIL constructs positive pairs from distinct label-preserving paraphrastic views of the same document-claim instance and negative pairs from opposite-label examples associated with the same source document. It further introduces quantile-aware semi-hard negative mining, which derives a boundary from the positive-pair similarity distribution and balances informative negatives with broader coverage. In the two-stage training procedure, Stage 1 learns an encoder from these task-aware pairs, and Stage 2 jointly fine-tunes the encoder and a linear classification head for binary factuality prediction. At inference time, CPIL requires no paraphrase generation, pair construction, or Siamese comparison and uses only one encoder-classifier forward pass. On the 11-task LLM-AggreFact benchmark, CPIL-2% and CPIL-3% achieve macro-F1 scores of 81.04 and 81.60 while using only 2-3% of the FactCG-released labeled pool. Both settings outperform all compared compact detectors and two vanilla LLM references. Ablations and sensitivity analyses support the contributions of task-aware pair construction, dynamic negative mining, and multi-pivot paraphrasing.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.10177

VArify: A Visual Analytics System for Verifying Knowledge Enhanced Large Language Model Responses in Food Science

Sam Yu-Te Lee, Yan To Linus Lam, Manami Nakagawa, Kwan-Liu Ma

原文摘要

Graph Retrieval-Augmented Generation (GraphRAG) grounds Large Language Model (LLM) responses in structured, domain-specific knowledge. However, verification remains difficult because errors can arise at multiple layers: an answer may not be faithful to its retrieved context, the retrieval pipeline may select irrelevant evidence, and the knowledge graph may omit relevant facts or contain incorrect triplets. We present VArify, a visual analytics system for food-science researchers to inspect and repair these layers in a GraphRAG workflow. A formative study with five participants using a conventional chat-and-table interface revealed behaviors reflecting answer anchoring, over-trust, and difficulty tracing multi-hop relationships. In response, VArify combines an evidence-first answer reveal with coordinated chat and hierarchical graph views, provenance inspection, and subquery editing. It connects the generated answer, the retrieval state, and the provenance-linked graph so that researchers can trace discrepancies across them and repair the retrieved context. From a qualitative system-use study on six food science researchers, we characterize how they scrutinize GraphRAG evidence with progressive visual inspection. Our study also reveals an important verification boundary: information absent from both retrieval and a user's knowledge remains unverifiable. We discuss the broader role of visualization in supporting oversight of LLM responses and outline future research directions.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16260

Low Language Transfer Speech-to-Text

Husein Zolkepli

原文摘要

A multilingual speech recogniser has heard much speech in its own languages. We ask how much of that it brings to a language it was never trained on, when it is fine-tuned on the little that language has. We score 28 open multilingual models untouched on Low-Language-TTS, 50 low-resource languages in 11 writing systems, and fine-tune 24 of them on at most 1,000 clips a language, 82 hours in all, with a dev set choosing every epoch. Fine-tuning lowers every model's macro character error rate (CER), by 16.6 to 53.1 points, to 9.5 at best, and a word language model takes three CTC models 1.2 to 1.4 points lower; WER is still 34.4 at best. On the 12 languages that no model lists, every model starts at 46 or worse and the best ends at 11.7. The same architectures from random weights stay 60 points or more behind, so the gain is transfer, and an encoder left untouched already gives a Whisper or Qwen decoder most of what it needs. It is the language, not the corpus: on FLEURS recordings that ours do not share, the median model keeps 79% of its gain. It costs the languages the models knew, 5.7 points of CER on English, Spanish, French and German in the median model. Low-rank adapters on 4% of the weights come within 1.1 points of tuning everything, and on 2 of 3 models forget less. Seq2seq and language-model decoders are done within three to five epochs, while a new CTC head is still improving at twenty or thirty. Data beats epochs: 25 clips a language take Qwen3-ASR 0.6B from 60.9 to 39.3, and at equal clips presented, ten times the data is worth 9.7 points. A model that first learned forty of the languages learns the other ten no faster. On a public Malay benchmark, untouched Whisper large-v3 scores 8.9 when it detects the language and 14.9 when told the clip is Malay, because it then translates the English that speakers mix in; trained on the Scicom telephony dataset it scores 6.0.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16259

Reconstruct What You Can: Distractor-free 4D Gaussian Splatting

Joel Julin, Liuyue Xie, Ananya Bal, Mose Sakashita, Koichiro Niinuma, Laszlo A. Jeni

原文摘要

Dynamic reconstruction from casual video must preserve valid subject motion while suppressing transient occluders, shadows, and volumetric effects. Existing methods either suppress valid motion through static-scene assumptions or model all observations jointly, producing ghosting and unstable geometry. We introduce ReCan-GS, a 4D Gaussian Splatting framework that separates coherent scene content from inconsistent observations. It derives a Jacobian-based deformation-sensitivity score from the learned deformation field, using it as an empirical proxy for reconstruction ambiguity. The score guides separation into dynamic Core Gaussians and per-view Distractor Gaussians, or post-hoc pruning of sensitive Core Gaussians. The same criterion supports removal of spatial occluders, photometric artifacts, and evolving smoke or fog without masks, pretrained segmenters, or medium-specific supervision. Experiments on synthetic and real dynamic scenes and synthetic smoke/fog scenes demonstrate its usefulness across the evaluated distractor regimes.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16257

Few-Shot Cross-Subject Neural--Image Retrieval via Stimulus-Anchored Latent Bias Calibration

Xizhang Yao, Li Zhang, Gan Huang, Zhen Liang

原文摘要

In cross-subject neural--image retrieval, comparing the mean of a few stimulus-matched target observations with the global source mean conflates subject-specific representation shifts with stimulus-composition effects. To address this problem, we propose Stimulus-Anchored Latent Bias Calibration (SA-LBC), which estimates the first-order shift under fixed preprocessing and a frozen source-trained representation by averaging residuals between target responses and same-stimulus source-population anchors, then shrinks the correction using source-derived uncertainty. Under uniform sampling without replacement from a finite stimulus population, we derive exact finite-population MSE expressions for the unshrunk anchored and global-mean estimators, including residual--anchor cross-covariance, and establish a necessary and sufficient condition for anchoring to reduce MSE relative to global-mean estimation. In a 10-subject leave-one-subject-out evaluation on THINGS-EEG2, SA-LBC increases mean reciprocal rank (MRR) for the Attention--CLIP ViT-B/32 configuration from 0.1867 without calibration to 0.2013 and 0.2336 with M=2 and M=16 stimulus-level calibration samples, respectively. Across six neural--visual configurations and all calibration budgets, stimulus-matched anchors yield higher MRR than anchors with shuffled stimulus identities, but retrieval gains over no calibration remain representation-dependent. At (M=2), shrinkage improves MRR over the unshrunk anchored estimator in all six configurations, but its effects at larger budgets vary across representations; the relative ranking of translation and orientation corrections also depends on regularization strength. Thus, lower shift-estimation MSE does not guarantee higher retrieval performance. The source code is publicly available at: https://github.com/Xizhang-Yao/SA-LBC.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16255

HybridCT: ML Accelerated Tomography for Climate Relevant 3D Cloud Observations

Linda Forster, Nicholas J. LaHaye, Marcin J. Kurowski, Anna Jungbluth, Bernhard Mayer, Anthony B. Davis

原文摘要

Low-level clouds are one of the largest sources of uncertainty in climate predictions, partly because we lack detailed three-dimensional (3D) measurements of their internal structure. Here, we present HybridCT, a cloud tomographic reconstruction scheme accelerated by machine learning (ML) that recovers 3D cloud extinction directly from passive multi-angle observations. An ML emulator maps radiances from multiple viewing angles to cloud optical thickness (COT), producing path-integrated projections, and a Simultaneous Algebraic Reconstruction Technique (SART) explicitly inverts these projections to retrieve 3D extinction. Training observations are generated from synthetic 3D cloud fields using radiative transfer simulations for nine viewing angles between $\pm$70$^{\circ}$. HybridCT reconstructs extinction with RMSE 13.3 km$^{-1}$ in 3.5 s, compared to 22.7 km$^{-1}$ in approx. 30 min for the state-of-the-art physics-based tomography framework AT3D, a speedup exceeding 500$\times$. HybridCT thus provides a scalable route toward large-scale observations of 3D cloud structure relevant to radiative-budget interpretation and evaluation of high-resolution cloud simulations.

physics.ao-ph · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.18859

RewardFlow: Can Action-Level Reward Be Estimated from State-Graph Topology in Agentic RL?

Xiao Feng, Bo Han, Zhanke Zhou, Jiaqi Fan, Jiangchao Yao, Ka Ho Li, Dahai Yu, Michael Kwok-Po Ng

原文摘要

In agentic tasks such as household assistance and web shopping, large language model (LLM) agents take multiple actions before receiving a final outcome indicating success or failure. For reinforcement learning (RL), this outcome obscures individual actions' contributions: a shopping trajectory may find the right product but fail to complete the purchase. To address this credit-assignment problem, we introduce RewardFlow, which connects multiple trajectories for the same task through shared states (states grouped by task-relevant equivalence or semantic similarity). The resulting directed state graph links observed trajectory segments. Therefore, an action in a failed trajectory may reach a state from which another trajectory succeeds. It propagates reward signals backward from states where the task succeeds, assigning state potentials that decrease with shortest-path distance to success in the graph. Potential differences then reward actions that reduce this distance, bringing the agent closer to success in the graph. These estimated rewards yield action-level advantages that complement trajectory-level advantages from outcome rewards during policy optimization, without a learned process reward model or manual action-level annotations. Experiments on ALFWorld, WebShop, Sokoban, and search tasks show gains over RL baselines across model scales. With 3B policies, graph construction and reward estimation take $1.47$-$2.39$ seconds per training step on ALFWorld, WebShop, and Sokoban (Fig. 1). Code is available at https://github.com/tmlr-group/RewardFlow.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.02615

TRACED-X enables in vivo imaging of cellular microstructure, intrinsic extracellular diffusivity, tortuosity, and membrane permeability in human glioma patients

Joshua K. Marchant, Hong-Hsi Lee, Elizabeth R. Gerstner, Susie Y. Huang, Bruce R. Rosen

原文摘要

The lack of analytical models describing diffusion time dependence at intermediate time scales in complex tissue microstructure limits accurate quantification of extracellular diffusivity and tissue microstructure. Cell membrane water permeability modulates the signal in complex ways and is often disregarded in tumor microstructure models. We introduce TRACED-X, a Monte Carlo-based model that incorporates diffusion time dependence and membrane permeability in cell distributions to quantify pathologically-relevant properties in solid tumors. Monte Carlo simulations of water diffusion in semipermeable spheres were used to train neural network regressors for parameter estimation. A separate neural network was trained to predict the extracellular effective diffusivity, enabling the estimation of extracellular space tortuosity. Diffusion data from eight mixed-grade glioma patients were fitted with TRACED-X and analyzed in conjunction with clinical images. Simulation results demonstrate improved parameter estimation compared to comparator models. TRACED-X enabled the simultaneous in vivo quantification of intracellular volume fraction, cell size distribution, intrinsic extracellular diffusivity, tortuosity, and membrane permeability in glioma patients. Parameter maps show coherence with radiological findings and expected tumor phenotypes. TRACED-X permits the rapid estimate of unique biophysical properties in solid tumors, such as intrinsic extracellular diffusivity, tortuosity, and membrane permeability, in addition to cell microstructure. TRACED-X maps show promise in identifying heterogenous tumor subregions before and after treatment. Neural network implementations of diffusion time-dependence and tortuosity showed behavior consistent with coarse-graining and effective medium theory, respectively. Future work will explore the clinical utility of TRACED-X parameters in additional patients.

physics.med-ph · cs.LG · eess.IV

查看论文
arXiv ↗PDF ↗