跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

arXiv 最近完成扫描:2026-11-20 06:44 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 07:31 — 2026-11-20 07:31(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-20 06:44最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 02:59

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

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

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 23,249 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 06:42(北京时间)
版本更新 · v2arXiv:2608.24735

Meta$^n$: Recursive Self-Improvement through Emergent Depth

Zae Myung Kim, Young-Jun Lee, Seungyeon Jwa, Dongyeop Kang

原文摘要

Self-improving LLM agents refine answers, not the process that produces those answers. Systems that add a meta-level hold that level fixed, and those that edit themselves must leave part of their own editing machinery untouched to stay stable, capping the meta-depth they realize at roughly two. We present Meta$^n$, which keeps the meta-operation fixed and recurses on its input instead. That operation, $Ω$, is applied repeatedly to its own products, reading the traces of the solver stack below together with the code that produced them, then writing the next layer as a strategic pre-process and a library of callable helpers. Because $Ω$ never changes, it cannot destabilize the system, and because its input strictly grows, each layer reasons from a higher vantage than the last. Depth is set by convergence rather than fixed in advance, and an evolutionary archive searches over layer chains. Across two backbones, Meta$^n$ outperforms prior self-improving agents on all eight benchmark families. The sharpest case is ARC-AGI-2, built to resist skill memorization, where it alone scores above zero. Ablations indicate that most of the gain from recursion comes from the conditioning each layer passes to the next, and distinct layer roles emerge with depth although no prompt prescribes them. Code available at https://github.com/minnesotanlp/meta-n

cs.AI · cs.CL · eess.SY

新论文 · v1arXiv:2611.23750

Beyond Replacement: Levenshtein Editing for Diffusion Language Models

Shuaidi Wang, Zhuocheng Gong, Xuejie Liu, Jianguo Li, Yu Zhang

原文摘要

Diffusion language models (DLMs) offer a flexible alternative to autoregressive models, enabling any-order infilling. While most existing decoding methods treat decoded tokens as fixed, some recent models allow previously decoded tokens to be revised only by replacing them with alternative tokens, a paradigm we refer to as replacement-only editing (ROE). Although ROE can correct individual tokens, it is inefficient for sequence shifts caused by missing or extra tokens and struggles when errors occur across many positions. To address these limitations, we propose LED (Levenshtein Editing for Diffusion Language Models), a post-training framework that extends ROE with insertion and deletion, enabling Levenshtein-style refinement of generated sequences. It uses two training designs. First, it reconstructs edit supervision on the fly during supervised fine-tuning using longest-common-subsequence alignment, enabling insertion and deletion learning without manually annotated labels. Second, it adopts multi-stage training, where the state from one stage becomes the input to the next, exposing the model to its earlier errors and enabling it to correct them. When applied to the 16B-parameter LLaDA2.1-Mini Base, LED raises the average score across twelve benchmarks from 54.86 to 57.10 under confidence-guided decoding while increasing tokens per forward from 6.14 to 7.05, whereas under confidence-free decoding it raises the average score from 27.52 to 47.19. We further show that LED achieves higher pass@k at large k than thresholded decoding without editing, demonstrating improved generation diversity and revealing the diversity potential of DLMs without confidence guidance. LED also improves robustness to large block sizes, raising the average score from 36.97 to 51.34 at block size 128. Together, these results suggest that LED supports more robust self-correction in DLMs.

cs.CL · cs.AI

版本更新 · v6arXiv:2605.08825

Rethinking Event-Based Object Detection through Representation-Level Temporal Aggregation and Model-Level Hypergraph Reasoning

Meisen Wang, Hao Deng, Wei Bao, Chengjie Wang, Zhiqiang Tian, Shaoyi Du, Siqi Li, Yue Gao

原文摘要

Event cameras provide microsecond-level temporal resolution, low latency, and high dynamic range, offering potential for perception under fast motion and challenging illumination conditions. However, existing Event-based Object Detection (EOD) methods face limitations at both the representation and model levels: prior event representations usually encode temporal information indirectly through redundant structures, while detection models struggle to explicitly aggregate fragmented event responses into coherent high-order object features. To address these limitations, we present \textbf{Event Dual Temporal-Relational Aggregation Detector (Ev-DTAD)}, a unified EOD framework that integrates representation-level temporal encoding with model-level temporal-hypergraph reasoning. Specifically, we introduce \textbf{Hierarchical Temporal Aggregation (HTA)}, a compact three-channel pseudo-RGB representation that explicitly embeds temporal information across intra- and inter-window events. To further enhance detection under sparse and fragmented event responses, we propose \textbf{Frequency-aware Hypergraph Temporal Fusion (FHTF)}, which refines multi-scale event features through temporal evolution modeling and high-order relational reasoning. Extensive experiments on Gen1 (\textbf{+0.8 mAP}), 1Mpx/Gen4 (\textbf{+0.5 mAP}), and eTraM (\textbf{+3.0 mAP}) demonstrate that Ev-DTAD achieves a competitive accuracy--efficiency trade-off, validating the complementarity between compact temporal representation and temporal-hypergraph feature reasoning (Fig.~\ref{fig:bubble}). The code is available at: https://github.com/meisenwang/Ev-DTAD.

cs.CV

新论文 · v1arXiv:2611.23749

Modeling LLM Reasoning Dynamics with Structural Representations

Ilia Karpov, Andrey Atamanyuk, Dmitry Ilvovsky, Aleksandr Anokhin, Alex Elizov, Dmitry Zagorulkin, Sergei O. Kuznetsov

原文摘要

Language-model reasoning alternates between sustained activities and local operations. We study how this temporal structure predicts continuation and the computation needed to analyze it. T/E/S combines text, local events, and spans of activity. Across reasoning and information-seeking tasks, events and spans improve next-outcome prediction in 70 of 76 evaluation groups for a Transformer and 74 of 76 for Qwen with LoRA. Span duration and preceding events are associated with transitions, and retaining event history across span boundaries improves prediction. We formulate budget-allocation counting and action-conditional continuation queries, prove counting hardness under explicit encodings, and derive conditions for affordable decision certification. In finite-process experiments, bounds that cancel shared continuation mass recover the same optimal actions as full dynamic programming while reducing mean inference CPU time by 77.7%. On 71 held-out HotpotQA and MuSiQue questions, a compact structural observer improves prediction of whether a fixed inference procedure finishes within a CPU allowance: Brier loss falls from 0.0836 to 0.0756. An annotation audit identifies substantial errors in that observer, separating this computational result from semantic validation of its features.

cs.AI

版本更新 · v4arXiv:2512.11273

Integrated Prediction and Multi-period Portfolio Optimization

Yuxuan Linghu, Zhiyuan Liu, Qi Deng

原文摘要

Multi-period portfolio optimization is important for real portfolio management, as it accounts for transaction costs, path-dependent risks, and the intertemporal structure of trading decisions that single-period models cannot capture. Classical methods usually follow a two-stage framework: machine learning algorithms are employed to produce forecasts that closely fit the realized returns, and the predicted values are then used in a downstream portfolio optimization problem to determine the asset weights. This separation leads to a fundamental misalignment between predictions and decision outcomes, while also ignoring the impact of transaction costs. To bridge this gap, recent studies have proposed the idea of end-to-end learning, integrating the two stages into a single pipeline. This paper introduces IPMO (Integrated Prediction and Multi-period Portfolio Optimization), a model for multi-period mean-variance portfolio optimization with turnover penalties. The predictor generates multi-period return forecasts that parameterize a differentiable convex optimization layer, which in turn drives learning via portfolio performance. For scalability, we introduce a mirror-descent fixed-point (MDFP) differentiation scheme that avoids factorizing the Karush-Kuhn-Tucker (KKT) systems, which thus yields stable implicit gradients and nearly scale-insensitive runtime as the decision horizon grows. In experiments with real market data and two representative time-series prediction models, the IPMO method consistently outperforms the two-stage benchmarks in risk-adjusted performance net of transaction costs and achieves more coherent allocation paths. Our results show that integrating machine learning prediction with optimization in the multi-period setting improves financial outcomes and remains computationally tractable.

cs.CE · cs.LG

新论文 · v1arXiv:2611.23747

A Comparison of Heuristic, Human-Sensitive, and Self-Play DRL Policies in Human-Agent Teaming

Ayman bin Kamruddin, Christopher Lam, Gaurav Patil, Mirco Musolesi, Mario di Bernardo, Michael J. Richardson

原文摘要

Dynamical Perceptual-Motor Primitives (DPMPs) offer a tractable framework for generating human-like movement dynamics in artificial agents (AAs) and have been used to support coordination in human-AI teaming tasks. Traditionally, DPMP controllers rely on heuristic (rule-based) decision policies derived from human behavior to guide goal selection and action sequencing. Although effective in structured tasks, such heuristics can be difficult to generalize to more complex settings, motivating interest in deep reinforcement learning (DRL) approaches for learning decision policies for human-AI interaction. A key challenge, however, is ensuring that DRL policies remain aligned with human strategies, particularly when agents are trained through self-play. To examine this issue, we compared three target-selection policies governing DPMP-based AAs in a first-person herding task: (1) a human-derived heuristic policy, (2) a self-play DRL policy (SP-DRL), and (3) a human-sensitive DRL policy (HS-DRL) trained alongside a heuristic agent. Results showed that heuristic agents most closely matched typical human-human coordination patterns, followed by HS-DRL agents, whereas SP-DRL agents deviated most. These findings highlight the importance of human-informed training when developing DRL-based teammates and suggest that simple heuristic policies may remain an effective approach for designing human-aligned AAs capable of human-AI collaboration.

cs.MA · cs.HC

新论文 · v1arXiv:2611.23746

ZERITH V2.5: From Predictive Power to Policy Learnability

Chenxi Han, Ruby, Epoch, Orion, Luke, Bin, Dusk, Lyra 等 21 位作者

原文摘要

When humans learn to manipulate an unfamiliar object, they may already be able to anticipate how its state will change while still being unable to control it skillfully. This gap between prediction and control motivates us to study how the priors acquired by video generation models can be used effectively by an action policy. We present ZERITH V2.5, a video-action model (VAM) in which the action policy reads intermediate features of a video generation model, and use it to study, under fixed demonstrations and a fixed total number of updates, what kind of predictive training improves subsequent action learning. We find that the way video predictive training is supervised affects subsequent action learning. In our experiments, adapting at many noise levels yields a large gain, while adapting only at the noise level used at deployment yields none. Weight-transfer experiments further show that the gain stays with the adapted weights when they remain in the video generation model and disappears when they are used only to initialize the action policy. Initial loss and gradient measurements at the start of joint training indicate that target-domain predictive training gives the video model a better starting state, making subsequent joint learning of prediction and action easier. Under matched data and training budgets, predictive adaptation improves control. We evaluate the complete policy on LIBERO, LIBERO-Plus, Meta-World MT50, and real-robot tasks.

cs.RO

版本更新 · v2arXiv:2611.19803

Pros4D: Modeling Evolving 4D Worlds in Latent Space for Dynamic Spatial Reasoning

Rongxin Gao, Dongxuan Liu, Chu Li, Chengyang Ji, Jialing Huang, Runyu Chen, Kairun Wen, Chenxin Li 等 15 位作者

原文摘要

Dynamic spatial reasoning from monocular video enables vision-language models (VLMs) to understand how 3D environments evolve over time, supporting physical world understanding and embodied intelligence. Existing efforts primarily address observed-dynamics understanding, whereas agents in dynamic environments also require future-dynamics prediction beyond the observation boundary. Moreover, external geometric processing and textual descriptions can increase inference complexity or lose information when representing continuous dynamics. These limitations motivate a shared internal state that preserves observed dynamics and remains predictive beyond the input video. Accordingly, we present Pros4D, a framework for modeling evolving 4D worlds in latent space that unifies retrospective understanding of observed-dynamics with prospective reasoning for future-dynamics prediction. Specifically, Pros4D-Engine derives geometry-grounded supervision and constructs paired examples for both tasks, while Pros4D-Bench evaluates them across eight spatial task categories spanning dynamic cameras, objects, and scenes. At the model level, Pros4D compresses observed dynamics into latent observed states and autoregressively rolls them forward into latent future states. 4D Latent Alignment (4DLA) grounds these states through complementary visual-semantic and geometric supervision, while joint language supervision connects them to task reasoning. Experiments across benchmarks show consistent improvements over strong baselines in both capabilities.

cs.CV

新论文 · v1arXiv:2611.23742

Same Rank, Different Needs: Rethinking LoRA Redistribution in Federated Learning

Jinqian Chen, Jihua Zhu, Chang Liu

原文摘要

Federated low-rank adaptation (LoRA) enables clients with different resource budgets to collaboratively fine-tune foundation models. To distribute an aggregated update within each client's rank budget, existing methods commonly retain its leading singular directions. However, directions that best reconstruct the update matrix need not best preserve its responses on a particular client's inputs: a lower-energy direction may matter more to that recipient. We formalize this mismatch and show that matrix-optimal truncation can incur arbitrarily larger response error than another readout of the same rank. Motivated by this result, we propose Receiver-Aware Subspace Adaptation (RASA), a plug-in framework for receiver-aware knowledge transfer. RASA uses compact diagonal input second moments to perform uncentered PCA of receiver-weighted update responses. The resulting readout is globally optimal for the rank-constrained receiver objective and preserves at least as much response energy as spectral truncation under the diagonal metric. RASA also introduces spectral-reference aggregation, which removes the personalized initialization offset while retaining the locally learned increment. Experiments on DomainNet-100, NICO++, GLUE, and SuperNI demonstrate RASA's effectiveness across methods under resource, task, and data heterogeneity. In particular, RASA improves DomainNet-100 accuracy by 3.23 percentage points with FlexLoRA and achieves gains of up to 8.33 ROUGE-L points on seen SuperNI tasks and 4.37 on unseen tasks with modest overhead.

cs.LG

新论文 · v1arXiv:2611.23736

GaussLearner: 3D Gaussian Primitives as Self-Regulating Continual Learners

Gaoxiang Linghu, Haonan Zhou, Xuanhe Liu, Weili Xu, Kaiyue Zhou, Jun Xiao, Gaoang Wang

原文摘要

Continual learning of 3D Gaussian fields aims to maintain faithful reconstructions of the evolving world. However, directly fine-tuning an existing Gaussian field on new observations can cause catastrophic forgetting of previously reconstructed content. To address this challenge, existing methods employ selective local optimization, replay, or parameter regularization, yet still struggle to balance adaptation to scene changes with preservation of still-valid content. Our key insight is to view 3D Gaussian primitives themselves as self-regulating continual learners. Based on this insight, we introduce GaussLearner, which equips each Gaussian with a closed continual-learning loop connecting observation, self-regulation, and adaptation at the primitive level. At each novel state, GaussLearner first attributes pixel-wise inconsistencies in current observations to their contributing Gaussians. Each Gaussian then self-regulates through a learning weight that balances current observations against cross-state reliability. This weight governs both Gaussian parameter adaptation and optimizer memory refresh. As current inconsistencies are resolved, the adaptation outcome renews each Gaussian's reliability for future states. The resulting field is a globally coupled population of locally self-regulating learners. Across scenes from CL-Splats, WAT, and our CL-3D dataset, GaussLearner improves average PSNR by 3.41 dB over the strongest baseline. On CL-3D, it achieves the best reconstruction quality on both changed and unchanged views.

cs.CV

版本更新 · v2arXiv:2610.04489

DV-Lens: Revealing the Functional Organization of Language Model Parameters

Chenhang Cui, Jian Yu, Jiani Luo, Shuyi Miao, Dingrui Liu, Rui Huang, Xiaohao Liu, Fei Shen 等 10 位作者

原文摘要

Understanding parameter functions helps elucidate the internal mechanisms of large language models (LLMs). However, how to connect parameters from different modules to verifiable output effects and further characterize the relationship between their functional organization and model capability remains to be explored. To this end, we introduce the downstream vocabulary lens (DV-Lens), a parameter-level interpretability framework that links native parameter directions to their downstream vocabulary responses. Specifically, we first estimate module-specific downstream Jacobians over a reference prompt set for attention query, key, value, and output (Q/K/V/O) projections and feed-forward networks (FFNs). Second, we use these mappings to project native parameter columns into the final vocabulary space, obtaining signed readouts that characterize their average local output responses. Third, we group parameter columns by their vocabulary readouts and introduce downstream vocabulary complexity (DV-Complexity), which quantifies within-group structural variation using normalized reconstruction residuals of the original weights. At the parameter level, randomized controls and finite-difference tests show that DV-Lens readouts capture non-random vocabulary structure and predict local logit changes with 98.0% coordinate-orientation agreement across 720 cases from nine models. These readouts further guide parameter ablation, steering, and swapping across 21 models, shifting target-token probabilities in the predicted directions under controlled conditions. At the model level, the joint-parameter score of DV-Complexity achieves a Spearman correlation of 0.904 with benchmark-based capability rankings across 48 language models. Together, these results provide intervention-based evidence for DV-Lens interpretations and reveal an association between DV-Complexity and model capability.

cs.CL · cs.LG

新论文 · v1arXiv:2611.23732

Reliability is a user-specific property of large language models

Xingyu Zhao

原文摘要

Public benchmarks support comparisons of large language model (LLM) capabilities, yet users can experience the same highly ranked model differently. Drawing on traditional software reliability, we argue that the reliability of an LLM service should be assessed for specified users and conditions of use. This requires more than a capability score: evaluation evidence must support a claim about failure during future operation. We distinguish testing to discover faults from testing to assess reliability and identify ten modelling considerations behind such claims. We propose a six-workstream research roadmap linking claim specification, dynamic operational profiles, graded outcomes and noisy judgements, local probabilistic robustness, interaction dependence, and statistical inference with reassessment. Local probabilistic robustness addresses the behavioural variation hidden when different concrete inputs are treated as the same task. Published findings and an illustrative customer-support example motivate the roadmap; its integrated validation remains an open research task. Reliability claims complement, but do not replace, separate safety and security arguments. Capability scores should therefore be complemented by versioned operational claims that state whose requirements are covered, under which conditions, and with what uncertainty.

cs.SE · cs.AI

版本更新 · v2arXiv:2611.16097

A Matching Lower Bound for Online Smooth Calibration

Kaixuan Ji, Quanquan Gu

原文摘要

We study smooth calibration error in sequential binary prediction, a measure of how far probabilistic forecasts are from being calibrated that is robust to small perturbations of the forecasts. The minimax smooth calibration error is known to lie between $Ω(T^{1/3})$ and $O(\sqrt T)$(Qiao and Zheng, 2024), where $T$ is the number of rounds. We close this gap for both adaptive and oblivious adversaries. We construct an adaptive adversary whose outcome mean moves with the forecaster's cumulative residual, which makes compensating for past residuals costly and forces every forecaster to incur $Ω(\sqrt T)$ expected smooth calibration error. Simulating this adversary against the forecaster's average prediction yields an oblivious adversary with the same guarantee. These lower bounds match the known $O(\sqrt T)$ upper bound up to universal constants, and are therefore minimax optimal. Our results also imply matching $Θ(\sqrt T)$ bounds for calibration distance and lower calibration distance. The proof ideas are partially developed by GPT-6 Astra under the authors' guidance.

cs.LG · stat.ML

新论文 · v1arXiv:2611.23731

RecallFlow: Episodic Memory as the Source Distribution of Generative Robot Policies

Xuji Zhang, Qilin Zhong, Zichen Zhang, Wei Zhai, Jian Di, Kun Li, Yang Cao, Wenjun Lv

原文摘要

Diffusion and flow-matching policies have become a standard choice for visuomotor imitation learning, owing to their ability to model multimodal action distributions. In memory-dependent manipulation, the robot must act on information that is no longer visible. Existing methods feed the observation history to the policy as an additional condition, while action generation still starts from Gaussian noise. However, the policy must then pick out the relevant target from a long and redundant history, leading to spurious correlations and unreliable decisions as the memory load grows. Additionally, the initial noise carries no information about what the robot has seen, leaving generation without guidance toward the remembered target. To address these issues, we propose RecallFlow, a flow-policy framework that builds the source distribution from episodic memory. Recall-Relocalization relates the memory to the current view through a few recall slots, so that the source reflects where the remembered targets are now. Recall Anchors then turns each slot into a Gaussian component of the source, enabling generation to start close to the intended action instead of from noise. The transport network then completes the action from the current observation alone, keeping inference nearly as cheap as a memoryless policy. We further build a suite of memory-dependent tasks grouped by memory load and compare all policies under a matched protocol. Extensive experiments show that RecallFlow achieves a state-of-the-art average success rate of 80.4% on the public MIKASA-Robo memory benchmark, and outperforms the strongest baseline by 20.3 points on our suite and by 18.8 points on four real-robot tasks.

cs.RO

新论文 · v1arXiv:2611.23729

Toward Out-of-Distribution Generalization in Neural AC Power Flow

Ojas Sanghi, Anvita Bhagavathula, Alvaro Carbonero, Priya L. Donti

原文摘要

Growing uncertainty in power system operations from renewables integration, extreme weather, and data center loads challenges the reliability of traditional power flow solvers at scale. Machine learning-based proxies are a potentially promising alternative, but the prohibitive cost of generating training data for large grids makes out-of-distribution generalization a key capability for deployment; currently, models trained on small grids lack that capability. In this work, we systematically evaluate how physics-informed losses, multi-grid training, and perturbation-based data augmentation improve the zero-shot transfer of three graph neural network-based power flow models from smaller systems to a larger, unseen 500-bus system. We find that (1) physics-informed losses improve transfer relative to purely supervised objectives; (2) multi-grid training on smaller systems matches the best single grid but does not close the gap to target-grid training; (3) perturbation-based augmentation on edge attributes improves transfer by up to 54.6%; and (4) random line/generator dropout does not consistently improve performance.

cs.LG · cs.AI

新论文 · v1arXiv:2611.23728

AdaS-ViT: Test-Time Adaptive Routing for Spiking Vision Transformers with Ultra-High Energy Efficiency

Zecheng Hao, Zihan Huang, Shenghao Xie, Jiyuan Zhang, Zhaofei Yu, Tiejun Huang

原文摘要

Spiking Neural Networks (SNNs) promise event-driven and energy-efficient vision, yet existing spiking vision transformers (S-ViTs) largely confine spiking tokens to fixed and uniform firing schemes along the temporal, spatial and channel dimensions, whereas suppressing the computational redundancy thus incurred calls for adaptive firing mechanisms that operate jointly across all three axes at test time. To this end, we propose the Adaptive Efficient Integrate-and-Fire (AdaE-IF) model, which consults the attention score of each spiking token and routes salient regions to fine-grained firing patterns while assigning energy-frugal coarse patterns to the remaining regions. Building on AdaE-IF, we further introduce Spiking Gated Self-Attention (S-GSA) and Spiking Local-Gated Unit (S-LGU), which enforce selective spike emission at token and channel granularity. We integrate the aforementioned mechanisms and modules into AdaS-ViT, a test-time adaptive-routing architecture trained with a progressive spatio-temporal curriculum that stabilizes the co-adaptation of firing precision and routing masks. Extensive experiments across benchmarks spanning diverse data scales and modalities demonstrate that AdaS-ViT consistently achieves highly competitive performance. Notably, on ImageNet-1k it consumes only 1.02 to 2.45 millijoules per image and attains an accuracy-per-energy ratio of 32$\times$ to 72$\times$, operating in an economical inference regime and thereby pushing the energy-efficiency boundary further.

cs.NE · cs.AI · cs.CV

版本更新 · v2arXiv:2610.26829

ProteinGeoBench: Frontier Structural-Biology Agents Are Fluent at Lookup but Lost in Geometry

Matt Turk, Brandon L. Neel, Diana M. Lopez, Zachary D. Smith, Grace N. Johnecheck, James B. Golden

原文摘要

ProteinGeoBench is a set of 131 tasks that give an agent protein structure files and ask it to look up recorded facts, check sequences, calculate geometry from atom coordinates or reason about structures. We ran four frontier models on every task several times (4,249 runs) and 26 models on a subset. A single overall score hides two different skills. Three of the four frontier models are best at looking up facts and worst at calculating from coordinates: Claude Opus 5 scores 0.907 on lookup and 0.716 on calculation. Gemini 3.1 Pro is the exception. Geometry is overrepresented among the hardest tasks. Half of the twelve tasks that all four models fail are calculations, although calculations are a fifth of the suite, and eight of the twelve were solved by none of the 26 models. The three leading models are within 0.031 of one another, too close to order, and with one run per task a different model ranks first in 24% of bootstrap resamples. Reports should therefore give scores by task type and the number of runs per task. They should also state the agent harness, the software that runs the model, and its network access, because both change scores. On a 15-task subset, blocking eight structural databases lowered scores, and removing network access lowered them more. Replacing our harness with each provider's own command-line agent moved scores by up to 0.09 in either direction. Across the 26 models, those that scored higher on the other tasks also scored higher on calculation.

cs.AI · cs.LG · q-bio.BM

新论文 · v1arXiv:2611.23727

GTA: Generative Tower of Agents for Scalable Holonic Scene Generation

Zeng Tao, Yunuo Chen, Xiang Feng, Yumeng He, Peihao Li, Nanxiang Jiang, Yaowei Guo, Fanlian Zeng 等 10 位作者

原文摘要

Scalable world modeling requires coordinating scene-wide goals with fine-grained objects and dynamic characters under limited time and context budgets. We introduce GTA (Generative Tower of Agents), which represents every unit at every level of an adaptive scene hierarchy as a holon, both a self-contained construction task and a composable scene unit. Parallel agents recursively plan the hierarchy top-down, generate assets, and assemble and refine them bottom-up. Uniform interfaces carry scene-wide requirements down the hierarchy, guiding local construction so that each holon fits into the larger one. GTA accelerates scalable world modeling through high-throughput parallel execution while preserving well-structured layouts and fine-grained asset details. GTA then populates the assembled environments with dynamic human characters whose appearance and motion are guided by the scene, yielding realized 4D worlds. Project page: https://zt-zeng-tao.github.io/GTA/

cs.CV

版本更新 · v2arXiv:2609.39167

Deep Learning-Based Tri-Hybrid Multi-User MIMO Precoding: The Blessing of EM-Reconfigurable Antennas

Zhen Gao, Kaijun Feng, Jiaxin He, Hongrui Yu, Anwen Liao, Ziwei Wan, Zhaocheng Wang

原文摘要

Electromagnetic (EM)-reconfigurable antennas provide multiple candidate radiation patterns per element, thereby introducing an additional EM-domain degree of freedom. Integrating radiation-pattern reconfigurability, realized as EM-domain precoding, with conventional hybrid analog--digital precoding yields tri-hybrid multiple-input multiple-output (MIMO) precoding, which can substantially improve the spectral efficiency of wideband multi-user MIMO orthogonal frequency-division multiplexing (OFDM) systems. However, the joint design of EM, analog, and digital precoding remains challenging. To address this challenge, we propose a tri-hybrid precoding network (Tri-PNet) based on Conformer, an emerging neural architecture that combines the local modeling strength of convolutional neural networks with the global dependency modeling of Transformers. Furthermore, two representative radiation-pattern modes, i.e., the non-regular mode and the 3rd Generation Partnership Project (3GPP) Technical Report (TR) 38.901 mode, are investigated. Tri-PNet is trained in an unsupervised manner to jointly learn EM, analog, and digital precoding by maximizing the average sum spectral efficiency. Its radiation-pattern selection network (RPSNet) employs a Conformer encoder to capture both local and global frequency-domain correlations, whereas its hybrid analog--digital precoding network (HPNet) combines cross-attention and dual-path processing with singular-value-decomposition (SVD) and zero-forcing (ZF) priors. Simulation results under both radiation-pattern modes demonstrate that Tri-PNet outperforms random EM precoding and conventional hybrid MIMO without EM precoding, approaches the greedy EM precoding search scheme with substantially lower online complexity, and remains robust to imperfect channel state information (CSI).

eess.SP · cs.IT · cs.LG

版本更新 · v2arXiv:2611.19138

SuperGlance: Driving at a Glance with a Vision-Language Model

Jieyuan Pei, Xin Yan, Mingwei Xu, Haiyi Zhang, Siyu Zou, Zhangyi Hu, Zhuoxuan Li, Yuguang Yang 等 12 位作者

原文摘要

Autonomous driving is turning to vision-language-action models (VLAs). They answer and plan by decoding, one step at a time. Each step is another forward pass, so a plan can take over a second of GPU time. Embodied AI often pairs such a slow, reasoning System 2 with a fast System 1 that acts. Human drivers plan at a glance, with System 1. Faster designs usually put System 1 outside the vision-language model (VLM), in a planner without its abilities. Yet before a VLM writes its first token, it has already read the scene into one hidden state. We show that, once trained, this hidden state is enough to drive and to answer questions about what the model sees. SuperGlance reads it to turn a decoder-only VLM into an encoder-style driving policy. Its linear head scores a fixed set of 5,273 candidate trajectories. With the set fixed, rewards are computed offline, so supervised targets can be reward-weighted and reinforcement learning maximizes the exact expected reward. Before and during policy training, multiple-choice training keeps the VLM's visual abilities in one pass, so the policy still answers questions about driving scenes. Training questions are built against shortcuts. Each must be answered right in two option orders. Against drift, a KL term keeps each stage near its starting model. One pass offers VLAs a more plausible path to System 1. SuperGlance answers visual multiple-choice questions as well as its base VLM does by decoding. It plans in 84 ms of GPU time, six times faster than Qwen-Drive-1.0, and at least as well on NAVSIM, PAI-AV and WOD-E2E. In AlpaSim closed loop, km per at-fault incident holds for both planners up to a 300-ms delay and drops beyond. With GPU time charged as delay, SuperGlance's lead over Qwen-Drive-1.0 grows from 2.8 to 3.9 times. Delayed by 1.2 s, our model falls below Qwen-Drive-1.0 at its own 518 ms.

cs.RO

版本更新 · v3arXiv:2611.20794

Regularizing Treatment Leakage for LLM-based Uplift Estimation

Bojing Feng, Jinqiu Deng, Zihan Hong, Yuan Xue, Wenqi Xiang, Shuhan Wang, Feng Xiao, Shiwei Wang 等 11 位作者

原文摘要

Large language models (LLMs) provide semantic features for uplift estimation, but treatment-revealing text can induce prediction shortcuts that do not transfer to deployment. We propose LLM-based Uplift Leakage Regularization (LULR) to address this risk. With the LLM encoder frozen, LULR penalizes dependence between the causal head's trainable shared representation and treatment while retaining separate outcome heads. The penalty uses a variational approximation to the contrastive log-ratio upper bound (CLUB) of mutual information, targeting treatment dependence rather than generic parameter shrinkage. Controlled proxy experiments provide exploratory evidence of improved ranking scores under injected treatment information relative to no regularization and the tested weight-decay setting. Structured-only benchmarks show modest, dataset-dependent effects. On an industrial pricing randomized controlled trial, mean offline lift@0.3 is 0.258 for LULR, compared with 0.106 for the same-backbone baseline. A separate one-week online A/B test of the complete deployed pricing policy records 5.45% higher sales volume and 1.91% higher gross merchandise value than the control arm. These short-term policy-level gains do not isolate the regularizer's effect.

cs.AI

版本更新 · v2arXiv:2611.13662

NIF-VIO: Visual--Inertial Odometry Across Inertial and Non-Inertial Reference Frames

Zichao Shu, Lijun Li, Zhuochen Li, Zetao Chen, Jianyu Wang

原文摘要

Conventional visual--inertial odometry (VIO) assumes that observations from cameras and an inertial measurement unit (IMU) are jointly consistent in an inertial reference frame. However, this assumption breaks down under non-inertial conditions. Inside accelerating or rotating carriers, visual observations of the interior reflect carrier-relative motion, while IMU measurements contain additional carrier-induced components, which can compromise conventional fusion. We therefore present NIF-VIO for localization relative to the local environment across inertial and non-inertial reference frames. It adapts visual--inertial fusion based on measurement consistency. As inertial conditions change, early constraint isolation is combined with local reoptimization to limit error propagation before inconsistency confirmation and repair the affected local geometry. Under non-inertial conditions, a compact model with temporally shared parameters is introduced to account for carrier motion while preserving inertial information that complements visual constraints. Experiments on public benchmarks and a self-collected dataset demonstrate that NIF-VIO achieves competitive performance under inertial conditions and improved localization accuracy and availability under non-inertial conditions.

cs.RO

新论文 · v1arXiv:2611.23720

Do 3D Point Representations Encode Architectural Functions? Probing Supervised and Pretrained Models on Urban Facades

Abdiaziz Muse, Jiju Poovvancheri

原文摘要

Semantic labels say what a building element is, not what it does: two identical-looking windows on one facade may be operable or fixed, a column may carry load or only decorate. We ask whether 3D point representations encode such architectural function. On 22 mobile-LiDAR buildings with 15 functional attributes per element, we hold out entire buildings and compare hand-crafted descriptors, networks trained from scratch and frozen self-supervised point transformers. Descriptors and frozen features are read by the same linear layer. No network trained from scratch, from PointNet to a 108M-parameter PTv3, clearly exceeds the descriptors (0.610 mAP on functionally ambiguous elements), whereas frozen Utonia reaches 0.732. Random-weight controls of the same architectures (0.649 and 0.652) attribute the gain to pretraining (Utonia: +0.080, 95% building interval [+0.035, +0.124]). Pretrained features improve at every tested number of labelled buildings while descriptors and random features plateau, and, in the configurations we tested, fine-tuning erodes the benefit: at today's data scale, function is better read from pretrained representations than learned from scratch.

cs.CV · cs.LG

版本更新 · v2arXiv:2606.02883

LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems

Amir Ghasemian, Homa Hosseinmardi, Upasana Dutta, Duncan J. Watts

原文摘要

Recommender systems shape what information we see, raising concerns about filter bubbles, radicalization, polarization, and social inequality. Large language models (LLMs) enable more powerful personalization that may intensify these dynamics, yet most recommenders are tuned for engagement or narrow accuracy metrics, with little attention to broader social effects. We investigate whether LLM-assisted reranking, while improving personalization, inadvertently amplifies exposure to ideologically congenial, extreme, or conspiratorial political content, a risk theorized but not yet empirically characterized. Using real YouTube trajectories, we rerank the platform's sidebar candidates by zero-shot prompting across three models, alongside an embedding baseline, and evaluate relevance, ideological alignment and diversity, and exposure to conspiratorial or extremist content. We find that (i) under a pure personalization instruction, reranking improves relevance while narrowing ideological exposure and, on two of three models, promoting problematic content for users with such histories; the third model, which declines most explicitly partisan requests, points to model-specific guardrails; (ii) lightweight prompt-level constraints substantially reduce problematic exposure on all three models, while the regularized rerankers still rank above the platform baseline on relevance; and (iii) synthetic experiments varying topical and partisan cues independently show no fixed preference between them: topic dominates on abortion and immigration, while partisanship takes over on elections, where the topical signal is weaker. Our results highlight the power of LLMs to operationalize contextual nuance in high-stakes political recommendation, and underscore the need to evaluate LLM-assisted personalization beyond accuracy and to treat prompt design as a value-laden choice rather than a neutral default.

cs.HC · cs.AI · cs.CY · cs.IR

新论文 · v1arXiv:2611.23719

Improving While Deployed: Learning Proactive End-to-End Driving from Imperfect Human Takeover Data

Yangang Ren, Di Zeng, Jun Li, Zirui Li, Chengjiang Zhang, Xiaoqing Ye, Ji Tao, Chen Lv

原文摘要

Once deployed on vehicles, end-to-end driving models continuously encounter challenging scenarios, generating valuable human takeover data that capture both model outputs and human behaviors. However, human interventions are often imperfect, as drivers may intervene too late or unnecessarily. Consequently, direct imitation can reinforce late responses or discourage otherwise appropriate maneuvers. To address this challenge, we propose an offline post-training framework that transforms imperfect takeover data into proactive supervision. We first construct diverse trajectory candidates by augmenting the plans of the deployed model and shifting recorded human corrective maneuvers earlier in time. We then train a scene-conditioned trajectory scorer to rank these candidates using expert demonstrations and unpaired preference signals from takeover logs. Using this scorer, we selectively replace pre-takeover training targets with higher-scoring candidates while retaining the original targets in normal driving scenarios. Finally, we distill the resulting targets into the driving model without changing its inference architecture. In closed-loop evaluations using real-world scenarios reconstructed with 4D Gaussian splatting, our method achieves the highest overall success rate, outperforming the deployed model, direct imitation learning and trajectory post-optimization. These results highlight a practical path toward efficient updates of deployed driving models using existing fleet logs.

cs.RO

新论文 · v1arXiv:2611.23718

HypoLoop: Revising Weight-Editing Plans from Scientific Feedback

Mengran Li, Xichen Yan, Bo Li, Chengyang Zhang, Jinfeng Xu, Zheng Lin, Zelin Zang, Zhen Lei 等 11 位作者

原文摘要

Scientific experiments continually reveal prediction errors. Effective updates depend on which parameters change and which errors drive the correction. We introduce HypoLoop, a family of native weight-editing methods that connects these choices to experimental feedback. Fixed, numerically adaptive, and LLM-guided policies produce editing plans; numerical solvers compute weight patches, and internal validation selects the deployed predictor. Successive observations and validation records support revisions to editable locations and fitting rules. Experiments cover 22 scientific tasks and both DeepSeek and Claude. On Burgers, reallocating a matched parameter budget reduces error by 58.80% and 47.72% relative to fixed locations. On DIODE, positive-residual weighting reduces absolute relative error (AbsRel) by 13.35% in internal cross-validation, with the same 33 editable coordinates. Revising the complete plan across rounds lowers final AbsRel by 10.59% relative to keeping the initial plan fixed. SpaceNet7 and Make3D connect accepted edits to improved spatial predictions. These results show how experimental evidence can shape the update problem itself. Code: https://github.com/limengran98/HypoLoop.

cs.LG

新论文 · v1arXiv:2611.23717

CoScan: Multi-Scale Content-Adaptive Space-Filling Scans for Causal State-Space Image Restoration

Wei Dong, Terry Ji, Yan Min, Shahram Shirani, Jun Chen, Han Zhou

原文摘要

Selective state-space models (SSMs) have recently shown strong potential for efficient image restoration. A central difficulty, however, is that a 2D feature map typically needs to be linearized into a 1D token sequence for causal state-space updates, making restoration performance highly sensitive to the imposed scan order. Existing deterministic scans follow space-filling principles but remain fixed and content-agnostic, and can yield fragmented or semantically inconsistent contexts under degradations. We propose \textbf{CoScan}, a \textbf{co}ntent-adaptive \textbf{scan}-order design for causal vision SSMs. CoScan learns image-dependent space-filling traversals via differentiable proxy supervision driven by \textbf{scan-quality objectives} that \textit{encourage short-range coherence and causal predictability, while preserving spatial adjacency}. To support hierarchical restoration backbones, we introduce an \textbf{efficient multi-scale scan construction by coarsening a fine-level minimum spanning tree}, producing coherent scans across feature resolutions. In addition, a \textbf{frequency-guided start selection strategy} is designed to \textit{place informative structures early in the sequence prefix to strengthen causal context formation}. Plugged into existing Mamba-based backbones, CoScan yields consistent improvements across several restoration benchmarks with minimal overhead and shows promising results on high-level vision tasks. Code will be released at https://github.com/dongw22/CoScan

cs.CV

新论文 · v1arXiv:2611.23716

Learning through Discernment: when a small language model learns from user feedback on the job, and when it decays

Sirisilp Kongsilp

原文摘要

Small language models on devices could keep improving by learning, overnight, from their own daily work. Without a true outcome, however, something must decide which attempts are worth learning from, and both the model's own judgment and the user's reaction can be wrong. We study a small model (Qwen3 0.6B and 1.7B) with a LoRA adapter, fine-tuned each night on the attempts a judge accepts, over 127 lives of up to a year on WebShop and $τ^2$-bench. We compare the true outcome, the user's stated verdict and the model's own judgment with a separate, frozen "feedback sense" that reads the user's reaction, built in three versions. Judging itself, the model improved and then decayed, over a year and whatever its adapter. A sense that took polite give-ups for success collapsed 3 of 5 lives; one built for discernment, which first asks whether the user gave a clear verdict, kept 4 of 5 near the oracle for two weeks, then faded on clean but scarce lessons, to the level of self-judging by day 60. When the user cannot see the outcome ($τ^2$-bench), the sense read reactions correctly, yet 80% of its lessons were failures the customer had thanked. Across 97 lives, the share of failed attempts among the lessons predicted the outcome (Spearman $ρ$ = -0.81). In our experiments, learning from users held up only where the judge kept failures out and the user could see the outcome; lopsided lessons may also narrow the model.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.23714

ExecGap: Exploiting Command-Execution Gap for Patch Attacks on Vision-Language-Action Models

Keke Tang, Guolin Qiu, Tianyu Hao, Daizong Liu, Yikai Zhang, Peican Zhu, Zhihong Tian

原文摘要

Vision-Language-Action (VLA) models have become a powerful paradigm for robotic manipulation and show strong promise for real-world deployment, making adversarial robustness critical for reliable robot operation. Existing adversarial attacks on VLA-controlled robots mainly optimize prediction-level discrepancies or rollout-level deviations to disrupt manipulation. However, they rarely account for the fact that VLA-predicted commands are not executed directly, but must be realized through downstream control and robot embodiment. In this paper, we propose ExecGap, an adversarial patch attack framework that exploits this command-execution gap to expose embodiment-specific execution vulnerabilities. Specifically, ExecGap biases VLA-predicted task-space commands toward low-executability directions, which are estimated from kinematic inefficiency and dynamic weak actuation. This induces execution degradation, where the predicted command becomes difficult to realize effectively, thereby impairing task completion. Extensive simulation experiments across multiple VLA policies show that ExecGap induces larger command-execution mismatch and weaker realized execution than existing patch attacks. Real-robot experiments further validate that the deployed patch can induce execution degradation on physical platforms.

cs.RO

版本更新 · v2arXiv:2610.32433

Tempo-Zero: Recursive Self-Play in Executable Worlds for Video Reasoning

Jingmin Zhu, Yanyan Zou, Xiuyu Li, James Bailey, Dinh Phung, Tao Yu, Yunyun Hou, Jun Liu 等 13 位作者

原文摘要

Video reasoning requires understanding how events unfold over time, yet videos with accurate temporal annotations are expensive to collect. Self-play offers an alternative by letting a model generate and solve its own tasks without manual annotation. However, existing video self-play methods train on fixed sets of recorded videos, so they cannot alter the underlying event dynamics and rely on noisy pseudo-labels derived from the model's own outputs, such as majority voting, that risk reinforcing shared model errors. To overcome these limitations, we introduce Tempo-Zero, a self-improvement framework that closes a loop of executable environments, execution-verified self-play, and environment evolution, where executing a program renders a video with the ground-truth option and interval of every question. A single policy plays both Questioner and Solver, proposing questions and answering them with timestamped evidence lines, and is trained on execution-grounded rewards instead of model consensus. The Solver's performance steers a curriculum over tasks and difficulty levels, and the policy selects rule changes that enrich the event dynamics of later rounds. Despite being trained solely on simple programs, without supervised fine-tuning or external video data which prior methods typically require, Tempo-Zero outperforms the base models and recent self-play baselines on average across twelve real-world video benchmarks at different model scales, with particularly strong gains on temporal grounding tasks. Project page: https://alchemist-jo.github.io/tempo-zero/

cs.CV