跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1673新增论文
+1257其中 AI 相关
+198已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-13 20:33 · 全站最近入库：2026-11-13 20:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-12 21:12 — 2026-11-13 21:12（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：2026-11-13 20:33最近发现新增版本：2026-11-13 20:44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6,727 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 2,191 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-13 20:29（北京时间）
新论文 · v1arXiv:2611.17320

Learning When Diffusion Language Models Should Regenerate

Minhae Oh, Jeonghye Kim, Jinwoo Koo, Yeongoon Kim, Jimin Seo, Minsik Seol, Jungwoo Lee

原文摘要

Remasking allows diffusion language models to revisit generated text, but effective correction requires knowing when and what to revise. Our diagnosis on Sudoku reveals two gaps. Hidden states contain error information that token confidence does not reliably expose, and remasking an isolated error usually reproduces it when the surrounding context remains fixed. These findings motivate DiVR , a verifier that predicts whether a partially generated sequence will reach a correct answer. Trained on the final correctness of the model's own trajectories, DiVR decides when to regenerate a block and which alternative to retain, while the generator itself stays unchanged. On five reasoning benchmarks with LLaDA-8B-Base, DiVR raises the average accuracy of the fine-tuned generator from 35.3\% to 43.4\% at $1.9$-$3.5\times$ the cost of greedy decoding, above search baselines that use $3.8$-$7.4\times$. It also complements post-training such as supervised fine-tuning and reinforcement learning, and generalizes to other generators, including Dream.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.17303

Towards a Theory of Learnability via Debate

Tosca Lechner, Vinayak Pathak, Sivan Sabato, Ruth Urner

原文摘要

Debate has been recently proposed as a training protocol that is hoped to produce more aligned models even as model capabilities scale. The idea is that the human, instead of providing supervision in the form of labels, judges a debate between two models that compete to prove the correctness of opposite labels. It can be shown that functions of a much higher computational complexity can be correctly judged in this way, compared to the complexity of functions that can be directly evaluated using a computationally weak evaluator. This suggests that perhaps debate can be used to teach very complicated functions to models. However, previous work has largely ignored the fact that this is a training protocol, and simply analyzes the game being played between the two debaters for a known judge. We take the first steps towards understanding the learning problem implicit within the protocol, by formulating it as an online learning problem. We show that once we formulate the learning problem precisely, there are cases where the best way to learn given access to a judge is different from running an adversarial debate. This motivates us to define a cooperative version of the protocol, whose learnability we characterize using a combinatorial dimension. We also consider the possibility of the human judge being fallible and occasionally judging the debate incorrectly. We show that a small number of errors in judgement can lead to a large error in learning.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2601.21419

Understanding and Learning Prediction Targets in Diffusion Models

Qing Jin, Chaoyang Wang

原文摘要

Recent advances in diffusion and flow matching models have highlighted a shift in the preferred prediction target -- moving from noise ($\varepsilon$) and velocity (v) to direct data (x) prediction -- particularly in high-dimensional settings. However, a formal explanation of why the optimal target depends on the specific properties of the data remains elusive. In this work, we provide a theoretical framework based on a generalized prediction formulation $u=kx-(1-k)n$, where $x$ represents clean data and $n$ denotes noise. This formulation accommodates arbitrary targets, of which $\varepsilon$-, v-, and x-prediction are special cases. We derive the analytical relationship between data's geometry and the optimal prediction target, offering a rigorous justification for why x-prediction becomes superior when the ambient dimension significantly exceeds the data's intrinsic dimension. Furthermore, our controlled analysis reveals how time conditioning and loss variations systematically modulate this optimal objective. While our theory identifies dimensionality as the governing factor for the optimal prediction target, the intrinsic dimension of manifold-bound data is typically intractable to estimate in practice. To bridge this gap, we propose k-Diff, a framework that employs a data-driven approach to learn the optimal prediction parameter k directly from data, bypassing the need for explicit dimension estimation. Extensive experiments in both latent-space and pixel-space image generation demonstrate that k-Diff consistently outperforms fixed-target baselines across varying architectures and data scales, providing a principled and automated approach to enhancing generative performance.

cs.LG · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.17294

Metal Sandbox: Isolated Execution and Command Scheduling for GPU Coding Agents on Apple Silicon

Haozhe Wang, Lina Chen, Fanqi Wan, Qi Han, Yinmin Zhang, Zheng Ge, Daxin Jiang, Junchi Yan

原文摘要

On-device inference requires kernels that make effective use of local accelerators. Efficient training and evaluation of models that generate Apple Metal kernels benefit from native macOS tools and concurrent agent sessions. These sessions alternate between model requests, development commands, and GPU execution, leaving GPU capacity idle for much of a rollout. We present Metal Sandbox, infrastructure that combines restricted per-instance file access, native command execution, and command-level scheduling across interconnected Macs. Each agent retains its workspace and private development environment. Parallel commands can run concurrently, while serial commands share one execution slot per node; eligible waiting commands can migrate to available Macs and return results to the original agent. Integration with Harbor supports task execution, automatic verification, and rollout collection through a common workflow. Controlled experiments on four Mac mini M4 nodes achieve $1.68\times$--$2.05\times$ gains in command throughput under concentrated demand. Sixteen static agent traces give an estimated $2.14\times$ sustained-throughput gain for four sessions per node versus one, assuming continuously replenished sessions and unchanged mean durations. Replaying these measured traces under dynamic scheduling reduces mean tool waiting by 18.8% and batch elapsed time by 22.3%, assuming unchanged phase durations. Metal Sandbox and its Harbor integration are open-source on GitHub.

cs.LG · cs.AI · cs.CL · cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.02665

Large Language Continuous Diffusion Models

Zhihan Yang, Wei Guo, Jean-Marie Lemercier, Simon Welker, Mohammad Mahdi Kamani, Yonggan Fu, Sajad Norouzi, Julius Berner 等 17 位作者

原文摘要

Despite the success of discrete diffusion language models (dLMs) for fast parallel decoding, their non-smooth, high-dimensional space hinders trajectory steering for reasoning and inference acceleration. To overcome this, we present Nemotron-Labs-Sigma, the first family of large-scale (3B/8B) continuous dLMs built on steerable, low-dimensional ODE/SDE latent trajectories. Trained blockwise via likelihood optimization, Nemotron-Labs-Sigma jointly denoises Gaussian-corrupted token embeddings while learning an optimal embedding geometry, and leverages pretrained autoregressive (AR) weights for warm-starting. At inference, we identify classifier-free guidance and score temperature as essential for high-fidelity reasoning and coding. Against state-of-the-art discrete counterparts (masked dLMs and AR baselines), Nemotron-Labs-Sigma outperforms them on standard benchmarks after pretraining (e.g., GSM8K, Minerva, HumanEval, MBPP) and on challenging reasoning tasks after supervised fine-tuning (e.g., MATH-500, AIME), with the largest consistent gains on coding. Beyond accuracy, we exploit two structural properties unique to continuous dLMs. First, smooth trajectories degrade gracefully at low NFEs and enable efficient few-step distillation: distribution matching proves strongest among the methods we study, giving roughly 8x acceleration on math and 4x on coding (8 and 4 tokens per forward pass) with negligible accuracy loss and preserved diversity. In addition, the one-step speculative decoding on the (pre-SFT) distilled 8B model yields a further ~3.5x throughput gain over the AR counterpart (on GB200), outperforming masked dLM baselines. Second, embedding-space steering controls the quality--diversity trade-off, yielding strong pass@$k$ that keeps improving as $k$ grows. Together, these results establish continuous dLMs as a promising paradigm for efficient language generation.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.00797

The Qualitative Laboratory: Theory Prototyping and Hypothesis Generation with Large Language Models

Hugues Draelants

原文摘要

The use of Large Language Models (LLMs) to simulate social actors has garnered attention for its implications for the epistemic status of discourses generated through such means. This paper considers the more modest question of whether sociological role-playing can serve as a heuristic instrument in the generation of qualitative hypotheses. We take as a case study the development of four divergent fictional characters using a theoretically informed Matrix of Climate Reception. These characters are asked to respond to a series of discourse frames covering two topics: a proposed ban on the sale of new gasoline-powered cars, and the inclusion of climate justice in the school curriculum. We then analyse the 32 model-generated responses for their commonalities, situational differences and divergences from the presuppositions underlying the characters' profiles. The experiment illustrates how LLMs can be used to flesh out theoretical presuppositions into contextual narratives and to propose avenues of further inquiry. It also shows that role-playing can generate considerable similarity between characters and is sensitive to how prompts are constructed, warning against the confusion of discursive coherence with sociological data. Role-playing is argued to be just one of several possible ways to use LLMs for generating hypotheses, with the heuristic specificity of this procedure compared with other methods of direct LLM-based reasoning or with other techniques remaining an open issue. The qualitative laboratory is thus conceived of as a heuristic instrument for provoking reflection and refining questions, not for testing theories with artificial data.

cs.CL · cs.AI · cs.CY · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.17191

Maximizing Capacity Utilization of LoRA Adapters for Mitigating the Learning-Forgetting Trade-off

Tomohiro Sawada, Kartik Goyal

原文摘要

Low-Rank Adaptation (LoRA) often underperforms full fine-tuning, especially in heterogeneous and continual-learning settings in which substantial forgetting occurs. In general, it suffers from an undesirable learning-forgetting trade-off across diverse fine-tuning settings. We identify a potential contributor: LoRA adapters, especially high-rank ones, frequently fail to realize the available capacity afforded by the configured rank. Specifically, we find that standard LoRA updates have effective rank far below their configured rank, limiting how broadly the update energy is distributed. Therefore, we propose training mechanisms that optimize the original objective while maximizing adapter effective rank. Our main method adds a simple, stable, differentiable, and SVD-free Rényi-2 effective-rank regularizer to the language-modeling loss. We also connect capacity maximization to norm-bounded updates. In mixed-domain rank sweeps on three models evaluated with multiple random seeds, a penalty weight of $λ=0.01$ lowers mean Wiki perplexity at every tested rank of at least $16$ relative to unpenalized LoRA. Mean training perplexity improves or increases by at most $0.02$ in all but one model-rank comparison. Single-task and scheduling experiments further show that the balance between learning and retention depends on the configuration. We also observe that several LoRA variants in the literature also suffer from the identified capacity issue, and our approach provides a complementary axis of improvement to LoRA-based parameter-efficient fine-tuning. These results suggest that effective rank is not only a post-hoc diagnostic of adapter quality, but a trainable objective for improving the learning-forgetting frontier. Our code is available at https://github.com/tomohiro-sawada/lora-capacity-utilization

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.17186

Cortex-FL: Agent-Mediated Collaboration for Federated Learning

Rui Sun, Jinfeng Peng, Zehua Cheng, Jiahao Sun, Zhipeng Wang

原文摘要

Federated learning (FL) enables independent data owners to train models collaboratively without centralizing raw data. However, identifying collaborators, preparing training tasks, and coordinating execution and incentives hinder its practical adoption by organizations without specialized expertise. We present Cortex-FL, an agent-native FL system that enables users to express learning objectives in natural language and delegate the collaboration required to train a model. Agents translate these objectives into shared tasks, discover collaborators, and negotiate participation agreements, connecting collaboration formation with distributed training and incentive management. The architecture separates agent coordination from local execution authority, allowing owners to delegate coordination while retaining control over their data, computation, and financial commitments. We demonstrate the complete workflow on a four-node deployment, in which a model requested in natural language proceeds through collaboration formation, contract-governed training, verified model delivery, and x402 settlement on a blockchain testnet.

cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.17163

UAV-Flow++: A Unified Suite for Benchmarking and Learning Language-Guided UAV Flight

Donglin Yang, Xiangyu Wang, Yantong Zhong, Wenhao Zheng, Zihan Ding, Yue Liao, Hongsheng Li, Ke Xu 等 9 位作者

原文摘要

Language-guided UAV navigation has largely focused on long-horizon route planning, leaving short-range, object-relative flight maneuvers underexplored. To address this gap, we formulate Flying-on-a-Word (Flow), a task requiring a UAV to convert concise natural-language instruction, egocentric visual observation, and current state dynamics into continuous flight actions. Flow encompasses both primitive motion commands and complex object-interactive behaviors, assessing motion intent comprehension and spatial context grounding. To enable policy learning and closed-loop evaluation, we introduce UAV-Flow, a comprehensive dataset comprising 30,692 expert-piloted real-world trajectories across eight distinct motion categories, alongside 10,109 simulation trajectories in the UAV-Flow-Sim environment equipped with task-specific completion criteria. Furthermore, we develop FlowVLA, which undergoes imitation pretraining on mixed real-sim demonstrations and online post-training via Tail-Aware GRPO (TGRPO). By leveraging group reward distributions, TGRPO effectively reinforces high-reward action sequences. Evaluated on 273 held-out UAV-Flow-Sim episodes, pretrained FlowVLA achieves a mean success rate of 75.58%, outperforming the strongest baseline by 6.72 percentage points, which TGRPO post-training further elevates to 93.16% with superior sample efficiency. Physical UAV experiments demonstrate robust execution of object-relative commands in both indoor and outdoor real-world scenes. Together, Flow establishes a novel benchmark and learning framework for language-conditioned flight maneuvers.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.17159

Inner Product Regularization for Imitation Learning

Benjamin A. Christie, Tianyu Qiu, Amy H. Choi, David Fridovich-Keil, Dylan P. Losey

原文摘要

Robots that learn from demonstrations should extrapolate their policy despite state perturbations such as sensor noise, scene variation, and compounding errors. One approach to this robustness is regularization. Prior regularizers consider each state on its own and limit how sensitive the policy is to any perturbation at that state. By contrast, we explore how the policy's output shifts when given the same perturbation at different states. Our insight is that, locally, the robot should respond to state perturbations in a consistent manner: e.g., if changing an irrelevant object position does not impact the policy at one state, that same change should not shift the policy output at a nearby state. Applying this insight, we develop inner product regularization (InneR). We show that the inner product on action space induces an inner product on state space through the policy Jacobian (the Fisher information for stochastic policies), and that the null space of this inner product governs which state perturbations have a first-order effect on the policy. By clustering states whose inner products are aligned, averaging the inner products within each cluster, and minimizing the smallest eigenvalues of that average, InneR shapes the learned policy so that nearby states share a common null space. InneR enforces consistent responses to perturbations without limiting policy expressiveness, and can be appended to existing imitation learning pipelines for deterministic or stochastic policies. In simulated experiments, InneR makes learned policies more robust to irrelevant state dimensions and shifts between training and test distributions, whereas norm penalties often perform worse than behavior cloning. On a real robot arm performing three manipulation tasks, InneR raises the average success rate of a diffusion policy from 18% to 57% without additional data.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.17148

Learning Dynamics of the Influencer's Game in Resource Landscapes

Mark Lovett Feng Fu

原文摘要

Across domains as varied as ecology, economics, and online platforms, individuals are incentivized to position themselves within resource-rich strategy spaces. In this work we introduce a new spatial game framework called the influencer's game. Within this new framework players' strategies are represented as positions within a trait space. Players then receive a share of a portion of a resource based on their relative influence at that resource's points traits. For the influencer's game, we show that there is a unique symmetric Nash equilibrium that exists under strict log-concavity of the influence kernel. Using the unique equilibrium we show that the stability of the system depends on the influence kernel's parameters, number of players, and the resource distribution shape. For any dimension we demonstrate a stability threshold that depends on both the scatter and curvature of the players. When this threshold is crossed, the symmetric equilibrium destabilizes and gives way to a variety of bifurcation types; including, specialist clusters, limit cycles, and sub-games that reproduce the larger game's structure. We ground these results using real-world data for resources as a demonstration of the game's application. Finally we extend the game dynamics to use multi-agent reinforcement learning and further show that the predicted bifurcation structure persists under partial observability and discretized strategy spaces. In all, the influencer's game provides a novel framework for predicting when competitive pressure drives convergence versus fragmentation with possible applications across domains.

cs.GT · econ.TH · physics.soc-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.17110

SALA: Semantically Aligned Latent Actions Enable Dual-Axis Scaling of Embodied Foundation Models

Jiachun Jin, Zetong Zhou, Haonan Wang, Xiao Yang, Jun Zhu, Zhijie Deng

原文摘要

Embodied foundation models hinge on diverse robot interaction data, which are costly to collect. Egocentric human videos offer a complementary source of experience, and latent action models (LAMs) provide a popular means of leveraging these videos for policy supervision. Compared with world-action models (WAMs), LAMs can offer greater training efficiency and potentially lower inference costs by avoiding explicit pixel prediction during policy learning and execution. However, most existing LAMs learn latent actions solely through video reconstruction, which can cause their representations to cluster by visual appearance rather than by the underlying actions. As a result, they struggle to align human actions with their robot counterparts. To bridge the gap, we introduce SALA, which emphasizes establishing the semantic correspondence for latent actions. Without requiring paired data, we use the language descriptions of unpaired human and robot clips to estimate semantic similarities and supervise cross-embodiment correspondence. Specifically, we translate these similarities into soft neighborhood structures that guide human latent actions toward semantically related robot latents, while robot action reconstruction grounds the latent space in control. The resulting shared latent action space provides a unified supervision signal for training an embodied foundation model on both human and robot videos. Notably, latent action supervision enables scaling along two axes: (1) pre-training on increasing amounts of general human video consistently reduces robot action prediction error on downstream tasks, and (2) post-training on increasing amounts of task-specific human video substantially improves real-world robot task success rates.

cs.RO · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.17100

Nearly Optimal Dilation for Non-Uniform k-Center with Constant-Factor Budget Violation

Jannis Blauth, Siri Prüßner

原文摘要

In Non-Uniform $k$-Center, we are given a metric space $(V,d)$ and $L$ levels of balls with prescribed radii $r_1 \ge \ldots \ge r_L$ and nonnegative integer budgets $k_1,\ldots,k_L$. The goal is to place at most $k_\ell$ centers of each level $\ell \in [L]$ in $V$ and minimize the dilation $λ$ such that the corresponding balls of radii $λr_1,\dots,λr_L$ cover $V$. While this problem admits no subexponential approximation factor unless P=NP, the picture changes drastically when additional centers are allowed. An $(α,β)$-bicriteria approximation to Smooth Non-Uniform $k$-Center covers $V$ with dilation $βλ_{\text{opt}}$ such that, for each $\ell \in [L]$, the number of centers of the first $\ell$ levels is at most $α$ times their total budget. For every fixed $\varepsilon>0$, we give a randomized $(1+\varepsilon,8+\varepsilon)$-approximation and a deterministic $(O_{\varepsilon}(1),2+\varepsilon)$-approximation, both running in polynomial time. Even for classical $k$-Center, obtaining an $(O(1),2-δ)$-approximation is NP-hard for every fixed $δ\in (0,1]$. Thus, our second result almost settles the optimal dilation when a constant-factor violation of the budget is allowed, unless P=NP. We combine a new primal-dual enumeration procedure with a simple bucketing argument that yields a new trade-off between the two approximation factors. It remains open whether there is a polynomial-time $(1+\varepsilon,2+\varepsilon)$-bicriteria approximation, which would almost match the classical $2$-approximation for $k$-Center.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.17019

Temporal Regularized Learning: Self-Supervised Learning Local in Space and Time

Davide Wiest

原文摘要

Layer-local self-supervised objectives remove the backward pass between layers, but almost all still compute their loss over a batch of samples and are therefore local in space but not in time. We introduce Temporal Regularized Learning (TeReL), a spatially and temporally local learning rule for self-supervised representation learning from sequential input streams. The key idea is to instantiate a VICReg-style objective with temporally adjacent positives and non-differentiated running population statistics, yielding a per-neuron online loss with bounded state. The objective is a soft form of Slow Feature Analysis, and its gradient is a Hebbian update of the feedforward weights and an anti-Hebbian update of one lateral matrix per layer. The aim of the experiments is to show that the rule works in a small network, not to compete with backpropagation. On a class-chunked MNIST stream, a two-layer fully connected network trained with batch size one outperforms random features (96.48% versus 95.09% linear-probe accuracy) and classical SFA, and a variant that relaxes both locality constraints is comparable to supervised backpropagation. Because training and inference use the same computation, the network can keep learning from unlabeled data during inference without loss of accuracy.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.17005

An Integrated Architecture for Data-Efficient Real-Time Neural Imitation of Nonlinear Time-Optimal Model Predictive Control

Maarten De Baecke, Flavia Sofia Acerbo, Andrea Giusti, Wilm Decré

原文摘要

Nonlinear time-optimal model predictive control (TOMPC) enables highly performant control of constrained systems, but its computational cost prohibits real-time use on fast dynamical systems. Neural network imitation of the TOMPC control law can reduce online computational costs, yet existing work mostly targets quadratic cost formulations in simulation and addresses the challenges of neural controllers in isolation. This work imitates a long-horizon nonconvex TOMPC with hard terminal constraints, whose high computational cost limits training-data generation. We present (i) \emph{self-informed sampling (SIFS)}, a data-efficient expert-sampling strategy that uses a learned time-to-go to query the expert only where the policy deviates from time-optimal behavior, (ii) a complete training and control architecture that jointly addresses dataset correlation, suboptimal expert labels, covariate shift, constraint satisfaction and model mismatch, and (iii) real-world validation on a Furuta pendulum. SIFS matches standard dataset aggregation performance in roughly one-third of the training time and with less than half the training data. The resulting controller matches the region of attraction of the expert TOMPC while raising the control frequency from 1.4~Hz to 1~kHz. On hardware, the controller swings up and stabilizes the pendulum along trajectories closely matching the expert TOMPC solution.

eess.SY · cs.LG · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.41216

TinyAstral: Transferring Self-Evolving Harnesses to Tiny Generalist Manipulation Agents

Kehong Gong, Xiaoxu Zheng, Guanli Hou, Seunghun Lee, Mengqi Guo, Runjia Tan, Zhengyu Wen, Qi Wang 等 11 位作者

原文摘要

Robot agents built on vision-language models depend on both the planner and its harness: the tools, feedback, memory, and recovery logic around it. Can improvements to a large teacher's harness be carried into a compact agent with lower inference compute cost? We present TinyAstral, a two-stage approach. We first freeze an open-weight teacher and improve its harness through recursive self-improvement (RSI): frontier LLM agents read the teacher's trajectories and propose harness edits, and each edit is accepted only if it passes a paired statistical test. We then freeze the final harness, collect teacher trajectories with reasoning and failure recovery, and distill a small student that replaces the teacher in the same harness. On RoboTwin, harness evolution raises the teacher's success from 33.4% to 63.6%; the final 4B student reaches 62.8%. Across four harness versions, distilled 4B students score close to their corresponding teachers, and later versions yield stronger students, showing that harness evolution gains carry into compact models. The harness gains also transfer to other frozen planners without retraining. On identical episodes, the final 4B student outperforms open 4B agents, the open 27B harness-RSI model SenseNova-RoboRSI, and our own teacher model placed in three competitors' harnesses. It stays close to its teacher on all three training benchmarks, and on three benchmarks never used for RSI or training it scores close to a 552B planner running the same harness. On the measured deployment episodes, it uses about one fifth of its teacher's accelerator time. Project page: https://garfield-kh.github.io/TinyAstral/

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.17003

Maturity$^2$: Assessing the Maturity of Crypto Agility Maturity Models

Leonie Wolf, Robin Leander Schröder, Sebastian Schinzel, Fabian Ising

原文摘要

Crypto agility maturity models aim to support organizations in preparing for cryptographic transitions, such as migrating to post-quantum cryptography. Recognizing the importance of measurable maturity, NIST references several such models in its guidance. Given NIST's influence on cybersecurity practice, these models may shape organizational planning and governance mechanisms. However, their design quality has not been systematically evaluated. In this work, we assess three industry-driven maturity models against established design principles. Our analysis reveals recurring weaknesses, particularly the lack of measurable, reproducible assessment criteria and limited prescriptive guidance for improving crypto agility. At the same time, we highlight individual strengths that can assist practitioners in choosing among the models and derive concrete recommendations for strengthening future crypto agility maturity models.

cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.21495

Scentree: a framework for generating scenario trees for multistage stochastic programming

Cristian Pachón-García, Albert Solà Vilalta, F. -Javier Heredia

原文摘要

We present scentree, an open-source Python package for constructing scenario trees for multistage stochastic programming models using either historical data or samples drawn from a probability distribution. It combines machine learning and multivariate time series models to obtain a scenario fan that captures dependencies in the stochastic processes. This scenario fan is subsequently reduced into a scenario tree that preserves representativeness of the stochastic process, providing a flexible and extensible framework for uncertainty modeling in stochastic programming problems. The framework can also be naturally applied to two-stage stochastic programming problems. Key contributions are the joint modeling of the stochastic process, preserving correlations between all random variables, and the automation of the complete workflow, including forecasting model selection, parameter estimation, scenario fan generation, and scenario tree construction. In addition, scentree does not assume any underlying data distribution, reducing the statistical expertise required to produce a scenario tree, and is modular by design, allowing external forecasts and other partial executions of the workflow.

stat.CO · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16913

CADET: Construction of PCB Routing Instances with Executable Demonstrations

Hyungseok Song, Won-Seok Choi, Seohui Bae, Han-Seul Jeong, Junseok Park, Youngjoon Park, Soonyoung Lee

原文摘要

Printed circuit board (PCB) routing is the stage of physical layout that finds paths connecting the placed pads of each net. Public datasets in this domain are few, and most contain only the final states of routed boards, not demonstrations of the electronic design automation (EDA) engine actions that produce them. To close this gap, we propose CADET (Constructing executAble Demonstrations for Engine-grounded Training), which jointly generates synthetic boards and demonstrations built from EDA engine actions. The resulting RouteDemos provides 100,000 synthetic boards routed with zero design rule violations (DRVs), together with their demonstrations. Their distributions over 17 statistics resemble those of 142 real reference boards. CADET trains a routing policy on these demonstrations with behavior cloning and fine-tunes it with reinforcement learning (RL). On real test boards, the policy raised the rate of complete DRV-free routing from 38.0% to 67.2% over an RL-only baseline. This rate was comparable to that of the open-source autorouter FreeRouting and exceeded those of the other baselines, including GPT-6 Astra. We release the dataset and its generation code as open source at https://github.com/LGAI-Research/CADET.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2512.00775

SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning

Ruijia Liu, Ancheng Hou, Xiang Yin

原文摘要

Linear Temporal Logic (LTL) provides a rigorous framework for specifying long-horizon robotic tasks, yet existing approaches face a trade-off: model-based synthesis relies on accurate labeled transition systems, whereas learning-based methods often require online interaction, task-specific rewards, or specification-conditioned training. We study LTL-specified robotic planning and execution in an offline, model-free setting, where the agent is given only fixed, task-agnostic trajectory fragments, with no dynamics model, task demonstrations, or online data collection. To address this setting, we propose SAGAS, a framework that combines the compositionality of symbolic synthesis with the data-driven reachability structure learned from offline trajectories. SAGAS first learns a reusable latent reachability graph and a frozen goal-conditioned executor from fragmented offline data. For each new LTL formula, it performs task-time semantic graph augmentation to ground state-defined propositions on the learned graph and applies Büchi product search to synthesize a cost-aware accepting prefix--suffix waypoint plan executed by the frozen executor. This separation of learning and planning enables zero-shot generalization to unseen LTL formulas and new predicates supported by the offline data, without task-specific rewards, additional data collection, or policy retraining. Experiments on LTL task suites constructed from OGBench locomotion domains show that SAGAS achieves higher success rates and lower execution costs than baselines on diverse unseen tasks, with further evaluation in OGBench Scene demonstrating its applicability to robotic manipulation.

cs.RO · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16882

Pretraining Data Statistics Shape the Phases of Learning Entity Comparison in Language Models

Yik Siu Chan, Jing Huang, Yanai Elazar, Atticus Geiger

原文摘要

How does data shape language model (LM) behavior throughout pretraining? We investigate this question through a case study on entity comparison, e.g., Between France and Brazil, which country is larger?, across nine comparison tasks spanning five entity types. We begin with controlled experiments in which we train small LMs (163M parameters) on mixtures of natural text from pretraining corpora and synthetic task data. Our analysis identifies three distinct phases of learning: (1) an early phase where the LM selects entities by frequency, (2) a middle phase where the LM selects entities by position in the prompt (first vs. last mentioned entity), and (3) a late phase where the LM selects the entity that is the correct answer. We show that the emergence of these three phases is causally determined by statistical properties of the training data. With small amounts of task-specific synthetic data, we observe only the first two phases and the model fails to learn the task; with large amounts, the model jumps directly from the frequency-based heuristic to solving the task correctly. Moreover, changing the entity frequency distribution from a naturally occurring Zipfian distribution (a small number of entities are very common and the vast majority are rare) to a uniform one weakens the frequency phase and speeds up learning of the task. Lastly, we show that the three phases of training dynamics from our controlled experiments appear in the open source model OLMo-2 32B. Together, our findings demonstrate that properties of pretraining data are causal drivers of heuristic learning and show that small-scale synthetic experiments can predict training dynamics at larger scales.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16872

ACE-CaP-0: Real-World Code-as-Policies in the Era of Experience

ACE-CaP Team, Changxu Wei, Yunpeng Qing, Guozheng Ma, Bowen Liu, Zexin He, Yilun Kong, Haoming Gu 等 28 位作者

原文摘要

Recent advances in frontier models have pushed the boundaries of agentic robot control, enabling agents to perform complex robotic tasks through reasoning and interaction. However, repeated calls to these models during execution can substantially increase task completion time. Code as Policies (CaP) offers a route for coding agents to acquire physical skills through experience and retain them in executable programs, allowing the reasoning invested in development to be reused across runs. Developing reliable code policies while limiting the cost of physical experimentation remains a central challenge. We investigate human guidance as a source of priors for feasible actions and simulation as an auxiliary environment for exploring and testing candidate policies. Our findings favor robot demonstrations available on request and simulation used selectively during real-world policy refinement. These findings inform ACE-CaP-0, an agentic recipe that couples policy revision with experience acquisition through Demonstrations on Request and Simulation on Demand. Across eight real-world manipulation tasks spanning alignment, multi-object handling, and bimanual coordination, the resulting frozen programs achieve 92.1\% success (221/240 trials). Mean execution times across tasks range from 0.97 to 2.27 minutes. The programs execute with runtime perception and control, without a human or coding agent in the loop. These results highlight CaP's potential to turn experience into reliable, reusable physical skills.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16844

Locality Meets Interference: Structure and Scheduling in Radio Multicasting

Qin Xin

原文摘要

We study multipoint-to-multipoint multicasting in synchronous radio networks with unknown participant locations and unrestricted message aggregation. Let $n$ be the network size, $k$ the number of participants, and $d$ their hop diameter. A supplied distance-two coloring with $C$ colors yields completion within $(C-1)d+1$ slots and at most $nk$ transmissions. In unit disk graphs, coordinates, one-hop neighbor data, and a common degree bound $Δ_0$ suffice for a $15(Δ_0+1)$-color schedule. A known fixed separation bound permits optimal deterministic $Θ(d)$ completion from coordinates alone. Without geometric data, strong selectivity gives $O(d\min\{n,(Δ_0+1)^2\log n\})$ slots when $n$ is known. Independent random transmission gives $O((Δ_0+1)(d+\log(k/η)))$ slots with failure probability at most $η$; for fixed $Δ_0$, this simplifies to $O(d+\log(1/η))$. A star construction shows that the logarithmic term is necessary for this random rule when the degree grows. We extend color schedules to fixed deletions and subgraphs connected over bounded windows of cycles. Separate conditional reductions preserve additive costs under diameter guessing and control parameter-table and cluster preprocessing. Finally, a counterexample shows that pruning and reranking a breadth-first tree can destroy interference-free delivery. For one-hop designated delivery with receiver degree at most $b$, we prove that the optimal schedule length equals the chromatic number of an associated conflict graph and is at most $2b-1$, with matching examples.

cs.DC · cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2509.03244

FoMEMO: Towards Foundation Models for Expensive Multi-objective Optimization

Yiming Yao, Fei Liu, Liang Zhao, Xi Lin, Yilu Liu, Qingfu Zhang

原文摘要

Expensive multi-objective optimization is a prevalent and crucial concern in many real-world scenarios, where sample-efficiency is vital due to the limited evaluations to recover the true Pareto front for decision making. Existing works either involve repeatedly fitting Gaussian process surrogates from scratch for each newly encountered problem, or rely on computationally demanding hypervolume-oriented policy learning for amortized optimization, making it challenging to achieve scalable pre-training and efficient yet robust adaptation for diverse emerging real-world applications. To address these challenges, we propose FoMEMO (Foundation Models for Expensive Multi-objective Optimization), which adopts a decomposition-based training paradigm that converts multi-objective optimization into preference-wise aggregated posterior learning tasks, enabling scalable pre-training on hundreds of millions of diverse synthetic datasets without relying on extensive real-world domain experiments. At test time, given observed trajectories from unseen problems and user preferences, the foundation model performs in-context posterior prediction and optimizes the derived acquisition functions for efficient candidate generation, achieving strong generalization and optimization performance without any subsequent model training or updates.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16779

Computation with Backward Feedback: Power, Observation, and Cost

Saman Farhat, Farzad Didehvar

原文摘要

How much can a computation gain by passing information back to an earlier stage, and how soon can an observer obtain the answer? We study deterministic programs whose runs are accessed at randomly selected stages. A program keeps a register, a finite block of memory. A random clock selects the current stage; each tick takes a random step, with a law fixed independently of input, program and register. When the clock moves backward, the register contents at the stage it leaves start a new run, and the clock continues where it lands. Equilibrium readout requires a distribution of clock position and register that one tick leaves unchanged, and a correct final answer under every such distribution. For bounded steps in both directions with negative average, we obtain an exact classification at each polynomial scale s. If running time and register length are both O(s), feedback gives exactly nondeterministic space O(s); without transmission the class is deterministic time O(s), which is strictly smaller. An observer that starts at stage zero with an all-zero register, reads sequentially and never accepts a nonmember sees, with fewer ticks than any exponential, only languages fixed by a bounded input prefix. Exponentially many ticks reveal every linear-time language. For a clock moving one step up or down, we bound the wait for useful backward moves and the rate of random erasures a stored counter tolerates. The results separate the power of feedback at equilibrium, observation from a fixed start, and the cost of obtaining and keeping information.

cs.CC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16767

Evaluating Video LLMs' Understanding of Corner Cases in Autonomous Driving

Gabriel Manalu, Minh Son Hoang, Hyeontaek Hwang, Jaesung Lee, Hyojin Choi, Tran Tuan Phong, Seon Kwon Kim, Saad Wazir 等 9 位作者

原文摘要

Natural language explanations promised by modern Video Large Language Models (Video LLMs) offer autonomous driving systems a path toward detailed scene description and interpretable decision making on the road. While recent benchmarks have begun assessing these models on driving scenes, they mainly target routine traffic conditions and general comprehension tasks based on existing driving datasets and therefore fail to evaluate model performance on the rarest and most safety-critical driving events, also known as "corner cases". To provide a comprehensive evaluation of Video LLMs on precisely these scenarios, we introduce DashBench, a benchmark testing 25 Video LLMs on 1,709 carefully curated driving videos spanning not only collision-related corner cases but also rare non-collision ones. Through extensive prompts and open-ended question answering, we expose a critical capability gap: all evaluated models perform substantially below the threshold required for safety-critical driving applications, frequently misjudging or missing dangerous events on the road ahead and hallucinating non-existent agents or actions in their explanations. We believe DashBench, combining an extensive dataset with a rigorous evaluation toolkit and a detailed diagnosis of current model limitations, drives progress toward safer, more explainable autonomous driving systems. The code and data will be shared at: cornercase-dashbench.github.io

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16756

Beyond Binary Classification: Multiclass Machine Learning for Diabetes and Prediabetes Risk Prediction Using NHANES

Aman Mujahid, Anita Penkova

原文摘要

Detecting diabetes risk early is important for preventing disease progression. Most existing machine learning approaches focus on binary classification, which limits their ability to capture intermediate risk states such as prediabetes. We develop a supervised learning framework to classify adults as normal, prediabetic, or diabetic using National Health and Nutrition Examination Survey data. The framework uses routinely collected demographic, clinical, and lifestyle variables from 15,356 adults, with glycated hemoglobin (HbA1c) used only to define labels and excluded from input features to prevent leakage. We compare conventional machine learning and transformer-based models and examine two binary formulations: normal versus prediabetes, and normal versus combined prediabetes and diabetes. Models are evaluated on a held-out test set using precision, sensitivity, specificity, and F1 score. In the multiclass setting, performance is broadly consistent across models, with accuracy up to 0.72 and macro-averaged F1 of 0.70. Prediabetes remains the most challenging class, with F1 scores of 0.54 to 0.56 for conventional models and 0.53 to 0.55 for transformers, reflecting its overlap with both neighboring states. When the task is reduced to normal versus prediabetes, F1 scores rise modestly to 0.62 to 0.64. A more substantial improvement is observed under a broader screening formulation combining prediabetes and diabetes, with F1 scores of 0.73 to 0.74 across all models. These findings suggest that feature overlap along the biological continuum between normal and diabetic states contributes more to the difficulty of prediabetes detection than model architecture. Multiclass prediction provides a more clinically informative representation of metabolic risk progression but highlights a trade-off between clinically meaningful stratification and predictive accuracy.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16752

AgriSense: Vision-Language Decision Support and Robotic Intervention in a Virtual Greenhouse Copy title

Lyes Saad Saoud, Oualid Doukhi, Reza Ghorbani, Moussa Ayyash

原文摘要

Autonomous greenhouse management increasingly requires robotic systems that integrate perception, navigation, environmental regulation, and plant-level intervention. This paper presents AgriSense, a framework combining an Isaac Sim virtual greenhouse, a quadruped mobile manipulator, RGB and LiDAR-inertial sensing, environmental control, and supervised vision-language decision support. Frozen DINOv2 and BERT encoders, together with structured environmental inputs, support joint prediction of twelve environmental references, a target zone, and an intervention flag. Checkpoint replay reproduces 41/43 zone decisions. Across five seeds on a source-grouped test set, the full, image-removed, and language-removed configurations each achieve 43/44 correct zone decisions, providing no evidence of incremental multimodal zone-accuracy improvement. The full model achieves mean absolute errors of 0.249 degrees C for temperature, 2.030 percentage points for humidity, and 0.997 percentage points for soil moisture. Sensor-only inputs match full-model zone accuracy, while language-only inputs achieve 68.64%. External real-image benchmarks reveal distribution-shift limitations. Five offline Point-LIO routes yield rigidly aligned trajectory errors of 5.22-17.32 mm. Of 40 virtual-arm targets, 32 satisfy geometric acceptance criteria and eight are rejected at boundaries. Six long-horizon climate cases and fault protocols characterize integration limits. Navigation and integrated treatment rely on simulator-state inputs; physical greenhouse performance and agronomic treatment efficacy remain unvalidated. The contribution is an evaluated decision-support and robotic-intervention framework for a virtual greenhouse.

cs.RO · cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.15269

Cloning is as Hard as Learning for Stabilizer States

Nikhil Bansal, Matthias C. Caro, Gaurav Mahajan

原文摘要

The impossibility of simultaneously cloning non-orthogonal states lies at the foundations of quantum theory. Even when allowing for approximation errors, cloning an arbitrary unknown pure state requires as many initial copies as needed to fully learn the state. Rather than arbitrary unknown states, modern quantum learning theory often considers structured classes of states and exploits such structure to develop learning algorithms that outperform general-state tomography. This raises the question: How do the sample complexities of learning and cloning relate for such structured classes. We answer this question for an important class of states. Namely, for $n$-qubit stabilizer states, we show that the optimal sample complexity of cloning is $Θ(n)$. Thus, also for this structured class of states, cloning is as hard as learning. To prove this result, we relate stabilizer state cloning to a variant of the sample amplification problem for probability distributions that was recently introduced in classical learning theory. This allows us to obtain our cloning lower bounds in analogy to new sample amplification lower bounds for classes of distributions with an underlying linear structure. Our results provide a more fine-grained perspective on No-Cloning theorems, opening up connections from foundations to quantum learning theory and quantum cryptography.

quant-ph · cs.LG · math.ST

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16661

Reducing Batch Makespan for LLM Agent Workloads through Inference-Environment Coordination

Wei Feng, Meiling Chen, Boxiao Chen, Lu Liu, Bin Zi, Libin Ye, Xingyu Lu, Lei Xu 等 9 位作者

原文摘要

Efficient batch execution of agent tasks is critical to LLM training and development workflows, including benchmark evaluation, synthetic-data generation, and RL rollouts. Since these tasks alternate between LLM inference and environment interaction, we present coordinated optimizations to reduce batch makespan, the time required to complete all tasks in a batch. For hybrid LLMs, a workload-based resource model guides GPU-memory allocation between key-value (KV) cache and recurrent state and provides a reference sample concurrency to exploit parallelism while limiting recomputation. Trajectory-aware routing and scheduling promote cache reuse while balancing worker load. Under constrained environment capacity, we decouple sample admission from environment execution and introduce Chain-Advancing Action Scheduling (CAAS), which prioritizes long chains using observed progress to shorten the batch tail. Controlled replay combines actual inference with recorded environment responses and durations for ablations of individual optimizations. Live evaluations with Ling-3.0-Flash and Ling-3.1-Flash on the BFCL, SWE-bench Multilingual, WideSearch, and MCP-Atlas benchmarks demonstrate makespan reductions of 10.4% to 65.0%, while evaluation scores remain aligned. Furthermore, these methods have been successfully applied to training and evaluation workflows for the Ling-3.x model series, accelerating the model-development cycle.

cs.DC · cs.AI

查看论文
arXiv ↗PDF ↗