跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+92新增 AI 导读

arXiv 最近完成扫描:2026-11-23 01:07 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-22 04:09 — 2026-11-23 04:09(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:2026-11-23 01:07最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 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 29,158 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-23 01:05(北京时间)
新论文 · v1arXiv:2611.26629

后验匹配蒸馏

Posterior Matching Distillation

Hidir Yesiltepe, Julius Berner, Arash Vahdat, Pinar Yanardag

AI 速读 基于摘要

PMD 通过匹配教师后验均值来蒸馏扩散模型,在保持多样性的同时实现少步生成。

cs.CV

查看原文摘要

Diffusion distillation accelerates image and video generation by compressing a pretrained teacher's iterative sampling process into a few network evaluations. Distribution-based methods achieve this by matching the student's output distribution to the teacher's. This matching is often driven by reverse-KL objectives, whose mode-seeking bias favors dominant teacher modes at the expense of diversity across samples. We introduce Posterior Matching Distillation (PMD), a new member of the distribution-based distillation family that combines mode-covering posterior sampling with any-step generation. At zero population loss, PMD recovers the teacher's full posterior of clean images at each trained noise level. Its stochastic student supports any-step sampling budgets within the trained timestep grid without further training. To learn these posteriors, PMD matches exponentially reweighted averages of student samples conditioned on a fixed noisy state to corresponding teacher posterior means. Under Gaussian corruption, exponentially tilted posterior mean is a single teacher evaluation at a shifted input. We prove that, matching tilted means over an open neighborhood uniquely identifies the full posterior. PMD thus supervises the entire conditional distribution through a family of mean constraints, without any auxiliary student-score network. Experiments on SDXL and FLUX.2 [klein] 4B demonstrate that PMD achieves the best FID among 4-step methods on both models, while maintaining competitive or leading performance across prompt-alignment and perceptual-quality metrics.

新论文 · v1arXiv:2611.26627

扩散Transformer中的强化学习后训练本质上是激活引导

RL Post-Training in Diffusion Transformers Is Activation Steering

Tuna Han Salih Meral, Kaan Oktay, Alec Helbling, Atakan Kara, Duen Horng Chau, Pinar Yanardag

AI 速读 基于摘要

作者发现,用一组与输入无关的固定引导向量即可复现扩散Transformer强化学习后训练的大部分奖励增益,说明这类后训练主要是在做激活引导。

cs.CV · cs.LG

查看原文摘要

Reinforcement learning (RL) post-training substantially improves the visual quality, text rendering, and compositional accuracy of diffusion transformers. Because capabilities such as rendering requested text or composing multiple objects are inherently prompt-dependent, a natural hypothesis is that improving them requires learning complex, input-dependent transformations. To isolate how much of these gains an input-independent shift explains, we probe each RL-tuned model with a deliberately simple parameterization: a fixed set of steering vectors added to the block outputs of the frozen base model. On SD3.5-M, these vectors hold 65x fewer parameters than the RL-tuned LoRA (0.29M against 18.8M). We fit them to match the velocity predictions of public RL-tuned checkpoints, with no reward in the objective. Although the vectors are identical for every prompt, token, and sampling seed, they recover 90.0-96.3% of the reward gains of six RL-tuned image models, and 89.8% and 111.9% on two RL-tuned video models. Initialized at zero and trained with online RL, the vectors alone exceed the reward gains of weight-based RL on text rendering (OCR) and human preference (PickScore) on SD3.5-M. A constant shift thus suffices for most of the gain of policy-gradient RL post-training: without new input-dependent transformations, it steers the pretrained generator toward what it can already compute.

新论文 · v1arXiv:2611.26624

PlayCraft:基于智能体游玩体验设计引人入胜的游戏

PlayCraft: Designing Engaging Games from Agent Play Experience

Weihao Cheng

AI 速读 基于摘要

PlayCraft 利用基于视觉的智能体反复游玩游戏并生成详细体验报告,再由 crafting 智能体据此修订游戏,以提升游戏的可掌握性和学习曲线。

cs.AI · cs.CV

查看原文摘要

Recent AI agents can generate playable games, but these games are not necessarily engaging. Mastery is a key source of engagement, yet designing for it requires extensive human play and tuning. We propose PlayCraft, an automated framework that uses a vision-based agent to play games and draws on its detailed play experience to revise them for mastery. Starting from an initial game, PlayCraft alternates between playing and crafting. In the playing stage, a player agent watches the game screen, uses the controls, and pursues the game objective over repeated episodes while retaining memory. After each episode, it reports its progress, outcomes, decisions, and reflections. In the crafting stage, a crafter agent uses these reports to revise the game. It estimates player abilities, predicts performance at different proficiency levels, and compares those predictions with a target learning progression. It diagnoses the game and addresses the gaps by giving players meaningful opportunities to improve through better decisions and execution. We evaluate games in fresh runs with player agents across three intelligence settings, measuring learning gain and learning slope. Compared with the initial games, PlayCraft yields larger learning gains and steeper learning slopes in most games. It also outperforms the baselines on the macro-average of each metric at every intelligence setting.

新论文 · v1arXiv:2611.26623

路径无关的去杠杆规则

Path-Independent Deleveraging Rules

Christoph Schlegel, Akaki Mamageishvili

AI 速读 基于摘要

作者将路径无关的自动去杠杆(ADL)规则刻画为扩展对数-指数族,并分析其在账户拆分免疫、同质性与公平性—平台风险权衡下的结构。

cs.GT · q-fin.RM

查看原文摘要

We characterise path-independent auto-deleveraging (ADL) rules as an extended log-exponential family. Immunity to account splitting, merging and reopening further restrict the class. Homogeneity (essentially) restricts the class to a one-parameter family ordered by both fairness and platform risk. Its split-proof members continuously interpolate between proportional division and water-filling. Among these rules, decreasing the parameter reduces risk at the cost of increasing inequality in how accounts are treated. This suggests selecting the parameter through an ex-ante calibration to a risk bound on historical data to choose a maximally fair rule subject to that bound. A counterfactual replay of Hyperliquid's ADL episode on 10 October 2025 finds that a range of intermediate parameters significantly improves on the observed allocation in both burden dispersion and subsequent risk statistics.

版本更新 · v2arXiv:2602.04417

EMA策略梯度:用EMA锚点和Top-k KL驯服LLM强化学习

EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL

Lunjun Zhang, Jimmy Ba

AI 速读 基于摘要

作者提出用指数移动平均(EMA)锚点替代固定锚点策略,并引入Top-k KL估计器,与GRPO结合后在数学推理和智能体RL任务上取得性能提升。

cs.LG · cs.AI

查看原文摘要

Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to acquire increasingly complex reasoning and agentic behaviors. In this work, we propose two simple techniques to improve policy gradient algorithms for LLMs. First, we replace the fixed anchor policy during RL with an Exponential Moving Average (EMA), similar to a target network in deep Q-learning. Second, we introduce Top-$k$ KL estimator, which allows for flexible interpolation between exact KL and sampled KL. We derive the stability conditions for using EMA anchor; moreover, we show that our Top-$k$ KL estimator yields both unbiased KL values and unbiased gradients at any $k$, while bringing the benefits of exact KL. When combined with GRPO, the two techniques (EMA-PG) lead to a significant performance boost. On math reasoning, it allows R1-distilled Qwen-1.5B to reach 53.9% on OlympiadBench compared to 50.8% by GRPO. On agentic RL domains, with Qwen-3B base, EMA-PG improves GRPO by an average of 35.6% across 7 datasets of Q&A with search engines, including 29.7% $\rightarrow$ 45.8% on HotpotQA, 27.4% $\rightarrow$ 40.5% on 2WikiMultiHopQA. Overall, we show that EMA-PG is a simple, principled, and powerful approach to scaling RL for LLMs. Code: https://github.com/LunjunZhang/ema-pg

新论文 · v1arXiv:2611.26619

TideCache:透明缓存管理与逐层流式传输的高效混合LLM服务

TideCache: Efficient Hybrid LLM Serving with Transparent Cache Management and Layer-Wise Streaming

Jinbin Luo, Xiaozhe Yao, Shang Yang, Zhijian Liu, Song Han, Qinghao Hu

AI 速读 基于摘要

TideCache 通过透明缓存池、缓存流式器和请求调度器,在 CPU-GPU 超级芯片上高效管理混合架构 LLM 的异构缓存,提升服务吞吐并降低延迟。

cs.DC · cs.LG

查看原文摘要

Hybrid architectures have become mainstream among open-weight language models. Their global-attention and bounded-state layers maintain heterogeneous caches whose demands vary with context length and concurrency. We present TideCache, a serving system on CPU--GPU superchips with three components for allocating GPU memory among caches and managing their residency across GPU and host memory. The Transparent Cache Pool redistributes physical pages among cache components behind fixed virtual addresses, preserving cache layouts and backend interfaces. The Cache Streamer uses computation intervals provided by bounded-state layers to prefetch the next global-attention layer's prefix into GPU slots shared across global-attention layers, reducing GPU residency while overlapping layer-wise transfers with computation. Generated KV remains resident. The Request Scheduler selects resident or streamed execution and triggers capacity adjustments according to request size and queue state. Together, they let HBM released by streaming accommodate other cache components and additional requests. Implemented in SGLang and evaluated on GB300 and GH200 across seven model/platform configurations, TideCache completes up to 2.04x as many agent turns, reduces overall P50 per-token latency by 20--59%, and improves agent P50 TTFT by 1.40--3.05x compared with SGLang with HiCache.

新论文 · v1arXiv:2611.26617

一个先验,两种动力学:复用视频扩散Transformer进行自监督潜在动作学习

One Prior, Two Dynamics: Repurposing Video Diffusion Transformers for Self-Supervised Latent Action Learning

Yuxin Jiang, Wenqiang Sun, Jiaqi Li, Yuchao Gu, Lvmin Zhang, Ivor Tsang, Mike Zheng Shou

AI 速读 基于摘要

O²LaF 从同一个预训练视频 DiT 初始化逆动力学和正动力学模型,通过控制信息访问和端到端瓶颈优化,从无标签视频中学习可迁移的潜在动作。

cs.CV · cs.AI · cs.LG · cs.RO

查看原文摘要

Videos reveal how the world changes, but rarely the actions that cause those changes. Latent action learning recovers such supervision from visual transitions, yet often learns the underlying dynamics largely from scratch. We ask whether a pretrained video generator can instead provide the prior for both inverse and forward dynamics. We introduce O$^{2}$LaF, built on a simple principle: one prior, two dynamics. We initialize both models from the same pretrained video DiT and adapt them to their distinct roles: a feed-forward transition encoder with learnable action queries for inverse dynamics, and a causal, action-conditioned video generator for forward dynamics. By controlling information access and optimizing both dynamics end-to-end through a compact bottleneck, O$^{2}$LaF learns transferable actions from unlabeled videos. Across navigation and robotic manipulation, O$^{2}$LaF sets a new state of the art in few-shot action probing and enables stronger zero-shot action transfer across visual contexts and embodiments. Beyond generative video priors, we further extend our framework to predictive representation priors such as V-JEPA2, achieving competitive performance. Our findings suggest a broader paradigm for latent-action learning: repurposing pretrained video models to discover transferable actions and predict their consequences.

新论文 · v1arXiv:2611.26615

ScaleWorld:通过共享预测与细化实现高分辨率世界生成

ScaleWorld: High-Resolution World Generation through Shared Prediction and Refinement

Yansong Qu, Wesker Zheng, Quanjian Song, Zhiyuan Zhang, Xiao Cao, Shengchuan Zhang, Liujuan Cao

AI 速读 基于摘要

ScaleWorld 用一个共享骨干网络在单个因果视频模型中统一低分辨率世界预测与高分辨率细化,从而以更低计算和内存开销生成高分辨率世界视频。

cs.CV

查看原文摘要

High-resolution generation enables video world models to render fine-grained scene structures and textures, but directly generating high-resolution video incurs substantial computational and memory costs. We present ScaleWorld, a causal video model that unifies low-resolution world prediction and high-resolution refinement within a single shared backbone. By refining its own predictions, ScaleWorld produces high-resolution world videos without requiring a separate refinement model. For each video chunk, the shared backbone first completes a low-resolution prediction and then performs one-step high-resolution refinement conditioned on that prediction. To support efficient streaming generation, we maintain separate causal states with a long low-resolution history for prediction and a short high-resolution history for refinement. To address task interference during distillation, we separate specialist optimization from capability consolidation and introduce task-asymmetric on-policy distillation (TA-OPD). This procedure transfers prediction and refinement behaviors from specialized teachers into a shared student through local velocity matching under their respective sampling and history policies. {Extensive experiments demonstrate that ScaleWorld achieves high-quality world generation with improved computational and memory efficiency.

新论文 · v1arXiv:2611.26613

AgentRoboCritic:理解前沿智能体在直接机器人控制中的能力

AgentRoboCritic: Understanding the Capability of Frontier Agents on Direct Robot Control

Yiyang Du, Yuxuan Kuang, Qitao Zhao, Yixuan Wang, Zhanqiu Guo, Yi Xu, Xin Li, Wenbin He 等 10 位作者

AI 速读 基于摘要

作者提出以意图为依据的动作级批评框架 AgentRoboCritic,在12个操作基准上系统分析前沿多模态语言智能体直接输出底层动作控制机器人的能力与失败模式。

cs.RO · cs.CL · cs.CV

查看原文摘要

Frontier multimodal language agents such as GPT-6 Astra have demonstrated strong capabilities in controlling robots directly via low-level numerical actions without high-level primitives. However, existing benchmarks report only episode-level success rates, which show neither how these agents succeed nor where they fail. In this paper, we present a systematic action-level analysis of frontier agents on direct robot control across 12 manipulation benchmarks. We introduce AgentRoboCritic, an intent-grounded critique framework in which the policy agent states a local intent alongside each action, and a critic evaluates the action's outcome and failure mode against this intent. Our action-level analysis demonstrates the promising capabilities of frontier agents on direct robot control, including closed-loop recovery from local execution failures, reliable semantic grounding across diverse scenes, and strong zero-shot manipulation without task-specific adaptation. It also identifies their current limitations, including task-relevant physical execution bottlenecks such as grasping and alignment, and uneven recovery across failure modes. Finally, we validate our critic on a 400-action human-annotated benchmark and release a dataset of 12,844 annotated actions alongside a fine-tuned open-source critic, Muse-Glimmer-30B, whose failure-mode accuracy rises from 32.58% to 74.24%, enabling low-cost action-level analysis.

版本更新 · v3arXiv:2405.01484

设计算法推荐以实现人机互补

Designing Algorithmic Recommendations to Achieve Human-AI Complementarity

Bryce McLaughlin, Jann Spiess

AI 速读 基于摘要

该文用因果推断的潜在结果框架建模推荐算法对人类二元决策的影响,并基于工具变量与单调性假设设计实现人机互补的推荐算法。

cs.HC · cs.LG · econ.EM · stat.ML

查看原文摘要

Algorithms frequently assist, rather than replace, human decision-makers. However, the design and analysis of algorithms often focus on predicting outcomes and do not explicitly model their effect on human decisions. This discrepancy between the design and role of algorithmic assistants becomes particularly concerning in light of empirical evidence that suggests that algorithmic assistants again and again fail to improve human decisions. In this article, we formalize the design of recommendation algorithms that assist human decision-makers without making restrictive ex-ante assumptions about how recommendations affect decisions. We formulate an algorithmic-design problem that leverages the potential-outcomes framework from causal inference to model the effect of recommendations on a human decision-maker's binary treatment choice. Within this model, we make a connection between algorithmic recommendations and instrumental variables. Leveraging this connection, we introduce a monotonicity assumption that leads to an intuitive classification of human responses to the algorithm. Under this assumption, we can express the human's response to algorithmic recommendations in terms of their compliance with the algorithm and the active decision they would take if the algorithm sends no recommendation. We showcase the utility of our framework using an online experiment that simulates a hiring task. We argue that our approach can make sense of the relative performance of different recommendation algorithms in the experiment and can help design solutions that realize human-AI complementarity. Finally, we leverage our approach to derive maximin-optimal recommendation algorithms that can be implemented with machine learning using limited training data.

新论文 · v1arXiv:2611.26611

用语义数据目录弥合 Solid 数据空间中的发现鸿沟

Bridging the Discovery Gap in Solid Dataspaces with a Semantic Data Catalog

Florian Hölken, Alexander Paulus, Tobias Meisen, André Pomp

AI 速读 基于摘要

作者提出一个面向 Solid 的、符合 FAIR 原则的语义数据目录,以缓解多 Solid 服务器去中心化数据空间中的数据发现难题。

cs.DB

查看原文摘要

Dataspaces are an emerging concept to enable secure and controlled data sharing between multiple stakeholders. However, most existing dataspace architectures, such as those based on the concepts of IDSA (International Data Spaces Association) and Gaia-X, are heavily concept-driven and require significant effort to implement, making it difficult to quickly build a functional dataspace. Solid (Social Linked Data) offers a compelling alternative by providing a lighter and more practical approach. However, for Solid to function as a true dataspace, like traditional dataspaces, it must be built in a decentralized manner, i.e., the dataspace must consist of more than a single Solid server. However, this decentralization introduces a key challenge: Data Discovery. Unlike traditional dataspace architectures, which often include predefined components such as data catalogs to facilitate data discovery and access, Solid does not inherently provide such mechanisms. As a result, managing and locating relevant data across multiple Solid servers and pods becomes a significant barrier to usability. To address this gap, we present a FAIR-compliant data catalog for Solid. Our catalog follows the FAIR principles (Findability, Accessibility, Interoperability, and Reusability) by integrating semantic models that describe all available data sources within the Solid ecosystem. This approach enables enhanced data discovery, improves accessibility through standardized metadata, enhances interoperability between different data sources, and promotes data reuse across applications. By bridging this critical gap, our catalog improves the usability of Solid-based dataspaces, making them a viable option for decentralized and open data ecosystems, such as smart city applications.

新论文 · v1arXiv:2611.26609

DiskANN 中束搜索的变体

Variants of Beam Search for DiskANN

Viraj Agrawal, Kirankumar Shiragur

AI 速读 基于摘要

该论文统一并推广了 α-可达图上自适应束搜索(ABS)的近似保证,并设计束预测器在亿级点基准上降低查询延迟。

cs.DS · cs.DB · cs.IR

查看原文摘要

Graph-based data structures such as DiskANN, HNSW, and NSG constitute the state of the art for large-scale approximate nearest-neighbor (ANN) search. Indyk and Xu introduced the notion of $α$-reachable graphs, which include graphs built by DiskANN's slow-preprocessing construction, and proved that greedy search achieves an approximation factor of $\tfrac{α+1}{α-1}$. Independently, Al-Jazzazi et al. proposed adaptive beam search (ABS) with a relaxation parameter $γ> 0$, showing a $\tfrac{2}γ$ approximation on navigable graphs ($α\approx 1$), where greedy search admits no guarantees. In this work, we unify and generalize these results by proving that ABS with parameter $γ$ on $α$-reachable graphs achieves an approximation of $\tfrac{α+1}{α(γ+1)-1}$ for any metric. Moreover, on sorted $α$-reachable graphs (introduced by Gollapudi et al.) under the $\ell_2$ metric, we obtain the tighter bound $\max\bigl(\tfracα{α(γ+1)-1}, \tfrac{α^{2}+1}{α^{2}(γ+1)-1}\bigr)$. Beyond these theoretical results, we design a beam predictor using features inspired by fine-grained analysis of ABS, trained via a constrained objective that minimizes mean distance computations subject to a target recall. On three 100-million-point benchmarks, using graphs built by DiskANN's practical construction, beam predictor lowers mean query latency on SSD-resident indices at matched recall by up to $29.6\%$ relative to classical beam search (CBS). Relative to ABS, it is faster in $11$ of $15$ settings, by up to $6.5\%$, and at most $1.4\%$ slower in the other $4$; at $95\%$ recall, its advantage over ABS grows from $0.8$--$4.2\%$ for $100$ neighbors to $4.6$--$5.6\%$ for $500$ neighbors. In memory, it needs $1.3$--$23.7\%$ fewer distance computations than CBS and $0.0$--$3.9\%$ fewer than ABS.

版本更新 · v2arXiv:2606.12200

个体行为的隐式神经表示

Implicit Neural Representations of Individual Behavior

Andrew Kang, Priya Narasimhan

AI 速读 基于摘要

作者提出Behavioral INR,一种自监督生成模型,将隐式神经表示从视觉迁移到行为,用于从无标签多策略数据中学习策略表示并推断策略身份。

cs.LG · cs.AI

查看原文摘要

We study policy representation learning from unlabeled multi-policy behavioral data. Each episode is generated by a fixed policy, but policy labels are unavailable. This setting appears in robotics play, demonstrations, games, racing, and other datasets where heterogeneous behaviors are mixed without annotations. We introduce Behavioral INR, a self-supervised generative model that adapts implicit neural representations (INRs) from vision to behavior. Instead of mapping coordinates to RGB values, Behavioral INR represents a policy as a state-action function mapping states to subsequent actions. An episode-level latent modulates this function through FiLM layers, yielding a generative prior over policies and allowing policy identity to be inferred without supervision. Because INRs treat each datapoint as samples from an underlying function, the same model naturally accommodates variable episode lengths and different sampling granularities, as in vision INRs with different image resolutions. We also define policy-level out-of-distribution (OOD) shifts along state-distribution and action-distribution axes, which arise when policies overlap in states or actions but are not captured by standard behavioral OOD settings based only on new agents or environments. We evaluate on synthetic Gaussian random field data, MuJoCo demonstrations with controlled OOD splits, and real-world chess, Formula 1 racing, robotics, and Seek-Avoid datasets. Behavioral INR most consistently improves policy identifiability in the hardest continuous state-action settings, especially when longer episodes, more policies, and OOD splits reduce the usefulness of marginal shortcuts; amortized history encoders remain competitive when policy identity can be recovered from symbolic repetition or low-dimensional action statistics.

新论文 · v1arXiv:2611.26607

Bio-PM引导的合成IMU数据生成

Bio-PM-Guided Synthetic IMU Generation

Deepali Singh, Deepesh Parpani, Aviral Gupta

AI 速读 基于摘要

作者在预训练生物信号编码器Bio-PM的表征空间中生成合成IMU数据,并将其用于跨被试人体活动识别增强。

cs.LG

查看原文摘要

Collecting and labeling inertial measurement unit (IMU) data for human activity recognition (HAR) is expensive, and models trained on one group of subjects often fail to generalize to unseen individuals. Even with balanced data, classifiers struggle to distinguish dynamically similar activity classes and benefit from targeted augmentation. We explore whether synthetic IMU data generated in the representation space of a pretrained biosignal encoder, Bio-PM \cite{b1}, can serve as a practical augmentation source. Rather than synthesizing raw signals, we leverage Bio-PM's frozen encoder to convert 10-second IMU windows into token embedding sequences and train class-conditional decoders in this space: (1) an autoregressive transformer decoder that predicts tokens sequentially, and (2) a diffusion decoder that learns the token distribution through a denoising objective. We analyze generation realism through distributional metrics and embedding-space visualizations, evaluate downstream utility through leave-one-subject-out HAR classification, and present a PatchDecoder for approximate raw waveform reconstruction. Our diffusion decoder achieves a Train-on-Synthetic-Test-on-Real (TSTR) macro-F1 of 0.68, demonstrating that generated tokens are realistic enough to train a classifier that transfers to real data. Combining synthetic-token augmentation with a 320-dimensional gravity-aware feature representation raises LOSO macro-F1 from 0.729 to 0.809 over a real-only baseline across 51 subjects on the WISDM benchmark, with statistically significant gains concentrated in the most challenging activity classes. These results demonstrate that high-fidelity generation in a pretrained encoder's representation space is achievable and practically useful for cross-subject HAR augmentation.

新论文 · v1arXiv:2611.26603Apple ML Research

Depth Pro 2:锐利且时序一致的度量单目深度

Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depth

Peiyun Hu, Marko Mihajlovic, Lyndon Duong, Lahav Lipson, Wei Dong, Amaël Delaunoy, Stephan R. Richter, Vladlen Koltun

AI 速读 基于摘要

Depth Pro 2 用一个可扩展的单一网络同时处理图像与视频,在原生分辨率下预测兼具度量准确、边界锐利与时序一致的稠密深度。

cs.CV · cs.LG

查看原文摘要

We present Depth Pro 2, an approach to estimating dense metric depth for images and video at full resolution. By analyzing prior methods for monocular depth estimation, we find that they commonly trade off temporal consistency and boundary sharpness: multi-frame methods favor consistency, single-frame methods favor sharpness. To overcome this trade-off, we train a single, scalable network that processes both images and video and predicts depth maps at native resolution. Depth Pro 2 produces depth maps that are metrically accurate, sharp, and temporally consistent all at once, outperforming prior work in all of these dimensions. We release a family of models that define a new Pareto frontier in terms of metric accuracy, sharpness, temporal consistency, and runtime. We release code and weights at https://apple-aiml-research.github.io/ml-depth-pro-2/

版本更新 · v2arXiv:2611.16843

捷径还是记忆?重新审视大语言模型在自然语言理解中的数据损坏实验

Shortcuts or Memorisation? Revisiting Data Corruption in Natural Language Understanding with Large Language Models

Aarne Talman, Stergios Chatzikyriakidis

AI 速读 基于摘要

作者通过扰动实验和污染指标分析,发现大语言模型在熟悉的NLI基准上的鲁棒性反映的是数据集捷径而非记忆,且与预训练暴露无关。

cs.CL

查看原文摘要

Pre-trained encoders fine-tuned on natural language inference (NLI) and other language understanding tasks keep much of their accuracy after the input is perturbed, e.g. by removing all nouns or shuffling the words. Does the same hold for large language models (LLMs), and if so, is it because they have seen the benchmarks during pre-training? In this paper we revisit these perturbation experiments with eight LLMs alongside fine-tuned encoders on GLUE and the three rounds of ANLI. Regardless of model size, every system that answers directly retains 36-72% of its above-chance performance without nouns on MNLI compared to only 14-29% on ANLI. Only a model that reasons before answering departs from this pattern. We also check contamination indicators (including exact $n$-gram counts in the public pre-training data of two of the models) and find no link between exposure and robustness. Our strongest evidence comes from 368 new, human-validated items that none of the models can have seen. All eight LLMs keep more of their performance without nouns on items written in MNLI's style than on items written without its cues. When the perturbation instead removes the function words carrying such cues, this advantage reverses. In light of these results, we argue that robustness to perturbation on familiar NLI benchmarks reflects dataset shortcuts rather than memorisation, and tells us more about the benchmark than about the model.

新论文 · v1arXiv:2611.26602

拟阵杯问题的一个高效算法

An Efficient Algorithm for Matroid Cups

Stephen Arndt, Benjamin Moseley, Kirk Pruhs

AI 速读 基于摘要

作者为拟阵杯(matroid cups)问题设计了一个多项式时间算法,并达到 O(1) 差异度。

cs.DS

查看原文摘要

We design a polynomial-time algorithm for matroid cups with $O(1)$ discrepancy. Our matroid cups algorithm design consists of a sequence of reductions to simpler instances, culminating in $O(n)$ instances of matroid cups where the matroid has rank 1.

新论文 · v1arXiv:2611.26601

SoK:评估LLM在软件漏洞研究中能力的演进

SoK: Assessing the Evolution of LLM Capability in Software Vulnerability Research

Amine Lbath, Manan Suri, Aurelien Delaitre, Vadim Okun, Massih-Reza Amini, Dinesh Manocha

AI 速读 基于摘要

该论文提出一个基于自动驾驶分级思想的自主性评级框架,系统化梳理LLM在漏洞发现、验证与修补方面的证据,并分析其能力演进对公开漏洞记录的影响。

cs.CR · cs.AI · cs.SE

查看原文摘要

LLM-based agents are becoming increasingly capable at discovering, validating and patching vulnerabilities in real software, and vendors and researchers report that this is already changing how vulnerabilities are found and fixed. These claims, however, are scattered across papers, vendor reports and disclosures and are rarely comparable. We introduce a framework that rates these capabilities on an autonomy scale modeled on the levels of driving automation, and qualifies each claim by its correctness, its availability and the strength of its evidence. We use this framework to systematize the published evidence on LLM capability in vulnerability research. We find that agents discovered, validated, and patched vulnerabilities in real-world software without human intervention before the restricted frontier models of 2026, and that open-weight models subsequently attained comparable autonomy for discovery and validation. We then measure the consequences of evolving LLM security capabilities in a decade of public vulnerability records, advisories and exploitation data. In 2026 the number of disclosed vulnerabilities more than doubled, with an increasing share rated critical or high, and severe bugs that had survived a decade or more in widely used code were reported several times more often than before. Yet the time between the stages of a vulnerability's life, from report to fix and from disclosure to attack, has not shifted noticeably so far. We grade the mitigations proposed in the literature with an explicit rubric and draw guidance for each group of stakeholders from the best-supported ones.

新论文 · v1arXiv:2611.26600

机器人中基于互补性的接触模型教程

A Tutorial on Complementarity-Based Contact Models for Robotics

Onur Beker, A. René Geist, Michael Posa, Marc Toussaint, Justin Carpentier, Georg Martius

AI 速读 基于摘要

本教程系统讲解基于锥互补性的刚体接触建模、求解方法及其在机器人中的应用,填补了机器人领域自包含教学材料的空白。

cs.RO · cs.GR · math.OC

查看原文摘要

Simulating rigid-body dynamics with contact is fundamental to robotics, from motion synthesis and control to mechanism design. Many widely used simulators rely on cone complementarity formulations, whose physical assumptions and numerical solution require substantial background. While excellent surveys, monographs, and course notes exist, they mostly address computational mechanics or computer graphics or document a single simulator. To the best of our knowledge, a self-contained pedagogical treatment for robotics, bringing these formulations and their solvers together with complete derivations and a unified notation, does not yet exist. This tutorial addresses this gap by connecting rigid-body dynamics, conic optimization, and frictional contact. In particular, we explain how complementarity conditions encode non-penetration and frictional dissipation, determining separation, sticking, and sliding without prescribed contact modes. We distinguish equivalent transcriptions from convex relaxations, showing how the latter can introduce artifacts such as lift-off and creep. We examine the existence and uniqueness of motion and contact forces, including the solver's role in selecting among multiple solutions. We then compare first-order and Newton-based methods, explain regularization and proximal strategies, and discuss trade-offs between computational cost, robustness, and physical fidelity. Connections to widely used simulators, optimal control, and differentiable simulation help readers interpret simulation results, choose suitable formulations and solvers, and develop their own contact dynamics routines.

新论文 · v1arXiv:2611.26598

通过蒸馏预言机教师实现主动特征获取

Active Feature Acquisition by Distilling an Oracle Teacher

Yang Meng, Zixin Ding, Robert L. Grossman, Yuxin Chen

AI 速读 基于摘要

作者提出 OracleImitator,在训练时用标签与未观测特征值构造一个闭式预言机教师来排序候选特征,再通过软目标模仿将其蒸馏为可部署的主动特征获取策略。

cs.LG · cs.AI

查看原文摘要

Acquiring every feature of an instance is often costly: a measurement can carry a monetary price, a time delay, or a privacy cost. Active Feature Acquisition (AFA) addresses this by learning a policy that decides, per instance, which features to acquire under a budget. Existing AFA methods train this policy by optimizing a self-constructed utility target rather than distilling an explicit teacher. We construct this teacher explicitly. At training time the label and the unobserved feature values are available, and together they determine the teacher in closed form: an oracle that ranks every candidate by its effect on the downstream predictor's error. OracleImitator distills this ranking into a deployable policy by soft-target imitation. Across multimodal medical diagnosis and the AFABench benchmark, OracleImitator matches or outperforms existing AFA methods across the budget range, recovering 90% of the attainable accuracy gain at under a quarter of the acquisition cost. Because the teacher is an explicit algorithmic object rather than an implicit optimization target, we can also measure directly how much of its ranking is recoverable by a policy restricted to what is visible at deployment.

版本更新 · v2arXiv:2610.01054

用任务算子刻画上下文学习动态

Capturing In-Context Learning Dynamics with Task Operators

Guangzhi Xiong, Zhenghao He, Bohan Liu, Sanchit Sinha, Wenqian Ye, Aidong Zhang

AI 速读 基于摘要

作者提出任务算子(Task Operator),把上下文学习(ICL)中注意力头的仿射变换参数提取为对注意力输出投影的解析更新,从而在无需完整示例上下文的情况下近似 ICL 效果。

cs.CL · cs.AI · cs.LG

查看原文摘要

In-context learning (ICL) enables language models to perform new tasks from demonstrations without weight updates. However, every ICL inference requires processing the full set of examples, resulting in inefficient deployments, and how ICL works mechanistically is not fully understood. Prior work compresses ICL into fixed activation vectors extracted from specific layers or positions, but these input-independent interventions fail on complex tasks where the output depends on fine-grained interactions with the input. By analyzing the ICL forward pass, we show that each attention head's output is an affine transformation of its context-masked counterpart, and that the parameters of this transformation are empirically stable across samples for a given task. Building on this, we introduce Task Operator (TO), which replays this transformation as an analytically derived update to the attention output projection. Across lexical, algorithmic, and reasoning tasks, TO achieves the best overall performance among prior methods and substantially narrows the gap between zero-shot inference and ICL. We further show that the extracted knowledge concentrates in a task-specific sparse circuit across layers and positions, and that averaging operators from disjoint demonstration batches enables effective many-shot scaling without expanding the context window. Our code is available at https://github.com/gzxiong/task_operator.

新论文 · v1arXiv:2611.26596

PGX:面向长时程人形机器人移动操作的可物理落地执行框架

PGX: Physically Grounded Execution for Long-Horizon Humanoid Loco-Manipulation

Kai Lu, Chenyang Ma, Ioannis Havoutis

AI 速读 基于摘要

PGX 将长时程人形移动操作中的时序与精度控制交给两个无需训练的经典组件,让 VLA 模型专注于各阶段的技能动态。

cs.RO · cs.AI

查看原文摘要

Robotic vision-language-action (VLA) models can execute diverse individual manipulation skills, yet they still struggle with long-horizon loco-manipulation tasks, where temporal structure, skills, and precision are tightly coupled within a monolithic model. We propose Physically Grounded Execution (PGX), a framework that offloads temporal and precision control to two classical training-free components, allowing the VLA to focus on stage-specific skill dynamics. PGX decomposes long-horizon loco-manipulation into three layers: (i) a predicate-based state machine governs task progression, using physical predicates to gate phase transitions, trigger recovery, and coordinate navigation and waiting. Shared predicate semantics connect offline demonstration segmentation, online execution, and stage-wise evaluation; (ii) VLA skills operate within active manipulation phases, with flat or stage-trained models concentrating on task-relevant actions; and (iii) world-coordinate locking (WCL) maintains spatial consistency through base station keeping, object-relative positioning, and world-anchored contact targets. We demonstrate the effectiveness of PGX with extensive experiments conducted on three simulated tasks and one real-world task using a Unitree G1 humanoid robot for long-horizon loco-manipulation, showing improvements in stage progression and task success rates. Project page is available at: https://kl-research.github.io/pgx

新论文 · v1arXiv:2611.26595

Coda-DaVinci:用代码到视频重新构想视频生成

Coda-DaVinci: Reimagining Video Generation with Code2Video

Yiyan Ji, Qixun Wang, Yang Shi, Zhuoran Zhang, Yifan Xu, Tengfei Liu, Yuqi Tang, Xiaohan Zhang 等 23 位作者

AI 速读 基于摘要

通过受控实验揭示Code2Video中代理粒度、物理模拟和提示的权衡,并提出任务自适应多智能体框架Coda-DaVinci以提升视频生成质量。

cs.CV

查看原文摘要

Code2Video uses agent-authored 3D proxies to guide video generation, enabling explicit control over structure and dynamics. However, how to construct proxies and prompts for optimal downstream quality remains underexplored, as do the capabilities and limitations of this paradigm. Through controlled experiments and blinded human evaluation, we study proxy granularity, physics simulation, and prompting. The results reveal task-dependent trade-offs: coarse proxies favor natural motion, while medium-grained proxies favor consistency. Physics simulation and proxy-aligned prompting further improve average quality. Guided by these findings, we introduce Coda-DaVinci, a task-adaptive agentic framework for Code2Video generation that selects between proxy-guided and direct generation, adapts modeling granularity to each entity, and coordinates simulation with proxy-grounded prompting. Its multi-agent harness preserves scene assets and guides repairs through visual inspection and independent review. Experiments demonstrate leading instruction following on VTR and scene consistency on R2M, improved physical plausibility over direct generation, and higher visual realism than the compared Code2Video baselines. Long-video evaluations further show gains in event structure and consistency across successive interactions, while revealing limitations in transition stability and adherence to scene settings.

新论文 · v1arXiv:2611.26592

实现可靠性 vs. 总体可靠性:相关推理下任意时间有效的自一致性认证

Realized versus Population Reliability: Anytime-Valid Self-Consistency Certification under Correlated Reasoning

Terence D. Agbeyegbe, Toneukarin G. Agbeyegbe

AI 速读 基于摘要

论文指出自一致性认证中样本独立假设在相关推理下失效,并区分实现零假设与总体零假设,提出提示级 e-process 恢复总体有效性。

stat.ME · cs.AI · cs.LG

查看原文摘要

Self-consistency certification treats repeated sampling from a language model as sequential evidence accumulation and stops when an anytime-valid e-process crosses a threshold, guaranteeing finite-sample Type I error control by Ville's inequality. Prior constructions assume sampled rollouts are conditionally independent. We show this assumption fails in practice: reasoning streams are positively correlated through shared reasoning prefixes or across-prompt heterogeneity, changing not merely certificate efficiency but the hypothesis certified. Modeling dependence via a per-unit latent state (the random-effects / intraclass-correlation structure) induces exchangeable, equi-correlated increments with correlation $ρ$. Correlation splits the single null into a realized null about the drawn belief and a population null about average model behavior, which coincide only when $ρ=0$. We show: (i) the standard betting e-process remains anytime-valid for the realized null, not the population null; (ii) read as a population-null test, a suitable mixture has asymptotic crossing probability at least $π=P(μ(Z)>0)$, potentially exceeding nominal $ε$; (iii) the within-unit mean's effective sample size saturates at $1/ρ$, so extra within-unit rollouts cannot restore population validity; and (iv) a prompt-level e-process restores population validity, with optimal allocation at one rollout per prompt under a pure rollout budget. Simulations and Claude Haiku 4.5 rollouts confirm this regime dependence: on GSM8K ($\hatρ=0.435$, $\hatθ=+0.96$) the gap is dormant, whereas on AIME ($\hatρ=0.480$, $\hatθ=-0.15$) the single-unit rule crosses on 24% of prompts at nominal $ε=0.05$, while the prompt-level procedure declines (0.00). This correctness result identifies which reliability claim an anytime-valid certificate actually supports under dependence.

版本更新 · v2arXiv:2605.20158

重新审视大型视觉语言模型在胸部X射线推理中的视觉归因

Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language Models

Guangzhi Xiong, Qiao Jin, Sanchit Sinha, Zhiyong Lu, Aidong Zhang

AI 速读 基于摘要

作者通过因果评估框架发现现有视觉归因方法常无法识别LVLM在胸片推理中使用的证据,并提出基于概念的MedFocus方法以改善归因。

cs.CV · cs.AI · cs.CL

查看原文摘要

Large Vision Language Models (LVLMs) show promise in medical applications, but their inability to faithfully ground responses in visual evidence raises serious concerns about clinical trustworthiness. While visual attribution methods are widely used to explain LVLM predictions, whether these explanations actually reflect the visual evidence underlying the model's decision is largely unverified, since ground-truth annotations for internal model reasoning are typically unavailable. We address this question for chest X-ray (CXR) reasoning by developing a causal evaluation framework that retains only CXR-VQA samples for which the expert-annotated region is verified, via counterfactual editing, to be causally responsible for the model's prediction. Using this framework across 11 attribution methods, six open-source LVLMs, and two output modes (direct answer and step-by-step reasoning), we find that existing attribution methods often fail to identify the evidence used by LVLMs. To address this failure, we propose MedFocus, a concept-based attribution method that localizes clinically meaningful anatomical regions via unbalanced optimal transport and measures their causal effect on model outputs through targeted interventions. MedFocus produces spatial, concept-level, and token-level attributions and substantially outperforms prior methods, taking a step toward more trustworthy attribution for medical LVLMs. Our data and code are available at https://github.com/gzxiong/medfocus/.

新论文 · v1arXiv:2611.26590

探究视觉语言模型中的“意识”心智:选择性访问与全局工作空间

Probing the "Conscious" Mind: Selective Access and Global Workspace in Vision-Language Models

Jiahao Huang, Jun Wang

AI 速读 基于摘要

作者提出多模态概念透镜(MC-Lens),在视觉语言模型中检验全局工作空间理论所描述的概念选择性访问与下游计算参与。

cs.AI · cs.CV · cs.LG

查看原文摘要

Vision-language models (VLMs) integrate visual and textual information, but their outputs do not reveal internal concept representations. Global workspace theory (GWT) proposes that information is selected from parallel brain processes, integrated in a shared workspace, and made available to specialised processes. We introduce the Multimodal Concept Lens (MC-Lens), a multimodal Jacobian lens, to study these functions in VLM concept processing. Its vision encoder and language decoder lenses map intermediate states to a shared semantic space defined by the decoder's output vocabulary to compare concept accessibility across modalities. MC-Lens supports internal concept interventions to examine the role of accessed concepts in downstream computation. (i) Accessibility and selective access. Multimodal concept information is readable in intermediate states and selectively accessible as tasks require. We extend "readout carriers" from one name token to a token set to better capture and express concept information and support counterfactual experiments. (ii) Concepts in downstream computation. Counterfactual experiments show that accessed concept information participates in downstream computation and reasoning. (iii) Development of cross-modal alignment and selective access. We develop two J-space metrics tracking the development of cross-modal concept alignment more clearly than hidden state cosine in controlled VLM training. The experiment also shows that reliable selective access develops later than concept accessibility. (iv) Shared functions across models. Across VLM families and sizes, we find shared patterns of concept accessibility, query-dependent selectivity and cross-task intervention effects despite differences in internal organisation. These findings offer an experimental basis to study GWT in multimodal artificial systems and how it can guide cross-modal alignment improvements.

新论文 · v1arXiv:2611.26588

验证验证器:面向逃逸UVM记分板的缺陷的、以规范为依据的LLM交叉检查

Verify the Verifier: Specification-Grounded LLM Cross-Checking for Bugs That Escape UVM Scoreboards

Ana E. Sanchez Villalobos, Michael D. Quinn, Aakash Tyagi, Minh D. Luu, David Kebo Houngninou

AI 速读 基于摘要

提出Verify the Verifier框架,用基于LLM的异常交叉检查器将通过的回归波形轨迹与规范对照,识别能逃过UVM记分板的规范违背型缺陷。

cs.SE · cs.AI · cs.AR

查看原文摘要

A passing UVM regression shows the design agrees with the reference model on what the scoreboard checks, not that it meets the specification. Bugs that pass every test yet violate the specification, termed scoreboard escapes, survive mature testbenches. We present Verify the Verifier, to our knowledge the first framework whose LLM-based Anomaly Cross-Checker examines a passing regression's traces against the specification. Of 564 bugs inserted into four OpenTitan IPs, 68 are candidate scoreboard escapes: non-equivalent, exercised by the tests, yet passing. The framework confirmed 41 as scoreboard escapes with assertions failing on the buggy design and proven on the original.

新论文 · v1arXiv:2611.26586

ProtoDiffusion:面向多层图像的逐层令牌生成建模

ProtoDiffusion: Token-per-Layer Generative Modeling of Multi-Layer Images

Adrià Ciurana Lanau, Harleen Hanspal, Lusine Abrahamyan, Emilio Tylson Baixauli, Yu Cao, Danai Triantafyllidou, Stefano Zorzi, Gustavo Zanoni Felipe 等 11 位作者

AI 速读 基于摘要

ProtoDiffusion 提出一种基于共享空间原型和每层候选向量的潜在扩散框架,以 HW+N 个令牌表示 N 层 RGBA 设计,支持图像到设计和文本到设计。

cs.AI

查看原文摘要

Graphic designs are ordered compositions of RGBA layers whose separation enables selection, movement, and reuse. Existing layered models represent each layer with a full-canvas or region-sized spatial latent grid, so representation size grows with the cumulative spatial extent of the layers. We present ProtoDiffusion, a latent-diffusion framework built on ProtoVAE, a multi-layer variational autoencoder that encodes a design into one shared spatial prototype and one candidate vector per layer. Each candidate conditions a shared decoder to reconstruct its corresponding RGBA layer. For $N$ layers, the representation contains $HW+N$ tokens before backbone-specific packing, compared with $NHW$ for full-grid-per-layer representations. ProtoDiffusion jointly denoises the prototype and a fixed set of candidate slots, conditioned on an image or text, with bounding boxes as optional layout guidance. The model leaves unneeded slots empty and determines the number of layers and, in absence of boxes, their layout, requiring neither as input. The same architecture supports both image-to-design and text-to-design. ProtoVAE achieves high-fidelity reconstruction from its compact shared latent representation, reaching 40.43 dB PSNR on layer crops. On the LayerD evaluation split, image-to-design achieves RGB L1 scores of 0.040 with bounding boxes and 0.057 without, with box-guided alpha soft IoU (0.850) comparable to the strongest fine-tuned baseline (0.871). On merged images, text-to-design reaches 66.41 FID versus 86.84 for FLUX.2 [klein], achieves a 0.860 text-accuracy score, and runs $19.1\times$ faster than the same-backbone generation-then-decomposition cascade.

版本更新 · v2arXiv:2611.18372

视觉-语言-动作模型:设计、训练与部署的全生命周期综述

Vision-Language-Action Models: A Life-Cycle Survey of Design, Training and Deployment

Suvarna Kadam, Soran Parsa

AI 速读 基于摘要

该综述按设计、训练、部署的生命周期梳理89项VLA研究,比较22个模型,并总结数据、模型规模与通用化三方面趋势。

cs.RO · cs.AI · cs.ET · cs.LG

查看原文摘要

Vision-language-action (VLA) models adapt web-pretrained vision-language models to output robot actions, so that web knowledge carries over to physical control. In under four years the field has grown from RT-2, the first VLA, to open models that fine-tune on a single consumer GPU and proprietary generalists that clean unseen homes. VLA research joins robotics, computer vision and language modelling, so this survey is written for researchers and practitioners from each of these fields. It reviews 89 works from December 2022 to October 2026, mainly on manipulation and navigation, plus humanoid control, world-action models and evaluation. Seven design axes follow a VLA's life cycle: model design (inputs and memory, architecture, action output, intermediate predictions), training (pretraining data, post-training) and deployment (real-time execution). We compare 22 models on these axes, with their training data, model size, inference speed and hardware. Three trends emerge. (i) Training data has broadened beyond teleoperated robot data (about 10,000 hours for $π_0$) to community-collected episodes and egocentric human video (20,000 hours for GR00T N1.7). (ii) Model sizes have split into two groups: most recent models have 3-7 billion parameters; a new group under one billion runs on consumer GPUs. (iii) Generalist VLAs handling both manipulation and navigation are emerging, such as UniVLA and Qwen-VLA. We also compare VLAs with world-action models, which predict future observations as well as actions, and review evidence that some VLAs with near-perfect benchmark scores fail after small scene changes. A practitioner's guide gives a default for each design decision, and a glossary supports readers new to the field.

版本更新 · v2arXiv:2605.06342

别失去焦点:通过键正交投影的激活引导

Don't Lose Focus: Activation Steering via Key-Orthogonal Projections

Haoyan Luo, Mateo Espinosa Zarlenga, Mateja Jamnik

AI 速读 基于摘要

作者提出SKOP方法,通过键正交投影约束激活引导对注意力匹配的干扰,在保持引导效果的同时大幅减少推理与检索性能退化。

cs.CL

查看原文摘要

Activation steering controls LLM behaviour towards target behaviour by intervening in internal representations, yet it often degrades reasoning and retrieval performance. We argue that a primary cause of this trade-off is attention rerouting: steering vectors alter query-key matching, shifting attention away from contextually important tokens toward less informative ones. To address this, we propose Steering via Key-Orthogonal Projections (SKOP), a steering method that constrains harmful attention rerouting without eliminating steering efficacy. SKOP achieves this by preserving attention patterns on a small set of focus tokens the model relies on for reasoning and retrieval, while allowing redistribution among less critical tail tokens. Across multiple steering benchmarks, we show that SKOP achieves the best joint steering-utility trade-off, reducing utility degradation by 5-7x while retaining over 95% of vanilla steering efficacy. Our results further suggest that, in long-context retrieval settings where vanilla steering approaches are ineffective, SKOP can maintain robust performance by avoiding attention rerouting.