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：2026-11-14 01:47 · 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 2026-11-13 01:48 — 2026-11-14 01:48（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：2026-11-14 01:47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 17,362 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-14 01:46（北京时间）
新论文 · v1arXiv:2611.07272

VREgo: Consumer VR Headsets for Learning Robot Manipulation from Egocentric Demonstrations

Liuchuan Yu

原文摘要

VREgo trains manipulation policies from demonstrations recorded on consumer VR headsets; we instantiate it with EgoKit on one such headset, the PICO 4 Ultra. On-device head and hand tracking and stereo object localisation allow the operator to begin a demonstration at the table. We adapt HumanEgo's preprocessing to estimate grasp thresholds per recording, update object positions after release, and propagate segmentation masks between keyframes. We evaluate policies in simulation on two tabletop tasks recorded by one operator. For cube placement, we compare PICO and Project Aria recordings of the same 41 layouts. With 40 training demonstrations, the PICO policies placed the cube on the tray in 67, 74, and 60 of 100 evaluation layouts across three training seeds. The corresponding Aria results were 73, 78, and 0. For a two-stage stacking task recorded with the PICO alone, the baseline placed the block on the tray in 94 of 100 layouts and met the end-of-episode criterion for both placements in two. In one diagnostic episode, repeated replanning deferred release beyond the eight executed steps. Demonstration replays also showed that the open gripper could displace the cube before grasping it. After adapting the training trajectories and adding task-specific execution rules that use simulator object positions, the system met both placement criteria in 93.8% of episodes across four evaluation noise seeds. The same 100 layouts informed rule development and evaluation. VREgo is available at https://vrego.chuange.org/.

cs.RO · cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.10938

ELF: Embedded Language Flows

Keya Hu, Linlu Qiu, Yiyang Lu, Hanhong Zhao, Tianhong Li, Yoon Kim, Jacob Andreas, Kaiming He

原文摘要

Diffusion and flow-based models have become the de facto approaches for generating continuous data, e.g., in domains such as images and videos. Their success has attracted growing interest in applying them to language modeling. Unlike their image-domain counterparts, today's leading diffusion language models (DLMs) primarily operate over discrete tokens. In this paper, we show that continuous DLMs can be made effective with minimal adaptation to the discrete domain. We propose Embedded Language Flows (ELF), a class of diffusion models in continuous embedding space based on continuous-time Flow Matching. Unlike existing DLMs, ELF predominantly stays within the continuous embedding space until the final time step, where it maps to discrete tokens using a shared-weight network. This formulation makes it straightforward to adapt established techniques from image-domain diffusion models, e.g., classifier-free guidance (CFG). Experiments show that ELF substantially outperforms leading discrete and continuous DLMs, achieving better generation quality with fewer sampling steps. These results suggest that ELF offers a promising path toward effective continuous DLMs.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07268

CRISP: Constraint-Resolved Interactions between Subsystems for Predictive Whole-Body Cooperation

Dario Valenzuela, Jeeseop Kim

原文摘要

This paper presents a layered control framework that recasts high-dimensional system dynamics as a composition of dynamically interconnected subsystems, with dynamic dual-arm manipulation on the humanoid serving as a representative application. The humanoid is decomposed into a single rigid body (SRB) representing the torso and floating-base dynamic models representing the articulated arms and lower-body. The rigid connections between arm and torso and the closed kinematic chain formed between the end-effectors during cooperative manipulation are represented as holonomic constraints. The corresponding Lagrange multipliers parametrize the interaction wrenches transmitted at the shoulders and between the end-effectors. The high-level nonlinear model predictive control (NMPC) jointly optimizes the subsystem state trajectories, arm torques, ground reaction forces (GRFs), and interaction wrenches, enabling online wrench design and optimization while preserving the dynamic coupling among the independently modeled subsystems. The optimized arm torques are applied directly for cooperative dual-arm manipulation, whereas the prescribed GRFs are mapped to lower-body joint torque for whole-body coordination. We validate the proposed framework through numerical simulations and hardware experiments on a G1 humanoid robot. The results demonstrate optimal interaction wrenches consistent with simulated contact measurement, cooperative dual-arm trajectory tracking, and stable whole-body coordination while executing the NMPC in online manner.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07265

How Deep is the Signal? Time-Context up to 30 Years for Colorectal Cancer Prediction in a Primary-Care EHR Model

Achille Raviez, Lan Wang, Brendan Delaney

原文摘要

EHR foundation models read medical events within a fixed context window, and long context has so far been measured only in tokens. How far back in time a model must look to capture the earliest predictive signal is unknown. We introduce time-context, the calendar lookback window before the prediction point, and provide, to our knowledge, the first systematic evaluation of decade-scale time-context for an EHR foundation model. We pretrained a decoder-only transformer (34.6M parameters) on 1.4B coded events from 3.6M primary-care patients in North West London and fine-tuned it to predict incident colorectal cancer under a 12-month pre-diagnostic buffer. A frozen cohort of 1,008 cases and 9,582 matched controls, all registered for at least 30 years, was evaluated at 15 nested lookback windows from 2 to 30 years, so that every truncation is compared within the same patients. Discrimination rose from an AUROC of 0.551 at 2 years to 0.590 at 18 years, then plateaued, with about 80% of the gain reached within 10 years; an XGBoost baseline converged to the same level (peak AUROC 0.589). A simulation further suggests that rotary position embeddings (RoPE) over elapsed time alias beyond about 20 years at the default base frequency, motivating a retuned $θ$. Time-context is a measurable design axis for clinical prediction models, distinct from token-context, and should be reported.

cs.LG · cs.AI · q-bio.QM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07263

HyFlash: A Prefix-Memory Prior for On-Device Speculative Decoding

Jongwoo Ko, Pashmina Cameron

原文摘要

Parallel block drafting accelerates speculative decoding by predicting multiple future positions in a single backbone pass, but on-device deployment constrains both drafter capacity and context storage. Under tight memory budgets, drafters must model long-range dependencies and fine-grained draft-position interactions without the growing KV-cache overhead of full-context attention. We propose HyFlash, a compact parallel drafter that introduces a prefix-memory prior to separate long-range context modeling from fine-grained draft-position interactions with limited capacity. Local attention captures recent context and draft-position interactions, while recurrent memory compresses historical target features into fixed-size states. This inductive bias enables effective local and long-range modeling with bounded draft-side memory. Experiments show that HyFlash achieves higher acceptance than full-context attention with substantially less KV storage and with larger gains for shallow drafters and long contexts.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.01739

Fixed-point neural samplers on discrete spaces

Jiajun He, Denis Blessing, Mouyang Cheng, Yuanqi Du, Carles Domingo-Enrich

原文摘要

Sampling from discrete, unnormalized distributions without access to data is a challenging problem. Neural samplers offer a promising approach by training generative models from density evaluations directly. However, existing discrete neural samplers are prone to mode collapse, come without convergence guarantees when trained via fixed-point iterations, and are often tied to a specific reference process such as masked or uniform diffusion. In this work, we introduce Discrete Gibbs Iterative Neural Sampler, a fixed-point neural sampler that addresses these limitations, enabling efficient, scalable learning, substantially reducing mode collapse in practice. Besides masked diffusion, the framework also extends to transport between arbitrary distributions. DIG-IN mitigates mode collapse on Ising and Potts models and scales to amortized sampling with up to 2,500 sites, recovers alloy phase diagrams, and learns to sample biomolecular Boltzmann distributions from energy alone. Its transport formulation accurately estimates solvation and conformational free energies. As a maximum-entropy RL policy, DIG-IN outperforms the Gaussian, diffusion, and flow policies we compare against across 20 continuous-control tasks.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07261

An Empirical Study of Reinforcement Learning for Keypoint Positioning of Deformable Linear Objects

Vinay Rodrigues, Sara Zeynalpour, Gokhan Solak, Sebastian Hjorth, Arash Ajoudani

原文摘要

Deformable linear object (DLO) manipulation is challenging because high-dimensional configurations, nonlinear contact dynamics, and diverse material and geometric properties produce a broad range of object responses that are both difficult to model and data-intensive to learn. This work studies reinforcement learning for planar manipulation of a one-end-grasped DLO, focusing on training efficiency, observation design, robustness, and zero-shot sim-to-real transfer. We compare three Proximal Policy Optimization training stacks and find that the GPU-parallel MuJoCo Playground stack enables faster convergence and more consistent performance than CPU-based alternatives under the same wall-clock budget. Relative keypoint observations and an asymmetric actor-critic formulation further improve learning efficiency. Policies trained with observation noise, delay, domain randomization, and disturbances achieve simulation success rates of 96.4% for single-point tracking, 98.0% for disturbance recovery, and 88.8% for two-point tracking. Using markerless RGB-D keypoint estimation, the policies transfer without real-world fine-tuning, succeeding in 9/10, 10/10, and 8/10 physical trials, respectively.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2505.22252

B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data

Magdalena Proszewska, Tomasz Danel, Antoni Antoszek, Dawid Rymarczyk

原文摘要

Understanding the reasoning behind deep learning model predictions is crucial in cheminformatics and drug discovery, where molecular design determines their properties. However, current evaluation frameworks for Explainable AI (XAI) in this domain often rely on artificial datasets or simplified tasks, employing data-derived metrics that fail to capture the complexity of real-world scenarios and lack a direct link to explanation faithfulness. To address this, we introduce B-XAIC, a novel benchmark constructed from real-world molecular data and diverse tasks with known ground-truth rationales for assigned labels. Through a comprehensive evaluation using B-XAIC, we reveal limitations of existing XAI methods for Graph Neural Networks (GNNs) in the molecular domain. This benchmark provides a valuable resource for gaining deeper insights into the faithfulness of XAI, facilitating the development of more reliable and interpretable models.

cs.LG · cs.CE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.26466

Soft Token Alignment for Cross-Lingual Reasoning

Jiayi He, Jungsoo Park, Wei Xu, Alan Ritter

原文摘要

Multilingual large language models often produce inconsistent reasoning and answers for semantically equivalent prompts in different languages. Prior work suggests that intermediate representations can be relatively language-agnostic, but generation becomes increasingly language-specific as models commit to discrete output tokens. This is problematic because language-specific lexical choices can cause semantically equivalent reasoning paths to diverge across languages. These divergences motivate searching for a cross-lingual alignment signal that is less tied to any single vocabulary item or script. We propose SOLAR, an auxiliary objective for supervised fine-tuning that aligns soft-token representations across languages, using English as a pivot. Soft tokens are probability-weighted mixtures over the vocabulary embeddings, yielding continuous representations that can aggregate information from semantically related tokens across languages. We then align each non-English soft-token summary to its English counterpart in the shared embedding space. Across four multilingual reasoning benchmarks, SOLAR improves accuracy by up to +17.7 points over the base model and +3.8 over standard supervised fine-tuning, with the largest gains on low-resource languages. SOLAR also strengthens final-layer cross-lingual similarity and substantially reduces language-cluster separability, suggesting that aligning soft-token representations helps preserve shared semantic structure during multilingual reasoning.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07258

Reweighting is not Harmless: Understanding the Role of Dataset Characteristics

Amalia Ionescu, Jose G. Hernandez, Emily F. Wong, Anil K. Saini, Jason H. Moore, Tiffani J. Bright

原文摘要

Reweighting is a widely used pre-processing method for promoting discrimination-free model behavior by assigning different weights to data points during model training. While it is often credited with improving fairness, particularly by mitigating systematic underestimation for underrepresented groups, it can also introduce unintended harms under certain data conditions. Using controlled simulations that vary group size and baseline event prevalence, we show how reweighting can yield misleading improvements in fairness by reducing underestimation for one group while introducing it for another. Across 3,000 simulated datasets with event prevalence of 7-14%, reweighting improved parity in positive classification and false negative rates (FNR) between groups, but did so partly by decreasing positive classifications and increasing FNR for the group with higher baseline prevalence. These effects were most pronounced when that group was a minority: its FNR rose by 6 percentage points, approximately 82 additional missed cases per 10,000 group members, and roughly three-quarters of the improvement in FNR parity came from this increase rather than from gains for the other group. The pattern held across six classifiers, from logistic regression to neural networks, while overall accuracy was essentially unchanged, leaving the shift invisible in aggregate performance metrics. These findings mirror patterns reported in real-world applications and underscore the critical role of data characteristics in shaping the impact of this fairness intervention. While reweighting may create desirable outcomes in some applications, practitioners should critically evaluate it relative to their problem area and goals. Specifically, when the goal is to reduce underestimation in one group without introducing underestimation in another, reweighting may not be the appropriate approach.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07256

TriAttention: Unified Sparse Mixed-Precision Attention for Long-Context LLM Inference

Hanzhi Zhang, Qiao Zhang, Qinglei Cao, Heng Fan, Yan Huang, Kewei Sha, Yunhe Feng

原文摘要

Sparsity and quantization reduce the cost of attention by skipping interactions and lowering the precision of those retained. However, useful interactions differ in their precision requirements: some tolerate low-precision scores while remaining sensitive to removal. We therefore introduce TriAttention, which assigns query-key (QK) tiles to skipping, 4-bit, or 8-bit computation, using 4-bit to retain quantization-tolerant interactions at lower cost. To represent compactly, we encode each head's computation regions with two diagonal-distance boundaries, keeping policy storage independent of context length. Offline calibration then evaluates candidate boundary pairs using normalized projected-output errors and complete-tile execution costs. Using these measurements, a model-wide allocator selects each head's boundaries to minimize calibration error under a shared computation budget. During prefill, the selected boundaries generate precision-grouped traversals for a fused kernel that skips omitted tiles and combines contributions from both QK precisions into one normalized attention output. The quantized keys and values prepared during prefill are then reused in a compressed key-value (KV) cache for decoding, reducing repeated reads of prompt data. Experiments show that TriAttention achieves end-to-end generation speedups of up to 7.88x over the Torch attention and 2.65x over the BF16 baseline. Meanwhile, TriAttention maintains quality comparable to the original models on general-purpose and long-context tasks. These results show how a compact retention-and-precision policy translates local sensitivities into attention computation and repeated KV-cache access. The implementation is https://github.com/HanzhiZhang-Ulrica/TriAttention.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07257

Evolutionary Adaptive Neighborhood Learning: A Genetic Algorithm for Instance-Dependent k Optimization in Nearest Neighbor Classification

Isaac Touza, Kaladzavi Guidedi, Kolyang

原文摘要

The number of neighbours k is the central hyperparameter of the k-nearest neighbour (k-NN) classifier and is usually selected globally through cross-validation or evolutionary search. However, the bias-variance trade-off is inherently local: dense and noise-free regions may favour small neighbourhoods, whereas sparse or noisy regions may require larger ones. Since global-k optimization is one-dimensional, replacing exhaustive search with a genetic algorithm offers little computational advantage. We therefore optimize an instance-dependent neighbourhood policy instead. We propose EANK (Evolutionary Adaptive Neighborhood K), which uses a low-dimensional policy to map local neighbourhood descriptors, including density, label entropy, vote margin, and concentration, to an adaptive number of neighbours k(x). A real-coded elitist genetic algorithm optimizes this policy using leave-one-out accuracy with a neighbourhood-smoothness penalty. Precomputed neighbour votes reduce fitness evaluation costs. We investigate theoretical properties of the method, including dominance over global-k solutions on the training criterion, evolutionary convergence, policy regularity, and generalization guarantees. Experiments on synthetic data with spatially heterogeneous structure and twelve public datasets evaluate predictive performance, robustness, and computational cost. Under nested cross-validation, EANK achieves competitive performance relative to tuned global-k baselines and improves upon the default k=5. We also examine the gap between training and test performance to assess the practical value of adaptive neighbourhood selection.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.10675

HiddenObjects: Scalable Spatial Prior Extraction for Object Placement from Diffusion Models

Marco Schouten, Ioannis Siglidis, Serge Belongie, Dim P. Papadopoulos

原文摘要

We learn explicit, class-conditioned spatial priors for object placement in natural scenes by distilling placement knowledge from text-conditioned diffusion models. Prior methods rely on sparse manual annotations or on inpainting object-removal pipelines, whose artifacts promote shortcut learning. To address these limitations, we propose a scalable pipeline that evaluates dense candidate placements by inserting objects into clean backgrounds. This produces HiddenObjects, a dataset of 27M bounding-box annotations (2M positives) across 27K diverse scenes and object categories. Human evaluation prefers our image editing composites over those guided by sparse annotations in 65.6% of comparisons. We distill the priors into a lightweight placement model that achieves the best accuracy among dedicated baselines and zero-shot vision-language models.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07254

Using Transformers for Teaching and Learning via Symbolic Distillation of Neural A-life Agents

Shuwei Wang, Vadim Bulitko, Matthew R. G. Brown, Michael Youngblood, Ramon Lawrence, Roscoe Smith, Shinichi Nakagawa, William Yeoh

原文摘要

Neural networks controlling behavior of A-life agents can evolve over multiple generations. While effective in making the agents survive, such networks are generally opaque to a human observer. Furthermore, the neural weights cannot be transferred between agents with different neural architectures. Distilling such neural networks into compact symbolic policies can help humans understand agent behavior in A-life. Additionally, it allows the agents to share their knowledge in a compact fashion, improving population-level learning. Distilling a neural policy into a symbolic policy is typically performed by searching the space of symbolic policies to find one that approximates the neural policy. However, even with a domain-specific language the space of policies can be large, necessitating incomplete stochastic search such as genetic algorithms. Yet the distillation remains computationally expensive. We propose to instead use a transformer pre-trained on readily available random percept-action data. Doing so speeds up distillation substantially. We derive the transformer architecture via a neural architecture search. Empirical results compare different distillation methods and the influence of the symbolic space on A-life population dynamics through self-reflection and teaching and learning.

cs.LG · cs.SC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.04373

Worst-Case Discovery and Runtime Protection for RL-Based Network Controllers

Hongyu Hè, Minhao Jin, Maria Apostolaki

原文摘要

RL-based controllers achieve strong average-case performance in networking tasks such as congestion control and adaptive bitrate streaming. Yet their performance can degrade severely under network conditions where strong performance is still achievable. Identifying such conditions and quantifying the resulting performance gap is intractable by enumeration, while the sequential and closed-loop nature of RL controllers makes formal verification methods impractical. We present ReGuard, a framework that discovers worst-case scenarios for a given RL controller and protects it against them at inference time without retraining. ReGuard formulates scenario discovery as a bilevel regret-maximization problem, certifying a lower bound on the controller's worst-case performance gap. ReGuard then analyzes the discovered counterfactual trajectories and compiles them into lightweight logic rules that intervene only when a risky state is detected, leaving the controller's behavior unchanged otherwise. We evaluate ReGuard across three RL-based network controllers: Pensieve, Sage, and Park. ReGuard discovers scenarios in which each controller suffers a 43-64% performance loss relative to what is achievable under the same conditions. ReGuard exposes performance gaps 57% to 6 times larger than those found by the strongest baselines and shrinks those gaps by 79-85% in its first iteration via lightweight rule-based protection, iteratively driving the remaining gap toward nominal levels. ReGuard's protection extends beyond the scenarios it discovers, improving performance across a wide range of network conditions.

cs.NI · cs.AI · eess.SY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2407.21665

A State-of-the-Art Review of Computational Models for Analyzing Longitudinal Wearable Sensor Data in Healthcare

Paula Lago

原文摘要

Wearable devices are increasingly used as tools for biomedical research, as the continuous stream of behavioral and physiological data they collect can provide insights about our health in everyday contexts. Long-term tracking, defined in the timescale of months of year, can provide insights of patterns and changes as indicators of health changes. These insights can make medicine and healthcare more predictive, preventive, personalized, and participative (The 4P's). However, the challenges in modeling, understanding and processing longitudinal data are a significant barrier to their adoption in research studies and clinical settings. In this paper, we review and discuss three models used to make sense of longitudinal data: routines, rhythms and stability metrics. We present the challenges associated with the processing and analysis of longitudinal wearable sensor data, with a special focus on how to handle the different temporal dynamics at various granularities. We then discuss current limitations and identify directions for future work. This review is essential to the advancement of computational modeling and analysis of longitudinal sensor data for pervasive healthcare.

cs.HC · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07250

Characterizing AI Service Traffic for 6G: An Open Testbed and Initial Results from 3GPP SA4

Imed Bouazizi

原文摘要

The design of sixth generation (6G) mobile systems requires measurements of artificial intelligence (AI) service traffic under controlled network conditions. The 3rd Generation Partnership Project (3GPP) Service and System Aspects Working Group 4 (SA4) documents such measurements in draft Technical Report 26.870. In this paper, we describe the open testbed used for the study and analyze the results recorded in version 0.6.2 and its companion workbook. The testbed combines network emulation, packet capture, application measurements, and scenario execution against hosted and self-hosted models. The reported uplink to downlink volume ratios span more than six orders of magnitude. A personal assistant agent has a ratio of 0.007 at its local control interface and 0.50 on its wide-area egress. Deterministic agent signaling follows the configured round-trip delay. In a tokenized video experiment with 125 questions per profile, the number of correct answers changes by at most three through 10% independent uplink loss. Larger losses reduce accuracy, but the available repetitions do not establish a tolerance threshold. We also analyze emulator behavior that affects the interpretation of the study. Per-packet jitter introduces reordering, correlated random-loss settings suppress rare loss events, and a Gilbert-Elliott parameter mapping changes the stationary loss rate. The results support characterization by scenario, measurement layer, and versioned network configuration.

cs.NI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07247

Goal Revelation as a Bridge Between Information-Theoretic Empowerment and Capability-Based Human Power

Jaime Ruiz-Serra, Tomáš Gavenčiak, Jobst Heitzig

原文摘要

Power matters for AI safety. Optimal agents tend to acquire power across a wide range of objectives (instrumental convergence). As we embed AI agents into socio-technical systems, humans risk gradual disempowerment. Both concerns call for a formal, quantitative measure of power. Two such measures in the context of Markov games are information-theoretic empowerment, the capacity of the channel from an agent's actions to future states, and capability-based individual power, a measure of goal attainment built from the probabilities that a human would attain each goal in a family of candidates were they pursuing it. We show where the two meet. From individual power, Fano's inequality yields a floor $B(s)$. This floor is a lower bound on what we term goal revelation, the mutual information $\mathbb{I}(G;ξ\mid s)$ between the human's latent goal and the realised trajectory. Empowerment caps revelation from above, so that $B(s) \le \mathbb{I}(G;ξ\mid s) \le \mathbb{I}(\mathbf{A}_h \to ξ\mid s) \le \mathfrak{E}_h(s)$. Each quantity can be large while the one below it stays at zero, highlighting the following failure modes. An assistant maximising empowerment can prefer an interface offering broad influence over goal-irrelevant degrees of freedom to one that lets the human attain every goal they might hold. An assistant maximising revelation cannot tell a working interface from one rewired so that every goal yields the wrong outcome, since relabelling goals leaves mutual information unchanged while zeroing every attainment probability. Positive guarantees therefore come only from the attainment end of the chain. A satisfaction floor, computable from two statistics of interaction logs, offers a way to monitor the power users retain in a deployed system, and simulations in random environments show the three quantities are correlated but far from interchangeable.

cs.AI · cs.IT · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07245

MAC-v2: Long-horizon model-based value expansion from pixels

Kwanyoung Park, Sergey Levine

原文摘要

We study whether \emph{long-horizon model-based value expansion} can serve as an effective framework in pixel-based offline reinforcement learning (RL). Long-horizon model-based value expansion from pixels is substantially harder than state-based environments, as the agent must learn both the representation and its dynamics, and errors from either can accumulate recursively over imagined trajectories. We introduce MAC-v2, which enables long-horizon model-based expansion from pixels by training a reconstruction-free latent world model with action chunking. By learning representations from prediction and control objectives, MAC-v2 does not need to encode control-irrelevant visual details that can hinder the dynamics prediction. Action chunking further mitigates the prediction error by reducing the number of recursive model predictions required for value expansion. Across diverse visual benchmarks including visual OGBench, MMBench2, Robomimic, and LIBERO-10, MAC-v2 achieves strong performance against model-free and model-based offline RL baselines. Our analyses show that long-horizon model-based value expansion is critical for the performance of MAC-v2, and that both action chunking and latent learning objectives are essential for reliable long-horizon latent imagination.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07241

$D^2$-OPD: Separating Direction and Distance in Extrapolative On-Policy Distillation

Bowen Fang, Dingmin Wang, Hengzhi Pei

原文摘要

On-policy distillation (OPD) trains a student model to match a teacher's next-token distributions on student-generated prefixes. Extrapolative OPD further extends the teacher's log-probability shift relative to a reference policy to construct stronger learning targets. However, existing methods couple extrapolation direction and distance, allowing the magnitude of the teacher's shift to dictate how far the target moves. We propose $D^2$-OPD, decoupling these two factors: a per-prefix hard KL constraint bounds the target's distance from the teacher, while an adaptive combination of the teacher's post-training shift and the initial student--teacher gap determines the extrapolation direction. We optimize the student toward this target using forward KL, providing learning signals even for low-probability tokens. We evaluate three settings: where standard OPD performs well, where it struggles with base-model initialization, and where no teacher reference is available. On mathematical reasoning benchmarks, $D^2$-OPD attains the highest score in all three settings, outperforming the strongest baseline by up to 9.45 points. Ablations validate the contributions of each component.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.07104

Almost Sure Convergence Rates of Stochastic Approximation and Reinforcement Learning via a Poisson-Moreau Drift

Xinyu Liu, Zixuan Xie, Shangtong Zhang

原文摘要

Establishing almost sure convergence rates for stochastic approximation and reinforcement learning under Markovian noise is a fundamental theoretical challenge. We make progress towards this challenge for a class of stochastic approximation algorithms whose expected updates are contractive, a setting that arises in many reinforcement learning algorithms such as $Q$-learning and linear temporal difference learning. Specifically, for a power-law learning rate $O(n^{-η})$ with $η\in (1/2, 1)$, we obtain an almost sure convergence rate arbitrarily close to $o(n^{1 - 2η})$. For the harmonic learning rate $α_n=α/(n+1)$, the almost sure squared-error rate is $o(n^{-ζ})$ for every $ζ<\min\{1,2(1-κ)α\}$, where $κ$ is the contraction factor. Thus exponents arbitrarily close to one are available when $2(1-κ)α\geq1$. This approaches the $n^{-1}$ polynomial exponent of classical law-of-the-iterated-logarithm benchmarks. Key to our analysis is a novel Lyapunov drift construction that applies a Poisson-equation based correction for Markovian noise to the well-established Moreau-envelope smoothing for the contractive mapping.

cs.LG · math.OC · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07238

How Do AI Agents Waste Your Money?

Huimin Zeng, Yuxuan Lu, Jesse Cai, Eric Hanchen Jiang, Di Wu, Po-Nien Kung, Wenbo Hu, Ziyi Wang 等 11 位作者

原文摘要

AI agents may consume massive tokens across a wide range of tasks, but how many of those tokens are really necessary? Although prior work has shown that agents can incur unexpectedly high token costs, we still lack a systematic way to identify and measure token waste. In this work, we introduce a unified framework for measuring token waste across heterogeneous agent systems. Our framework records and normalizes complete agent trajectories, identifies removable spans using an LLM-as-a-Judge (LLMaJ), and maps the identified text spans back to the original trajectory for token-level measurement. We validate the identified waste through direct interventions by removing marked spans, resuming agent execution, and measuring changes in task outcomes and subsequent actions. In online pruning experiments, we remove 41-46% of the model's reasoning while largely preserving task performance across two distinct agent benchmarks. Using this framework, we analyze agents across multiple settings. Our analysis shows that token waste has a system-level structure that aggregate token usage alone cannot reveal. First, waste varies more across tasks and agent settings than across models. Second, reasoning and visible execution can exhibit different waste patterns. Third, different harnesses can introduce distinct sources of inefficiency even under the same model and task. Overall, our framework transforms token waste into an actionable optimization signal, enabling researchers and practitioners to train more efficient models, design better reasoning strategies, and optimize agent harnesses toward reducing unnecessary computation rather than merely reducing token usage.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07235

Adaptive Hybrid Force-Vision Control with EMG-Derived References for Deformable Bottle Manipulation

Jeffrey Lee, Geoffrey Hanks, Evangeline Bouganim, Yue Hu

原文摘要

Robotic automation of laboratory tasks has become a growing interest to remove researchers from hazardous environments and repetitive procedures. However, even equipment as simple as squeeze bottles poses a challenging manipulation problem due to its deformability. This paper presents an adaptive hybrid vision-force controller for robotic grippers to effectively manipulate laboratory squeeze bottles to dispense liquid. This approach integrates force and vision feedback according to the interaction state, enabling effective squeezing while accounting for bottle deformation and recovery. The proposed controller is validated by comparing its performance with a pure force controller on 12 combinations of conditions consisting of 2 target dispense volumes, 2 plastic squeeze bottles, and 1 to 3 squeezes used to dispense. Human demonstrations of these operating conditions were collected using electromyography (EMG) sensing mapped to a desired grip force, which was then used as the force reference for the controllers to squeeze the bottles. Results demonstrated that the proposed adaptive hybrid vision-force controller achieved more accurate liquid dispensing with a mean absolute error (MAE) of 6.54 mL compared to a MAE of 15.92 mL from the pure force controller, while also replicating the human action recorded from the EMG signal more closely.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.24720

Colour me shocked: Exact Molecular Hessians from local MLIPs in O(N) time using sparse differentiation!

Luca Thiede, Andreas Burger, Alán Aspuru-Guzik

原文摘要

The Hessian of the energy with respect to the nuclear positions is indispensable in atomistic modelling. However, constructing this matrix requires $O(N)$ Hessian vector products, traditionally limiting high-accuracy Hessians to small systems. Machine learning interatomic potentials (MLIPs) have accelerated atomistic modelling by providing highly accurate energies and forces at $O(N)$ cost, yet the resulting $O(N^2)$ cost of Hessians remains a practical bottleneck for large systems. Based on the insight that we can derive the sparsity pattern for an MLIP's Hessians in closed form, we show in this paper how to use techniques from sparse automatic differentiation to reduce the cost of a local MLIP's Hessians to a system-size-independent number of Hessian-vector products, yielding overall $O(N)$ total cost without any approximations. We benchmark our approach on a variety of systems ranging from alkane chains to water clusters to $A\beta40$ conformers. Depending on the MLIP configuration, we achieve the linear scaling regime already on relatively small systems, resulting in large runtime reductions between 2$\times$-15$\times$ for these systems. This opens up the possibility of scaling high-accuracy MLIP Hessians to very large systems, such as proteins that were previously inaccessible.

cs.CE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07232

Recursive Sparse Attention: Million-Token Length Extrapolation at Logarithmic Cost

Ruitian Wang, Xinyu Yang, Minshen Zhang, Hao Zhang

原文摘要

At context lengths of about 1M tokens, dense attention is costly in prefill and decoding, and training typically relies on long documents, which become scarcer as the target length increases. Most sparse attention methods score all preceding blocks or tokens, so their selection cost per query is $O(L)$ at context length $L$; hierarchical selection reduces it to $O(\log L)$, but prior trainable hierarchical methods report accuracy only within their training length. We propose RecSA (Recursive Sparse Attention), which builds a tree over the KV cache in which each node summarizes its subtree with one key and one mean-pooled value. The keys come from one pooler per layer, shared by all levels and distilled from dense attention. Each level above the tokens selects at most $k$ candidates, so each query has $O(\log L)$ selection cost and reads $O(\log L)$ entries; the summaries of unselected candidates share one softmax with the exact tokens. Each entry's RoPE position is its index among the candidates of its level, so at any length every relative distance stays within the range seen during training. Initialized from Qwen3-4B and trained on 0.62B tokens at the original model's 32K training length, RecSA outperforms all baselines on RULER at every length from 131K to 2M; at 1M, it scores 60.5, compared with 40.0 for the best baseline, Dense + DCA. With our optimized kernels, RecSA is faster than dense attention in end-to-end prefill and decoding from 64K to 2M; at 524K on one H200 GPU, it accelerates prefill by 3.2x and decoding by 3.8x.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07231

Efficient Projection-Based Reduced-Order Modeling for Computational Fluid Dynamics via Multifidelity Basis Construction

Ashok Viswanathan, Charbel Farhat

原文摘要

Projection-based reduced-order models (PROMs) accelerate computational fluid dynamics simulations, but generating high-fidelity (HF) training snapshots remains expensive. We present a multifidelity methodology that reduces offline basis-construction costs by combining a small HF database with low-fidelity (LF) solutions. The method accommodates discrepancies in physical models and spatial discretizations. Parameter-matched HF and aligned LF snapshots define a correction basis. At new parameters, LF predictions are corrected by minimizing the HF residual over an affine trial space, with selective Reynolds-averaged Navier-Stokes (RANS) smoothing. Accepted snapshots enrich the training database and update the correction basis. The resulting basis is compatible with conventional projection methods, including least-squares Petrov-Galerkin projection. For steady flow over a NACA0012 airfoil, using fine-grid RANS and coarse-grid Euler models, four HF snapshots and 36 LF-derived snapshots reduce snapshot-generation cost by a factor of 7.8. At basis dimension 40, mean lift, drag, and lift-to-drag ratio errors are 1.1%, 3.6%, and 3.9%, and the mean relative skin-friction error is approximately 5%, compared with 0.18%, 2.9%, 2.8%, and 4% for an HF-only PROM. Errors are evaluated against fully converged HF solutions on a test set emphasizing shock-containing flows. Increasing the initial HF snapshot count raises cost without monotonically improving accuracy. Among the tested multifidelity configurations, ten initial HF snapshots give the lowest aerodynamic errors at dimension 40; increasing the count to twelve worsens all three. The results demonstrate reduced snapshot-generation costs while retaining compatibility with established PROM formulations.

cs.CE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07229

Spatial-UMI-Dream: Scaling World Action Models with Metric Geometry for UMI Manipulation

Weiduo Yuan, Ze Yuan, Sihan Liu, Jionghao Wang, Liang Heng, Zhenyu Zhao, Yue Wang

原文摘要

The Universal Manipulation Interface (UMI) enables scalable demonstration collection independently of a specific robot. However, its moving, close-range gripper cameras entangle camera and object motion without a stable external view, leaving the metric geometry needed for precise manipulation implicit in RGB. We introduce Spatial-UMI-Dream, a 5B spatial World Action Model (WAM) pretrained on 605 hours of RGB-D UMI data through two-stage training -- world-only adaptation followed by joint world-action learning -- to jointly predict future RGB, fisheye-aligned metric depth, and actions. Stereo-derived depth makes scene scale and spatial relationships explicit within a unified dual-gripper RGB-D representation. Furthermore, evaluating UMI policies requires testing whether UMI's robot-independent demonstration collection translates into policy generalization across robot embodiments, alongside robustness to environmental changes. We introduce RoboTwin-UMI, a twenty-task simulation benchmark built on RoboTwin with UMI wrist-mounted fisheye observations, enabling controlled, repeatable evaluation of UMI policies under environment and embodiment changes separately and jointly without additional fine-tuning. On RoboTwin-UMI, Spatial-UMI-Dream achieves 79.10% in-domain success and 72.15% under combined embodiment and environment shifts, exceeding the strongest evaluated baseline in each setting by 4.65 and 10.30 percentage points, respectively. It also exhibits the smallest success-rate drop under embodiment transfer among the evaluated policies. In a matched pretraining ablation, RGB-only pretraining leads to a 5.75-percentage-point decrease in in-domain success compared with RGB-D pretraining. Across six real-world tasks, Spatial-UMI-Dream achieves 85.0% average success, exceeding the strongest baseline by 24.2 percentage points. Project page: https://weiduoyuan.com/spatial-umi-dream/

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07228

Source-balanced Capped Fisher: Bounded Evidence Aggregation for User Inference in Language Models

Yang Liu, Ran Zou, Wanrong Zhu

原文摘要

User inference asks whether a source contributed documents to a language-model update, even when the auditor observes only fresh documents from that source. Document-level scores can provide evidence of participation, but combining this evidence is challenging: documents differ in baseline predictability and in how strongly they reflect information learned from other documents of the same source. We propose source-balanced capped Fisher (SCF), an aggregation method that uses known nonparticipating sources to assess how unusual each document score is. It transforms the resulting reference-tail frequencies into negative-log evidence, caps individual contributions, and averages them within each source. This limits the influence of isolated extreme scores while retaining evidence across multiple documents. We complete the inference procedure with a decision rule that tests source participation using a p-value calibrated against a separate set of known nonparticipating sources. The rule provides finite-sample Type-I error control under source exchangeability. Experiments across four real-world datasets show that SCF achieves the highest AUROC among the evaluated aggregation methods in four domains. With the calibration-based decision rule, SCF delivers consistently competitive detection power across the tested settings, achieving the highest power in many cases, while empirical false-positive rates remain generally close to or below the nominal levels.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07226

Loopback Transformer: Towards a Unified View of Residual Looped Transformers

Xuan Ouyang, Zefan Cai, Chenlong Zhang, Cheng Luo, Ke Wan, Junjie Hu

原文摘要

Looped Transformers reduce parameter count by repeatedly applying shared blocks, but parameter sharing alone does not determine how the results of repeated computation are reused. We take the depth-memory view of residual connections and analyze which representation is stored after each block application and how later reads weight it. A full block output contains both its input and its new update, so weighting that output also reweights the history already carried by the input. Reading individual updates instead, with the shared stack's input kept on a separate path, gives separate controls over input strength, total update weight, and allocation across updates. The Loopback Transformer implements these controls: geometric decay sets the total update weight and supplies a recency prior, and attention learns how to allocate that weight. On ClimbMix, Loopback reaches lower validation loss than standard Transformer baselines with 40-75% of their Transformer parameters (excluding token embeddings and the output head) at reference scales from 191M to 3B, with training tokens and executed depth matched. It also has higher mean accuracy over thirteen downstream tasks at 1.4B and 3B. At 191M, 374M, and 778M, it has the lowest validation loss and the highest thirteen-task mean among the standard Transformer and seven looped residual designs.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07225

PRB Starvation at Slot Time via Rank Indicator Inflation: Attacking Proportional Fair Memory in the Scheduler

Ryan Barker, Julia Boone, Tolunay Seyfi, Alirez Ebrahimi, Ethan Farquhar, Brian Davis, Joseph Boccuzzi, Fatemeh Afghah

原文摘要

Proportional fair (PF) scheduling in fifth-generation (5G) New Radio (NR) ranks user equipment (UE) by instantaneous rate over an exponentially weighted moving average (EWMA) of delivered service. We identify a served-but-undelivered denial-of-service (DoS) attack in which rank indicator (RI) inflation induces persistent physical resource block (PRB) starvation. Unsupported spatial layers cause first-attempt delivery failure, keeping the attacker's service EWMA low; the evaluated PF allocator repeatedly grants it the full PRB pool, denying honest UEs transmission opportunities. We formalize this recurrence and evaluate it in 3,300 paired, 200 slot multi-user shards spanning rank 1 and rank 2 Sionna Ray Tracing geometries, three link adaptation controllers, PF and round robin (RR), four target identities, and five seeds. On the rank 2 geometry, selective RI inflation yields 94--95\% target capture, reduces PRB Jain fairness from 0.997 to 0.28, and produces mean honest zero-grant runs of 41--56\,ms; RR preserves equal allocation. Exact offline replay and a Monte Carlo recurrence isolate the delivered-service denominator as the causal path. Cross-field and controller ablations show a weaker, controller-dependent channel-quality trigger, while activity-gated EWMA defenses remain structurally blind. The results motivate RI-consistency checks before feedback acquires scheduling authority and slot-time PRB evidence inside the O-RAN Distributed Unit.

cs.NI

查看论文
arXiv ↗PDF ↗