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
+93新增 AI 导读

arXiv 最近完成扫描：2026-11-16 01:34 · 全站最近入库：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 05:50 — 2026-11-16 05:50（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：2026-11-16 01:34最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 02:59

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

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

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 23,348 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33（北京时间）
新论文 · v1arXiv:2611.15974

Video-Action Models for Data-Efficient Industrial Manipulation

Eugenio Chisari, Stefanos Charalambous, Oliver Sanchez, Thomas Umbach, Michael Gentner, Fabio Quattrini, Norica Bacuieti, Sabin Grube Doiz 等 26 位作者

原文摘要

Industrial manipulation requires precise alignment and controlled handling of rigid, deformable, and flexible components. Yet, the benefits of pretrained visuomotor policies remain underexplored in settings where limited access to specialized hardware, components, and fixtures constrains demonstration collection and evaluation. Understanding task-specific data requirements is important for assessing their scalability across diverse processes on the factory floor. We investigate whether video pretraining can support reliable industrial manipulation with limited action data. We propose FLUX-mimic, a video-action model, motivated by the potential of video pretraining to capture motion and interaction patterns that enable sample-efficient training. FLUX-mimic is built on a backbone pretrained on large-scale web and industrial task data, and an action expert to generate robot trajectories. We train our policy by joint video-action training. Across four automotive manufacturing benchmark tasks and two bimanual robot platforms, FLUX-mimic outperforms all considered baselines on the dexterous robot platform and matches pi_{0.5}'s average success rate on the gripper-based robot platform. On a deformable part kitting task, FLUX-mimic reaches 77.5% success with as little as two hours of task-specific action-labeled demonstrations.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.00328

KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering

Albert Sawczyn, Piotr Bielak, Tomasz Kajdanowicz

原文摘要

Large language models (LLMs) are increasingly used for knowledge base question answering (KBQA), also referred to as knowledge graph question answering (KGQA), where answering requires selecting entities from a question-specific knowledge graph subgraph. Yet LLMs are known to hallucinate across tasks, and KBQA is no exception: even when we provide a graph as the knowledge source, the model may rely on parametric knowledge instead of graph evidence or perform invalid reasoning over the given relations. Such hallucinated answer nodes can limit the practical deployment of KBQA systems, especially in high-stakes domains such as healthcare. We formulate hallucination detection in KBQA as an answer-node classification problem and propose a lightweight graph-based framework that treats the answering LLM as a black box. KG-Guard represents each KBQA instance as an augmented graph. It initializes node features with semantic representations of KG entities, marks topic entities and LLM-proposed answer nodes with learned vectors, and connects a virtual question node to the topic entities. A graph encoder then produces verification-oriented node representations, and a small MLP classifies each proposed answer node using its graph representation together with the question embedding. Experiments on WebQSP, ComplexWebQuestions, and PUGG show that our detector achieves the best average rank across all three benchmarks (F1 82.0, 87.4, and 84.3), while using ${\sim}$305$\times$ fewer parameters than LLM-based baselines. It also retains the best average rank when jointly evaluated across an extended set of pipelines and settings. Beyond detection, the node-level feedback is actionable: when flagged answers are fed back to the KBQA system for iterative refinement, downstream KBQA F1 improves by 13.0-14.5 points and Exact Match by 16.9-17.6 points.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.13679

A Simplified Layout Algebra for GPU Kernels

Nan An, Xiaotian Zhou

原文摘要

The layout algebra behind NVIDIA's CuTe library describes how tensor tiles map onto threads and memory. A layout is a shape with a stride for each entry, so a coordinate's address is the sum of its indices times their strides. As formalized by Shah and by Cecka, its central operations (e.g., composition, complement, division, product) are guarded by at least six interacting admissibility conditions. We show that this complexity is an artifact of a representational choice, not of the domain. We present a layout algebra in which every layout names the space its inputs and outputs live in: logical, physical, or thread-value indices. A layout into logical or thread-value space must be a bijection from its $N$ coordinates onto $[0,N)$. A layout into physical space must be alias-free: distinct coordinates land on distinct addresses, except under broadcast, where many threads read one value on purpose and the layout must mark where. Nothing maps out of a physical index. Composing $f$ with $g$ requires only that $f$'s range be exactly $g$'s flattened coordinate set. The index arithmetic can always be emitted naively: compute $f$, split the result by division and remainder into $g$'s coordinates, and apply $g$. Often the composite simplifies to a layout; we show that when it does, there is a coarsest such form, whose digits every other one refines, and we emit that. A warp's or thread's slice is a \emph{restriction}. A restricted layout is no longer composable, which forces the user to settle the whole view of a tile before taking slices. We validate the algebra by reproducing within it CuTe's operations, such as composition, complement, and division. We implement it in OCaml and use the implementation to rederive CuTe's atoms and usage patterns. The decision procedure is proved correct in Rocq.

cs.PL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15971

Better Boundary Prediction Does Not Guarantee Better Structural Representation

Michael Zhou, Markus Frohmann, Junghyun Min, En-Shiun Annie Lee

原文摘要

Punctuation marks often mark phrase boundaries, carrying linguistic information. Therefore, punctuation marks' abundance and feasibility as proxies of linguistic structure has led to suggestions that using punctuation marks to optimise on phrasal structure may help language models (LMs) improve their representations of argument, semantic, and syntactic structures. In this paper, we test the above claim in English across three primary LM architectures: decoder-only, encoder-only, and encoder-decoder LMs, by complementing traditional token prediction with punctuation restoration (PR). Our evidence, collected at the <1B parameter scale, suggests that optimising for boundary prediction does not necessarily guarantee higher-quality structural representation in decoder-only, encoder-decoder, and encoder-only LMs, failing to improve performance on downstream tasks that require understanding structure in linguistic input.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2602.09297

Laplacian Heads Improve Transformers by Smoothing Token Representations

Yuchong Zhang, Vardan Papyan

原文摘要

Transformers update token representations through multi-head attention and residual connections: $X \leftarrow X + \sum_{i} P^{(i)}\text{Norm}(X)W_{V_i}W_{o_i}$, where $P^{(i)}$ is the softmax probability matrix in head $i$. We propose replacing some $P^{(i)}$'s with $I - P^{(i)}$, giving $X \leftarrow X + \sum_{i \in \mathcal{A}} P^{(i)}\text{Norm}(X)W_{V_i}W_{o_i} + \sum_{i \in \mathcal{L}} (I - P^{(i)})\text{Norm}(X)W_{V_i}W_{o_i}$. We call heads that use $I - P^{(i)}$ Laplacian heads. Our proposal has two motivations. First, it allows attention heads to update the mean of token representations, while Laplacian heads can directly control within-sequence variance. Second, if tokens are viewed as nodes in a graph with normalized edge weights $P^{(i)}$, then $I - P^{(i)}$ is a graph Laplacian operator, and the update can be interpreted as one step of heat diffusion on the graph. We show that this simple modification improves performance across supervised learning, causal language modeling, and vision self-supervised learning tasks. To investigate why, we examine the token representations learned with and without Laplacian heads. In supervised learning, Laplacian heads collapse token representations within the same sequence and align the sequence means with the geometry of Neural Collapse. In language modeling, they increase the separability of token representations that share the same next-token prediction. In vision self-supervised learning, they produce token representations whose top principal components better capture segmentation structure. Across modalities, they also lead to faster-decaying spectra, indicating stronger token smoothing. Overall, our findings challenge the prevailing view that token oversmoothing is inherently harmful, showing instead that certain forms of smoothing can be beneficial.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15968

DuoJEPA: Cross-Modal Translation Between Unaligned Self-Supervised Embedding Spaces

Mahmut S. Gokmen, Mitchell A. Klusty, Evan W. Damron, Caroline N. Leach, Samuel E. Armstrong, V. K. Cody Bumgardner

原文摘要

Learning from paired modalities is commonly equated with aligning them: two encoders are trained until the embeddings of a pair coincide in a shared space. We study whether cross-modal retrieval and classification can instead be obtained while the two encoders' own embedding spaces remain directly unaligned. DuoJEPA trains one encoder per modality with the self-supervised LeJEPA objective and appends to each encoder a single transformer layer that translates its embedding into the other encoder's space, supervised by a contrastive objective computed entirely within that target space. No loss term compares the two own spaces directly, although the encoders are optimised jointly through the translation objective. In our experiments, the translator's residual connections determine where the cross-modal pressure is absorbed: with a residual translator the two encoders become directly aligned, whereas with a skipless (residual-free) translator a paired-cosine test detects no alignment in the final models, and at most a weak one in the ablations, at comparable cross-modal performance. The learned class-token translation is well approximated by a single scaled rotation of the source space. We evaluate DuoJEPA on two modality pairs that differ in nearly every respect. On chest radiographs and reports from CheXpert Plus, it attains a zero-shot AUC of 86.6 and a cross-modal retrieval score of 78.5, compared with 60.0 and 64.2 for our reimplementation of LeVLJEPA with the same encoders and data. On Sentinel-2 optical and Sentinel-1 radar imagery, the frozen encoders fall within the range of published Sentinel foundation models under our reproduction of the Copernicus-Bench linear-probe protocol, the translator retrieves the paired image of the other sensor among 4,000 candidates in 77-79% of cases, and a patch-level extension transfers the within-image similarity structure of the scene.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.31248

Scaling Storm-Resolving Atmospheric AI Simulation to the Entire Planet

Zeyuan Hu, Akshay Subramaniam, Noel Keen, Tao Ge, Jaideep Pathak, Mohammad Shoaib Abbas, Suman Ravuri, Karthik Kashinath 等 12 位作者

原文摘要

Kilometer-scale convection shapes precipitation extremes, tropical organization, and cloud feedbacks, but most global atmospheric models approximate these processes at 25-100 km resolution. Global storm-resolving physics models resolve convective systems explicitly, but at a cost (roughly one MWh per simulated day on exascale supercomputers) that limits long-duration simulation. We introduce STRATA (Storm-resolving Tile-based autoRegressive Atmosphere Transformer Architecture), the first autoregressive AI emulator for global storm-resolving atmospheric dynamics. STRATA is trained on the highest-resolution atmospheric dataset yet used for global AI emulation: 17 days of SCREAM physics-model output at 4.9-km resolution (~25 million grid cells) sampled every 10 minutes. Our central premise is that on 10-minute timescales atmospheric dynamics are predominantly local, so training on small spatial tiles trades scarce global temporal samples for abundant local spatial samples and enables global rollout via overlapping-tile blending. STRATA combines 3D patch embedding and local 3D neighborhood attention, a novel Stereographic Rotary Position Embedding (StereoRoPE) for grid-invariant encoding, and a pixel-space de-aliasing decoder that suppresses patch-scale rollout artifacts. An iso-FLOP scaling study reveals that km-scale emulation requires ~10x more FLOPs per grid point than coarse-resolution AI weather models, consistent with the higher information density of convective-scale dynamics. Trained on only 17 days of data, STRATA produces stable 24-hour global rollouts with realistic km-scale dynamics across diverse regimes, though large-scale biases develop with lead time. It achieves 48 simulated days per megawatt-hour (more than 50 times better energy efficiency than the SCREAM physics model) and 741 simulated days per wall-clock day at 512 H100 GPUs.

physics.ao-ph · cs.CE · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2607.02338

Graph-Based Nearest-Neighbor Search with Recall Guarantees Using Graph Spanners

Minghao Li, Raghav Mittal, Sanjivni Rana, Suraj Shetiya, Gautam Das, Nick Koudas

原文摘要

Graph-based indexes such as Hierarchical Navigable Small World (HNSW) graphs make nearest-neighbor retrieval efficient, but a high average recall can hide queries whose results fall below an application's quality requirement. We introduce Certify-then-Rectify (CTR), which returns an initial graph-search result when a calibrated rule accepts it and searches for missing neighbors otherwise. The recovery search reuses the existing graph and the distances already evaluated by the initial search. To determine how far this search should proceed, we relate metric distances to graph-path lengths through graph stretch. We develop Stretch-Bounded Expansion from Query (SBE-Q), together with Metric Bound Verification (MBV) to prune unnecessary work, and estimate its budget from paths to the fraction of true neighbors needed for the requested recall. Finite-sample tolerance bounds support this recall-aligned estimate; paths recorded during proposal recovery offer a conservative alternative to separate shortest-path computations. Independent tests certify initial acceptance and recovery outcomes, giving an end-to-end population recall guarantee even when the estimated stretch does not cover every relevant path. If recovery cannot be certified, rejected queries use exact scan. Experiments on HNSW compare five stretch estimators, assess recovery efficiency, and evaluate compliance and throughput on databases of up to 100 million vectors. CTR is not specific to HNSW, and we also evaluate it on another graph index.

cs.DB · cs.CL · cs.IR · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15966

Subject-Held-Out Evaluation of Deep Ground Reaction Force Estimators Across Two Laboratories: Leakage and Cross-Laboratory Transfer

Hernan David Santos, Yinong Chen, Yu Ding, Xudong Zhang, Jian Tao

原文摘要

Deep networks that estimate ground reaction forces and centers of pressure from motion-capture markers are validated within one laboratory, in a seldom-stated coordinate frame, and sometimes with trial-level splits that put the same person in the training and the test set. We measured what each practice costs, and whether such models transfer between laboratories. Three sequence models (convolutional, convolutional-recurrent, and convolutional-transformer) were evaluated on two independent datasets, locomotion (6 subjects) and occupational patient handling (10 subjects), under one pipeline, one tuning procedure, three seeds, and four protocols: trial-level split, leave-one-subject-out, pooled two-laboratory training with matched held-out subjects, and cross-laboratory transfer. At a fixed configuration, trial-level splits overstated the subject-held-out coefficient of determination by +0.040 to +0.194; on occupational data the overstatement exceeded every difference between architectures. With subjects held out, the three models reached values between 0.583 and 0.804; the leader differed between datasets, and gaps lay within subject-to-subject variability. Pooling the laboratories changed neither dataset on matched subjects. Transfer between laboratories was below chance in both directions, including the vertical force, which no in-plane rotation can affect. Leaving force targets in the plate frame while inputs were heading-aligned cost 0.57 of locomotion anteroposterior-force explained variance, enough to make that force look hardest; a Newton's-law correlation detected the mismatch before training. Split protocol and target frame changed reported accuracy more than architecture did. Learned force estimators should be validated with subjects held out, checked for frame consistency before training, and tested across laboratories before deployment claims are made.

cs.LG · eess.SP · q-bio.QM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15965

PhysICL: In-Context Learning of Physical Fields on Unstructured Meshes from Procedural Priors

Fabien Casenave

原文摘要

Engineering design studies produce a few tens to a few hundred simulations of one problem, each on its own mesh, and their surrogates are retrained for every study. Tabular foundation models instead infer a new task from its examples in one forward pass, after pretraining on synthetic tasks. We demonstrate the feasibility of in-context learning for physical field prediction on unstructured meshes. A single model, PhysICL, pretrained solely on procedural tasks, predicts fields, with quantiles, directly on each query mesh from labeled simulations, without updating its weights. The same checkpoint accepts variable numbers of context examples, scalar inputs and input fields, and any number of output fields, while mesh size and connectivity can vary within a task. Its procedural prior draws generic laws and boundary-element physical models on morphed 2D and 3D template meshes, evaluated only at the points the model samples, fast enough that tasks generated on the fly by CPU workers keep the GPUs busy throughout pretraining. On five PLAID datasets never seen in pretraining, its field error decreases as the context grows and, from $K = 32$, is below that of the nearest context simulation on every dataset and context draw. It is on par with per-dataset reduced-order models on two of them, behind them where the fields are low-rank. On AhmedML surfaces with a median of 1.1 million nodes, twenty times the largest pretraining mesh, its fixed spatial budgets keep the peak GPU memory at $K = 64$ at 4.27 GiB, against 4.07 GiB on the 6,000-node meshes of 2D\_MSHE. Finally, on 2D\_MSHE, far from the prior, fine-tuning on procedural tasks that reproduce its geometry and loads, without any of its outputs, at a tenth of the pretraining cost, divides the stress error by 2.7.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15964

COMBS: Concealed Object Multi-modal Bayesian Search

Taylor Bergeron, Kevin Leahy

原文摘要

This work addresses the problem of finding a concealed object in an environment by unifying formalisms for partially observable environments with multi-modal priors drawn from a mix of ontologies, semantic networks, LLMs, and VLMs. We propose a concealment-adaptive mixed-observability MDP (CA-MOMDP), a Bayes-adaptive setting where uncertainty is over both object locations and which nodes can conceal them, held as a hypothesis with a bounded ontology prior and resolved only by interaction. We define a hierarchical transition system (HTS) to abstract the environment into room and object nodes that can be planned over via our CA-MOMDP. We further propose a COMBS-score: a multi-modal fusion of a human informed semantic network, LLM, and VLM, to initialize the belief over object locations, which grounds our abstractions and reduces reliance on a single model. Belief is maintained via Bayes' rule, which never lets a look rule out a closed container. We prove a present target is found in a bounded number of searches under exact perception and that its location is never ruled out given missed detection under noisy perception. We ablate each component to demonstrate their significance. Across five simulator configurations, from a gridworld to Matterport3D with a real detector, COMBS finds 92-100% of in-distribution and 92-100% of out-of-distribution targets, matches or beats the baselines in processing speed, significantly outperforms a per-step LLM policy at lower cost on the larger scenes, recovers more out-of-distribution placements than a TidyBot ranking, and matches an LLM-only prior at a fraction of its per-decision latency. COMBS is the only standalone method that can declare a target absent at a stated error level, and the per-step LLM policy offered a termination action abandons 12-22% of targets that were present, against 1.6-3.2% for COMBS on the same episodes.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15963

WELP : Weighted Ensemble in the LooP for committor learning

Jacky Chen, Rishal Aggarwal, David Ryan Koes

原文摘要

Understanding how complex molecular systems transition between metastable states is a central challenge in computational chemistry and biophysics. A key tool for characterizing these transitions is the committor function: the probability that a trajectory initiated from a given configuration reaches one state before another. Because the committor encodes both the progress and the mechanism of a transition, it is an ideal collective variable (CV). Learning it, however, requires sampling the rare transitions it describes. We address this circular dependency with a ``WE-in-the-loop'' framework that couples committor learning with weighted ensemble (WE), an enhanced sampling method that uses a CV to drive transition dynamics. Our framework alternates between the two: WE simulation generates transition data for training a neural network committor with a self-consistent loss, and the learned committor then serves as an improved CV for subsequent WE simulation. Across a two-channel 2D system, alanine dipeptide, and chignolin, our framework consistently outperforms greedy baselines, highlighting the importance of principled exploration. We also curate a public benchmark of empirically determined committor values for alanine dipeptide. Together, the framework and benchmark provide a new method for studying rare transitions in high-dimensional molecular systems and a standard for evaluating committor learning methods.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15961

Is Spoken Hungarian Low-resource?: A Quantitative Survey of Hungarian Speech Data Sets

Péter Mihajlik, Katalin Mády, Anna Kohári, Fruzsina Sára Vargha, Gábor Kiss, Tekla Etelka Gráczi, A. Seza Doğruöz

原文摘要

Even though various speech data sets are available in Hungarian, there is a lack of a general overview about their types and sizes. To fill in this gap, we provide a survey of available data sets in spoken Hungarian in five categories (e.g., monolingual, Hungarian part of multilingual, pathological, child-related and dialectal collections). In total, the estimated size of available data is about 2800 hours (across 7500 speakers) and it represents a rich spoken language diversity. However, the distribution of the data and its alignment to real-life (e.g. speech recognition) tasks is far from optimal indicating the need for additional larger-scale natural language speech data sets. Our survey presents an overview of available data sets for Hungarian explaining their strengths and weaknesses which is useful for researchers working on Hungarian across disciplines. In addition, our survey serves as a starting point towards a unified foundational speech model specific to Hungarian.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.05556

AGORA: Reliability-Aware Aggregation of LLM Judges on Small Evaluation Sets

Junhyung Ahn

原文摘要

LLM-as-a-judge is a common substitute for costly human evaluation, and aggregating several judges is the standard remedy for any single judge's bias. Judge pools mix judges of very different reliability, while the human-labeled sets that validate them hold a few hundred items or fewer. In this regime the per-item mean weights weak judges as heavily as strong ones, and confusion-table models such as Dawid-Skene must estimate a per-judge error table from too few items. We propose AGORA (Aggregation Of Reliability-weighted Assessments), an item-response-theory aggregator that places every item on one latent quality scale and describes each judge by a sensitivity parameter and ordered rating thresholds, so judge reliability is learned from all items jointly and without human labels. Across three benchmarks, AGORA matches or exceeds Dawid-Skene on large evaluation sets, and its advantage widens as the set shrinks toward a few hundred items. It remains accurate as pools grow more uneven, a label-free dispersion statistic indicates in advance when trust weighting helps, and its learned trust weights track per-judge human validity. Code is available at https://github.com/JunhyungAhn/llm-as-judge-irt.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15958

DUFT: Device-Unique Feedback Traversal for Entropy-Estimated Response Extraction and Mutual Authentication using SRAM PUFs

Syed Talha Imam, Amna Zafar, Arslan Munir

原文摘要

Static Random Access Memory (SRAM) Physical Unclonable Functions (PUFs) are a promising technology in the realm of random number generation for key generation, but for PUF-based authentication, they have been sidelined due to their limited challenge space as a reservoir of Challenge-Response Pairs (CRPs). In this paper, we develop a seed-based, round-iterated feedback mechanism, which we name Device-Unique Feedback Traversal (DUFT). The feedback chain is driven by the device's unstable and stable bit positions in its stability mask against the address to create a unique traversal. Additionally, a device-key hashed from the unique SRAM-PUF array is also included in calculating the next round of the chain to keep it secret. By estimating the physical SRAM source's entropy and error rate empirically, or by having a source with established metrics in both, DUFT estimates the number of rounds of feedback in the traversal to be performed to achieve a certain amount of min-entropy. We reach 128 bits of estimated min-entropy on our reference hardware under stated assumptions and experimental estimates. The number of rounds in the traversal scales directly with measured source-entropy, allowing security to be increased for weaker sources at the cost of running time. Using this feedback-traversal wrapper over SRAM-PUFs to obtain a measured-response, we propose an extremely lightweight authentication and key-encapsulation protocol for resource-constrained embedded devices. We realize and evaluate DUFT end-to-end on physical IoT/embedded hardware: a discrete-SRAM node pair running the complete mechanism and end-to-end protocol, and an embedded-SRAM microcontroller for the mechanism alone.

cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.07408

Addressable Memory for Video World Models

Xindi Wu, Sven Elflein, James Lucas, Olga Russakovsky, Laura Leal-Taixé, Despoina Paschalidou, Jonathan Lorraine, Aljoša Ošep

原文摘要

We study visual persistence in interactive video world models. These models rely on a Key-Value (KV) cache as a growing visual memory to carry forward previously generated frames. However, we find that models can no longer reliably address stored content once rollouts extend beyond the training horizon, because temporal Rotary Positional Embedding (RoPE) offsets can exceed the training range and the model struggles to retrieve the relevant visual information through attention. Moreover, naively compressing the cache in the RoPE-rotated space degrades memory by averaging keys with incompatible positional phases. To address this, we propose WorldTrace, a training-free memory framework for long-horizon visual persistence. WorldTrace keeps compressed memory addressable by assigning each summary slot a distinct, in-distribution virtual position. Within this cache, WorldTrace uses the model's own attention to decide which observations to retain verbatim and which redundant ones to merge into compressed summaries, all within one bounded addressable memory bank. We evaluate this ability with LoopBench, a benchmark that tests whether a compressed cache can reconstruct a previously visited scene after a long detour. On LoopBench, WorldTrace improves average DINOv2 recall similarity by 32.6% over a sliding window at the same cache budget, extending visually persistent generation without retraining.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15954

Riordan Arrays as Structured Operators for Artificial Intelligence

Dennis Davenport, Dewayne A. Dixon, Moussa Doumbia

原文摘要

Riordan arrays have traditionally been studied as infinite lower-triangular matrices that encode generating-function transformations and combinatorial relationships. This note proposes a complementary direction: using Riordan arrays as structured operators in artificial intelligence and data analysis. For a data sequence with generating function $A(z)$, a Riordan array $(g(z),f(z))$ produces the transformation \[ A(z)\longmapsto g(z)A(f(z)). \] This yields a parameterized family of causal linear operators that combine convolution, substitution, and multiscale mixing. The resulting structure may support parameter-efficient neural-network layers, variable-length sequence models, interpretable recurrent systems, invertible architectures, and models for hierarchical or recursively generated data. We explain what the infinite-dimensional viewpoint does and does not provide, outline several possible architectures, identify theoretical and numerical challenges, and propose an initial experimental program. The aim is not to claim that Riordan arrays are appropriate for all data, but to identify settings in which their algebraic structure supplies a useful inductive bias.

cs.LG · math.CO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15952

Quasi-Cyclic Qudit Lifted Product Codes with Almost Linear Minimum Distance

Shantom K. Borah, Abhinav Vaishya, V. Lalitha, Asit Kumar Pradhan, Bane Vasic, Narayanan Rengaswamy

原文摘要

Quantum low-density parity-check (QLDPC) codes are a promising route to fault-tolerant quantum computation with low overhead, and qudits offer advantages over qubits including more efficient information representation, improved magic state distillation, and richer algebraic structure for code design. Asymptotically good QLDPC codes arise from the lifted product (LP) construction with non-abelian lifts, but cyclic lifts remain attractive in practice because the resulting quasi-cyclic codes have circulant structure that hardware decoders exploit, which matters especially for non-binary decoders with costly check node operations. We introduce a qudit generalization of the LP construction over cyclic group algebras, which extends hypergraph product and LP codes to arbitrary prime-power dimensions and yields quasi-cyclic qudit CSS codes for every stacking order. We bound encoding rates via a connection to additive codes, and show that in the fully stacked case, qudit LP codes built from lifted Tanner codes on expander graphs form families with $Θ(\log N)$ logical qudits and almost linear minimum distance $Θ(N/\log N)$, via a distance bound that holds for a general class of LP factors. We also study an additive decoder for general qudit codes and a linear merged-syndrome decoder for fully stacked codes. Monte Carlo simulations under a depolarizing channel with equal symbol error probability show that qudit codes achieve lower frame error rates than comparable qubit codes, and that the linear decoder gives further gains for fully stacked codes.

quant-ph · cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15951

Starscream: Reimagining LLM Sharding on AMD Instinct GPUs with GPU Partitioning

Sumanth Gudaparthi, Smeet Chheda, Ganesh Dasika

原文摘要

As GPU accelerators grow larger to meet rising compute demands, they exhibit increasingly pronounced non-uniform memory access (NUMA) characteristics that challenge existing LLM frameworks. Chiplet-based architectures provide a practical path to larger GPUs while mitigating manufacturing yield constraints. Modern GPUs such as AMD Instinct MI300X employs such a multi-die design, and further offer GPU partitioning capabilities, partitioning a single physical GPU into multiple logical devices with NUMA-aware memory domains, promising faster kernel launches, and reduced memory access latencies with improved locality. However, current parallelization strategies, designed for homogeneous GPU topologies, when applied under partitioning, extend its unidimensional sharding causing significant performance degradation. Three bottlenecks emerge: (1) memory redundancy; (2) arithmetic intensity collapse; (3) communication overhead from flat collectives. We present Starscream, a rethinking of LLM sharding for the chiplet era. Rather than stretching inter-GPU sharding thinner, Starscream adds intra-GPU sharding along an orthogonal dimension, grounded in three foundational principles: kernel shape preservation, memory redundancy elimination, and communication overhead minimization. These principles form the basis for extending any sharding strategy into the partitioning regime. We demonstrate their effectiveness using tensor parallelism as a case study. On AMD MI300X and MI355X, exploiting partitioning capabilities yields up to 4x speedup for attention and 1.43x for fused GEMMs compared to chiplet-oblivious baselines, demonstrating the effectiveness of chiplet-aware designs. Starscream's principles generalize across sharding strategies and future architectures.

cs.DC · cs.AR · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.18777

PertReason: A Knowledge-Grounded Benchmark and Framework for Cell-State-Conditioned Mechanistic Reasoning of Perturbation Effects

Dongkwan Kim, Yiming Gao, Yining Yang, Yang Shen

原文摘要

Evaluating machine learning in scientific domains requires separating correct predictions from correct reasons under realistic distribution shifts. We introduce PertReason, a knowledge-grounded approach to evaluating and improving cell-state-conditioned reasoning about perturbation effects. Our framework comprises PertReasonQA, a benchmark that provides evaluation and supervision, and PertReasonLM, a reference large language model that demonstrates how such supervision supports reasoning-centric training. PertReasonQA tests whether models can generate mechanistically faithful explanations while remaining robust to complex shifts, such as new cells, unseen perturbations, cross-modal or combinatorial extrapolations. PertReasonQA combines single-cell genetic and chemical perturbation data across multiple cellular contexts with knowledge graphs, and dynamically conditions pathways on cell-specific basal states to avoid generic memorization. Evaluations of state-of-the-art models reveal systematic gaps between outcome prediction and mechanistic reasoning. As a reference probe of the benchmark, PertReasonLM is trained through supervised fine-tuning and reinforcement learning using mechanistic supervision from PertReasonQA. PertReasonLM improves predictive accuracy and reduces answer-reason disagreement by grounding rationales in context-specific pathways. Together, we provide a diagnostic framework for exposing and mitigating failures in faithful reasoning in data-rich scientific systems. We release our datasets to support further research at https://dongkwan-kim.github.io/PertReason/.

cs.LG · q-bio.MN

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15950

Modeling the Travel Time-Pollution Exposure Trade-off in Urban Route Choice

Cafer Avci, Zhaoyao Bao, Maximilian Dittgen, Danni Lu, Alireza Yazdiani, Mohammad Tayarani, H. Oliver Gao

原文摘要

Traffic-related air pollution is a major contributor to respiratory and cardiovascular disease, and travel time disproportionately drives daily exposure. Conventional routing algorithms minimize time or distance, ignoring street-level pollutant variability and leaving travelers exposed to avoidable risk. We develop a bi-objective routing framework that couples a high-resolution AERMOD-based PM2.5 dispersion surface with a shortest-path algorithm. The algorithm uses a deterministic, gradient-based weight-update scheme to enumerate Pareto-optimal paths along the time-exposure frontier. We apply the framework to 790,000 origin-destination pairs on New York City's road network, covering 1.48 million daily commuters. Link-level concentrations differed by a factor of two or more between adjacent parallel streets. Exposure-aware routes reduced cumulative exposure by about 38% at a median travel time increase of about 28%. The algorithm ran in 30 milliseconds per query and recovered more frontier paths than uniform weight sampling (4.5 vs. 2.4). These results show that exposure-aware routing is computationally practical at metropolitan scale and suitable for real-time navigation and infrastructure planning.

cs.CE · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15949

Efficient Influence Minimization via Source-Integrated Sampling

Jingbang Chen, Junyao Wang

原文摘要

Influence minimization by node blocking is a fundamental problem in graph data management that seeks a small set of vertices whose removal minimizes the expected spread from a fixed source set. It supports decisions about where to intervene in large interaction networks to control harmful propagation, such as the spread of rumors and infectious diseases. Under the Independent Cascade (IC) model, selecting blockers requires comparing a large number of candidate sets, and estimating their effects on propagation can be costly. We propose SIG (Source-Integrated Greedy), a sampling framework for efficiently finding high-quality approximate solutions. Our key idea is to group the possible sets of neighbors directly activated by the sources according to their effects on blocker selection. SIG represents these groups in a compact weighted tree and computes their probabilities directly, allowing each sample to account for all source outcomes without enumerating them. We prove that SIG produces unbiased estimates of the lower-bound objective without increasing variance for fixed blocking plans, and establish a high-probability quality guarantee through independent validation. Extensive experiments on real-world networks show that SIG has the lowest mean total running time in all main comparisons, with speedups of up to 583x over the fastest baseline. SIG produces solutions competitive with those of prior methods and achieves the highest influence reduction in multiple settings, including on many of the largest networks, where several baselines exceed the runtime limit. Additional experiments show that SIG maintains consistently low running times as graph size and the blocking budget increase, while delivering stronger blocking solutions at larger budgets.

cs.SI · cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15945

Reinforcement Learning for Inventory Control under Regime-Switching Demand: A Controlled Comparison of LSTM, MLP, and (s,S) Policies

Alex Haines, Nathanael L. Baisa

原文摘要

Classical inventory policies such as (s,S) are provably optimal under stationary demand but cannot adapt when demand switches between hidden regimes, and memoryless deep reinforcement learning policies, confined to a fixed observation window, cannot maintain a belief over latent demand structure. We ask whether a recurrent policy offers a measurable advantage over both a memoryless policy and a classical baseline under regime-switching demand, and how that advantage scales with supply-chain lead time. We build a custom Gymnasium environment in which daily demand is generated by a two-state hidden Markov process with Poisson emissions, so that the regime is known at evaluation time but hidden from the agent. An optimised (s,S) heuristic, an MLP PPO agent, and an LSTM Recurrent PPO agent are trained under matched compute and evaluated at lead times of 0, 3, 6, and 10 days over 30 deterministic episodes each. The recurrent policy outperforms both alternatives at every lead time, and its margin over the MLP widens monotonically with lead time, from parity at lead time 0 to 2.17$\times$ at lead time 10. Principal component analysis of the LSTM hidden state explains the widening gap: the representation shifts from encoding a binary regime indicator at short lead times to encoding multi-step pipeline state at long lead times. Recurrent memory becomes the decisive architectural factor as the credit-assignment horizon lengthens.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.20658

Ownership in AI-Assisted Everyday Tasks

Megan Wei, Melanie Subbiah, Audrey Lee, Annya Dahmani, Dave Edwards, Helen Edwards, Ellie Pavlick

原文摘要

When does work done with AI still feel like ours? As AI becomes woven into everyday tasks, we must examine what happens to our sense of ownership and contribution when a machine shares in producing what we make. We report an exploratory qualitative survey in which participants were asked to describe two recent, self-selected tasks completed with AI: one that felt like their own and one that did not. We find that felt ownership depends on the process of collaboration: people disown work when they merely approve AI's suggestions, but retain ownership when they lead, iterate, or rewrite. Ownership can also extend to settings where people own the vision for a project but not the execution; respondents reported high ownership on tasks they could not have completed without AI. Loss of personal voice and a lack of comprehension of the output both erode ownership. Finally, willingness to disclose AI use is often decoupled from actual pride or ownership, and instead shaped by community norms and fear of credit erasure. We propose several research directions as a result of these findings to promote AI development that supports people's sense of authorship over their own lives.

cs.AI · cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15941

Lang-SVG: Hierarchical Image Vectorization with Language Priors

Xi Liu, Chaoyi Zhou, Run Wang, Jiaang Li, Feng Luo, Junxiang Huang, Siyu Huang

原文摘要

Image vectorization reconstructs raster images as compact scalable vector graph- ics (SVG), providing a structured and editable code representation of images. However, most existing vectorization methods optimize for pixel-level render- ing fidelity, often producing SVGs that lack alignment with human-perceived object-part hierarchies, making them difficult to manipulate. To address this, we propose Lang-SVG, which introduces an explicit tree structure to organize SVG primitives with semantic labels and parent-child relationships. Lang-SVG incorporates granularity-controllable and open-vocabulary segmentation priors to initialize object-part hierarchies and leverages multimodal large language models (MLLMs) with SVG tree context to assign semantic labels to unlabeled nodes. To reduce redundancy, we introduce depth-adaptive simplification to reduce shape complexity and Tree-Guided Pruning and Merging to eliminate redundant SVG nodes. L1-SAM-Prompting further recovers missing regions to improve recon- struction fidelity and structural completeness. Beyond reconstruction fidelity, we introduce a new evaluation protocol that measures structural quality and semantic part alignment. Experiments demonstrate that Lang-SVG achieves state-of-the-art performance in both rendering fidelity and structural quality. Project website: https://xiliu8006.github.io/Lang-SVG/.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.08151

A second order regret bound for NormalHedge

Yoav Freund, Nicholas J. A. Harvey, Victor S. Portella, Yabing Qi, Yu-Xiang Wang

原文摘要

We consider the problem of prediction with expert advice for "easy" sequences. We show that a variant of NormalHedge enjoys a second-order $ε$-quantile regret bound of $O(\sqrt{V_T \log(V_T/ε)})$ when $V_T > \log N$, where $V_T$ is the cumulative second moment of the instantaneous per-expert regret, averaged with respect to a natural distribution $\mathbf{q}_t$ determined by the algorithm. The algorithm is motivated by a continuous time limit using Stochastic Differential Equations. The discrete time analysis uses self-concordance techniques.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.07594

BiGym 2.0: Benchmarking Learned and Agent-Developed Policies for Humanoid Household Manipulation

Zexi Zhang, Zecheng Zhu, Zidong Chen, Zulkhuu Tuya, Stephen James

原文摘要

Humanoid household manipulation requires the arms to act while the body balances, steps and changes posture. We present BiGym 2.0, an adaptation of BiGym for the Unitree G1 across 20 household tasks using a unified whole-body controller for demonstration and evaluation. The suite provides 60 native human virtual-reality demonstrations per task with synchronised multi-camera views and full-body execution records. We benchmark vision-language-action fine-tuning, imitation learning, demo-driven reinforcement learning, and cold-start coding agents given the interaction budget of online reinforcement learning. With the same onboard views, proprioception and whole-body controller for every method, vision-language-action fine-tuning has the highest nine-task mean, and agent-developed programs outperform every demo-driven reinforcement learning baseline on this mean and lead on bimanual reaching. Cross-workspace stacking remains open, $π_{0.5}$ stays low on pick-box, and multi-object transport is hard for imitation learning, demo-driven reinforcement learning and coding agents. All environments, human demonstrations, and evaluation traces are open-sourced at https://github.com/swirl-uk/BiGym2.

cs.RO · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15937

MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes

Richard Shi, Mohammad Mahdavian, Mehrdad Momeni Zadeh, Mohammed Elmahgiubi, Amir Rasouli

原文摘要

Vision-Language-Action (VLA) models have demonstrated strong performance in robotic manipulation, yet most rely primarily on 2D visual observations and language instructions, leaving scene geometry and obstacle relationships to be inferred implicitly. This limitation is particularly problematic in cluttered environments, where small spatial errors can lead to unintended contacts or collisions. We propose MOSAIC, a modular spatial- and obstacle-aware framework that can be integrated with pretrained VLA policies to improve object-level scene understanding and action generation. Our method augments the VLA backbone with an auxiliary semantic grounding task that predicts role-specific masks for the target object, destination region, and surrounding obstacles. We further combine the target and destination masks with depth estimated from 3D scene reconstruction to construct role-specific geometric tokens that are injected directly into the action expert. In addition, we propose obstacle-aware attention supervision that emphasizes obstacles near the robot body during task execution. The resulting attention features are subsequently injected into later action-expert layers to further guide action generation. Together, these components provide explicit semantic, geometric, and obstacle-aware cues while preserving the underlying pretrained VLA architecture. We evaluate our framework on pretrained VLA model using the RoboPRO benchmark, including visual perturbation tests, and further validate it on real-world manipulation tasks. MOSAIC improves the success rate by 5.1% in cluttered scenes, and by 9.7% under visual perturbations, with gains of up to 25.0% in the most challenging environment. We will release our code and dataset upon acceptance at the following Github page: https://mmahdavian.github.io/MOSAIC/

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.05040

Calibrated Weak Supervision for Post-Harvest Burned-Cropland Mapping Under Label Scarcity

Raunak Bhagate, Maitri Polisetty, R I Minu

原文摘要

Mapping post-harvest burned cropland is difficult when fires are small and fragmented and reliable labels are scarce. We developed a calibrated weak-supervision framework for Punjab, India, using Sentinel-2 spectral change, VIIRS active-fire context, and MODIS MCD64A1 as a coarse external calibration and agreement reference. Three pseudo-label recipes, five feature representations, and linear, tree-based, boosted, and neural classifiers were evaluated using nested district-held-out cross-validation over three seeds and five folds. NBR and dNBR were excluded from classifier inputs. The best configuration used the very-strict recipe, a multilayer perceptron, and the full optical feature set (mean Cohen's kappa 0.395, AUROC 0.753, F1 0.747, balanced accuracy 0.703); Random Forest, XGBoost, and LightGBM were practically tied. Higher agreement with held-out pseudo-labels did not establish improved label correctness or independent burned-area accuracy. For deployment, a Random Forest with the very-strict recipe and full optical features was retained. An externally calibrated threshold of 0.60 yielded district-level MODIS agreement of R-squared 0.636, a mapped-to-MODIS burned-area ratio of 1.005, and Spearman correlation of 0.779 with district fire counts. Pixel-level MODIS agreement remained modest (F1 0.205, kappa 0.093). Zero-shot transfer to Haryana was promising (mean kappa 0.641), but Punjab cross-year stability was weak, and Sentinel-1/Sentinel-2 feature concatenation did not improve the optical baseline. Optical observations ended before the seasonal fire context, limiting coverage of late burns. The framework supports district-scale burden assessment and hotspot screening, with limited support for exact scar boundaries or temporally stable annual mapping.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15928

Runtime Safety and Emergency Stops on a Full-Size Humanoid: Deployment Lessons and a Case for Graduated Force Authority

Max Conway, Yutong Zhang, Allen Devaraj, William Xie, Alessandro Roncone, Nikolaus Correll

原文摘要

Full-size humanoid robots are being considered for hazardous industrial work such as disassembling electric-vehicle batteries. We describe the safety mechanisms of an open-source autonomy stack for the Unitree H1-2 humanoid and what deploying them taught us. All joint commands pass through a safety layer that runs separately from the control software. It enforces joint position, velocity, and torque limits, and it stops the robot when a state estimate becomes stale or when the hard-wired emergency stop (e-stop) is pressed or disconnected. We pushed the standing robot until it lost balance. With a model-predictive lower-body controller it never recovered, and the operator had to press the e-stop in every trial. Pressing it removes balance control, and the robot falls. The safety layer's own limits trigger the same stop, and limits chosen for manipulation were exceeded during normal walking. Near an operator or a battery pack, the fall can be more dangerous than the cause of the stop. Joint limits bound how much force a robot can apply, but not when applying it is appropriate. Drawing on research on responsibility and on child and adolescent development, we therefore make a case for granting robots force authority in stages, with a person or organization explicitly responsible for its use.

cs.RO

查看论文
arXiv ↗PDF ↗