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

+479新增论文
+361其中 AI 相关
+63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:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 18:06 — 2026-11-16 18:06(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:2026-11-16 13:44库内论文最新更新时间:2026-11-14 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。

23,827 已收录论文19,941 AI 相关6,921 有修订112 HF 社区发现

浏览论文库

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

找到 23,827 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:2611.13161

Cognitive Multi-Agent Search and Rescue: Language-Grounded Hierarchical Reinforcement Learning for Collaborative Robotics

Sepideh Ravanbakhsh, Hamidreza Moradi

原文摘要

Effective search and rescue (SAR) operations require autonomous systems capable of coordinating multiple heterogeneous agents, adapting to dynamic hazards, and aligning with human mission intent. Existing language-guided reinforcement learning (RL) methods primarily focus on single-agent instruction following and lack mechanisms for team-level coordination in complex, partially observable environments. This paper presents a Cognitive Multi-Agent Framework based on Language-Grounded Hierarchical Reinforcement Learning (LG-HRL) that integrates natural-language understanding, hierarchical policy decomposition, and a shared cognitive workspace to achieve cohesive multi-agent behavior in SAR scenarios. Human instructions are interpreted by a large language model (LLM) and transformed into structured semantic cues that guide high-level strategy selection and role assignment across UAV and UGV agents. A formal Language-Grounded Multi-Agent Hierarchical Decision Process (LG-MAHDP) is introduced to model the interplay between semantic grounding, hierarchical control, and distributed coordination. Comprehensive experiments in a simulated disaster environment show that LG-HRL improves learning speed by 2.3 times, increases coordination coherence by 37%, and enhances subgoal accuracy and hazard avoidance by 46% and 31%, respectively. The system achieves 20-30% higher victim rescue rates, demonstrates emergent role specialization, and adapts immediately to human verbal updates. Ablation studies confirm that both the shared cognitive workspace and language grounding are critical to overall system performance. Overall, this work establishes a new paradigm for language-guided multi-agent SAR robotics, demonstrating that semantic grounding combined with hierarchical reasoning enables safer, more efficient, and more interpretable autonomous rescue operations.

cs.AI · cs.CE

新论文 · v1arXiv:2611.13160

How Much of Your VLA Is kNN

Denis Grachev, Damien LaRocque, Omar Moured

原文摘要

Vision-language-action (VLA) models now exceed 95% success on the LIBERO simulation benchmark, yet it remains unclear how much of this performance requires generalization beyond the training demonstrations. In this work, we show that retrieving nearby demonstrations and reusing their action chunks achieves a success rate of 91.7 % on LIBERO without policy training. Under LIBERO-Plus perturbations, retrieval shows the smallest drop of all evaluated policies. Across nine publicly available VLAs, fine-tuning mostly makes the vision-language backbone a better retrieval key, and the actions of the VLAs remain close to the demonstrations. In addition, we introduce Local Action Consistency (LAC), an offline metric that measures whether nearby observations in representation space are also associated with similar future actions. We show that LAC tracks the success rate of retrieval and can guide the training of a retrieval key. Our evaluation and source code are available at https://github.com/sereact/lerobot_knn.

cs.RO · cs.AI · cs.LG

版本更新 · v2arXiv:2609.02982

Equation Recast for Canonical Operator Learning Across Parametric PDEs

Qiyun Cheng, Valentin Duruisseaux, Cesar F. Clauser, Md Hossain Sahadath, Huihua Yang, Shaowu Pan, Nathaniel Ferraro, Anima Anandkumar 等 10 位作者

原文摘要

Learning solution operators across broad parameter ranges can require substantial coverage of both input functions and physical parameters, particularly for purely data-driven parametric models. In addition, the resulting models may fail silently outside the training distribution. We introduce equation recast, which reformulates parametric operator learning as the learning of a single canonical operator. Parameter-induced operator variations are derived analytically from the governing equation and absorbed into effective sources, enabling zero-shot prediction across new parameter regimes. Across multi-parameter, nonlinear, and singular PDE settings, equation recast supports extrapolation, integrates sparse heterogeneous datasets in a shared canonical representation, and uses loss of convergence as an internal warning signal for failure of the recast iteration. In high-fidelity tokamak simulations for nuclear fusion, the framework unifies electron-temperature data across four device geometries through canonical-domain mapping within one jointly trained operator. Equation recast provides a route toward reusable neural PDE solvers combining equation-guided transfer, data efficiency, and monitorable inference.

cs.LG · physics.comp-ph · physics.plasm-ph

版本更新 · v2arXiv:2606.13954

On the Solvability of Sound Distributed Verification under Byzantine Faults

Gilde Valeria Rodríguez, Borzoo Bonakdarpour, Armando Castañeda, Sergio Rajsbaum

原文摘要

Modern distributed systems, ranging from distributed tracing platforms to blockchain oracle networks, frequently rely on processes holding partial observations to collectively certify a global execution state. Under Byzantine failures, a single malicious process withholding or fabricating partial states renders sound verification impossible, as genuine observations remain indistinguishable from fabricated assertions. To overcome this impossibility, we study input overlap x: the minimum number of processes that initially witness each element of a target execution I. We formalize this challenge as the x-reconstruction problem in asynchronous message-passing systems with up to t failures, where the goal is for all correct processes to recover I completely given an input overlap x. We establish tight matching upper and lower bounds for solvability: under crash failures, x-reconstruction is solvable if and only if x >= t + 1; under Byzantine failures, x-reconstruction is solvable if and only if x >= 2t + 1. Finally, we connect these structural bounds to semantic verification. For globally dependent safety properties (such as consensus, linearizability, k-set agreement, and leader election), sound verification under Byzantine faults requires a certificate of size c = t + 1 to guarantee at least one honest report. Consequently, sound distributed verification under Byzantine faults is achievable if and only if the input overlap satisfies x >= 2t + 1.

cs.DC

版本更新 · v2arXiv:2607.11585

Machine Learning-Based Reconstruction for Resistive Silicon Sensors

Alexander Aoki, Gaetano Barone, Leena Diehl, Gabriele Giacomini, Vagelis Gkougkousis, Hanshal Goyal, Rohan Kher, Daniel Li 等 16 位作者

原文摘要

Low-Gain Avalanche Diodes (LGADs) and AC-coupled Low-Gain Avalanche Diodes (AC-LGADs) are promising technologies for precision timing and four-dimensional tracking. In AC-LGADs, the AC pad is coupled to the resistive n$^{+}$ layer through a dielectric layer, while the gain layer remains unsegmented. This structure provides a 100\% fill factor and enables good spatial resolution with a relaxed readout pitch. The same signal-sharing mechanism that makes interpolation possible complicates the readout: charge spreads across multiple pads, the useful information can approach the electronic-noise threshold, and matrix-inversion approaches can become computationally challenging and sensitive to off-diagonal noise. In this work, we study machine-learning-based reconstruction and compression for resistive silicon sensors. We use full-waveform information from correlated pads to regularise the reconstruction and extract spatial information beyond what is available from binary readouts or reduced-amplitude summaries. We first introduce recurrent neural network models based on LSTM layers, which provide a proof-of-concept implementation for full-waveform reconstruction and have been tested for FPGA deployment using \hls. We also study routes towards bandwidth reduction with waveform rasterisation and window-selection methods, and extend the approach beyond the first model to topology-agnostic transformer-based architectures that use pad coordinates as part of the input. These models are designed to support arbitrary pad counts and geometries, mitigate edge distortions, preserve approximately $10~μ\mathrm{m}$ position resolution for $500~μ\mathrm{m}\times500~μ\mathrm{m}$ pitched sensors, and guide future resistive-silicon sensor designs

hep-ex · cs.LG · nucl-ex

新论文 · v1arXiv:2611.13150

VIGOR: Benchmarking Visual Rationale Correctness in Multimodal Large Language Models

Yanlin Chen, Tang Li, Xi Peng

原文摘要

Multimodal large language models (MLLMs) are typically evaluated by whether they produce correct answers, but correctness alone does not reveal whether their outputs are supported by the right visual evidence. We introduce VIGOR, a benchmark for evaluating VIsually GrOunded Rationales in MLLMs. VIGOR represents visual rationales as explicit concepts paired with pixel-level groundings, covering multiple abstraction levels including low-level visual properties, intermediate structures, objects, parts and high-level motion, relations. To construct VIGOR at scale, we develop an automatic annotation framework that reuses existing dense supervision when available and generates missing concept groundings through proposal-based annotation followed by conservative multimodal verification. Using VIGOR, we evaluate whether MLLMs "look at what they say" by comparing model-derived visual evidence for each expressed concept against annotated ground-truth rationales. Our results show that current MLLMs exhibit limited visual rationale correctness and reveal distinct grounding failures across concept levels. VIGOR provides a benchmark and scalable data construction pipeline for studying whether MLLM outputs are supported by appropriate visual evidence. Code is available at https://github.com/deep-real/VIGOR

cs.CV · cs.LG

版本更新 · v2arXiv:2603.12751

Show, Don't Tell: Detecting Novel Objects by Watching Human Videos

James Akl, Jose Nicolas Avendano Arbelaez, James Barabas, Jennifer L. Barry, Kalie Ching, Noam Eshed, Jiahui Fu, Michel Hidalgo 等 19 位作者

原文摘要

How can a robot quickly identify and recognize new objects shown to it during a human demonstration? Existing closed-set object detectors frequently fail at this because the objects are out-of-distribution. While open-set detectors (e.g., VLMs) sometimes succeed, they often require expensive and tedious human-in-the-loop prompt engineering to uniquely recognize novel object instances. In this paper, we present a self-supervised system that eliminates the need for tedious language descriptions and expensive prompt engineering by training a bespoke object detector on an automatically created dataset, supervised by the human demonstration itself. In our approach, "Show, Don't Tell," we show the detector the specific objects of interest during the demonstration, rather than telling the detector about these objects via complex language descriptions. By bypassing language altogether, this paradigm enables us to quickly train bespoke detectors tailored to the relevant objects observed in human task demonstrations. We develop an integrated on-robot system to deploy our "Show, Don't Tell" paradigm of automatic dataset creation and novel object-detection on a real-world robot. Empirical results demonstrate that our pipeline significantly outperforms state-of-the-art detection and recognition methods for manipulated objects, leading to improved task completion for the robot.

cs.CV · cs.LG · cs.RO

新论文 · v1arXiv:2611.13146

Everything in its right place: attention is a radio head

Lluís Arola-Fernández, Aissam Khadraoui, Alex Arenas

原文摘要

Attention, the core of language models, is a digital calculation over tokens: an exponential selects them, a division normalizes and a positional code sets the order. We show that attention can instead emerge from the synchronization of a receiver with its context tokens. Each past token is an oscillator whose state carries its content and whose frequency drifts with its age. The present token selects them by content, aligning an antenna with its query, and by position, setting the frequency of a receiver with its dial. Solving Kuramoto's problem for this receiver yields an attention layer in closed form with two phases: above a critical coupling set by the context, the receiver locks and its weights normalize; below it, it stays silent and its weights sum to less than one. Trained networks use both phases to select, abstain and count, fail where the theory predicts and keep reading far beyond the training length. Each part of attention finds its place in one device, a radio head: it tunes in to what to hear and when, and stays silent when nothing relevant is on air.

physics.soc-ph · cond-mat.dis-nn · cs.AI · cs.LG · nlin.AO

版本更新 · v2arXiv:2609.07235

Asymmetric quantum error correction efficiently tackles application-specific noise effects

Abhishek Yadav, Peter K. Schuhmacher, Michael Epping

原文摘要

Noise is a major challenge for current quantum computers. It can be broadly categorized into bit-flip and phase-flip errors. These two types do not necessarily affect the executed algorithm, thus also the application, in the same way. We illustrate this general effect for the example of the quantum approximate optimization algorithm (QAOA) applied to a small instance of the flight-gate assignment (FGA) problem. We compare bit-flip and phase-flip Pauli noise under both layer-level and gate-level noise models, using two circuit decompositions of the same ideal QAOA unitary: a CNOT-based decomposition and a native-RZZ decomposition. For the six-qubit FGA instance considered here, bit-flip noise produces a larger degradation in the optimized QAOA performance across the investigated circuit depths and noise models. The asymmetry is most pronounced in the layer-level and native-RZZ simulations. We explain this behavior through the commutation and propagation properties of the errors and their effects on the final computational-basis measurements. Since these mechanisms are not specific to the considered FGA instance, we expect similar noise asymmetries to arise in other Ising-based QAOA applications, although this remains to be investigated. We then exploit these insights to tackle noise particularly efficiently using asymmetric error-correcting codes. As an illustration, we use the quantum parity code (QPC), a generalization of the 9-qubit Shor code, and show that a smaller asymmetric code can achieve nearly the same improvement as a larger symmetric choice. This suggests that allocating error-correction resources according to algorithmic noise sensitivity, rather than physical error rates alone, can be beneficial even when the physical noise is symmetric. Finally, we discuss how information about the noise obtained through calibration can be exploited in our approach.

quant-ph · cs.ET

版本更新 · v2arXiv:2512.24340

DermaVQA-DAS: Dermatology Assessment Schema (DAS) & Datasets for Closed-Ended Question Answering & Segmentation in Patient-Generated Dermatology Images

Wen-wai Yim, Yujuan Fu, Asma Ben Abacha, Meliha Yetisgen, Noel Codella, Roberto Andres Novoa, Josep Malvehy

原文摘要

Recent advances in dermatological image analysis have been driven by large-scale annotated datasets; however, most existing benchmarks focus on dermatoscopic images and lack patient-authored queries and clinical context, limiting their applicability to patient-centered care. To address this gap, we introduce DermaVQA-DAS, an extension of the DermaVQA dataset that supports two complementary tasks: closed-ended question answering (QA) and dermatological lesion segmentation. Central to this work is the Dermatology Assessment Schema (DAS), a novel expert-developed framework that systematically captures clinically meaningful dermatological features in a structured and standardized form. DAS comprises 36 high-level and 27 fine-grained assessment questions, with multiple-choice options in English and Chinese. Leveraging DAS, we provide expert-annotated datasets for both closed QA and segmentation and benchmark state-of-the-art multimodal models. For segmentation, we evaluate multiple prompting strategies and show that prompt design impacts performance: the default prompt achieves the best results under Mean-of-Max and Mean-of-Mean evaluation aggregation schemes, while an augmented prompt incorporating both patient query title and content yields the highest performance under majority-vote-based microscore evaluation, achieving a Jaccard index of 0.395 and a Dice score of 0.566 with BiomedParse. For closed-ended QA, overall performance is strong across models, with average accuracies ranging from 0.729 to 0.798; o3 achieves the best overall accuracy (0.798), closely followed by GPT-4.1 (0.796), while Gemini-1.5-Pro shows competitive performance within the Gemini family (0.783). We publicly release DermaVQA-DAS, the DAS schema, and evaluation protocols to support and accelerate future research in patient-centered dermatological vision-language modeling (https://osf.io/72rp3).

cs.CV · cs.AI · cs.CL

新论文 · v1arXiv:2611.13144

Teaching the Harness: Student-Aware Skill Transfer for LLM Agents

Chang Liu, Bo Wu

原文摘要

Effective teaching requires reasoning about the learner as well as the task, a capacity that Theory of Mind describes as inferring another agent's latent state from its behavior. We ask whether a stronger LLM teaches a fixed student better when it applies this principle. The student is an LLM agent acting through a harness that fixes its tools, context, and action budget, so a procedure that helps one model can exhaust the budget of another. We introduce Student-Aware Teaching (SAT). The teacher builds a learner model that pairs an empirical profile with hypotheses about the student's limitations, tests these hypotheses with diagnostic probes, and writes reusable skills for the diagnosed failures. A skill enters the library only after it raises success on matched development tasks. With Claude-Sonnet-5 teaching DeepSeek-V4-Flash, SAT reaches 86.46% task success across four primary runs, leading both a profile-free teacher with the same framework (81.04%) and the untaught student (75.00%) in each run. Removing the analytical learner model lowers both prediction and success, and under misleading learner profiles none of the 48 candidate skills passes admission. When DeepSeek-V4-Flash and Gemini-3.8-Flash exchange libraries, each performs better with its own. Saved libraries keep average gains of up to 11.1 points after the teacher leaves. The benefit depends on a student that can follow instructions and a deployment route that delivers them.

cs.AI

新论文 · v1arXiv:2611.13143

Autonomous Optimization of Numerical Algorithms by an AI Agent: Application to Atomistic Simulation

Jeheon Woo

原文摘要

Coding agents built on large language models, run in automated improvement loops, can discover more efficient algorithms. We present AIOA, a framework that brings this approach to the numerical algorithms of atomistic simulation: an agent improves an algorithm against a pre-specified metric in a loop guarded by verifiers it cannot alter. Applied to ASE, a widely used atomistic simulation library, AIOA targets two facets of an algorithm: its implementation, rewritten to run faster with unchanged results, and the method itself, redesigned to converge with fewer force evaluations. Agents made six kernels 22-24 times faster on average in Python with NumPy and SciPy. On unseen problems, optimizers from the best configuration needed 3.1-3.4 times fewer force evaluations than L-BFGS for structure relaxation and 4.6-17 times fewer than standard climbing-image nudged elastic band calculations for reaction paths. The agents' optimizers also contain two algorithmic components we did not find in the literature.

physics.chem-ph · cs.AI

新论文 · v1arXiv:2611.13142

DOBB: Dynamic Oriented Bounding Boxes for Multi-Agent Collision Avoidance under State Uncertainty and Heterogeneous Dynamics

Pedro Antonio Alarcon Granadeno, Jane Cleland-Huang

原文摘要

Learning-based decentralized collision avoidance must remain reliable under state-estimation uncertainty and heterogeneous agent dynamics. Existing methods typically address these factors through training-domain variation or by exposing uncertainty and capability estimates to the policy at runtime. However, both leave the policy to infer how these quantities should alter the physical separation required for safe interaction, which can couple collision-avoidance behavior to relationships learned from the training distribution. We introduce the Dynamic Oriented Bounding Box (DOBB), an online geometric representation that maps the current state estimate, uncertainty, and agent-specific response characteristics into a dynamic, direction-dependent safety margin. We derive geometric features that jointly characterize the relative configuration and severity of interactions between agents' DOBBs, along with a reward function that preserves the physical interpretation of those interactions. Across four evaluation environments, DOBB achieves the lowest mean total failure rate of 2.6%. This performance persists under out-of-distribution shifts in actuation dynamics and state-estimation uncertainty, with collision-based failure remaining at or below 2.3% in every tested condition. We attribute this robustness to the geometric abstraction of the safety margin, which is less coupled to the specific uncertainty and actuation regimes encountered during training.

cs.RO · cs.AI

新论文 · v1arXiv:2611.13140

Agreeing on the Answer but Not the Reason: Measurement Limits of LLM Reasoning Failure Taxonomies

Madhu Sudhan Rao Beesetty

原文摘要

Failure taxonomies for LLM reasoning are increasingly reported as measurements: papers state what fraction of a model's errors fall into named categories, then compare those fractions across models. We show that for one such category the reported fraction is largely a property of the measurement procedure. We defined Compositional Collapse (a model notices a required sub-part of a problem, then drops or misapplies it) and measured it across twelve models and eleven languages on a public multilingual math benchmark (2,316 graded records). First, 50.1% of failures carry evidence for more than one category, so the reported plurality depends on the order in which the classifier tests them: reversing two tests moves it in eleven of twelve models, and across all six orderings Collapse's share spans 26.4% to 76.4%. Second, agreement collapses for the category but not for the task. Native speakers of all eleven languages judged 179 transcripts, agreeing with our inspector at kappa = 0.932 on answer correctness but only kappa = 0.093 on Collapse. A second native speaker per language re-rated 142 items; on 121 determinate pairs the two humans agree with each other at kappa = 0.659, while each agrees with the inspector at kappa <= 0.094. Re-running the same inspector model with the human instructions verbatim raises kappa against Human 2 from 0.147 to 0.636, so the gap is largely attributable to the prompt, not the model. Third, the inspector labels Collapse 1.81 times as often as native speakers, but only 1.17 times once a defective benchmark item (a deleted clause in the Bengali and Chinese translations) is excluded. We recommend four cheap checks before comparing failure-mode rates across models: report label co-occurrence, permute the tie-break, validate on a shared independent sample, and audit systematic disagreements.

cs.AI · cs.CL

新论文 · v1arXiv:2611.13138

Answering Conjunctive Queries over Linear Existential Rules with Transitivity

Cristina Feier, Tomasz Gogacz, Filip Murlak

原文摘要

We study Conjunctive Query Entailment Problem over ontologies con- sisting of Linear Tuple Generating Dependencies and transitivity asser- tions. A special case of this problem has been shown to be decidable in [1]. In particular, it covers the case of linear single head TGDs with bi- nary signature. In This paper we show that The problem for linear multi head TGDs with binary signature is Ackermanian hard

cs.DB

新论文 · v1arXiv:2611.13137

Byzantine-Robust Muon: Resilient Momentum Orthogonalization for Distributed Learning

Grigory Malinovsky, Yury Demidovich, Peter Richtárik

原文摘要

Optimization methods, including the Muon optimizer based on the Linear Minimization Oracle (LMO) and momentum orthogonalization, have shown strong empirical performance in large-scale and distributed learning, yet their robustness to adversarial behavior and data heterogeneity is not well understood. We study these methods within a unified first-order trust-region framework and analyze Muon-based updates with robust aggregation for Byzantine-robust distributed and federated learning. Our analysis does not rely on the i.i.d. assumption and introduces a non-Euclidean notion of heterogeneity consistent with the trust-region geometry. Under this framework, we establish convergence guarantees for both general non-convex and star-convex objectives. Our results provide a theoretical characterization of Byzantine-robust Muon-based optimization, with an additive heterogeneity error floor consistent with known impossibility results, under explicit aggregation assumptions. Under an explicit additive oracle-error condition, the guarantees also cover inexact orthogonalization, with the non-convex Byzantine terms in the bound's numerator unchanged but a smaller progress denominator. In simulated federated training with ResNet-18 and ViT-Tiny on CIFAR-10, additional image benchmarks, and a 38M-parameter byte-level language model on TinyStories, the tested Muon configuration attains higher attacked accuracy (lower perplexity) than the tested SGD and normalized-SGD configurations, and than sign updates on CIFAR-10. Fixed-honest controls further show a substantial RFA advantage over averaging under a bounded RFA-query attack, higher attacked accuracy for Muon-NS than tensorwise Euclidean normalization from shared checkpoints, and lower held-out TinyStories perplexity than a tuned AdamW baseline.

cs.LG

新论文 · v1arXiv:2611.13135

Which Successes Make Good References? Action-Sequence Alignment for Multi-Turn On-Policy Distillation

Mufei Li, Nikki Lijing Kuang, Zhuoer Wang, Samson Koelle, Jie Yuan, Manqing Mao, Hong Wang, Yanjun Lin 等 12 位作者

原文摘要

On-policy distillation (OPD) reduces train-inference distribution mismatch by supervising a student on its own trajectories. For multi-turn tool-use agents, conditioning the teacher on a validated same-task successful trajectory as a reference can provide useful hindsight, but different successes may reach incompatible interaction states and offer misleading supervision. We cast successful-reference selection as a free-target optimal transport problem, which reduces to assigning each failed trajectory its most compatible successful reference. Because latent state paths are hidden, we use action-sequence alignment as an observable proxy for compatibility and instantiate it with longest common subsequence (LCS), which identifies a shared ordered backbone of actions while allowing recoverable detours. This perspective makes trajectory compatibility the central criterion for reference selection in multi-turn OPD. Experiments on ALFWorld and the airline domain of $τ^3$-bench show that LCS is the only evaluated reference selector to improve over reference-free OPD on both ALFWorld overall scores and all three airline metrics. Without further optimization, the airline-trained models also transfer to the retail domain, where LCS improves all three metrics.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.13134

A Fast Algorithm for Subspace Convolution

Shlomo A. Perles, Omri Weinstein

原文摘要

A cornerstone result in Boolean lattice theory is the subset-zeta transform, which computes the $f$-weighted subset summation problem $(Z f)(B)=\sum_{A\subseteq B}f(A)$ for all $ B\subseteq[n]$ in $O(N \log N)$ additions instead of the naïve $O(3^n) = O(N^{\log_2 3})$, where $N=2^n$. This paper studies the algebraic analogue of this problem--the subspace summation problem--where subsets are replaced by linear subspaces in $\mathbb{F}_q^n$. Surprisingly, we show that this problem admits a similar $Θ_q(N_q \log N_q)$-time algorithm, where $N_q$ is the number of subspaces. This improves substantially (in both theory and practice) over lattice-based algorithms ([BHK+16, KKW16]), which are known to be optimal for addition-only algorithms over $\mathbb R$. We prove similar runtimes for inversion, rank-constrained sums and span convolution. We describe two main applications: Fast linear algebra on Grassmann graphs: Matrix--vector multiplication for arbitrary distance-invariant kernels on $N$-vertex Grassmann graphs in $O_q(N\log N)$ arithmetic operations, together with fast spectral projections and exact solutions of the corresponding linear systems. Graph coloring of low binary cut-rank graphs: An $n^{2^{r^2/4+O(1)}}$-time algorithm for computing the chromatic number and chromatic polynomial of an $n$-vertex graph, given a rank-decomposition of width $r$. We also give quantitative reductions from satisfiability and monotone constraint problems. Experiments show speedups in measured running time of up to $18$ over the covering-pair algorithm for the zeta transform, $190$ over Poisson summation for rank-constrained sums, and $22$ over the distance-matrix recurrence for Grassmann kernel multiplication. Lean 4 formalizations of the transform identities, arithmetic operation bounds, and graph-coloring constructions accompany the paper [PW26].

cs.DS · cs.CC

新论文 · v1arXiv:2611.13131

Useful Work Can Increase Energy Use: Demand Elasticity and Proof of Useful Work

Isaiah Hull, Or Sattath

原文摘要

A serious criticism of Bitcoin's Proof-of-Work is its enormous electricity consumption. Proof-of-Useful-Work (PoUW), introduced by Ball, Rosen, Sabin, and Vasudevan (2017), in which mining performs useful computations, was suggested as an alternative to reduce electricity expenditure, with matrix multiplication (MatMul) as a recent concrete instantiation by Komargodski and Weinstein (2026). Perhaps surprisingly, we show that switching to PoUW may increase the total electricity consumption, echoing Jevons' paradox. Intuitively, the PoUW mechanism acts as a subsidy that lowers the effective price of the useful work. Recall that demand is elastic if a discount of x percent in the price leads to an increase of more than x percent in the quantity demanded. If demand is elastic, the resulting increase in quantity demanded leads to a net increase in total electricity consumption; if inelastic, total electricity consumption decreases. Even then, the electricity consumption due to PoUW never vanishes, since the mining subsidy is spent on useful work that would not have been produced without the subsidy. This result is proved in a simple model with electricity-only costs, no PoUW overhead, and an unchanged mining subsidy. The analysis extends to less restrictive settings with adjusted thresholds.

cs.CR · cs.GT

新论文 · v1arXiv:2611.13127

Activation-Guided Graph Retrieval for Cognitive Memory Reconstruction in Language Model Systems

Marvin Danig

原文摘要

Retrieval-augmented language model systems generally select context by query-conditioned relevance. We argue that long-lived AI systems require a second operator: activation-conditioned memory availability. We specify an architecture in which request and goal cues seed an authorized memory graph, activation and fan attenuation allocate a bounded traversal frontier, retrieved entities recursively emit cues, and a typed evidence graph is reconstructed before generation. The specification yields five architectural consequences about candidate selection, traversal control, graph regularization, evidence reconstruction, and reinforcement. We derive implementation-level cost estimates and define ablations, failure conditions, and a reproducible evaluation protocol. The central claim is narrowed or falsified if a simpler graph reranker matches full traversal on causal and temporal recovery under equal budgets. This architecture-and-analysis preprint reports no benchmark measurements. If the claim holds, retrieval returns the evidence path that makes a memory available, not only a ranked list.

cs.AI · cs.CL · cs.IR

新论文 · v1arXiv:2611.13125

MiniZoo: An Evolving Dataset of Mini Apps for the Research Community

Luca Ferrari, Marco Alecci, Jordan Samhi, Tegawendé F. Bissyandé, Jacques Klein, Luca Verderame

原文摘要

Mini apps run within host applications (apps) such as WeChat, Alipay, Baidu, and Telegram, providing services without requiring users to install separate native apps. Their growing ecosystem has attracted research on software quality, security, and privacy, creating a need for reusable datasets. However, building and maintaining such datasets is challenging, requiring platform-specific collection infrastructure and mechanisms to handle incomplete packages, changing availability, and heterogeneous metadata. A shared, continuously maintained collection is still lacking, therefore motivating the development of a common research resource, whose value has been demonstrated by the experience of AndroZoo in the Android ecosystem. In this paper, we present MiniZoo, an evolving corpus of mini apps and associated metadata. The initial release comprises 16,273 mini-app packages, with multiple versions of the same mini apps. The dataset is managed and distributed through AndroZoo under its existing access conditions. To facilitate its reuse, we describe the collection process, data organization, provenance, and limitations, and explain how researchers can select and access the data. MiniZoo is designed to grow continuously through the addition of newly discovered mini apps, the inclusion of further host ecosystems, and the collection of successive versions of previously collected apps. This ongoing expansion will enable both comparisons across ecosystems and longitudinal studies of how mini apps evolve over time.

cs.SE

版本更新 · v2arXiv:2607.18298

Disentangling Forced and Internal Climate Variability in Single Realizations using Dynamic Mode Decomposition with Control

Nathan Mankovich, Andrei Gavrilov, Gustau Camps-Valls

原文摘要

Separating externally forced trends from internal climate variability is a fundamental challenge in climate science, particularly when analyzing observational records that exist only as a single realization. We show that a single climate realization can be decomposed into forced and internal components by treating external forcing as a dynamical driver within a linear stochastic system, an idea grounded in pullback attractor theory. This addresses a central challenge for climate projection and for detecting and attributing the forced response. Existing single-realization methods rely on linear inverse models (LIMs), which ignore forcing, or linear regression, which omits dynamics. Here we introduce PullbackDMDc, a method grounded in non-autonomous dynamical systems theory and dynamic mode decomposition with control (DMDc), incorporating pullback attractor estimation to decompose a single climate realization into spatial modes and their associated forced and internal components, yielding a physically interpretable picture of the underlying dynamics. After testing on a synthetic system with a known forced response, we illustrate the utility of PullbackDMDc for Earth System Model (ESM) evaluation by applying it to near-surface air temperature and sea-level pressure from reanalysis and four ESM large ensembles. PullbackDMDc estimates the forced response with skill matching or exceeding established baselines and helps select forcing predictors against model-based ground truth. Its internal-variability components reveal that ESMs qualitatively capture interannual and decadal modes while exhibiting systematic differences relative to each other and to observations. Skillful forced-response estimation and a novel decomposition position PullbackDMDc as a practical tool for single-realization climate analysis and ESM evaluation.

stat.ML · cs.LG · physics.ao-ph

新论文 · v1arXiv:2611.13120

Just Image Transformers with Late-Stage Pixel Refinement

Denis Lukovnikov, Andreas Müller, Asja Fischer

原文摘要

Recent work on latent-free diffusion transformers has demonstrated the feasibility of training image generators without a latent VAE. This avoids compression artifacts from the VAE and simplifies the training pipeline. In particular, JiT showed that even a standard transformer can be trained to generate images when the model is trained to predict the final image ($x$-prediction). Even though JiT unlocks training efficiency comparable to latent models, it still suffers from reduced image quality likely arising from modeling the image as a collection of large patches. In this work, we revisit JiT and show that adding simple convolutional pixel-pathway layers in a post-training phase significantly improves generation quality. Moreover, we show that the added pixel-pathway does not need to be active in the early denoising stages, and can be activated as late as in the last $20\%$ of the denoising process. Our experiments on ImageNet@256 show improvements compared to the original JiT results, achieving an FID of $1.78$ (from $2.34$ with corrected sampling), without using additional losses.

cs.CV · cs.AI

版本更新 · v2arXiv:2611.07854

Towards Foundation Decision Models: Drex

Nischay Dhankhar, Alisher Amantay, Zhanibek Datbayev, Darkhan Akhmetov, Yash Shah, Nurmukhamed Ubaidullayev, Raman Saparkhan, Dos Baha 等 9 位作者

原文摘要

Autoregressive approaches with large language models, such as long chain-of-thought reasoning, have become the default for new AI applications because they reach higher accuracy on a wide range of tasks. In production, however, they give inconsistent answers, require parsing of outputs, and add cost and latency. Decision models address this: given a question and a set of options supplied by the user, they return a probability distribution over the options without autoregressive decoding. We present Drex, a family of four open decision models with 8B (DLM), 9B (v1.5), 35B with 3B active (v2.0), and 27B (Max) parameters. Each request consists of a state (a document, record, or agent context, optionally with images) and questions about it, each asking for a choice among options, a yes/no judgment, or a score on an ordered scale. Training combines supervised fine-tuning with reinforcement learning from adjusted feedback (RLAF), plus vision tuning for Max. Ablations show that RLAF improves accuracy and that consistency losses improve robustness to option order. On Decision Index 0.4.1, Max sets a new state of the art among the decision models we compare (67.52 on the public suite vs. 60.70 for Jev 1.14.0). On Decision Bench v4, it is statistically tied with d3-turbo and GPT-6 Sol and trails Claude Opus 5.5 by 1.6 points, and it has the highest accuracy among decision models on DecideBench. Max answers a typical request in 183 ms, against about 2.0 s for GPT-6 Sol and 3.5 s for Claude Opus 5.5, and its outputs are stable under option reordering. All four models are open source: https://github.com/nace-ai/drex-decision-models

cs.CL

新论文 · v1arXiv:2611.13114

ASPIRE: An Agentic System-Identification Platform for Iterative Reasoning and Exploration

Erik Derner, Jiří Kubalík, Robert Babuška

原文摘要

System identification requires expert decisions on the identification method, incorporation of prior physical knowledge, and model validation. We propose ASPIRE, a framework for nonlinear system identification in which a large language model agent selects and executes the identification method. ASPIRE constructs closed-form, nonlinear static or dynamic models from measured data, optionally supplemented by a system description, the intended use of the model, and physical requirements expressed formally or in natural language. Each model includes its parameters, an estimation record, an interpretation of its terms, and an error evaluated on test data inaccessible to the agent. Formal physical requirements are verified independently. ASPIRE operates autonomously or interactively, allowing the agent to ask questions and the user to request further analyses and identification rounds. We evaluate ASPIRE on three measured systems: a mobile robot, a rotational system with dry friction, and a laboratory fermenter. Each system is tested with and without a description, in five runs per task. All 30 runs delivered valid models, at a cost of 0.96 to 3.38 US dollars per run. An assessment by the authors found that, for the 30 models recommended by the agent, one per run, the interpretation of the model and the documentation of its structure selection and parameter estimation fully satisfied 132 of 150 assessed items and partly satisfied 18. The most frequent discrepancy, found in nine models, concerned inaccurate or unsupported claims about model structure selection.

cs.RO · cs.AI · cs.CL · cs.LG · eess.SY

新论文 · v1arXiv:2611.13113

Building World Models from Intrinsic Motivation

Reece Keller, Declan Kutscher, Xaq Pitkow, Aran Nayebi

原文摘要

In the absence of extrinsic rewards or task supervision, human behavior is guided by intrinsic motivation---neural signals that drive curiosity, creativity, play, and other essential facets of intelligence. Intrinsic motivation plays an important developmental role in building robust world models that enable generalization and adaptation. Yet existing studies leave open how a broad range of intrinsic motivations interacts with world-model representation learning to support downstream control. This limits our understanding of which intrinsically collected experiences build reusable models. To address these gaps, we integrate 24 intrinsic objectives, including established methods and explicit variants spanning curiosity, entropy, and competency, into a common model-based reinforcement learning framework. We evaluate the world models they build through zero-shot, few-shot, and multi-task control in locomotion, manipulation, and open-ended gaming environments, using three representation-learning strategies: observation reconstruction, latent prediction, and redundancy reduction. Curiosity-driven exploration with observation reconstruction yields the strongest aggregate family profile, although the best individual pairing depends on the experiment. In compositional vision-based tasks, intrinsic motivation derived from both episodic and lifelong novelty---providing a complementary memory to the world model's generic recurrent state---achieves the best zero-shot transfer and few-shot adaptation. These findings motivate designing intrinsic motivation and representation learning jointly. Our results demonstrate world models as a powerful tool for measuring the quality of intrinsically motivated experience, and positions intrinsic motivation as a key ingredient for building world models autonomously.

cs.AI · cs.LG

新论文 · v1arXiv:2611.13107

Catch It Where It Happens: Real Time Error Correction During LLM Reasoning

Rotem Elimelech, Michael Shalyt, Ido Kaminer

原文摘要

Large language models (LLMs) are increasingly trusted with mathematical, scientific and engineering work, yet their mistakes are often confidently written and hard to spot. A single wrong step tends to propagate, making the model waste inference tokens following a false premise. Existing safeguards either check only the final answer and restart from scratch, or rely on a verifier LLM that competes for GPU capacity and slows down response time. We propose online, deterministic verification: many kinds of reasoning steps can be validated by code, so a step can be verified in real time, as it is written, without any model call or GPU use. Whenever a check fails, we point out the mistake and let the model continue from the same spot. We demonstrate this approach on symbolic mathematics, where derivations already contain explicit expressions that a computer algebra system can check in milliseconds. Tested on the ASyMoB benchmark with three open-weights models, our online validation improves accuracy by 1.4-5.6 percentage points, corresponding to a 1.8-14.9% net reduction in incorrect answers, while increasing token usage by only 6-7%. Because the verifier is independent of the model, the approach complements progress in LLMs rather than competing with it: every new model can benefit immediately, and the benefit grows as deterministic checkers extend to more kinds of reasoning steps.

cs.CL

版本更新 · v3arXiv:2609.18784

Computing the entropy rate of a quantized stationary Gaussian process

Jeremy Magland

原文摘要

The entropy rate of a uniformly quantized stationary Gaussian process is the fundamental limit on its lossless compression. It has no closed form, and the classical high-resolution approximation breaks down whenever the spectral density is small on part of the band, as routine smoothing and filtering produce. Here we present two methods for computing the rate. The first is an analytical approximation, obtained from an exact dithering identity and the Kolmogorov-Szegő formula, in which the quantization noise power acts as a floor on the spectral density. The second is a Monte Carlo estimate of the exact rate: a minimum-phase moving-average representation makes the quantized sequence a hidden Markov process whose optimal particle filter is available in closed form, and the filter's log-likelihood on one long sequence gives the rate. The approximation agrees with the estimate to within a few millibits per sample over most of the parameter range for quantization steps up to the signal standard deviation, including processes on which the classical formula fails; for coarser steps the estimate should be used instead. At a step of a quarter of the standard deviation, linear predictive coding comes within 2 to 4 percent of the rate, FLAC within 3 to 32 percent, and general-purpose compressors remain 12 to 89 percent above it.

cs.IT

版本更新 · v2arXiv:2610.39568

Diffusion models for the $O(3)$ nonlinear sigma model

Daniel Schubring

原文摘要

A score-based diffusion model is trained on the two-dimensional classical Heisenberg model, the lattice representation of the $O(3)$ nonlinear sigma model. Neural networks are trained on three different coarse-grainings of the same training set to implement a multiscale sampling scheme that modestly improves both the accuracy and computational cost of direct sampling on the finest lattice. Stein (or Schwinger-Dyson) diagnostics for the two-point correlation function are introduced to assess the quality of the learned score without relying on reverse diffusion sampling. These diagnostics are also incorporated into an additional training loss. We discuss several technical considerations relevant to implementing diffusion models on $S^2$. These include a consideration of lifting the network input to $S^3$, as in the $CP^1$ representation, and developing a boundary-layer approximation to the short-time spherical heat kernel that extends its usefulness to larger diffusion times.

cond-mat.stat-mech · cs.LG · hep-lat

新论文 · v1arXiv:2611.13077

One Temperature to Rule Them All?

Aviv Orly, Ori Shem-Ur, Yaron Oz

原文摘要

Inference-time sampling is a central mechanism for improving large language models, with temperature controlling the tradeoff between reliability and diversity. While recent work suggests that varying temperature across samples can improve multi-sample inference, simple fixed-temperature schemes remain the standard in practice. We investigate this discrepancy in the canonical pass@K setting, asking when temperature diversity is useful, and when a single tuned temperature suffices. To this end, we analyze per-question success probabilities across multiple models and datasets, tracking how they vary with sampling temperature. We identify several consistent properties of these profiles, including that harder questions are less likely to share efficient sampling temperatures, although this trend is only logarithmic in hardness. We then derive an efficient method for evaluating the theoretically optimal multi-temperature allocation scheme, and show that although such a scheme improves performance, its gains over single-temperature baselines are typically modest when temperature is tuned as a function of the sampling budget K. We explain this phenomenon through mathematical mechanisms that we call dulling effects, and show how they ensure the robustness of temperature choices across different question distributions. Our results clarify when multi-temperature sampling is useful, and how temperatures should ideally be chosen.

cs.LG · cs.AI · cs.CL