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 05:56 — 2026-11-16 05:56（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:2611.15926

NVIDIA Vera: A Microarchitecture-Level Comparison with Grace, Turin, and Granite Rapids

Joseph Moore, Thomas Green, Simon McIntosh-Smith

原文摘要

The majority of new HPC systems are centered around NVIDIA, AMD, or Intel CPUs. Vera is NVIDIA's latest data-center CPU, including its first custom data-center core design, Olympus. This paper investigates Vera in comparison to AMD Turin and Intel Granite Rapids, using NVIDIA Grace as a baseline. We navigate up the performance ladder, from microbenchmarks that isolate performance metrics, through NAS kernels and miniapps, to single-socket performance of a range of scientific codes. We find that Vera achieves the best performance of the architectures evaluated in most codes tested, and that this gain is primarily attributed to its high memory bandwidth, effective Spatial Multithreading implementation, and low-latency memory subsystem aided by the architecture's predictive structures. While Vera represents a major leap over its predecessor, we show that its comparatively modest floating-point performance trails Intel and AMD in a small number of compute-bound workloads reflecting NVIDIA's GPU focus for such workloads.

cs.DC · cs.AR · cs.PF

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.28498

Copied, Mixed or Computed? Testing Latent Intermediate Values with Minimal Pairs

Aur Shalev Merin

原文摘要

Probing studies of latent reasoning read a model's state where the answer begins, and take a successful probe as evidence that an intermediate value was computed and a failed one as evidence that it was not. With prompts that differ in one token, we show that a digit copied from the question is present there in two looped and two standard language models, while a probe that sees one prompt at a time reads it at no more than 0.52 even after 45,000 training questions. Every token we varied leaves such a trace, so a successful probe may be reading the inputs. We give a protocol that tests a candidate value against copies of the inputs, against generic mixing of them (an operation swap with a bar set on synthetic mixtures), and for use (a clamp that controls for the copy), and we check each test where the answer is known. The clamp detects values a model is about to write or reads four tokens later, an unwritten bridge entity in two-hop recall (and not where it is readable but unused), and, in small transformers trained from scratch, an unwritten value used eight tokens later. Our first operation swap failed its positive control; its variance-based replacement passed two fresh controls but, in the small transformers, fires wherever the value is present. In the looped Ouro-1.4B the protocol finds a small code of the unwritten intermediate whose sign follows the operation, but it cannot be told apart from the answer with a copied number added back, and whether the model uses it is unresolved. For a published claim that sub-answers are computed only while a chain of thought is written, weaker tests suggest an early sub-answer; in correctly answered direct answers, whole-state patches find the sub-answer not carried on its own past its equation and, with different answers, the partner's answer in 8% of pairs (below our bar), mostly from the "=" before the answer (post hoc).

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15925

ShadowBench: Exposing Lexical Anchoring and the Illusion of Forgetting in Large Language Models

Sujan Maharjan, Lu Liu

原文摘要

Large Language Models (LLMs) have emerged as primary interfaces for factual retrieval, yet current evaluation paradigms rely almost exclusively on explicit entity names. In this work, we demonstrate that LLM knowledge is fundamentally lexically anchored: models possess extensive factual information but find it significantly difficult to retrieve without explicit name tokens. To quantify this limitation, we introduce ShadowBench, a rigorously hardened, shortcut-resistant benchmark designed to evaluate Latent Entity Association via a novel Dual-Trait Association (DTA) task. Our evaluation reveals a pervasive "Shadow Gap" across all model scales$\unicode{x2013}$up to the frontier models GPT-5.4 and Claude-Sonnet-4.6$\unicode{x2013}$where removing lexical anchors causes performance drops of over 20%. Furthermore, we demonstrate that this lexical dependency exposes a critical vulnerability in AI safety. Applying ShadowBench to Machine Unlearning, we find that state-of-the-art algorithms (e.g., Gradient Difference, NPO) achieve only superficial lexical erasure. While unlearned models fail on direct queries, our novel Latent Entity Leakage Rate (LELR) metric reveals that for popular entities, models explicitly reconstruct the "forgotten" entity in their internal reasoning traces in over 74% of cases, utilizing residual shadow knowledge to solve associative tasks. Conversely, for niche entities, models retain high shadow accuracy (60-90%) via implicit attribute correlation despite 0% LELR. Ultimately, ShadowBench indicates that current unlearning paradigms create an "Illusion of Forgetting," demonstrating that existing methods act as superficial output filters and are not yet reliable for achieving true parametric erasure.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15924

The Distributed Run Manager A C++ Library for Distributed Processing

Brian Harrawood

原文摘要

The DistributedRunManager (DRM) is a C++ library for distributing a computing task among a number of computer systems for parallel processing on a network. The library was originally designed to accelerate synthetic image production for tomographic images, but is also a general solution for distributing a software task across diverse, multiple hardware platforms. The DRM self-configures using a novel C++ class, the ElectionManager. This class selects a server cooperatively at runtime and eliminates the need for a priori distribution configuration. All communication, logging, and fault-tolerance mechanisms are encapsulated by the DRM, providing a "black-box" interface to the application developer.

cs.CE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.05420

When AI Classifies: What Counts as Public Administration?

Shaoming Cheng, Laurie A. Schintler

原文摘要

This study examines how alternative systems of scholarly representation identify and characterize public administration (PA) and artificial intelligence-related PA (AI-in-PA) scholarship. The central question is not which system provides a definitive classification of PA, but how alternative systems of scholarly classification differ in identifying and representing its intellectual boundaries. With an exploratory and comparative analysis of Web of Science and OpenAlex, the study compares five approaches based on author-defined, citation-driven, and AI-assisted representations. The results highlight substantial differences and limited overlap in corpus size, publication type, DOI availability, publishing outlets, temporal patterns, and thematic structure. The alternative approaches tend to produce distinct representations because they identify substantially different bodies of scholarship rather than merely larger or smaller subsets of the same literature. The findings suggest that algorithmic knowledge organization influences how interdisciplinary scholarship is classified, connected, and understood and, epistemologically, how its visibility, structure, and intellectual identity are represented. AI-enabled scholarly classifications are not neutral but interpretative, potentially self-reinforcing, and may constrain the evolution and adaptation of disciplinary boundaries. Human expert judgment therefore remains essential and is complemented rather than replaced by AI-assisted scholarly classification.

cs.DL · cs.AI · cs.CY · cs.DB

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15920

Spec-Driven PBT: Deriving Semantic Invariants from Code Specifications for Agentic Property-based Testing

Aditya Shukla, Kartik Gupta, Ali Alavi, Pashootan Vaezipoor

原文摘要

Software is increasingly written by AI agents that produce an implementation from a natural language specification, a practice known as agentic coding. Code is now produced faster than it can be reviewed, and has been shown to exhibit its own characteristic failure patterns. Property-based testing (PBT), a long-standing technique in which invariant properties of a program are checked against many generated inputs, has recently been revisited with LLM agents authoring the properties, thereby removing the high-effort derivation of invariants that has long hindered its adoption. Existing methods, however, derive these properties from the implementation alone (Code-driven PBT). At the same time, a thorough specification such as a product requirements document has become routine within agentic coding, yet its role in testing the resulting code remains underexplored. We study the value of the specification as a source of properties for testing agent-written code. Our key insight is that the specification, unlike the implementation, records what the code was meant to do, and invariants derived from it are not biased by particular implementation choices. We propose Spec-Driven PBT, an agent that first expresses invariants in natural language from the specification and only then inspects the implementation to translate them into concrete tests. Across 25 applications from ViBench, Spec-Driven PBT finds a novel set of bugs that Code-driven PBT misses, while writing 2.4x fewer property tests. Though the two approaches surface a roughly equivalent number of bugs, there is little overlap: nearly 60% of the 169 total bugs are found by only one. Qualitatively, we find that the bugs unique to Spec-Driven PBT tend to violate documented product workflows whereas those to Code-driven PBT instead concentrate on implementation robustness, offering complementary value for bug discovery in agent-written code.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15917

Owned Edits to a Shared Decision Rule: Learning Private Exceptions as Typed, Gated, Withdrawable Weight Edits

John J. O'Hare

原文摘要

Organisations that apply the same published decision rule often hold private evidence that the rule is wrong for their own cases, and will not pool it. We describe a learning mechanism for that setting whose unit of change is an owned edit. The published rule is compiled exactly into a small ReLU network, a structured prior. Each party's learner searches a small typed space of declarations, a few named values such as subject, scope, form and size, and proposes one only when its own records pass a selection-aware evidence gate. The learning is that gated search around the prior. In two analyses registered before they ran, on synthetic data with 20 sampled hidden truths, the learner at 30 records per party was non-inferior, within 2 points, to all seven tuned baselines (a confined gradient learner, Ditto, FedRep, federated averaging, two pooled networks and pooled gradient-boosted trees), scoring 96.6% against 91.7% for the unchanged rule; the same search without the prior or the gate scored 84.0%. In a third registered test, typed edits over a network trained on shared records beat that network alone by 5.4 points and the same edits over the published rule by 3.1. An acceptance body recomputes each edit from its declaration and writes it into units reserved for that party, so by construction an edit changes no decision about any other subject, withdraws exactly, discloses at most log2 of the typed space's size in bits, and can hide nothing beyond its declared values. We report where it loses: truths shared by all parties, relaxations, ten records, a pre-stated gate criterion that failed in both runs, and a language model given the records that decided about as accurately on one draw. On a rule-only base, a table of owned exceptions makes the same decisions.

cs.LG · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15911

Smart Model Routing for Order-of-Magnitude LLM Cost Reduction

Hesham Elbakoury, Deep Shah, Ankur Sharma

原文摘要

Frontier large language models (LLMs) deliver the strongest response quality but carry per-token prices often more than an order of magnitude above those of smaller, task-adequate models. Smart model routing addresses this mismatch by assigning each query to the cheapest model expected to answer it adequately, rather than sending every request to the most capable, most expensive endpoint. This paper develops a formal cost-quality optimization framework for routing -- including a derived optimal threshold-policy structure, a calibration-versus-discrimination distinction, a cascade breakeven condition, and a sensitivity analysis over price ratio and traffic skew -- situates that framework against the principal routing architectures and the signals used to estimate query difficulty, and works through a numerical example showing how a calibrated router can reduce blended inference cost by roughly an order of magnitude relative to an always-frontier deployment under specific, stated pricing and traffic assumptions, reporting both the gross reduction from routing policy alone and the net figure with the router's own overhead priced in. We situate this figure against the range reported by published routing systems (roughly 2x to frontier-level accuracy at one-fifth the cost), and close with the practical risks -- under- and over-routing, aggregate quality constraints masking segment-level harm, calibration without discrimination, calibration drift, prompt injection into routing signals, and operational failures such as tier outages and multi-provider price variation -- that determine whether the savings materialize in production. The analysis is primarily analytical, complemented by a GSM8K evaluation of the cascade framework (Section 5), validated (Section 5.2); extending the evaluation across tasks and model families is future work.

cs.DC · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.12407

Tamper-Proofing with Self-Modifying Code

Gregory Morse, Tamás Kozsik

原文摘要

Classical computability theory tells us that self-modifying code (SMC) on a deterministic universal Turing machine can be simulated by non-SMC code on the same model. That abstraction, however, omits the external timing inputs, concurrency, and microarchitectural state that dominate practical execution on modern processors. We argue that once timing, ordering, and self-introspective effects are treated as observables, a practically faithful non-SMC reproduction of timed SMC becomes detectably expensive on commodity systems. We present a tamper-proofing model that combines introspective and polymorphic SMC, reliable clocks, and runtime timing predicates to bind integrity checks to execution behavior. We distinguish static and dynamic SMC generation, characterize the timing semantics needed to avoid catastrophic pipeline clears, and give x86-64 design primitives for checksum-driven self-patching. We also report timer measurements, performance comparisons, and performance-monitoring counter evidence showing that careful engineering - especially loop unrolling and cross-page modification - substantially reduces the overhead of SMC while preserving its tamper-detection value. The paper concludes with an efficiency analysis, a threat model, and deployment guidance for trusted code executing in untrusted environments. The threat model is formalized in Lean 4, relative to an explicit platform contract: the security theorem, the necessity of each assumption and which assumptions each adversary level satisfies or breaks are machine-checked, and the development is registered with the Palomar registry.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15904

HeriKGQA: Grounded Knowledge-Graph Question Answering over Cultural Heritage Sensor Data

Lingxiao Kong, Vasileios Arampatzakis, Vasileios Sevetlidis, George Pavlidis, Zeyd Boukhers

原文摘要

Cultural heritage sites are increasingly monitored by sensor networks, but querying their data requires database expertise. Large Language Models (LLMs) offer a natural-language interface, yet over raw sensor records they lose track of which sensor, site, and time each value belongs to, and silently miscompute. We present HeriKGQA, a knowledge-graph question-answering method that confines the LLM to interpreting questions and phrasing answers, leaving computation to SPARQL and deterministic code. Questions are parsed into intents constrained by a heritage ontology aligning W3C SOSA/SSN with CIDOC-CRM, compiled into SPARQL, and answered from query results and temporal, spatial, and anomaly facts derived by a grounding layer, with error correction guarding each LLM step. On 500 questions over real data from five heritage sites, HeriKGQA reaches 99.0% accuracy, 18.2 points above the strongest of three baselines using the same LLM and receiving the same anomaly rules and answer conventions, with comparable answer quality while running almost four times faster. Without grounding, accuracy drops by 12.2 points and on anomaly questions from 99% to 66%. We report lessons from development and live deployment.

cs.CL · cs.AI · cs.DB · cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.05435

DP-MacAdam: Differentially Private Mechanism with Adaptive Clipping and Adaptive Momentum

Naima Tasnim, Lalitha Sankar, Oliver Kosut

原文摘要

Differentially private stochastic gradient descent (DP-SGD) has become the standard framework for privacy-preserving machine learning, yet its reliance on a fixed gradient clipping threshold to limit sensitivity remains a significant practical limitation. Adaptive clipping algorithms such as AdaClip shift and scale the gradient prior to clipping and adding noise so that the clipped gradient yields a more informative descent direction. The shift and scaling parameters are selected adaptively based on the empirical mean and variance. However, in existing adaptive clipping algorithms, these empirical estimates have not been also used for momentum to accelerate training itself. On the other hand, DP-Adam is an algorithm that exploits Adam-like momentum updates based on the gradient mean and variance to accelerate training, but does not exploit these estimates for adaptive clipping. In this work, we propose Differentially Private Mechanism with Adaptive Clipping and Adaptive Momentum (DP-MacAdam), a novel algorithm that combines these two approaches so as to use the same mean and variance estimates for both clipping and momentum. We perform an analysis showing that DP-MacAdam estimates the gradient variances in a bias-free manner. In addition, we empirically evaluate the privacy and accuracy of DP-MacAdam, demonstrating that it achieves improved model utility compared to DP-SGD, AdaClip, and DP-Adam baselines, without requiring manual tuning of the clipping threshold.

cs.LG · cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.38520

What Hallucinations Have We Measured? Semantic Illusion, Confabulation, and Expressed Uncertainty

Hazel H. Kim, Jakub Binkowski, Ekaterina Fadeeva, Juan David Guerra, Yijie Hao, Zheng Yi Ho, Baixiang Huang, Buyun Liang 等 26 位作者

原文摘要

Hallucination remains one of the most critical challenges in deploying large lan- guage models (LLMs) reliably and safely. Yet the term is used inconsistently across the research community. We argue for a strict definition of hallucinations in LLMs. First, hallucinations should be confident incorrectness, kept separate from expressed uncertainty (UNK). UNK reveals that the model may be wrong, whereas a hallucination does not reveal it and is therefore more dangerous in prac- tice. Conflating the two obscures their distinct behaviors and makes them hard to study. Second, hallucinations should be split by a simple re-elicitation test: does any semantically equivalent prompt recover the correct response? This test probes whether the relevant knowledge is accessible. If none does, the knowledge is likely absent or inaccessible, and the error type is a confabulation (CF) that likely requires external knowledge or retraining; if some does, the knowledge is accessible from the model but applied inconsistently, and the error type is a semantic illusion (SI) that simple prompt or decoding changes can mitigate3. Re-evaluating 14 recent hallucination methods under this taxonomy yields three findings. (1) Mitigation methods are far more effective for SI than for CF. (2) Detection methods flag UNK more often than hallucinated responses (i.e., SI and CF). (3) Latent signals are more informative than output-level signals for CF. An audit of recent hallucination papers shows that most conflate these categories. We recommend reporting CF, SI, and UNK separately, and introduce a practical labeling protocol that needs only a modest number of semantically equivalent prompts.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2607.12775

Learning-enabled Acceleration of Scenario-based Model Predictive Control

Trinh Tran, Binh Nguyen, Truong X. Nghiem

原文摘要

Scenario-based model predictive control (SBMPC) is a variant of model predictive control (MPC) that explicitly accounts for uncertainty by optimizing control actions over multiple predicted scenarios. However, its computational complexity increases rapidly with the number of scenarios and prediction horizon, limiting its applicability to real-time planning and control. This paper presents a learning-accelerated Alternating Direction Method of Multipliers (ADMM) algorithm for efficiently solving SBMPC problems by leveraging parallel computing and Moreau envelope learning, while maintaining high solution accuracy. We reformulate the SBMPC problems into consensus forms that can be decomposed via ADMM, separating the scenario-dependent dynamics from non-anticipativity constraints and enabling parallel updates across scenarios and time steps. Building on this decomposition, we utilize a learning-to-optimize scheme that leverages Moreau envelope learning of the cost function to accelerate the primal update in ADMM, thereby reducing computation time. The proposed framework is evaluated on a microgrid energy management problem subject to load and renewable generation uncertainties. Comparisons with IPOPT and MadNLP, two popular and modern nonlinear programming solvers, demonstrate substantial computational speedups while maintaining reliable closed-loop control performance.

math.OC · cs.LG · eess.SY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.06262

SonoDyno: A Sonic Dynamometer for Engine Speed and Load Estimation from Audio

Robin Doerfler, Beat Rossmy

原文摘要

Controllable engine sound synthesis, Active Sound Design and engine order analysis all build on the relationship between the sound of an engine and its momentary operating state: its speed and its load. Recordings of engine sound are abundant in archives, sample packs and online video, yet they rarely carry time-aligned annotations of that state, which limits their applicability to controllable engine sound generation. We present SonoDyno, which estimates the engine speed, the cylinder count and an engine-normalized load intensity from a microphone signal alone, with no tachometer, no bus access and no prior knowledge of the engine configuration. A convolutional scorer of 124,302 parameters reads the energy at the engine orders, the harmonics of half the rotation frequency, in each frame at three time-frequency resolutions to jointly score cylinder count and speed, and a decoder imposes the rotational dynamics of the engine on the speed trajectory. A second head estimates the load intensity, the position of the torque between the engine's drag floor at 0 and its full-load ceiling at 1, from the order levels at the decoded speed. On recordings of engines it has never heard, with microphone position, engine type and cylinder count unknown, SonoDyno places 93 to 97% of the frames within 2% of the true speed, identifies the cylinder count with 80% accuracy and confuses the octave on fewer than 2% of the frames. On an unseen engine of a known type, the load intensity has a mean absolute error of 0.12, and the sign of the torque, driving or braking, is right on 91% of the frames. General pitch trackers fall behind even when the harmonic order of each engine is supplied: on our validation recordings and at a tolerance of 5%, the best of them places 62% of the frames within the tolerance, against 96% for SonoDyno.

cs.SD · eess.AS · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15895

Your Hypergradient is Skewed: Antithetic Neumann Estimation for Bilevel Optimization

Jason Bohne, Pawel Polak, Gary Kazantsev, David Rosenberg

原文摘要

Bilevel optimization is a core tool in practical machine learning workflows, including hyperparameter tuning, data reweighting, robust learning, reinforcement learning, and imbalanced classification. Hypergradient computation requires the inverse of the inner Hessian, typically estimated via a truncated Neumann series. While existing analyses focus on bias and variance, we show that the product structure of the Neumann series introduces a third source of error: skewness. We identify that, unlike ordinary gradients, whose asymmetry is suppressed by mini-batch averaging, the Neumann estimator amplifies skewness across factors, with the third-moment error growing, under weak contraction, with truncation depth, inner condition number, and per-factor noise asymmetry. This arises in many practical settings such as corrupted labels, outliers, heterogeneous or class-imbalanced datasets. To address this, we introduce the Antithetic Neumann Estimator (ANE), which pairs each Hessian sample with a mirrored counterpart around a reference Hessian and averages the resulting inverse-Hessian estimates. With an exact reference, the antithetic product retains only even-order noise, eliminating all odd-order perturbation terms; with an approximate reference, the residual odd-order contribution is bounded linearly in the reference error. ANE requires only a modification of the Hessian vector step and combines with existing stochastic or variance-reduced bilevel methods. We instantiate ANE-SGD and ANE-VR, the latter adding recursive variance reduction. Across robust regression, data cleaning, offline reinforcement learning, and imbalanced classification, ANE-based methods improve on stochastic and variance-reduced baselines on every task (20 seeds each), lowering loss by 4 to 25% relative to the best baseline; the largest gains, on robust regression, are a 25% lower test loss and a 54% higher test r-squared.

cs.LG · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15885

Reward-Driven Collider Physics Challenges for Self-Improving Agentic AI via Reinforcement Learning

Alexander Yue, Qibin Liu, Julia Gonski

原文摘要

Recent advances in agentic AI have demonstrated the potential to automate complex high-energy physics (HEP) workflows. We focus on the regime of HEP tasks where frontier models still struggle to provide correct and complete solutions, and introduce an open-ended optimization task format with continuous, automatically evaluated rewards. Unlike conventional benchmarks focused on task completion, these tasks target reinforcement learning (RL) environments to generate agentic improvement on state- of-the-art HEP challenges. We benchmark frontier reasoning models on several HEP tasks and demonstrate an initial proof of concept in which a small language model improves through RL using automated feedback without human intervention. By connecting challenging HEP problems with verifiable scientific rewards and RL, we aim to advance agentic AI from reproducing established workflows to autonomously discovering better scientific solutions, paving the way toward self-improving scientific agents.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15849

Sharp Lower Bounds for Parallel Log-Concave Sampling

Evan Dogariu

原文摘要

How many rounds of parallel queries are needed to sample from a smooth, strongly log-concave distribution on $\mathbb{R}^d$? For every fixed condition number $κ\in (1, \infty)$, we prove that any sampler making polynomially many queries per round requires $Ω_κ(\log d)$ rounds to achieve constant total variation error in the worst case. The lower bound holds even if queries return derivatives of all orders. Together with the first-order parallel Picard algorithm of \cite{zhou2025parallel}, this establishes a depth complexity of $Θ_κ(\log d)$ for parallel log-concave sampling with $\operatorname{poly}(d)$ width. We then study centered Gaussian targets to understand how much width is needed at a given depth. From \cite{chewi2023query,zhou2026complexitygaussiansampling}, it is known that either one round of width $d$ or $\mathcal{O}(\sqrtκ \log d)$ rounds of constant width suffice for first-order Gaussian sampling. At fixed $κ$ we characterize the depth-width tradeoff interpolating between these regimes: when using $ \lceil c \log d\rceil$ rounds, if $0 < c < c_\star(κ)$ then the optimal width at constant TV error is $\widetildeΘ(d^{1-c/c_\star(κ)})$, while if $c \geq c_\star(κ)$ then it is $Θ_κ(1)$. Here, $c_\star(κ)$ is an explicit constant with $c_\star(κ) \sim \sqrtκ / 8$ as $κ\to \infty$.

cs.DS · math.PR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15847

SoK: Design Choices in Tendermint BFT Consensus

Sanaz Taheri-Boshrooyeh, Yahya Hassanzadeh-Nazarabadi

原文摘要

Tendermint is a consensus protocol that tolerates Byzantine faults, implemented first by the Tendermint Core engine and now by CometBFT. Realizing the protocol's separation of agreement from execution, the Application Blockchain Interface (ABCI) of these engines keeps consensus apart from the replicated application, so one engine can serve many independent proof-of-stake chains. A sustained body of research proposes changes that span the protocol's mechanisms, from vote dissemination to block proposal and reward distribution, yet to our knowledge no survey studies the protocol and these works as one family, and broader surveys do not take Tendermint as their subject. We describe the baseline, the protocol as consolidated from its original descriptions, by its design choices. Each is a decision, such as how votes spread or how proposers rotate, through which the baseline provides safety and liveness or another property under its fault and timing model. We classify each work by the design choice it renegotiates, that is, modifies or replaces, by the properties it strengthens or weakens, and by whether its result needs a stronger model. Taking a broader perspective on that classification, we group the surveyed works' solutions into a few threads of concern in the baseline, namely its performance, the accountability of its validators, and the protection of exploitable information. For each thread, we identify the recurring strategies that their approaches follow. Together, these threads and strategies describe the current state of research on the Tendermint family. Where the strategies leave gaps, we pose future directions, each as an open question under an explicit fault and timing model.

cs.DC · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15846

Conflict-Free Cuts: Exploring the Boundaries of Tractability

Subrahmanyam Kalyanasundaram, Subodh Kumar

原文摘要

A conflict-free cut of a host graph $G$ is an edge cut containing no conflicting pair of edges. The conflicts are specified by a conflict graph $\widehat G$ whose vertex set is $E(G)$. The conflict-free cut problem asks if the given instance $(G, \widehat G)$ has a conflict-free cut. When restricted to planar $G$ and 1-regular $\widehat G$, the problem is polynomial time solvable when $G$ has maximum degree 4, but NP-complete already at maximum degree 5. We study the complexity of conflict-free cut problem under restrictions on the degrees of $G$, the components of $\widehat G$, and the locality of the conflicts. A conflict is local if its two edges share an endpoint in $G$. We prove the following results. * For $Δ(\widehat G)\le1$, a directed-cycle formulation gives a polynomial-time algorithm when $|E(G)|\le2|V(G)|$, hence for maximum degree four. The problem is NP-complete on $5$-regular hosts with exactly $1$-regular conflicts. * For $Δ(\widehat G)\le1$, we give a constructive FPT algorithm in $s_4(G)=\sum_v\max\{0,d_G(v)-4\}$, single-exponential for planar hosts. For arbitrary conflicts, we give an XP algorithm in $η=\max\{0,|E(\widehat G)|-|V(G)|\}$. * On $4$-regular hosts, local exactly $2$-regular conflicts with components $C_3,C_4$ give NP-completeness. For local conflicts at maximum degree four, pair or triangle components separately permit polynomial algorithms, but mixing them gives NP-completeness. We classify cases where $\widehat G$ is a union of cliques. * An $a$-COC is a vertex set whose deletion leaves components of order at most $a$. For local conflicts, the problem is FPT in the minimum $2$-COC size, but NP-complete with a supplied $3$-COC of size six. Without locality, hardness holds with a supplied $2$-COC of size six. Both hardness results use exactly $1$-regular conflicts.

cs.DS · math.CO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15844

Open Vision Banana: A Fully Open Recipe for Generative Visual Perception

Arpit Jadon, Valentinos Pariza, Jona Ruthardt, Ryousuke Yamada, A. Sophia Koepke, Andrei Bursuc, Yuki M. Asano

原文摘要

Recent work suggests that pretrained image generators encode real-world understanding beyond image synthesis. Vision Banana exploits this by framing vision tasks as conditional image editing. However, its data, weights, code, and implementation details are not public. We present Open Vision Banana (OVB), a fully open and reproducible recipe for converting pretrained generators into unified multi-task perception systems. Our analyses identify the design choices that matter most for generalization, including color encoding, prompt design, parameter adaptation, and task balancing. These choices interact, so individually helpful choices can hurt when combined with others. Starting from 4B and 9B parameter open-weight base models and using 2.1M-3.8M training pairs from public datasets, OVB surpasses Vision Banana's reported Cityscapes zero-shot performance (73.9 vs. 69.9 mIoU) and rivals state-of-the-art affine-invariant depth estimators. Its non-zero-shot variants come within five points of Vision Banana on referring and reasoning segmentation but remain further behind on instance segmentation. All models largely retain the base model's image-editing abilities. With legend ensembling, we introduce a test-time scaling method for generator-based perception. It segments an image under several class-color legends and fuses the results by majority vote, correcting unstable color-class bindings and improving mIoU by up to 8.7 points on Cityscapes and 15.0 points on COCO-Object without retraining. We release the dataset construction and processing pipeline, the training and evaluation code, as well as the final, intermediate, and ablation checkpoints. Project website: https://openvisionbanana.github.io

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15843

Food Critic: An Agentic Visualization System for Auditable Restaurant-Safety Reasoning

Arleth Salinas, Ishrat Jahan Eliza, Valerio Pascucci

原文摘要

Generative AI agents are increasingly being embedded into visualization systems that can search data, invoke tools, summarize evidence, and produce recommendations. However, when agents rely solely on their own knowledge, the visualization problem is not only whether the agent provides a useful answer, but also whether users can inspect how that answer is grounded. We present Food Critic, an agentic visualization system for diners' restaurant decision support that integrates public health inspection records with crowd review data. The system grounds agents under three conditions: a database-only ReAct agent, a retrieval- augmented agent with access to food-safety regulations, and an ontology-guided agent that produces structured hypotheses and typed evidence. Food Critic externalizes the agent's reasoning within these groundings as inspectable visual evidence. We evaluate LLM models with several use cases under each grounding of our agentic system. Our work positions restaurant choice as a concrete case for studying human-agent collaboration, visual provenance of agent reasoning, and the design of visual interfaces for grounded GenAI decision support.

cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15842

Fewer Expert Transfers Without Changing Routing: Expert Eviction for MoE Offloading

Pierre-Luc Bacon, Diego Calanzone, Jean-Maxime Larouche

原文摘要

A mixture-of-experts (MoE) language model uses only a few experts per token, so a server can keep most expert weights in CPU memory and copy an expert to the GPU when the router requests it. Recent methods train the router to keep the same experts for several tokens, and treat fewer routing switches as a proxy for fewer copies. We measure the trade-off directly, in a harness that performs and times real CPU-to-GPU copies for OLMoE-1B-7B. On an L40S GPU, every tested policy that holds an expert set fixed and decodes faster than the least-recently-used (LRU) cache increases next-token loss by at least 0.067 nats. A change that leaves every routing decision intact does better: when the cache must evict an expert, evict the one whose next use lies farthest in the future. This rule copies 2.1x fewer experts than LRU at no loss in quality and is within 3.5% of the fewest copies possible. It needs future requests; the next sixteen tokens of demand recover 96% of its reduction, whereas a rule based on counts of past requests recovers 27%.

cs.LG · cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.07546

Meta-Scaling Laws: On the Invariance and Generality of Neural Scaling

Xing Han, Liu Ziyin, Suchi Saria, Paul Pu Liang

原文摘要

Neural scaling laws establish a predictable relationship between model performance and data or compute, offering crucial guidance for resource allocation in new domains and tasks. Yet such laws are most needed precisely where they are hardest to obtain: fitting one for a new model and task pair demands expensive sweeps that typically exhaust the very compute budget the law is meant to economize. We study meta-scaling laws: relations that characterize when neural scaling behavior is preserved and predict how it changes under data transformations, enabling forecasts across domains when the shift can be approximated by a compatible transformation. We address this by identifying the right invariants: scaling laws are preserved under bijective (information-preserving) transformations of the data and modified in predictable, information-theoretically grounded ways under non-bijective transformations that lower its information resolution $ρ$: a single axis along which a law fit in one domain can be transported to another. We validate this across language, vision, and speech, and demonstrate two cross-domain applications: predicting scaling for language models trained on electronic health records from laws fit on general text, and predicting time-series classification scaling under varying levels of noise injection, recovering the data-scaling exponents to within $3\%$ error.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15839

k-partite quantum homomorphisms

Amin Karamlou

原文摘要

$k$-partite XOR games and linear binary constraint system (BCS) games arise from systems of linear equations over $\mathbb{Z}_2$, providing distinct quantum relaxations of the same classical constraint satisfaction problem (CSP). Linear BCS games have been generalised to synchronous homomorphism games on arbitrary relational structures, with compositional semantics provided by the quantum monad. We introduce $k$-partite homomorphism games, extending $k$-XOR games from linear systems to arbitrary relational structures. This yields a framework for studying multipartite quantum CSPs and quantum homomorphisms. We characterise perfect strategies in both the tensor-product and commuting-operator models as Kleisli morphisms of suitable state-dependent graded quantum monads on a category of $k$-partite relational structures. We then study quantum advantage in the pseudotelepathic sense: the existence of a perfect quantum strategy without a perfect classical strategy. We show that synchronous and $k$-partite quantum advantage are incomparable at the level of CSP instances. The GHZ instance admits three-player quantum advantage but no synchronous commuting-operator advantage, whereas the magic-square instance admits synchronous quantum advantage but no $k$-partite commuting-operator advantage for any number of players or proper colouring. We also exhibit an explicit six-element template whose CSP is NP-complete and admits two-player quantum advantage. Finally, we prove that no bounded-width CSP template admits $k$-partite quantum advantage, even in the commuting-operator model.

quant-ph · cs.LO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15838

Before AI Agents Negotiate for Us: A Competitive Tournament of Rule-Based, Search, Optimization, Learned, and Language-Model Negotiators Under Scarcity

Eduardo de Avila-Armenta, Raúl Alejandro Aquino-Ibarra, Jorge Octavio Nicolás-Díaz, Umberto Leon-Dominguez

原文摘要

Automated bilateral negotiation underlies two-sided matching markets such as freight brokering, where many shippers and carriers negotiate price before a matching mechanism decides who is paired with whom. Prior strategy comparisons typically use isolated one-on-one duels or a single fixed market, so they cannot show how a strategy behaves against several live rivals under a changing balance of supply and demand. We built nine negotiation architectures spanning rule-based, search-based, optimization-based, imitation-learning, and reinforcement-learning families, and ran all nine simultaneously on both sides of a Gale-Shapley matching market under a balanced condition and two scarcity conditions rotated across all 36 exclusion pairs. In the balanced carrier market, an imitation-learned engine (ML2), a reinforcement-learning policy trained only on isolated negotiations (RL), and an expected-utility optimization engine (OPT) formed a statistically tied top group, and no architecture led in every condition and role. RL beat all eight carrier rivals when carriers were scarce, but its match rate collapsed from 62% to 16% when shippers were scarce and it had to compete with the other carrier agents for demand. A second reinforcement-learning policy trained against rival agents (RL2) kept its match rate above 91% in every condition, yet lost on realized payoff to all eight shipper-side rivals in two of the three conditions, traced to a confirmed train/deployment feature mismatch. We also tested nine large language models (LLMs), from 1 to 72 billion parameters, under the same protocol: they lost significantly to the two strongest engines (OPT2 and ML2) in 32 of 36 comparisons and won none. These results show that isolated or single-condition evaluation can hide failure modes that a many-sided, scarcity-varying, statistically corrected tournament exposes directly.

cs.AI · cs.GT · cs.LG · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15837

The BEATS Dataset: Towards Understanding Music-Physiology Dynamics in Real-World Scenarios

Benjamin Gutierrez Serafin, Tanaya Guha, Fahim Kawsar

原文摘要

We introduce the BEATS dataset, a robust compilation of psycho-physiological data collected in the wild from 30 participants while they listened to curated playlists intended to promote well-being. An acronym for Biomarkers, Experience and Affect from Therapeutic Soundscapes, the BEATS dataset aims to support research on wellbeing, music psychology, affective computing and signal processing. More specifically, this dataset includes: (1) sensor data collected during music listening sessions using a research-grade wearable device in free-movement environments; (2) music listening activity records, stimulus metadata, acoustic features, and self-reports associated with the listening sessions (3) individual characteristics, such as demographics, music preference, musical skills, and personality traits; and (4) self-reported psychological measures before and after their experimental participation spanning for a number of weeks. By situating data collection outside of lab settings, the BEATS dataset offers the opportunity to study real-world music-listening scenarios, allowing for a richer exploration of the physiological, subjective and therapeutic effects of music under real-world conditions.

eess.SP · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15835

Controlling the Probability of Unknown Unknowns in Pre-Deployment Testing of AI Systems

Rachel Li, Chris Hays, Aaditya Ramdas, Manish Raghavan

原文摘要

In pre-deployment testing of AI systems such as AI agents, a developer can often deal with known failure modes (e.g., leaking API keys, deleting important databases, or installing a malicious package) by implementing fixes or making contingency plans for when the same issue might occur again. What is more challenging are the unknown unknowns: the unseen failure modes that haven't surfaced during testing. The decision to stop testing and deploy therefore faces an inherent tradeoff: continue testing to observe more behaviors, at the cost of time and resources, or stop testing and deploy, at the risk of failure modes remaining undiscovered. How then does the developer decide when they have tested enough? To answer this, we develop an algorithm that certifies when the probability of observing an unseen failure mode is sufficiently small. The algorithm constructs an anytime-valid upper confidence sequence on this quantity, so the developer can repeatedly test a system, inspect the bound, and decide to stop when it falls below a chosen threshold without invalidating the statistical guarantee. Our problem can be interpreted as a sequential variant of the missing-mass estimation problem which gave rise to the classic Good-Turing estimator (Good, 1953). On SWE-Chat, a dataset of real-world coding agent traces (Baumann et al., 2026), we implement our procedure and show that it achieves tighter upper bounds than a simple multiple-testing corrected Good-Turing baseline, and even dominates a fixed-horizon (non-multiple-testing-corrected) Good-Turing upper confidence bound, which is not anytime valid. Additionally, to better match realistic evaluation pipelines, we extend our method to handle sampling from a different task distribution and imperfect automated failure labeling.

cs.AI · cs.CY · math.ST

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15834

Where to Generate Touch: Do Image Latents Preserve Material Recognition?

Wanghao Ye, Aarosh Das, Sihan Chen, Yiting Wang, Bowei Tian, Guoheng Sun, Shwai He, Zheyu Shen 等 29 位作者

原文摘要

Generated touch could extend robot learning beyond recorded contacts. A tactile generator needs a latent space, and we choose one by testing whether a material classifier trained on real GelSight presses still works on encode-decode reconstructions from pretrained image models. On ObjectFolder Real, the classifier loses 6.5 to 9.7 points on reconstructions from three 16x discrete tokenizers and 0.3 points on those from the Stable Diffusion VAE (SD-VAE). The 16x tokenizers again lose far more on Touch and Go and on DIGIT object recognition (YCB-Slide). Retraining the classifier on reconstructions, with no new labels, narrows the discrete gap. SD-VAE reconstructions also keep object identity, with 76.7% object-matching accuracy against 78.9% for real touch and 67.0% for MAGVIT-v2. We therefore select SD-VAE latents and show a photo-to-touch generator trained in them. Code will be released upon acceptance.

cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15831

NIBench: benchmarking autonomous AI agents for execution, skill evolution and scientific judgment in neuroimaging

Lujia Zhong, Yihao Xia, Jianwei Zhang, Shuo Huang, Xinyu Nie, Mingyang Xia, Zhiwei Deng, Jiaxin Yue 等 11 位作者

原文摘要

Autonomous AI agents are increasingly used to automate biomedical research, creating a growing need to benchmark their capabilities on real scientific data and workflows. Their reliability in neuroimaging remains insufficiently characterized, where plausible analytical outputs can conceal errors that affect scientific conclusions. Existing studies have advanced scientific question answering and tool-based automation, but provide limited evidence on workflow reconstruction, acquisition of procedural expertise and evidence-based scientific judgment. Here we present NIBench, a neuroimaging benchmark comprising three complementary evaluations of autonomous agents. First, we benchmark execution and workflow reconstruction using 56 tasks across seven tool ecosystems, covering structural, diffusion and functional magnetic resonance imaging, positron emission tomography and multimodal analyses. Second, we examine whether agents can evolve their procedural skills through distillation of execution trajectories, evaluating the resulting skills on previously encountered tasks, unseen tasks and other models. Third, we assess scientific judgment using 36 claims from published Alzheimer's disease studies, requiring agents to analyse raw cohort data and provide reproducible evidence. We evaluate 19 language models within a shared agent framework, with selected models undergoing skill distillation and claim evaluation. Leading agents execute supplied analysis protocols nearly perfectly, whereas withholding procedural guidance widens performance differences. Distilled skills improve performance on acquisition tasks and transfer between models, but benefits on unseen tasks are inconsistent. Agents reproduce their reported results yet sometimes reach conclusions inconsistent with expert-derived answers, and access to data does not always improve judgment.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15829

Training Calibrated Conditional Generative Models with a Sample-Only Coverage Loss

Benjamin Remy, Raphael Rossellini, Chihway Chang, Rebecca Willett

原文摘要

Conditional generative models have become the tool of choice for sampling posteriors in scientific inverse problems, where we seek to sample images or signals conditioned on a set of indirect and noisy measurements. Yet they are often overconfident, which is a critical failure in scientific applications where accurate uncertainty quantification is essential. Existing regularizers fall short in complementary ways: differentiable coverage objectives require the model's density and do not identify the posterior, while strictly proper scoring rules such as the energy score need only samples but do not directly enforce coverage. We close this gap by introducing a differentiable loss function based on the expected coverage probability, estimated from samples alone. It applies to any conditional generative model, with no need for tractable densities or architectural changes. We prove that it is a strict divergence, vanishing if and only if the model equals the true posterior. On simulation-based inference benchmarks, it matches a density-based coverage loss without evaluating the density. On high-dimensional imaging inverse problems, it yields better-calibrated posteriors than scoring-rule regularizers, with little change in the reconstruction quality of point estimates.

cs.LG · stat.ME · stat.ML

查看论文
arXiv ↗PDF ↗