跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+1352新增论文
+1083其中 AI 相关
+143已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 15:04各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 15:33 — 2026-11-19 15:33(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:2026-11-19 06:59最近发现新增版本:2026-11-19 15:04库内论文最新更新时间:2026-11-19 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。

27,409 已收录论文22,787 AI 相关8,342 有修订112 HF 社区发现

论文修订列表

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 8,342 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
版本更新 · v3arXiv:2610.34599

An Agentic AI Workflow for Liver Lesion Segmentation and Structured Radiology Reporting

Fatma Ahmed Mansour, Rahatara Ferdousi, Zyad Medhat Mahmoud Ashor, Manar Fathy Elshenawy, Ibrahim Shehaby, Salma Elmongi, S. Ahmed

原文摘要

Despite advances in automated liver lesion segmentation, a gap remains between image-derived predictions and clinically interpretable radiology reports. Bridging this gap requires quantitative measurements that are both reproducible and traceable. We present an evidence-grounded agentic AI framework that connects liver and lesion segmentation with deterministic quantification and structured reporting. TotalSegmentator-based nnU-Net models delineate the liver, Couinaud segments, and lesions, while computational tools extract volumes, dimensions, counts, and anatomical locations. A large language model (LLM) organizes these measurements into a predefined reporting schema, with numerical consistency checks against source measurements. On 51 LiTS cases, the segmentation stage achieved a liver Dice score of 0.947, lesion sensitivity of 75.6%, and positive predictive value of 68.9%. Exploratory screening of 25,494 MERLIN reports identified 10,208 (40.0%) with liver-related abnormalities. By connecting quantitative imaging evidence with agentic report generation, this work takes a step toward human-centered medical AI that prioritizes traceability and clinical relevance.

cs.CV · cs.LG

版本更新 · v2arXiv:2606.05138

Generating Financial Time Series by Matching Random Convolutional Features

Konrad J. Mueller, Nikita Zozoulenko, Ben Wood, Thomas Cass, Lukas Gonon

原文摘要

Generating realistic financial time series is challenging as training data is often limited to a single historical path. With such scarce data, overfitting is hard to avoid, especially under adversarial training where a trained discriminator can memorize the training samples. To mitigate this, recent approaches train generators to minimize the discrepancy between untrained feature representations of real and generated time series. In these works, the feature maps are based on path signatures, which can fail to capture relevant time series properties at tractable truncation depths. In this work, we instead train generators by matching random convolutional features of real and generated time series. Existing random convolutional feature maps, such as Rocket and Hydra, have been shown to provide informative representations of real-world time series, but cannot supervise generative models because they are non-differentiable. We introduce SOCK (SOft Competing Kernels), a fully differentiable random convolutional feature map, suited to train generative time series models. We show that generators trained by matching random SOCK features outperform signature and diffusion baselines on most evaluation metrics across a wide range of small-sample financial datasets. We further demonstrate SOCK's expressiveness on two-sample hypothesis testing and time series classification tasks, where SOCK matches or outperforms existing unsupervised feature maps.

cs.LG · q-fin.ST

版本更新 · v2arXiv:2601.09859

Tune-Up Open-Weight CLIP: Optimization Framework for Self-Supervised Fine-tuning of CLIP

Anant Mehta, Xingyu Chen, Xiyuan Wei, Tianbao Yang

原文摘要

CLIP has become a cornerstone of multimodal representation learning, yet improving its performance typically requires a prohibitively costly process of training from scratch on billions of samples. We ask a different question: Can we improve the performance of open-weight CLIP models across various downstream tasks using only existing self-supervised datasets? Unlike supervised fine-tuning, which adapts a pretrained model to a single downstream task, our setting seeks to improve general performance across various tasks. However, as both our experiments and prior studies reveal, simply applying standard training protocols starting from an open-weight CLIP model often fails, leading to performance degradation. In this paper, we introduce TuneCLIP, a self-supervised fine-tuning framework that overcomes the performance degradation. TuneCLIP has two key components: (1) a warm-up stage of recovering optimization statistics to reduce cold-start bias, inspired by theoretical analysis, and (2) a fine-tuning stage of optimizing a new contrastive loss to mitigate the penalization on false negative pairs. Our extensive experiments show that TuneCLIP consistently improves performance across model architectures and scales. Notably, it elevates leading open-weight models like SigLIP (ViT-B/16), achieving gains of up to +2.5% on ImageNet and related out-of-distribution benchmarks, and +1.2% on the highly competitive DataComp benchmark, setting a new strong baseline for efficient post-pretraining adaptation. The code is available at https://github.com/Optimization-AI/TuneCLIP.

cs.CV · cs.LG

版本更新 · v2arXiv:2610.10446

Subset Sum via Partial Match

Baitian Li, Lixi Ye

原文摘要

We show that the subset sum problem can be solved in randomized time $O(2^{0.49999\overline{7}n})$, breaking the $2^{n/2}$ meet-in-the-middle barrier. Our approach builds on the representation technique framework of Randolph and Węgrzycki (STOC 2026). We choose a representation for which testing the compatibility of pairs of partial solution vectors is exactly the partial match problem. To beat exponent $1/2$ for subset sum, it then suffices to give a nontrivial partial match algorithm in a certain parameter regime. We achieve this by designing a depth-2 linear circuit for the partial match matrix, which yields an efficient algorithm via the framework of Alman and Li (FOCS 2025).

cs.DS · cs.CC

版本更新 · v2arXiv:2610.42112

Subquadratic Attention with a Hierarchical Tree-Structured Indexer

Leon Lufkin, Cutter Dawes, Alexander Speicher, Kamesh Krishnamurthy, Tomás Figliolia, Beren Millidge

原文摘要

The quadratic scaling of attention is a fundamental bottleneck limiting the long-context capabilities of large language models (LLMs). A variety of approaches have attempted to circumvent this, but they either fail to match attention's expressiveness (e.g., sliding-window or linear attention variants with fixed-size state) or only achieve constant-factor speedups (e.g., sparse attention methods whose indexers themselves scale quadratically). In this paper, we derive an asymptotically subquadratic sparse attention method based on a hierarchical, tree-structured indexer, which we call Zyphra Hierarchical Attention (ZHA). ZHA constructs a tree of recursively compressed key summaries over the KV cache, which future queries traverse from the top down to retrieve a sparse subset of keys. Crucially, by iteratively growing the tree's depth, the total cost including routing and final attention grows sublinearly in sequence length, resulting in overall subquadratic (but superlinear) scaling for attention. We demonstrate that ZHA can be cheaply applied to existing pretrained models with only a short KL distillation training stage of a billion tokens, and maintains performance on long-context retrieval and challenging reasoning, mathematical, and agentic coding evaluation tasks. Moreover, we show that our method is highly robust to tree geometry including very deep trees of up to 6 levels. Finally, we develop a detailed performance model and show that our approach scales subquadratically, dramatically outperforms competing methods beyond 1 million tokens of context, and ultimately has the potential to extend effective context windows to the hundreds of millions or billions of tokens.

cs.CL · cs.AI

版本更新 · v2arXiv:2603.10052

OmniGuide: Universal Spatial Guidance Fields for Enhancing Generalist Robot Policies

Yunzhou Song, Long Le, Yong-Hyun Park, Jie Wang, Junyao Shi, Lingjie Liu, Jiatao Gu, Eric Eaton 等 10 位作者

原文摘要

Vision-language-action (VLA) models have shown great promise as generalist policies for a large range of relatively simple tasks. However, they demonstrate limited performance on more complex tasks, such as those requiring complex spatial or semantic understanding, manipulation in clutter, or precise manipulation. We propose OmniGuide, a flexible framework that improves VLA performance on such tasks by leveraging arbitrary sources of guidance, such as 3D foundation models, semantic-reasoning VLMs, and human pose models. We show how many kinds of guidance can be naturally expressed as differentiable energy functions with task-specific attractors and repellers located in 3D space, that influence the sampling of VLA actions. In this way, OmniGuide enables guidance sources with complementary task-relevant strengths to improve a VLA model's performance on challenging tasks. Extensive experiments in both simulation and real-world environments, across diverse sources of guidance, demonstrate that OmniGuide enhances the performance of state-of-the-art generalist policies (e.g., $π_{0.5}$, GR00T N1.6) significantly across success and safety rates. Critically, our unified framework matches or surpasses the performance of prior methods designed to incorporate specific sources of guidance into VLA policies. Project page: https://omniguide.github.io/

cs.RO · cs.LG

版本更新 · v2arXiv:2603.20406

Thinking in Different Spaces: Domain-Specific Latent Geometry Survives Cross-Architecture Translation

Marcus Armstrong, Navid Ayoobi, Arjun Mukherjee

原文摘要

We investigate whether independently trained language models converge to geometrically compatible latent representations, and whether this compatibility can be exploited to correct model behavior at inference time without any weight updates. We learn a linear projection matrix that maps activation vectors from a large teacher model into the coordinate system of a smaller student model, then intervene on the student's residual stream during generation by substituting its internal state with the translated teacher representation. Across a fully crossed experimental matrix of 20 heterogeneous teacher-student pairings spanning mixture-of-experts, dense, code-specialized, and synthetically trained architectures, the Ridge projection consistently achieves R^2 = 0.50 on verbal reasoning and R^2 = 0.40 on mathematical reasoning, collapsing to R^2 = -0.22 under permutation control and R^2 = 0.01 under L_1 regularization. Behavioral correction rates range from 14.0% to 50.0% on TruthfulQA (mean 25.2%) and from 8.5% to 43.3% on GSM8K arithmetic reasoning (mean 25.5%), demonstrating that the method generalizes across fundamentally different reasoning domains. We report a near-zero correlation between geometric alignment quality and behavioral correction rate (r = -0.07), revealing a dissociation between representation space fidelity and output space impact. Intervention strength is architecture-specific: student models exhibit characteristic sensitivity profiles that invert across domains, with the most steerable verbal student becoming the least steerable mathematical student. Finally, a double dissociation experiment conducted across all 20 model pairings confirms without exception that projection matrices collapse catastrophically when transferred across reasoning domains (mean R^2 = -3.83 in both transfer directions), establishing domain-specific subspace geometry as a universal property of LMs.

cs.LG · cs.AI

版本更新 · v2arXiv:2610.34556

Admissible sets of integers in imaginary quadratic fields of class number 1

Daniel Shiu

原文摘要

Let $\mathcal O_K$ be the ring of integers of a number field $K$. A finite subset $\mathcal H=\{η_1,\ldots,η_k\}\subset\mathcal O_K$ is said to be \emph{admissible} if for every prime ideal $\mathfrak p$ in $\mathcal O_K$, the reductions of the $η_i$ modulo $\mathfrak p$ do not represent every residue class. The diameter of a finite subset $S$ of $\mathcal O_K$ is defined to be \[\mathrm{diam}(S):= \max_{η_i,η_j\in S:η_i\neqη_j}|\mathcal N(η_i-η_j)|\] where $\mathcal N$ denotes the norm down to the rational field. This paper computationally investigates admissible subsets of rings of integers in imaginary quadratic fields of class number 1 (such as the Gaussian integers or the Eisenstein integers) that are large relative to their diameter. The motivation is twofold. Firstly, there is the improvement of results analogous to the question of an upper bound for the least gap between large rational primes, which has been one of the great number theoretic successes of the twenty-first century. A second motivation is that there is the opportunity to disprove a variation of the second Hardy-Littlewood conjecture. The calculations in the paper provide new records on the smallest distance between primes in the fields in question, and explicit counter-examples to a generalisation of the second Hardy-Littlewood conjecture in all bar one of the fields.

math.NT · cs.DM

版本更新 · v2arXiv:2606.11425

JailbreakOPT: Iterative Jailbreak Prompt Optimization with Macro-Action

Ge Shi, Jun Yin, Donglin Xie, Fangyi Liu, Yucan Li, Menglin Liu

原文摘要

Jailbreak attacks expose persistent safety weaknesses in large language models (LLMs), but existing stateless single-turn methods face a trade-off: hand-crafted prompts are expressive but static, while iterative prompt optimization can adapt but often relies on low-level mutations that require many target-model responses. We propose JailbreakOPT, a method that maintains a library of reusable prompt transformations (actions) and composes them into macro-actions for within-episode search, generating standalone attack prompts. To reuse experience across episodes, JailbreakOPT learns an action-selection policy using contextual Thompson sampling and outcomes from prior search paths. Experiments across multiple LLMs and benchmarks show that JailbreakOPT improves attack success rate (ASR) over single-action and iterative baselines. More broadly, exploration and exploitation over human-designed attack strategies can help probe residual vulnerabilities and identify failure patterns that may inform defenses aimed at broader classes of attacks.

cs.CR · cs.AI

版本更新 · v2arXiv:2606.04858

Integer points close to a transcendental curve: an algorithmic approach

Nicolas Brisebarre, Guillaume Hanrot

原文摘要

In this article, we propose an algorithmic approach to determine the integer points located near a transcendental curve. This approach is closely related to a celebrated work by Bombieri and Pila and to the so-called Coppersmith's method. We establish the underlying theoretical foundations, prove the algorithms, study their complexity and present practical experiments; we also compare our approach with previously existing ones. From a practical point of view, we focus on an instance of our general problem, called the Table Maker's Dilemma, whose solving makes it possible to evaluate a given function with correct rounding. Our experiments show a significant speedup. In particular, our results show that the development of a correctly rounded mathematical library for the binary128 format is now possible at a much smaller cost than with previously existing approaches.

math.NT · cs.SC

版本更新 · v2arXiv:2605.09481

TSNBench: Benchmarking LLM Proficiency in Time-Sensitive Networking

Rubi Debnath, Daniel Bujosa Mateu, Luxi Zhao, Silviu S. Craciunas, Paul Pop, Sebastian Steinhorst

原文摘要

We present TSNBench, the first benchmark for evaluating large language model (LLM) proficiency in Time-Sensitive Networking (TSN), a suite of IEEE 802.1 standards for deterministic communication with bounded latency in safety-critical domains such as autonomous vehicles, aviation, defense, and industrial automation. While LLMs have been extensively evaluated on general knowledge tasks, their capabilities in safety-critical networking domains remain largely unexplored. TSNBench comprises 939 expert-validated multiple-choice questions (MCQs) covering diverse TSN mechanisms, along with 100 open-ended Worst-Case Delay (WCD) computation tasks for each of Credit-Based Shaper (CBS) and Cyclic Queuing and Forwarding (CQF), across varying topologies and traffic flows. The ground-truth (GT) WCD values are computed using a verified Network Calculus (NC) solver for CBS and closed-form upper bounds for CQF. We evaluate 16 LLMs and find that although models achieve 67 to 95% accuracy on MCQs, they fail substantially on open-ended WCD computation. For CBS, the best-performing model, GPT-5, deviates from the GT by 150.2 $μ$s on average (mean absolute error, MAE), and its predicted WCD is within 50 $μ$s of the GT for only 39.4% of flows, while all other models exceed an MAE of 250 $μ$s. Providing the WCD equations in the prompt lowers the error for 9 of 10 models on CQF but only 2 of 9 on CBS. Such errors are large relative to TSN latency budgets and can lead to violations of real-time constraints and unsafe configurations. TSNBench demonstrates that MCQ benchmarks may overestimate LLM capabilities in safety-critical networking.

cs.NI

版本更新 · v2arXiv:2610.38277

The Role of Quantization in Loss Spikes

Zaiqian Chen, Aditya Somasundaram, Sophie Li, Sean McLeish, John Kirchenbauer, Tom Goldstein, Micah Goldblum

原文摘要

Loss spikes in language model pretraining can waste substantial compute and derail otherwise healthy training runs. A primary driver of these instabilities is the growth and divergence of output logits in the final language modeling (LM) head. In this work, we study a particularly costly form of this instability associated with output logit growth: delayed, terminal divergences that emerge only after prolonged training, which we call time-bomb spikes. We find that these instabilities are preceded by rapidly growing quantization error in the LM head, which eventually culminates in a loss spike. Crucially, reducing numerical precision accelerates time-bomb spikes, while increasing precision improves stability. We then propose a simple yet effective mitigation that replaces AdamW on the LM head with SGD with momentum, suppressing logit growth and improving stability over long training horizons. Finally, we find that existing mitigation techniques from the literature (along with our own) all reduce quantization error, suggesting a shared numerical mechanism behind their effectiveness. Together, our results identify finite precision error as a hidden driver of time-bomb spikes and show that suppressing this error is key to stable long-horizon pretraining.

cs.LG · cs.AI

版本更新 · v2arXiv:2608.23307

Teach Your DBMS to LIKE Strings: Fast and General Pattern Matching for Wildcard Joins and Filters

Lam-Duy Nguyen, Pascal Ginter, Duc-Tam Nguyen, Thomas Neumann, Viktor Leis

原文摘要

Nowadays, modern applications do more than just store text -- they need to derive meaningful insights from it. To do that, they usually rely on wildcard queries with LIKE predicate to extract patterns. However, modern database management systems (DBMSs) handle these wildcard operations poorly, resorting to nested loops for joins and expensive interpreted evaluation for filters. To address the former, we propose a new join algorithm based on the Aho-Corasick algorithm, which significantly reduces the time complexity. For wildcard filtering, we leverage the code-generation infrastructure to improve performance: we generate specialized code for the LIKE predicate, eliminating the overhead of interpreting the pattern per tuple. Our experimental results show that the new wildcard join algorithm significantly outperforms both baseline DuckDB and Umbra, achieving speedups of up to 30.6x and 114.75x, respectively. The new wildcard filter approach likewise outperforms both baselines, achieving a speedup of 13.3x in a filter-focused stress benchmark. We believe these two techniques will play key roles for high-performance text analytics in modern query engines.

cs.DB

版本更新 · v2arXiv:2610.36019

Causal DAG-Guided Reinforcement Learning for Long-Term Physical Activity Maintenance: Using Prior Data to Inform Future Deployment

Xueqing Liu, Young Hyun Cho, Bhanu Teja Gullapalli, Predrag Klasnja, Susan Murphy

原文摘要

Digital health interventions can provide scalable, personalized support for physical activity (PA), yet sustaining PA over the long-term remains difficult. Because affective experiences with PA are important for activity sustainment, we developed an online reinforcement learning (RL) system for the forthcoming ADAPT factorial trial that personalizes twice-daily activity suggestions aimed at improving affective associations with PA. This setting poses several challenges: participant-specific data are scarce relative to the candidate state space, important states and rewards are partially observed, interventions are frequent while the primary outcome is measured weekly, and activity suggestions can both improve PA-related experiences and increase intervention burden. We address these challenges using an expert-specified causal directed acyclic graph as an integrated RL design tool, guiding state construction, estimation of partially observed states, delayed credit assignment, and representation of beneficial and adverse intervention pathways. We further construct a longitudinal simulator calibrated from a prior micro-randomized trial to compare candidate RL designs under realistic state evolution, missingness, and participant heterogeneity before deployment. Together, this work illustrates how causal domain knowledge and prior trial data can make long-horizon, participant-specific RL more practical for digital health interventions targeting sustained behavior change.

stat.AP · cs.LG

版本更新 · v7arXiv:2601.14252

Semantic Completeness for Correct Maintenance: A Strict Hierarchy of Typing and Inheritance

Tristan Simas

原文摘要

Removing nominal types or inheritance is defended as reducing burden; cited Java and Go rationales measure no comparison. Correct maintenance minimizes outside answers and repair obligations, preserving required answers and excluding invalid states. Answers identify meanings, memberships, and required implementations. Five capacities form a strict chain. With nominal identities fixed, only multiple contract and implementation parents attain the answer-and-repair optimum on every finite declared history. Incomplete mechanisms force slop: answers restated in code or tooling. In 20 pinned multiple-inheritance Python projects, recovered implementation-class pairs grouped by source class would need outside supply: 12,880 without inheritance, 8,792 under first parents, 739 under sound one-parent optima (checked), zero with multiple parents. With provider and state carriers fixed, state-bearing rows alone force 236 outside pairs. Java and C# interface defaults supply no instance state. At least 24 of 65 size-qualified wheels among the top 150 pure-Python downloads have positive recovered gap (36.9%, 34 unscored). For distinct, independently changing implementations, the ancestry gap is the exact outside-pair minimum with one parent supplying only required pairs, even with reparenting, infinite helpers, delegation, or generators. Zero gap and one-parent contract coverage hold iff class sets nest or are disjoint. Identical records with distinct answers need the confusability graph's chromatic number of keys. Every tree-shaped growth step inserting an off-path provider strictly between ancestors forces one-parent repair. Every snapshot in our constructed history has gap zero, yet repair obligations recur each step; multiple parents add one edge per step. At fixed design costs, bans never lower optima; savings imply suboptimal unrestricted choices.

cs.IT · cs.PL

版本更新 · v3arXiv:2606.03344

RogueMerge: Robust and Unified Attacks against LLM Model Merging

Jinghuai Zhang, Yetian He, Kunlin Cai, Han Zhao, Fnu Suya, Yuan Tian

原文摘要

Model merging composes specialized capabilities into a single LLM by aggregating task-specific LLMs sourced from unverified public platforms, exposing a critical supply-chain attack surface: Because any malicious behavior can be encoded into a task vector, and merging grants third-party vectors direct write access to model weights, an attacker-provided task vector can enable or amplify diverse downstream threats. Prior work only examines backdoor attacks against model merging for classifiers using static arithmetic heuristics, which fail to effectively achieve diverse attacks on generative LLMs for three reasons: (i) LLMs rely on autoregressive decoding, where even a minor parameter drift introduced by merging compounds across tokens and rapidly degrades the attack. (ii) Attackers have no knowledge of the victim's merging configurations, causing a static attack vector optimized in isolation to be easily diluted or neutralized. (iii) Practical threat induction must generalize to attack prompts unseen during optimization, which static vectors cannot adequately encode. In light of these gaps, we present RogueMerge, the first unified attack framework addressing all three challenges. To handle autoregressive generation, we replace static arithmetic with a joint optimization that explicitly enforces attack success after merging. To better simulate unknown merging settings, we formulate attack injection as a stochastic min-max optimization problem and solve it via meta-gradient descent. To generalize across heterogeneous attack prompts, we employ distributionally robust optimization and derive a tractable first-order Taylor approximation at LLM scale, with a provable error bound. Across four threats, six merging algorithms, and over 170 merged LLMs, RogueMerge consistently outperforms prior attacks. It also remains stable across diverse merging settings and resists standard defenses.

cs.CR · cs.LG

版本更新 · v3arXiv:2605.14939

Real-time virtual circuits for plasma shape control via neural network emulators

Alasdair Ross, George K. Holt, Kamran Pentland, Adriano Agnello, Nicola C. Amorisco, Pedro Cavestany, Aran Garrod, Timothy Nunn 等 10 位作者

原文摘要

Reliable position and shape control in tokamak plasmas requires accurate real-time regulation of several strongly coupled shape parameters. The control vectors that disentangle these couplings, referred to as \textit{virtual circuits} (VCs), enable independent shape parameter control for a specific Grad--Shafranov (GS) equilibrium. Numerical calculation of VCs is not currently feasible in real time, therefore VCs are usually computed prior to each experiment, using a small number of reference GS equilibria sampled along the desired scenario trajectory, with each VC used to control the plasma within a preset time interval. While effective near the reference equilibrium, this approach can lead to degraded performance as the plasma departs from the reference equilibrium and/or from the desired trajectory, and it complicates the design of robust control strategies for rapidly evolving plasma configurations. In this paper, we construct neural-network-based emulators of plasma shape parameters from which VCs can be derived, to provide the MAST Upgrade (MAST-U) plasma control system with state-aware VCs in real-time. To do this, we develop an extensive library of over a million simulated GS equilibria, covering a substantial portion of the MAST-U operational space. These emulators provide differentiable functions whose gradients can be rapidly computed, enabling the derivation of accurate VCs for real-time shape control. We perform extensive verification of the emulated VCs by testing whether they disentangle the control problem. The neural-network-based approach delivers high accuracy and orthogonality across a diverse range of equilibria. This work establishes the physical validity of emulated VCs as a scalable and general alternative to schedules of precomputed VCs.

physics.plasm-ph · cs.LG

版本更新 · v2arXiv:2606.23655

Dynamic estimation of slowly varying sequences

Prashant Gokhale, Mikhail Khodak, Sandeep Silwal

原文摘要

We consider the problem of sequentially approximating a target function of each element in a slowly-varying sequence, i.e. one where the magnitude $α_i$ of the difference between the elements at positions $i$ and $i-1$, measured in an appropriate norm, is small. Recent work on implicit trace estimation shows that when $α_i$ is small in Frobenius norm, reusing queries to past sequence elements can reduce the overall cost. We introduce a framework that generalizes this approach to linear and nonlinear functions on normed vector spaces, obtaining sequential estimation results for matrix powers, spectral densities, Monte Carlo integration, and certain boundary value problems from partial differential equations~(PDEs). Furthermore, we develop an algorithm that locally scales the estimation budget with $α_i$, obtaining sharper path-length-style variation bounds of the form $\mathcal{O}\left(\tfrac1{ε^2}\sum_{i=1}^m α_i\right)$ on the cost of estimating a sequence of length $m$ to accuracy $ε$. This improves upon the earlier implicit trace estimation dependence on $\tfrac m{ε^2}\max_iα_i$, which results from fixing the query budget using the worst-case step size $α_i$ and is thus inefficient for stable sequences with rare bursts. Furthermore, while prior theoretical guarantees assume a known bound on the step sizes, we show in certain cases how to estimate them on the fly with (nearly) no added cost. Lastly, we complement our theoretical results with experiments demonstrating improved accuracy-cost trade-offs over prior baselines on trace estimation and Hessian tracking. In summary, our framework makes sequential approximation general-purpose and adaptive while sharpening state-of-the-art guarantees for dynamic trace estimation.

cs.LG · cs.DS

版本更新 · v3arXiv:2411.05819

HierSentNet: Hierarchical Sentiment Analysis Framework for Hate Speech Detection Using Binary and Multiclass Classification

Shahran Rahman Alve, Faria Naznin, Md Touhidur Rahman, Mohammad Ashrafuzzaman Khan

原文摘要

Hate speech detectors must separate hateful posts from the far more common offensive ones, and two popular ideas for doing so are hierarchical classification and sentiment features. We define HierSentNet, a framework that combines a dominant-class-first hierarchy with sentiment features, and test each component in a controlled study on Davidson et al. (24,783 tweets) and HateXplain (19,229 posts) with five random splits and paired significance tests. With linear n-gram models, the dominant-class-first hierarchy of HierSentNet lowered macro-F1 by 1.1-1.5 points (p<=0.007), and VADER sentiment features never changed class-weighted Davidson macro-F1 significantly, because hateful and offensive tweets are almost equally negative. Class weighting was the only large effect (+2.0 to +3.5 macro-F1, +5.9 to +9.1 hate F1). These results held for NRC emotion features, soft hierarchical inference, smaller training sets, other imbalance remedies and a convolutional network. On OLID, whose labels are hierarchical, a matching hierarchy improved only its first decision (+1.4 macro-F1, p=0.009), and sentiment helped (+2.8, p=0.005) because there it separates offensive from non-offensive text. Robustness is the main weakness: cross-dataset transfer cut macro-F1 to 43-53, a reclaimed slur doubled the false hate rate, hate recall ranged from 54% to 85% across target communities, and on the HateCheck functional tests the detectors caught only 12-31% of hateful cases. Errors concentrate where annotators disagree, and temperature scaling restores the calibration lost to class weighting.

cs.CL · cs.AI

版本更新 · v2arXiv:2610.40577

Multi-View Latent MoE: Letting Every Router Shape Expert Computation

Zelin Zhao, Junyuan Shang, Tianchi Ma, Shuohuan Wang, Dianhai Yu

原文摘要

Sparse mixture-of-experts (MoE) models expand parameter capacity by activating a small subset of experts per token. Expert selection directly affects model capabilities under a fixed active-expert budget. Dense evaluation of all experts reveals weak agreement between single-router rankings and expert-utility evaluation rankings, especially in middle and deep layers. Richer signals for selection and computation incur additional cost: selection based on internal expert activations requires preliminary computation, while processing multiple full representations separately through the same expert repeats its computation. We propose Multi-View Latent MoE to improve expert selection with multiple routers and reuse their preferences to modulate expert computation under a fixed expert budget. Its Multi-Router submodule aggregates sigmoid scores from independently initialized routers. These routers develop highly differentiated expert preferences during training, allowing experts strongly favored by one router or jointly supported by several routers to be selected. Multi-View further uses each selected expert's relative scores across routers to mix learned latent views into its input, reusing routing preferences for both selection and computation. Each selected expert executes one forward pass, preserving the active-expert count, expert FLOPs, and all-to-all communication volume. On a 24-layer 10B-A1B model trained on 708B tokens, Multi-View Latent MoE improves the nine-task downstream mean by 1.18 percentage points over the baseline. Multi-Router alone yields a 0.6-percentage-point gain and improves the rank correlation between router scores and evaluated expert utility, with relative increases of 8.1% globally and approximately 58% in the layer with the lowest single-router alignment. Controlled mixing interventions show the model uses input differences that depend on the expert and token.

cs.CL

版本更新 · v5arXiv:2503.17894

Generative Learner for Distributional Causal Effects

Maria Nareklishvili, Nicholas Polson, Vadim Sokolov

原文摘要

We propose a generative learner for estimating conditional average treatment effects and characterizing the full distribution of these effects. The learner takes the form of a multi-head feed-forward neural network with three jointly estimated subnetworks: the propensity score, the conditional quantile function of the baseline outcome, and the conditional quantile treatment effect. Each quantile-indexed subnetwork combines a covariate representation with cosine quantile embeddings through element-wise multiplication. We then recover the conditional average treatment effect as an integral over conditional quantile treatment effects. Under the classical causal assumptions within the Neyman--Rubin potential outcomes framework, we find that the proposed generative learner reduces out-of-sample mean squared error relative to the generalized random forest, double machine learning, and generative adversarial networks, with gains ranging from 5.4% to 93.5% on average across experimental designs. In an empirical application, we formalize the Stefan--Boltzmann law within a unidirectional causal model and apply the method to publicly available stellar data. The estimated effects satisfy the restrictions the law implies.

astro-ph.SR · astro-ph.GA · cs.AI

版本更新 · v2arXiv:2602.21553

Revisiting RAG Retrievers: An Information Theoretic Benchmark

Wenqing Zheng, Dmitri Kalaev, Noah Fatsi, Daniel Barcklow, Owen Reinert, Igor Melnyk, Senthil Kumar, C. Bayan Bruss

原文摘要

Retrieval-Augmented Generation (RAG) systems rely critically on the retriever module to surface relevant context for large language models. Although numerous retrievers have recently been proposed, each built on different ranking principles such as lexical matching, dense embeddings, or graph citations, there remains a lack of systematic understanding of how these mechanisms differ and overlap. Existing benchmarks primarily compare entire RAG pipelines or rely on aggregate ranking metrics (Recall, MRR, nDCG) that assume item-level independence, providing little guidance on redundancy or complementarity between retrievers. This work presents MIGRASCOPE, a Mutual Information based RAG Retriever Analysis Scope. We introduce principled metrics grounded in information theory to quantify retrieval quality, redundancy/synergy, and marginal contribution. Although the framework is designed to be applicable to any setting where a ground-truth answer can construct a pseudo chunk distribution, the present empirical study focuses on multi-hop question answering - a demanding setting where retriever complementarity is especially pronounced. On four corpora and thirteen SOTA retrievers spanning lexical, dense, and graph-based families, we show that (i) the MI-based divergence metric captures retriever quality dimensions not reflected by Recall or MRR, (ii) graph-based retrievers are redundant with each other while BM25 remains informationally complementary, and (iii) in the multi-hop QA setting, a carefully chosen ensemble guided by MI-based attribution can outperform any single retriever. We position these findings as task-specific insights and provide a reusable framework for retriever analysis that practitioners can re-estimate on their own target domains.

cs.IR · cs.AI · cs.LG

版本更新 · v2arXiv:2610.38968

TableTune: Measured, Self-Correcting Draft-Length Tables for Dynamic Speculative Decoding

Abhishek Malvankar, Paul Castro, Nick Mitchell

原文摘要

Speculative decoding speeds up large language model (LLM) serving only while the GPU has spare compute, so the best draft length, the number of tokens a small drafter guesses per step, shrinks as the batch grows. vLLM lets operators set the draft length for each batch size with a hand-written table, but nothing measures or corrects that table. We present TableTune. Its tuner times the decoding step for every batch size and draft length on vLLM's own serving path and computes, in minutes, the table that maximizes throughput. Its controller, a vLLM plugin, tracks how many guesses are accepted in live traffic and rebuilds the table while serving. We measure TableTune only against other ways to speculate. On an H100, the tuned table delivers at least 94% of the throughput of the best fixed draft length at every load in four of five drafter settings (88% in the fifth) without the operator having to know which length that is. Against reimplementations of TurboSpec- and Nightjar-style control on the same engine, its worst-case loss is never higher than theirs, and with the EAGLE-3 drafter it is 3% against 9% and 12%. On a mixture-of-experts model, vLLM's documented table loses up to 18% and the tuned table at most 3%. Starting from mistuned tables, the controller raises throughput by up to 58% (up to 45% on vLLM's default runner), and after a workload switch with the DFlash drafter it recovers 96% of a stale table's loss. In llm-d's optimized-baseline deployment as shipped, two Qwen3-32B replicas on four GPUs, the tuned table is up to 32% faster than a fixed draft length of 3 and up to 25% faster than vLLM's documented table at high load, and the controller raises the documented table's throughput by up to 29%.

cs.ET · cs.AI

版本更新 · v2arXiv:2610.09166

Lower Bounds for Parallel Diffusion Sampling

Yiwen Kou, Yimeng Wang

原文摘要

Standard diffusion samplers generate samples through sequential evaluations of a learned score function, with each query depending on previous answers. Parallel samplers seek to accelerate this process by making multiple score queries simultaneously. We ask how many adaptive rounds are necessary when each round allows polynomially many queries. We establish the first polynomial lower bounds on the round complexity of diffusion sampling with approximate scores satisfying a mean-square accuracy guarantee. Specifically, we prove (1) a $\widetildeΩ(d^{1/3})$-round lower bound for sampling smooth, near-isotropic Gaussian mixtures in $\mathbb{R}^d$, and (2) a tight $Ω(d)$-round lower bound for uniform sampling from anisotropic axis-aligned boxes contained in the unit ball. Both bounds hold for arbitrary randomized algorithms making polynomially many queries per round at arbitrary locations and noise levels, with inverse-polynomial score error and constant total variation accuracy. Our near-isotropic construction follows the blockwise approach of earlier lower bounds for parallel matroid search and discrete sampling \cite{KUW85,AGR24}. We use independent coordinate blocks containing random codebooks with well-separated rates and construct approximate score oracles whose responses in each block depend on consistency tests in earlier blocks. Together, the rate separation and these tests ensure that each round reveals information about at most one additional block with high probability.

cs.DS · cs.AI · cs.CC · cs.LG · stat.ML

版本更新 · v2arXiv:2609.32537

RIPE-MambaSpike: Resolution-Independent Spiking-State-Space Interfaces for Parameter-Efficient Event-Based Vision

Md Muhiminul Islam, Shoaib Ahmed Dipu, Sayeed Shafayet Chowdhury

原文摘要

Spiking-Mamba hybrids reach strong accuracy on event-based vision, but existing designs often require tens of millions of parameters. Much of that cost comes from how the spiking front-end is connected to the state-space backbone rather than from the hybrid architecture itself. In a representative model, a single resolution-dependent projection accounts for 33.55M of 36.25M parameters. To that end, we introduce RIPE-MambaSpike (Resolution-Independent, Parameter-Efficient), which replaces that projection with a hierarchical multi-resolution bridge of fixed channel width. Its deployed footprint is 0.870M parameters, constant at fixed time steps and widths across a 43x range of input areas. Reparameterized spiking stages, temporal decoupled modulation, and a dynamic convex-hull-bounded dual-stream membrane-potential attention preserve accuracy under this compact design. Result-wise, RIPE-MambaSpike is pareto-optimal on CIFAR10-DVS, N-Caltech101, and DailyDVS-200. Notably, on the 200-class DailyDVS-200, a scaled 8.04M configuration achieves 45.7% top-1 accuracy, the best reported spiking result on that benchmark, and outperforms prior spiking methods with 3.0-15.1x fewer parameters than dense ANNs. Overall, our findings demonstrate that competitive event-based recognition does not require resolution-dependent parameter growth. Code is available at https://github.com/MuhiminOsim/RIPE-MambaSpike.

cs.CV · cs.NE

版本更新 · v2arXiv:2602.21136

SparkMe: Adaptive Semi-Structured Interviewing for Qualitative Insight Discovery

David Anugraha, Vishakh Padmakumar, Diyi Yang

原文摘要

Qualitative insights from user experiences are critical for informing product and policy decisions, but scaling qualitative data collection is constrained by the availability of trained interviewers. Recent work has explored using large language models (LLMs) to automate interviewing, yet existing systems lack a principled mechanism for balancing systematic coverage of predefined topics with adaptive exploration, or the ability to pursue follow-ups, deep dives, and emergent themes that arise organically during conversation. In this work, we formulate adaptive semi-structured interviewing as an optimization problem over the interviewer's behavior. We define interview utility as a trade-off between coverage of a predefined interview topic guide, discovery of relevant emergent themes, and interview cost measured by length. Based on this formulation, we introduce SparkMe, a multi-agent LLM interviewer that performs deliberative planning via simulated conversation rollouts to select questions with high expected utility. We evaluate SparkMe through controlled experiments with LLM-based interviewees, showing that it achieves higher interview utility, improving topic guide coverage ($+4.7\%$ over the best baseline) and eliciting richer emergent insights while using fewer conversational turns than prior LLM interviewing approaches. We further validate SparkMe in a user study with $70$ participants across $7$ professions, where occupational domain experts rate it as producing higher-quality, more adaptive interviews and validate profession-specific insights not captured by the baseline. In addition, separately recruited experts in qualitative or human-centered research also find stronger responsiveness and probing in SparkMe. The code and evaluation resources for SparkMe are available as open source at https://github.com/SALT-NLP/SparkMe.

cs.HC · cs.AI · cs.CY

版本更新 · v2arXiv:2609.26778

An Exponential Succinctness Gap between Three-Variable Logic and the Calculus of Relations

Yuya Uezato, Yoshiki Nakamura

原文摘要

Three-variable first-order logic ($\mathrm{FO}^3$) and the calculus of relations (CoR) define the same binary queries, an equivalence that goes back to Tarski's work in the 1940s. The classical translation from $\mathrm{FO}^3$ to CoR is single-exponential, but it has remained open whether this blowup is necessary. We prove that it is, even over finite structures and even for circuits that share subterms. Our proof introduces a new technique: we modify a single finite structure in exponentially many local ways, each changing the answer of a short $\mathrm{FO}^3$ formula $\varphi$. In any CoR circuit $C$ equivalent to $\varphi$, only compositions of binary relations can notice these modifications, and each composition can notice at most two; thus, $C$ requires exponentially many compositions. The same technique gives an exponential succinctness gap between $\mathrm{FO}^3$ and $\mathrm{FO}^2$, and exponential lower bounds for matrix query languages over the Boolean and tropical semirings, where the analogous question was also open.

cs.LO · cs.CC

版本更新 · v3arXiv:2608.05165

A Study of ASR Adaptation and Representation Dimensionality Reduction in Persian Speech Emotion Recognition Using Whisper

Ali Shendabadi, Parnia Izadirad, Mostafa Salehi

原文摘要

Speech Emotion Recognition (SER) in low-resource languages remains a challenging problem due to limited labeled data. In this work, we study the use of Whisper for Persian SER with a particular focus on representation dimensionality reduction and language-specific model adaptation. We propose a SER framework in which frame-level embeddings extracted from the Whisper encoder are reduced in dimensionality using PCA, eliminating the need for learned projection layers and substantially reducing the number of trainable parameters. The reduced representations are aggregated using an attention-based pooling mechanism and classified with a lightweight prediction head. In addition, we investigate whether fine-tuning Whisper on a Persian automatic speech recognition (ASR) task improves downstream SER performance. Experiments conducted on the ShEMO dataset under a speaker-independent evaluation protocol show that PCA-based dimensionality reduction consistently improves emotion recognition performance while reducing training latency and memory usage. ASR fine-tuning yields only modest gains for SER, suggesting limited transfer from language adaptation to emotion-related representations under the evaluated conditions. These findings provide practical insights into the efficient use of large pretrained speech models for emotion recognition in low-resource languages.

cs.CL · cs.AI · cs.LG · cs.SD

版本更新 · v2arXiv:2605.17749

Testable and Actionable Calibration for Full Swap Regret

Konstantina Bairaktari, Lunjia Hu, Huy L. Nguyen, Jonathan Ullman

原文摘要

AI generated predictions increasingly inform decision making in critical tasks, and therefore must be trustworthy. One widely used measure of trustworthiness is calibration, which requires that the predictions match the true frequencies and can be treated like real probabilities of a given outcome. However, defining calibration is subtle, and designing good measures of calibration error has been an active topic of recent research. The first goal is to find calibration measures that are actionable, meaning they can inform decision makers about their utility loss when predictions are treated as true probabilities, which is known as swap regret. The second goal is to find calibration measures that are testable, meaning that calibration error can be measured from a small sample of predictions and outcomes. Although these are very basic requirements, there is no existing calibration measure that fully satisfies both properties, and all existing measures relax actionability by bounding a weaker notion of swap regret, or relax testability by having suboptimal estimation error. We introduce a new calibration measure, Soft-Binned Calibration Decision Loss (SCDL), which we prove is fully actionable without weakening either requirement, and testable with nearly optimal error rate. In addition, SCDL satisfies other desired properties such as continuity and consistency. We also provide a set of experiments confirming that the theoretical advantages of SCDL compared to other measures lead to better performance in practice.

cs.LG · stat.ML

版本更新 · v2arXiv:2607.04133

LNML-based Causal Discovery with Latent Confounders: Theory and Experiments

Zhongyi Que, Shin Matsushima, Kenji Yamanishi

原文摘要

Causal discovery with nonlinear mechanisms and latent confounders remains challenging. Existing methods often rely on either linear assumptions or causal sufficiency, limiting their applicability. We propose an MDL-based causal discovery framework that accommodates latent confounders and flexible nonlinear mechanisms using the luckiness normalized maximum likelihood (LNML) code-length. To complement code-length-based model selection, we introduce $Δ$-pseudo-collinearity as a criterion for identifying potential latent-confounding candidates. We theoretically show that, in the presence of a latent confounder, the directional code-length gap $Δ$ admits an upper bound that grows at most linearly with the sample size and decreases as the latent causal mechanisms become more similar, providing support for the proposed criterion. Based on this formulation, we develop a greedy algorithm, termed Pseudo-Collinearity Guided Causal Discovery (PCG-CD). Experiments on synthetic and real-world datasets demonstrate the ability of PCG-CD to recover directed causal relationships and identify potential latent-confounding candidates, while revealing limitations in latent-confounder discrimination.

cs.LG