跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 02:00 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 02:23 — 2026-11-09 02:23（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：2026-11-09 02:00最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,057 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 3,292 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 01:58（北京时间）
新论文 · v1arXiv:2611.03586

FedReady: Bounded Agents for Federation Formation

Ziyue Xu, Holger R. Roth, Chester Chen, Peter Cnudde

原文摘要

Federated learning (FL) runtimes standardize aggregation and deployment, but each new study still requires federation formation: selecting task-eligible sites and preparing their local data and task code for federated training or analysis. This preparation recurs when the target changes, while raw records and site-private mappings are excluded from cross-site FL messages. We present FedReady, a system that performs federation formation with bounded LLM agents. Agents propose shared contracts, local adapters, and task code; the runtime owns workflow state and accepts artifacts only after checks tied to their digests. Candidate site discovery prioritizes recall; local eligibility verification checks task support before site admission. Once participating sites and artifacts are fixed, conventional federated training or analysis proceeds without readiness agents. Across 39 simulated retinal sites and four tasks, discovery reaches recall 1.00 at precision 0.65; local eligibility verification removes all 17 false positives without losing an eligible site-task pair. The participating sites supply 45,575 task-record instances and complete four 100-round jobs, including one with a runtime-generated contract. Across ten patient cohorts, preparation supports seven patient populations and holds endpoints at three sources as unsupported. Comparison with manually prepared reference populations and analysis (the manual reference) gives a maximum survival-curve difference of 0.001133. We also analyze 19 development failures, targeted classification ablations, and standalone and heterogeneous agent configurations. These results establish the feasibility of task-specific data preparation before ordinary FL training or analysis.

cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03557

PlantVLM-Edge: Quantized Vision-Language Models for On-Device Crop Health Diagnosis

Gaurab Wagle, Bishal Adhikari, Jiajia Li, Xiaolei Huang, Dong Chen

原文摘要

Timely and accurate crop health diagnosis is essential for sustainable agricultural production, yet accurate diagnosis often requires expert knowledge that is not readily available. Recent vision-language models (VLMs) have demonstrated remarkable capabilities in visual understanding, reasoning, and natural-language interaction, creating new opportunities for intelligent crop health assessment. However, deploying VLMs on resource-constrained devices remains challenging due to their substantial computational and memory requirements. This paper presents PlantVLM-Edge, a quantized vision-language framework for conversational crop health diagnosis that can run entirely on resource-constrained edge devices. PlantVLM-Edge combines agricultural domain adaptation, post-training quantization, and on-device serving with an offline chat interface, allowing growers to ask open-ended questions and receive diagnoses, symptom explanations, and management guidance without cloud connectivity. The framework is backbone-agnostic: we validate it with two different VLM types with varying scale and architecture (Qwen3-VL-2B and LLaVA-1.5-7B), four quantization schemes, and two diagnostic domains (plant diseases and insect pests), and we deploy all variants on an NVIDIA Jetson AGX Orin. Eight-bit quantization affects answer quality minimally relative to the full-precision model, and 4-bit activation-aware weight quantization (AWQ) retains 98.6% of full-precision answer quality on both domains while reducing the weight memory of the 2B backbone by 49%. In its most compact form, PlantVLM-Edge requires 2.01 GiB of weight memory, returns its first token in about 0.12 s, and completes a 64-token diagnostic response in 0.78 s. These results demonstrate that timely and accurate crop health diagnosis is practical on edge devices, providing a foundation for next-generation crop monitoring and decision support systems.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03555

MCP Tool Poisoning in Agentic AI Frameworks: A Cross-Framework Measurement Study

Farooq Shaikh, Biagio Montaruli

原文摘要

The Model Context Protocol (MCP) lets agentic AI frameworks connect language models to external tool providers, but it carries attacker-controlled content (tool descriptions, schema fields, and response data) into model context without validation. Prior benchmarks measure model compliance with poisoned instructions without confirming real execution. We present the first cross-framework measurement of MCP tool poisoning with real tool execution. A 25-class root-cause taxonomy unifies prior classifications, and the open-source tool mcpvenom drives a 9,720-cell susceptibility matrix across 12 frameworks, 18 models, and 45 attack scenarios, with a dual oracle that confirms exfiltration via canary HTTP receipt. The overall attack success rate is 22.9% (2,113 vulnerable cells). Of these, 64.9% dispatch an attacker tool call, 23.0% contact the attacker endpoint, and 12.1% verifiably exfiltrate a secret. Resistance is model-level: nine core frameworks cluster within 23 to 26% (chi-squared = 3.30, p = 0.91), and no framework implements intentional defense. Incidental framework properties mitigate in specific cases, and a regex description scanner rejects 20 of 45 scenarios at a 7.2% false-positive rate, so metadata scanning alone is a partial control. Model ASR ranges from 0.4% to 49.7%. Claude Opus 4.8 is vulnerable in 8 of 530 cells while issuing 223 explicit refusals. A code-level audit finds no intentional defense across twelve frameworks, and all five coordinated disclosures across four vendors were rejected.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03551

Can LLM Agents Be Forward-Deployed Engineers? Requirement Discovery and Delivery for Enterprise Text-to-SQL

Marianne Menglin Liu, Rongguang Wang, Zheng Wang, Yewen Wang, Leonid Boytsov, Tao Sheng, Sujith Ravi, Dan Roth

原文摘要

LLM coding agents can increasingly automate model post-training, but whether they can act as forward-deployed engineer (FDE) agents, discovering customer requirements and turning them into deployment decisions, remains unclear. We study this on a real enterprise text-to-SQL engagement: a simulated customer, grounded in the real use case's requirements, starts with an ambiguous request. An agent must discover acceptance criteria, data permissions, and hardware constraints in the discovery phase, then plan and execute a post-training recipe in the delivery phase. Across 15 models, the strongest discover over 80% of withheld requirements and open-weight models discover 40-50%; in the delivery phase, only 25% of runs across eight coding-agent configurations pass all acceptance criteria. We identify four bottlenecks in this engagement: (1) incomplete discovery, with 40% of withheld requirements missing or misrepresented; (2) unreliable execution; (3) underused compute budgets and a lack of systematic comparisons across base models and post-training methods; and (4) benchmark accuracy does not guarantee production readiness. We suggest human review of discovered requirements, monitoring of the agent's plan during execution, and an explicit experiment-environment specification covering hardware, budget scope, and production checks.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03534

An Agentic Framework for Automated Power System Studies and Grid Connection Assessment

MaoXun Huang, Kshitij Kapoor, Eli Louise

原文摘要

Connecting new generation and demand to the grid depends on two scarce skills: checking applications against a large, changing body of regulation, and running the network studies that decide where and how a project connects. We present Grid Agents, an AI system that brings both together, and the methodology we use to evaluate it. The Grid Ontology is its knowledge system. It represents the regulation, standards and engineering knowledge that grid work depends on, makes it searchable, and evolves as the agents learn from use. Every answer drawn from it rests on evidence the agents cite. Grid Studio is an agent system specialised for power-system engineering. It works in its own engineering environment with domain tools and a study framework, draws on the Grid Ontology, and relies on established solvers for every number it reports. In both, engineers make the decisions. We bring eight published power-system benchmark families, previously scattered across separate papers, into one suite of 519 tasks, and we verify not only each answer but the work behind it, by replaying the agent's tool calls. The Grid Ontology cites the right regulatory evidence more often than a general coding agent or retrieval pipelines, leads on LegalBench-RAG and ranks first on the public leaderboards of the Enterprise RAG Challenge and ViDoRe V3. Grid Studio scores highest on the 519 power-system tasks and is the fastest of all the systems we compare, both by a statistically significant margin. With an optimiser in the loop, its reinforcement packages cost 33-67% less on average than those the agent designs alone.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03528

Contrastive Adapter Training and Consensus Knowledge Distillation for Multi-Source-Free Domain Adaptation in Skin Cancer Diagnosis

Ali Abedi, Q. M. Jonathan Wu, Ning Zhang, Farhad Pourpanah

原文摘要

Skin cancer diagnosis, particularly differentiating melanoma from benign nevi, is challenging due to the visual similarity between lesions. Although convolutional neural networks (CNNs) and vision transformers (ViTs) have shown promising performance, their effectiveness often deteriorates on data from heterogeneous clinical sources. Conventional domain adaptation methods address domain shift but require access to source data during adaptation, which is often infeasible due to privacy regulations. Multi-source-free unsupervised domain adaptation (MSFDA) addresses this limitation by leveraging multiple labeled source domains to generalize to an unlabeled target domain without requiring access to source data. However, existing MSFDA methods rely on full backbone fine-tuning, leading to catastrophic forgetting and overfitting on small clinical datasets, and address domain shift at the aggregation stage without establishing a shared domain-invariant feature space. Furthermore, their reliance on hard pseudo-labels or confidence-weighted aggregation introduces noisy supervision signals under domain shift. To address these limitations, we propose CAT-CKD, consisting of two components: (1) contrastive adapter training (CAT), which trains lightweight ConvPass adapters within a frozen ViT backbone using supervised contrastive learning (SCL) to establish a shared domain-invariant feature space before source-specific model training, and (2) consensus knowledge distillation (CKD), which aggregates logits from multiple source models into a consensus supervisory signal and adapts a student model on unlabeled target data using KL divergence. Experiments on five publicly available skin lesion datasets show that CAT-CKD achieves an average AUROC of 86.1%, outperforming existing MSFDA methods while requiring only 4.3M trainable parameters. The code is available at https://github.com/A-Abedi/CAT_CKD.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03525

Grading the Unannotated: Insights from the WorkRB Skill Extraction Challenge at RecSys-HR 2026

Warre Veys, Luis Gasco, Jens-Joris Decorte

原文摘要

Skill extraction benchmarks score models against a few human-annotated positives and treat every other skill in the vocabulary as equally wrong. At the scale of ESCO (13,939 skills) this binary view can reward models that rank the annotated positive high for the wrong reason, and hides semantically nonsensical predictions. The WorkRB Challenge at RecSys-HR 2026 replaces it with graded relevance: every candidate skill in a model's ranking window carries a 0 to 4 grade, and the leaderboard scores nDCG@100 against these grades. Since ternary judgements proved too coarse for objective annotation, relevance is decomposed into a cascade of four binary questions (same domain, activity mentioned, right granularity, replacement of a gold positive) that a smaller LLM judge can answer reliably; the labels are validated with blind human and frontier-model re-annotation. This paper documents the annotation methodology, the construction of five benchmark datasets (four with vacancy sentences as queries, one with lexically distant skill surface forms), the validation of the LLM cascade, and insights from the submissions. The field converged on multi-stage retrieve-and-rerank pipelines, whose gains come from clearing nonsense out of the ranking window rather than finding more positives: at the top of the leaderboard, the graded ordering is uncorrelated with what binary evaluation would have said. Graded labels expose much bigger gaps between top submissions and baselines than binary evaluation does, and show that semantic-understanding skill recommendation is still wide open. The clear next direction is bringing efficiency back: every submitted system we could size uses at least 42x, typically several hundred times, more parameters than the baselines it beats.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03526

Library of Layers (LoL): Adaptively Ordering Transformer Layers at Runtime

Abdellah Rahmani, Sean McLeish, Ang Li, Sanae Lotfi, Pascal Frossard, Micah Goldblum

原文摘要

Computer programmers chain together the same reusable computational primitives, for example, conditional statements or loops, but in different orders to implement different algorithms. In contrast, existing language model architectures always execute their layers in the same order. We introduce Library of Layers (LoL), an architecture that dynamically orders its layers during inference to solve the problem at hand. LoL has a single hyperparameter, the size of its global library of transformer blocks, that allows it to transition seamlessly between parameter reuse and sparsity, generalizing the parameter-efficiency and FLOPs-efficiency tradeoffs of dense, depth-recurrent, and mixture of experts architectures in one unified family. We show that LoL achieves competitive performance with all three above baselines when pretrained on text data. On synthetic sudoku and maze data, we observe that the model employs distinct layer orderings to implement different solution strategies, and we can intervene on routing to force a model to apply a specific solution strategy to a problem instance. In a multilingual natural language setting, we find that LoL chooses different layer order patterns based on language and script. Similarly, we train LoL on safety data and fit probes to its router outputs, finding that these probes distinguish safe from unsafe text with high AUROC. LoL provides a path toward a future in which models dynamically compose their own computational graph, enabling more efficient and controllable reasoning.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03520

PanoTac: A Dense Three-Axis Tactile Sensor for Robust Touch-Centric Manipulation

Binglin, Wang, Xiaole, Jiang, Zicheng Teng, Xinqi Liu, Yunzhu Li, Lerrel Pinto 等 10 位作者

原文摘要

Contact-rich manipulation benefits from tactile feedback that captures both detailed contact geometry and interaction forces. When scooping grains, contact patterns help infer spoon orientation, while resistance transmitted through the grasp guides motion. To provide these complementary sensing capabilities, we present PanoTac, a low-cost, compliant tactile fingertip designed for dense three-axis tactile sensing. Each fingertip provides a $12 \times 32 \times 3$ tactile representation, with one normal ($z$) and two shear ($x$, $y$) response components at each taxel. The sensor operates at 60 Hz and costs less than $50 per fingertip. Sensor characterization quantifies response repeatability and consistency across sensor instances and contact locations. We integrate PanoTac into a robotic system with a visuo-tactile pipeline. Across test-tube preparation, grain scooping, and salt pouring, the resulting policies outperform vision-only baselines by an average of 46.7 percentage points. Ablations show that removing either spatial contact information or shear feedback reduces overall performance across the task suite. Our project page is available at https://panotac.github.io.

cs.RO · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03518

VIAS: Value-Isolating Activation Steering for Multi-Value Alignment and Compliance for Organisations

Avni Mittal, Avinash Anand, Dikshant Kukreja, Erik Cambria, Rajiv Ratn Shah, Sandipan Dandapat

原文摘要

Organisations increasingly deploy large language model agents that must follow organisational values. We check whether activation steering, which adds vectors to a model's internal activations during generation without changing its weights, can improve compliance beyond prompting alone. Since most scenarios involve several values at once, we focus on multi-value steering. A simple way to build these vectors is to contrast responses that follow all values relevant to a scenario with responses that violate them. However, this gives nearly identical vectors for different values: they capture a general compliance signal rather than individual values, which limits their use when combining several values. We propose Value-Isolating Activation Steering (VIAS), which contrasts responses to the same scenario under two prompts, one listing all relevant values and one omitting a single target value. We keep a pair only if the target value changes from compliant to non-compliant and both responses still meet a minimum compliance level on the other values. We evaluate VIAS on PROTECT, a workplace compliance dataset where each scenario is tagged with relevant values from a 21-value taxonomy. VIAS reduces overlap between value vectors, making them better suited for multi-value steering, although this alone does not lead to independent control over each value. Combined with prompting, VIAS complies with every tagged value on 69.6% of scenarios for Qwen2.5-7B, 75.2% for Mistral-7B, and 72.6% for Phi-3.5-mini, outperforming prompting alone for all three models.

cs.CL · cs.AI · cs.LG · cs.MA

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.02711

Dynamic Mixed-Precision Routing for Efficient Multi-step LLM Interaction

Yuanzhe Li, Jianing Deng, Jingtong Hu, Tianlong Chen, Song Wang, Huanrui Yang

原文摘要

Large language models (LLMs) achieve strong performance in long-horizon agentic tasks through multi-step interaction and reasoning at test time. However, repeatedly invoking these models incurs substantial inference cost over an episode. Post-training quantization (PTQ) reduces this cost, but using a fixed low precision throughout an episode can sharply lower task success. We observe that interaction steps differ sharply in their sensitivity to quantization: given the same context, decoding a step at low precision turns a success into a failure at only about 1% of the steps, which we call critical steps. Based on this observation, we propose Dynamic Mixed-Precision Routing (DMR), a framework that adaptively selects between high-precision and low-precision versions of the same LLM at each decision step. Leveraging an entire-space factorization to jointly predict a step's divergence and its effect on the outcome, DMR learns to recognize these critical steps by training only a lightweight router on the model's hidden state. By reusing a shared high-precision KV cache and the hidden states, DMR avoids redundant context prefill and a separate text encoder, enabling precision switching with less than 1 ms of overhead per step and adding less than 0.11% to step latency for routing. This mixed-precision design also enables nested quantization, reducing the memory footprint by 39% on average compared with FP16. Across three long-horizon agentic benchmarks with nested quantization, DMR achieves an average 2.44x decode speedup over FP16 at comparable task success rates, without fine-tuning the underlying model. On ALFWorld with GPTQ, DMR achieves a 1.71x decode speedup with 86.9% success, compared with 87.2% for FP16.

cs.AI

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03503

A Cross-Domain Matrix Engine for Signal Processing and Deep Neural Net Inference

Mehdi Safarpour

原文摘要

Matrix multiplication dominates both PHY signal processing and Deep Neural Network (DNN) inference, yet these domains place opposing demands on the matrix engine. Signal processing requires low-latency execution of relatively small matrix operations, whereas DNN inference, particularly at large batch sizes, prioritizes high throughput and energy efficiency for large matrix multiplications. While offering efficient memory access profile, a Systolic Array (SA) adds fill and drain delays per matrix. Those can be amortized for large matrices but not for small matrices. Conversely, a tensor unit completes the kernel in few cycles but would require repeated reads of same operand tiles over large matrices. This makes SA too slow for signal processing and tensor too inefficient for AI. We show that this need not be a choice between systolic and tensor structuring of Multiply-Accumulate (MAC) units. We propose a single engine that operates primarily as a SA and, through low-cost reconfiguration, transforms into a tensor-style engine on a per-operation basis. MUXes create both the spatial reduction adder tree and temporal reduction accumulators from the existing MACs and registers within the systolic array. The proposed reconfigurable SA simulated using modified SCALESim simulator, verified on an Zynq 702 FPGA and synthesized using ASAP 7nm FinFET library. SCALE-Sim simulations shows up to 7.5x lower latency for small complex value PHY kernels. Even on DNN workloads, it achieves up to 1.65x speedups over vanilla SA execution with trivial increase of memory accesses, retaining the systolic array's memory access advantage. Synthesis results estimate reconfigurable fabric costs only 8% power and 13.6% area overheads.

cs.AR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03500

Can AI Do Formal Demography? Why Vaccinating the Oldest Saves Both the Most Lives and the Most Years of Life

Joshua R. Goldstein, Kenneth W. Wachter

原文摘要

Can AI contribute to formal demography? We report an experiment in which an AI model, Claude, was asked to explain and then simplify the proof of an earlier result: that vaccinating the oldest against COVID-19 saves both the most lives and the most years of life, because the years saved per person treated rise with age. The model proposed a new proof that is shorter, more intuitive, and somewhat more general than the original, built from a known life-table identity and the definition of convexity. It states the condition for the result as the convexity of the reciprocal of the hazard, which can be checked from the hazard alone and holds for most familiar parametric models, and it yields a lower bound on life expectancy whenever that condition is met. Prompted by a further question, the model also gave an exact form of the condition, showing how far convexity can be relaxed. The model traced these identities and related results in earlier literature. An edited record of the sessions is provided, and complete transcripts are available on request. The exercise suggests that AI can revisit established results, make them easier to understand, and prove valuable generalizations.

cs.AI · q-bio.PE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03496

Online Label-Free Gradient Matching for Continual Language Model Training

Sajjad Pakdamansavoji, Mohammad Reza Rezaei, Ilija Subasic, Pedro Garzon, Radu Paradovschi, Zhao Chen

原文摘要

Language models in customer-facing products must be continually updated, since the data they serve shifts over time. As retraining on the full accumulated data is impractical, each update should instead run on a small set of examples carrying the training signal of all data seen so far. The strongest current methods build this set by gradient matching, which synthesizes examples whose training gradients match those of the full data. However, they require ground-truth labels, run once on a fixed snapshot rather than on a growing stream, and are slow on large data. We introduce \textbf{OLGA}, which lifts these limitations. It distills unlabeled data by drawing the gradient matching targets from the model's own next-token predictions. Across five text classification benchmarks with phi-1.5, it improves accuracy by 10 percentage points over the strongest selection baseline using as few as five examples. OLGA also distills online data streams by keeping a running rehearsal memory of synthetic examples, which is re-distilled together with each new batch as it arrives. In the online setting, it outperforms the strongest selection-based continual baseline by 6.6 stream-AUC percentage points. Finally, our method scales to large data by pairing distillation with selection in a hybrid pipeline, letting selection handle the mild stage of compression and distillation the extreme one. It cuts runtime by 30\% versus distillation alone at similar accuracy, and beats the best selection-only pipeline by up to 12.6 percentage points.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03494

Harder Than the Task: From Technical to Organizational Difficulty in AI Benchmarking

Victor Barres, Aden Barton, Nicolai J. Foss, Henrik M. Nielsen

原文摘要

AI benchmarks have made remarkable progress in measuring the ability of AI systems to perform increasingly demanding cognitive and technical tasks. Yet, many of these benchmarks treat technical tasks as the unit of analysis, while much economically valuable work takes place within organizations, where tasks are embedded in a system of relations. Within organizations, successful task performance depends not only on solving the technical demands of the task but also on navigating the interdependence of activities, distributed knowledge, differentiated authority, temporal constraints, conflicting interests, and changing environmental conditions while the task is underway. Accordingly, we argue that organizational task difficulty constitutes a distinct and insufficiently recognized dimension of AI capability, and that existing approaches to benchmarking provide an incomplete basis for assessing how effectively AI agents can perform real-world organizational work. By drawing on organization theory, we develop a taxonomy of the structure of work that characterizes the conditions that agents face in organizational work. Applying this taxonomy to analyze existing benchmarks, we find limited and uneven coverage of organizational dimensions, with fewer than one quarter of prominent benchmarks claiming any of them. We therefore argue that AI benchmarks should increasingly move beyond the evaluation of technically difficult tasks toward the systematic assessment of agents' ability to navigate the organizational conditions under which economically valuable work takes place.

cs.CY · cs.AI

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03772

RuntimeTickets: Source-Grounded Security Obligations for Agent Skills

Kuiyi Gao, Xue Liu, Bowei He

原文摘要

Third-party Agent Skills extend what an autonomous agent can do, but a malicious Skill can hide data exposure or output manipulation inside a legitimate workflow. Neither reading a Skill's description nor granting it tool permissions tells whether its execution meets the user's security requirements. We introduce RuntimeTickets, a protocol that enforces and audits these requirements while a Skill runs. From released malicious-Skill datasets we derive a risk model and build adversarial-benign Skill pairs. From the task's delivery contract, a language model proposes security obligations for that task. Each obligation cites the Skill lines it answers, and the ticket tightens the host's approvals into fine-grained allowed actions but never loosens them. A runtime gate checks the recipient, object and amount of every outbound send before forwarding it, and trusted monitors record the effects within their observation scope. The ticket links these checks and observations to the approved obligations of each Skill run, and a deterministic decoder turns the ticket's status into governable data flows and verifies each obligation. Neither enforcement nor decoding involves a language model, so text injected by a Skill can change the proposal but never the rule that decides a send. We evaluate RuntimeTickets at the network egress boundary of three unmodified agent frameworks against production Skill scanners and runtime baselines, among them an AgentBound-derived allow-list and SkillGuard. RuntimeTickets eliminated both failure modes of current Skill defenses, overlook (malicious Skills let through) and overkill (benign Skills blocked): its overlook rate was 0.0% and its overkill rate 0.0%, while the scanners erred on both sides. RuntimeTickets ties approved requirements to verifiable execution evidence and offers a common foundation for the safe and auditable deployment of third-party Skills.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2510.20094

On the Structure of Stationary Solutions to McKean-Vlasov Equations with Applications to Noisy Transformers

Krishnakumar Balasubramanian, Sayan Banerjee, Philippe Rigollet

原文摘要

We study stationary solutions of McKean-Vlasov equations on the circle. We establish an exact equivalence between solutions of the stationary McKean-Vlasov equation and an infinite-dimensional quadratic system of equations over Fourier coefficients, allowing explicit characterization of stationary states in a sequence space rather than a function space. This framework provides a transparent description of local bifurcations, their periodicity and resonance structures, while accommodating singular potentials. We derive analytic expressions for the emergence, form and shape (supercritical, critical, subcritical or transcritical) of bifurcations involving possibly multiple Fourier modes and connect them with discontinuous phase transitions. We also characterize, under suitable assumptions, the detailed structure of the stationary bifurcating solutions through leading small-amplitude coefficients for arbitrarily many fixed Fourier modes. At the global level, we establish regularity and concavity properties of the free energy landscape, proving existence, compactness, and coexistence of globally minimizing stationary measures, and identifying discontinuous phase transitions with points of non-differentiability of the minimum free energy map. We apply the theory to the Noisy Mean-Field Transformer model, where we show how changing the inverse temperature $β$ affects the geometry of the infinitely many bifurcations from the uniform measure. We also discuss how increasing $β$ motivates the study of approximate multi-mode stationary profiles as candidates for a separate metastability analysis; persistence times require additional dynamical estimates. Moreover, we determine the exact threshold $β_0\simeq2.447$ separating continuous and discontinuous phase transitions in this model. The same threshold marks the change of the first bifurcation from supercritical to subcritical.

math.PR · cs.AI · cs.LG · math.AP · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2412.05331

Smart Surveillance: Deep Learning and Hybrid Approaches for Dynamic Scene Analysis, Object Detection and Motion Tracking

Shahran Rahman Alve, Shahnewaz Siddique

原文摘要

Event-triggered recording reduces the footage a surveillance camera must store, but the trigger decides how much idle video is kept, how many events are missed, and how much computation is spent. We compare six motion triggers (frame differencing, dense optical flow, MOG2, KNN, CNT, GSOC), a CNN detector, strided detection, and three motion-gated hybrids under one recording policy, on a benchmark of seven static-camera scenes (5,800 frames, 27 annotated events) with thresholds transferred to unseen scenes by leave-one-video-out. Detector-based triggers stored 19-28% of idle frames, against 36-89% for motion triggers. Under simulated camera jitter, frame differencing, optical flow, MOG2 and KNN stored 97-100% of idle frames, while detector triggers stayed below 29%. Running the detector on every 8th frame kept 99.7% of event frames at 9.8 ms of CPU per frame, cheaper and more robust than gating it with background subtraction. On VisDrone, raising YOLO11n's input from 640 to 1280 px raised AP from 15.5 to 26.8, more than a larger model, and INT8 quantization cut latency by 17% for 0.3 AP. In tracking, longer track memory raised IDF1 from 70.5 to 76.7, but every tracker recovered only 39-44% of overlapped people, because detection rather than association failed.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03439

Playing Dumb: How a Chess Transformer Simulates Users Across Skill Levels

Difan Jiao, George Eilender, Zhenwei Tang, Ashton Anderson

原文摘要

Generative models increasingly simulate users at different skill levels in education and AI evaluation. Yet it remains unclear whether lower-skill behavior reflects less internal knowledge or a different use of retained knowledge. This distinction is difficult to study in natural language, where proficiency and relevant knowledge are hard to measure. In this work, we study Maia-2, a chess transformer that predicts human moves conditioned on player skill, using quantitative skill ratings and deterministically labeled chess concepts. We hold board positions and model weights fixed and analyze positions where skill conditioning changes the prediction from a blunder to the best move. First, we measure encoded knowledge by training probes to predict the presence of 172 chess concepts from Maia-2's internal states. Probe accuracy remains nearly constant across skill conditions, and probes trained at one level transfer accurately to the others. To test whether stronger decisions can be recovered from this retained knowledge, we fine-tune only Maia-2's final output layer, raising best-move accuracy in the lowest skill band from 14.4% to 82.8%. Training this layer only on highest-skill representations retains most of the improvement at lower levels, showing that recovery does not require direct training on lower-skill states. Steering concept-relevant features learned by a sparse autoencoder also improves lower-skill decisions while leaving probe-measured concept encoding practically unchanged. These results support an account in which skill conditioning changes how retained concept knowledge influences move selection, showing that weaker behavior can understate the knowledge available within a model.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗