跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+406新增论文
+306其中 AI 相关
+55已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 11:42各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 12:31 — 2026-11-16 12:31(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-16 11:42库内论文最新更新时间:2026-11-14 01:29

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

23,754 已收录论文19,886 AI 相关6,892 有修订112 HF 社区发现

浏览论文库

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

找到 23,754 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
版本更新 · v2arXiv:2601.12716

CellularS2-Bench: A Staged, Evidence-Grounded Benchmark for Cellular Network Security Reasoning

Ke Xie, Xingyi Zhao, Yiwen Hu, Haotian Lin, Shuhan Yuan, Wen Li, Tian Xie

原文摘要

Cellular networks are critical infrastructure supporting billions of worldwide users and safety- and mission-critical services. Vulnerabilities in cellular networks can therefore cause service disruption, privacy breaches, and broad societal harm, motivating growing efforts to analyze 3GPP specifications that define required device and operator behavior. However, existing benchmarks for this domain share three systematic deficiencies: they rely on LLM-generated entries without expert verification, they do not require faithful interpretation of normative language, reasoning across cross-referenced clauses, and verifiable conclusions grounded in multimodal evidence such as tables and figures, and they do not evaluate security reasoning over end-to-end protocol behavior. To address these gaps, we present CellularS2-Bench, a staged benchmark. CellularS2-Bench covers core control-plane specifications, processing over 1,866 paragraphs, 22,033 sentences, 424 figures, and 248 tables. It comprises 13,851 questions and instances across three progressive stages, of which 10,269 (74.14%) are newly constructed from 3GPP specifications and 43 real-world vulnerabilities. Beyond newly constructed tasks, CellularS2-Bench integrates and corrects 3,582 (25.86%) instances from 7 prior datasets to broaden task coverage. To establish a reproducible baseline on CellularS2-Bench, we introduce CellularS2-ARI, a unified Adapt-Retrieve-Integrate framework for systematic understanding and specification-driven security analysis of 3GPP specifications. Together, they establish an accessible and reproducible foundation for quantifying progress in specification understanding and security reasoning in cellular network security.

cs.CR

版本更新 · v2arXiv:2611.07289

Patch-Based Generalized Neural Texture Upscaling

Shin Fujieda, Takahiro Harada

原文摘要

We propose a lightweight neural texture upscaling method. A single generalized MLP is trained on a diverse collection of texture patches and integrated into the texture sampling stage, upscaling low-resolution textures on-the-fly at rendering time. Because the model is generalized rather than overfit to specific content, no per-asset training is required - the same model applies to any existing scene without modifying texture data or the asset pipeline. Storing lower-resolution base textures reduces disk footprint, upscaling at sampling time eliminates the need to store high-resolution textures in VRAM, and sharing a single set of model weights across all textures ensures non-divergent GPU execution. We evaluate our method across multiple texture classes, demonstrating consistent improvement over analytic upscaling methods in perceptual quality.

cs.GR

版本更新 · v2arXiv:2611.08698

VICTR: Value-Informed In-Context Learning for Vision-Language-Action Models

Luca Macesanu, Tianluo Zhang, Aditya Patil, Archit Sharma, Kevin Angers, Christopher M. Clark, Chen Feng, Juexiao Zhang

原文摘要

Recent advances in robot foundation models have highlighted the potential of in-context learning (ICL) for adapting robot behavior from demonstrations without further fine-tuning. Previous work has used retrieval-based post-training to equip pretrained vision-language-action (VLA) models with the capability for ICL by teaching them to condition action predictions on retrieved visually-relevant demonstration chunks. However, the effectiveness of retrieval hinges on selecting context relevant to the current execution stage, which visual similarity alone may not capture. We introduce VICTR, a framework enabling in-context learning in VLAs via progress-informed context retrieval built around an In-Context Value Function Estimator (IC-VFE). IC-VFE conditions on a reference demonstration video, a language instruction and the current observation to estimate task-relative progress. By conditioning progress estimation on a reference demonstration, IC-VFE can align the current state with a demonstrated execution even for tasks unseen during training. VICTR uses the estimated progress to select demonstration chunks at corresponding stages of execution and supplies them to a $π_{0.5}$ policy post-trained for in-context action generation. On unseen out-of-domain real-world manipulation tasks, VICTR raises the success rate from 6.2% for a fine-tuned $π_{0.5}$ baseline to 23.8% and more than doubles the task progress rate, from 28.9% to 55.5%. Project page with code, data and videos: https://ai4ce.github.io/VICTR/

cs.RO

新论文 · v1arXiv:2611.14700

Probe What-If Worlds Before You Ship: Persona Simulation for Real-World Decision Making

Julie Zhu, Jianheng Hou, Zhixu Silvia Tao, Shi Bo, Yilan Fan, Yixuan He, Zhiyuan Hu, Shirley Huang 等 24 位作者

原文摘要

User research and system testing reveal whether products and services meet user needs, yet recruiting specialized participants, designing controlled what-if comparisons, and repeating studies as designs evolve often bottleneck design iteration and data-driven decision-making. We present a framework and execution infrastructure that translates real-world industry inquiries into controlled experiments with simulated users. Our methodology formally defines the target cohort, experimental stimuli, and decision-relevant metrics, while the pipeline supports large-scale concurrent runs over cohort-stimulus-environment combinations (survey, web, chatbot, and OS app), auditable trial-level logging, cohort-level outcome aggregation, and cross-cohort and cross-variant statistical reports. Across twelve industry partner cases spanning five domains, we show how constructing hard-to-reach or what-if persona cohorts supports exploratory studies and distills simulated responses into testable design hypotheses. Cross-model comparisons on selected cases largely preserve primary conclusions, whereas perturbing or ablating persona attributes alters service outcomes, effect sizes, and inter-group differences, indicating that grounding target cohorts in detailed personas materially shapes simulation results. Together, these studies show that persona-enabled agents can test specified cohorts at design speed, diagnose systems under test, and deliver directional evidence that focuses problem definition, steers design and strategic decisions, and guides further study.

cs.CL

版本更新 · v2arXiv:2611.09422

Robust & Scalable Website Fingerprinting via Minimal DRAM Traffic

Shubham Roy, Samar Perwez, Biswabandan Panda

原文摘要

Website fingerprinting attacks infer websites visited by users and threaten their privacy. These attacks are classified as on-path, which monitor network traffic, and co-located, which exploit shared system resources. Existing co-located attacks, such as sweep-counting and loop-counting, achieve over 90% accuracy but suffer significant performance degradation on many-core systems. Loop-counting accuracy drops from 93% on 8 cores to 50% on 24 cores, while sweep-counting accuracy decreases from 84% to 45% across multiple Core Complex Dies (CCDs). To address these limitations, we propose memory-chasing, a scalable website fingerprinting attack that exploits DRAM traffic interference through pointer-chasing traversals with minimal interference. By counting DRAM accesses over fixed intervals, the attack generates distinctive traces for website classification. Evaluated on the top 50 websites, memory-chasing achieves 96% accuracy on a 24-core system, 86% across multiple CCDs, 80% across multiple sockets, and 97% in an open-world setting. Extensive evaluation across hardware configurations, browsers, operating systems, isolation mechanisms, system noise, and countermeasures demonstrates its robustness and scalability.

cs.CR · cs.AR

新论文 · v1arXiv:2611.14699

Conformal Risk Certificates for Portfolio Optimization Under Uncertainty: A Gated Reinforcement-Learning Approach

Mohammad Zarei, Amirhossein MohammadpourAzari, Moslem Habibi

原文摘要

Reinforcement-learning portfolio policies can optimize allocations from prices, covariances, and prior positions, yet they lack a calibrated, replayable mechanism for certifying that a proposed allocation respects a bounded risk envelope before execution. Regulators increasingly expect automated portfolio systems to provide exactly this kind of pre-trade audit trail, interpretable risk limit, and human-oversight mechanism. Gated Conformal Semantic Risk Control addresses this gap by separating return-seeking allocation from text-conditioned downside-risk verification. An instruction-tuned language model maps timestamped disclosures into schema-validated semantic risk states over macro, liquidity, earnings, and sector channels. These states induce correlated ellipsoidal factor-shock uncertainty sets whose conformal radii are calibrated by rolling finite-sample prediction over localized semantic nonconformity buckets. An asymmetric second-order cone gate then checks each raw PPO proposal against a certified worst-case semantic loss budget. The gate stays inactive for compliant proposals and intervenes only when that budget is exceeded. In walk-forward out-of-sample tests on nine liquid U.S. Select Sector SPDR ETFs, Raw PPO earns a 12.7% annual return while incurring a 4.05% semantic violation rate. Gated-CSRC removes all observed out-of-sample semantic limit breaches while retaining an 11.7% annual return. This 100-basis-point auditable safety premium is smaller than the yield loss imposed by unconditional hard projection, and exact McNemar testing confirms the compliance gain at $p < 10^{-15}$. Loughran-McDonald lexicon controls and time-shuffled text controls fail to reproduce this certificate.

q-fin.PM · cs.LG · math.OC · q-fin.RM

新论文 · v1arXiv:2611.14698

Incrementally Verifiable Oracle Aided Computation

Shafi Goldwasser, Yael Kalai

原文摘要

Incrementally verifiable computation (IVC) allows a prover to maintain a short proof that can be efficiently updated after each computation step, without retaining or recomputing the preceding execution. Standard IVC schemes do not directly address a crucial feature of AI tasks: their dependence on external information and expertise. We construct IVC schemes for oracle-aided computations under the LWE assumption by first constructing SNARGs, and then extending them to IVC. We consider the following two settings, where below, k is the security parameter, n is the input length, and T, S, and Q are the time, space, and oracle-query bounds. 1. Robust computations: For bounded-space computations, including non-deterministic computations, in which every accepting purported execution on a false input contains at least an eps-fraction of incorrect oracle answers, we construct privately verifiable SNARGs and IVC. Public parameters, private verification keys, and proofs have length poly(k ,S, log T,1/eps), and verification uses O(k/eps) oracle calls. We complement this result with a lower bound ruling out (deterministic) publicly verifiable SNARGs and IVCs with public parameters of length o(n), and o(Q) verifier oracle queries. 2. Signed oracles: For oracles that digitally sign their query-answer pairs, we construct publicly verifiable SNARGs and IVC without a robustness assumption, and with oracle-free setup and verification. Public parameters and proofs have length poly(k,S,log T). For deterministic computations with oracle query and answer lengths poly(k,log T), we remove the dependence on S, obtaining public parameter and proof lengths poly(k,log T). All our constructions have adaptive completeness and soundness.

cs.CR

版本更新 · v2arXiv:2610.15903

BRQGen: Towards Adaptive Completeness Assessment and Follow-Up Question Generation for Bug Reports

Tevfik Emre Sungur, Akif Emre Köşüş, Uğurcan Doğruçam, Eray Tüzün

原文摘要

Many bug reports lack the necessary information required to reproduce issues. In early studies, large language models have been employed to generate follow-up questions to enhance incomplete reports. However, they ask a fixed number of questions regardless of whether the report is incomplete. We propose BRQGen, an iterative framework that identifies missing or ambiguous information in bug reports and generates targeted follow-up questions, only if necessary. Reports with no identified gaps are classified as sufficient. When the author responds, BRQGen evaluates whether the answers provide the requested information and generates further questions for any exposed gaps. We curated a novel dataset of 429 incomplete bug reports from Home Assistant and Brave Browser, each containing at least one maintainer follow-up question. Each question is mapped to the author's answer and assigned a label indicating whether the requested information could have been provided directly through the issue template. Earlier maintainer requests were associated with author responses, whereas delayed requests were associated with no response. Among responding authors, requests within one hour received median replies after 0.52 hours in Home Assistant and 1.45 hours in Brave, versus 9.76 and 13.49 hours after four hours. BRQGen covered 35.4% (Qwen 3.8 Flash) to 51.8% (DeepSeek V4.1 Flash) of the 1,073 ground-truth follow-up questions. DeepSeek V4.1 Flash managed to ask 45.7% of all detailed questions and 63.9% of all generic questions. Gemini 3 Flash Preview reached the highest macro-F1 for completeness assessment of 49.3%, but with a post-hoc analysis by getting only the gaps with high severities, Qwen 3.8 Flash reaches 73.6% macro-F1 score. Completeness assessment improved when at least one identified gap had high severity, and nearly all ground-truth questions were captured within the first two iterations.

cs.SE

新论文 · v1arXiv:2611.14697

Beyond Row-Level Prediction: Evaluating and Learning Composition for Reusable Table Representations

Ali Younes, Saeed Ghoorchian, Maximilian Schambach, Georgia Chalvatzaki, Johannes Höhne

原文摘要

Tables are compositional, with content spread across a schema, cell values, rows, and columns. Large-scale operations such as retrieval, overlap estimation, deduplication, and data curation need these local signals composed into one reusable embedding vector per table. Table representation methods, however, are mostly evaluated through row-level prediction or supervised downstream tasks, which do not measure table-level embedding quality directly. We introduce a benchmark that evaluates table-level embeddings through four desiderata: consistency under partial views, discriminability across label granularities, robustness to benign perturbations, and efficiency. Across twelve methods on synthetic and real corpora, lightweight schema- and text-based fingerprints are among the strongest. The sharpest contrast comes from two tabular foundation models, TabPFN and ConTextTab: although both are strong row-level predictors, their states, composed by mean, max, or three further parameter-free pooling rules, trail the strongest fingerprints. We therefore ask whether the gap lies in the encoder or in the compositional rule. Keeping ConTextTab frozen, we learn only the compositional rule over its cell states, using support-conditioned distribution matching (SCDM), a self-supervised loss we propose that matches the distribution of embedding similarities to the distribution of partition overlaps within and across tables. Across all fifteen head configurations, the learned rule raises the Spearman correlation between embedding similarity and partial-view overlap from 0.04 to 0.43-0.50 on synthetic data and improves triplet ranking, clustering, and retrieval, with smaller but systematic gains on real data. A downstream parent-table retrieval task confirms these findings. How local states are composed, and with what objective, substantially affects the quality of table-level embeddings.

cs.LG

新论文 · v1arXiv:2611.14696

Risk-Aware Joint Inference and Resource Control for Physical AI in 6G Networks

Amin Farajzadeh, Melike Erol-Kantarci

原文摘要

Wireless edge inference enables Physical-AI devices to execute edge-inferred actions using transmitted sensory inputs. Since the risk of incorrect actions vary across observations and tasks, the associated uplink transmission of sensory inputs requires different levels of wireless reliability. For instance, applying a fixed signal-to-interference-plus-noise ratio (SINR) requirement can overprovision low-risk tasks while underprovisioning high-risk ones. Therefore, we propose risk-aware control for edge inference (RACE), which maps predicted action-failure probability and task criticality to adaptive SINR targets and combines them with deadline-derived SINR requirements. A slow-timescale large language model (LLM) proposes task requirements for deterministic validation, while a fast hybrid actor selects inference configurations and transmit power levels, complemented by analytical receive beamforming and finite power restoration. Simulations show $11\%$ improvement in the average accuracy-latency-energy objective over fixed-high-SINR control, with near-zero constraint outage.

cs.NI · cs.AI · cs.LG · eess.SP

版本更新 · v2arXiv:2605.31460

On-Device Robotic Planning: Eliminating Inference Redundancy for Efficient Decision-Making

Joonhee Lee, Sungmin Lee, Hyunseung Shin, Hyunmi Kim, Pei Zhang, Jeonggil Ko

原文摘要

Reasoning-based robotic policies using large language and vision-language models achieve strong semantic planning capabilities but mostly suffer from a high inference latency that limits practical real-time deployment. In this work, we observe that robotic reasoning workloads contain substantial temporal redundancy, where consecutive observations frequently produce identical actions and subgoals. Based on this insight, we present REIS, a human cognition inspired robotic decision-making framework that minimizes unnecessary reasoning while preserving semantic adaptability. REIS combines lightweight scene gating, KV-steered affordance routing, and deliberative reasoning to accelerate robotic control under embodied constraints. Experiments on ALFRED, and real-world robotic tasks demonstrate that REIS significantly suppresses reasoning overhead while maintaining competitive task performance

cs.RO · eess.SY

版本更新 · v3arXiv:2606.17413

Amortized Probabilistic Retrieval of Atmospheric CO2 from OCO-2 Spectra Using Deep Learning with Laplace Approximations and Normalizing Flows

Alejandro Calle-Saldarriaga, Felix Jimenez, Jack Grosskreuz, Jiazheng Wang, Jonathan Hobbs, Matthias Katzfuss

原文摘要

Space-based monitoring of atmospheric carbon dioxide (CO$_2$) constrains the global carbon budget. NASA's Orbiting Carbon Observatory-2 (OCO-2) estimates column-averaged dry-air mole fractions of CO$_2$ (XCO$_2$) from high-resolution spectra, but operational retrievals are computationally expensive and impose stringent Gaussianity assumptions on the retrieved posterior. We present a deep learning framework that addresses both through amortized probabilistic inference. Lacking ground truth for real observations, we train and evaluate on a high-fidelity OCO-2 simulation ensemble with calibrated forward-model errors, comparing against the version-10 operational full-physics retrieval, without its bias correction, on the same radiances. Our architecture encodes each spectral band separately and estimates posteriors of the full CO$_2$ column, or summaries thereof, with Laplace approximations and conditional normalizing flows. Once trained, inference costs milliseconds per sounding rather than minutes. Trained on simulations that explicitly include forward-model discrepancy, our retrievals are more accurate than the operational one for XCO$_2$ on both data partitions we consider, and competitive on profiles. The flow represents asymmetric posteriors that a Gaussian cannot, a gain attributable to shape rather than scale, and its advantage in predictive density persists where its accuracy advantage does not. These results are established on a land-only ensemble against one configuration of the operational algorithm. On held-out reference soundings and two unseen months the XCO$_2$ and density advantages persist. For XCO$_2$, coverage is near nominal on February data and, though below nominal on the unseen months, remains far closer to it than the operational retrieval's.

cs.LG · stat.AP

版本更新 · v2arXiv:2609.39532

Tight Liquid Welfare Guarantees for Auctions with Budgets

Twan Kroll, Guido Schäfer, Artem Tsikiridis

原文摘要

We study the efficiency of auctions with budget-constrained bidders and derive tight price of anarchy (PoA) bounds for coarse correlated equilibria (CCE). To this end, we develop a general framework that reduces proving PoA guarantees to bounding the optimal value of a linear program. The LP is formulated over a small number of per-bidder equilibrium statistics, incorporates constraints implied by the auction setting and equilibrium behavior, and captures a novel smoothness notion tailored to budget-constrained environments; we provide a reduction from classical smoothness to this new notion. Our approach enables simple and tight PoA analyses across a broad range of auction formats. Using our framework, we obtain tight liquid welfare guarantees for simultaneous first-price, second-price, and all-pay auctions, simultaneous first-price auctions in which every bidder scales her values by a single bid multiplier (Deng et al., 2021), discriminatory and uniform price multi-unit auctions, and generalized first-price and second-price position auctions. Beyond budget-constrained settings, we also prove tight bounds for the budget-free uniform price auction and the budget-free generalized second-price auction.

cs.GT

版本更新 · v2arXiv:2603.14073

MotionCFG: Boosting Motion Dynamics via Semantic Motion Sharpening

Byungjun Kim, Soobin Um, Jong Chul Ye

原文摘要

Despite recent advancements in Text-to-Video (T2V) synthesis, generating high-fidelity and dynamic motion remains a significant challenge. Existing methods primarily rely on Classifier-Free Guidance (CFG), but standard CFG treats all semantic dimensions uniformly and provides no mechanism to selectively resolve ambiguity along the motion axis. To address this, we propose MotionCFG, a training-free approach that introduces selective guidance along the motion subspace of the condition embedding. Specifically, we construct a motion-perturbed negative condition by injecting Gaussian noise into motion-related embeddings, and steer generation away from it to selectively amplify motion intent. We show theoretically that this procedure implicitly approximates Semantic Laplacian Sharpening, a second-order correction that suppresses motion-ambiguous regions of the score landscape and amplifies well-resolved dynamic peaks. Combined with a piecewise guidance schedule that confines intervention to the early denoising steps, MotionCFG consistently improves motion dynamics across state-of-the-art T2V frameworks with negligible overhead. We further demonstrate that this Laplacian sharpening principle generalizes beyond motion, effectively steering complex, non-linear concepts such as precise object numerosity that are typically difficult to modulate via standard text-based guidance. Our project page is available at https://motion-cfg.vercel.app/.

cs.CV · cs.AI · cs.LG

新论文 · v1arXiv:2611.14686

What Entropy-Based View Selection Cannot See: An Audit of Test-Time Adaptation for Vision-Language Models

Sivasuthan Sukumar, Uthayasanker Thayasivam

原文摘要

Vision-language models such as CLIP can classify images into categories they were never explicitly trained to recognize, but accuracy degrades when test images differ in style or source from their training data. A common remedy generates randomly cropped and flipped copies of each test image, called views, and combines their predictions. Since some views miss the object, methods must identify which views to trust. The dominant approach uses prediction entropy to measure confidence and retains the most certain views. Other methods use signals such as embedding typicality. Despite repeated refinements of these scoring functions, the information they rely on, the model's own response to each view, remains largely unexamined. We investigate this choice while holding other pipeline stages fixed. First, we show that view selection, rather than the gradient update, accounts for almost all accuracy gains. We then examine whether entropy identifies useful views when predictions are wrong, despite at least one view predicting the correct class. In these cases, entropy ranks correct views above incorrect ones no better than chance, recovering only about one-twentieth of the accuracy recovered by an oracle over the same views. This finding holds across two image encoders and under a control ruling out an obvious statistical artifact. An exact analysis explains this limitation: entropy measures confidence but not which class a view favors. We identify an unused signal already available in the augmentation pipeline: the fraction of the original image retained by each crop. Ranking views by this quantity improves accuracy on 14 of 15 benchmark datasets over entropy and on 11 of 15 over the strongest scoring function tested. A pre-method measurement also predicts which datasets benefit.

cs.CV · cs.AI

新论文 · v1arXiv:2611.14685

Terrain-Aware Thompson Sampling for Multi-Drone Search and Rescue

Riana Gagnon Souleiman, Giovanni Beltrame

原文摘要

In this work, we propose a decentralized terrain-aware multi-drone Thompson Sampling algorithm tailored for search and rescue (SAR) applications. A probability distribution of locating a lost person is informed by terrain data, using established SAR models (displacement ring, elevation, watershed, dispersion angle, and track offset) derived from historical SAR case data on lost person behavior. Exploration is conducted by a team of drones using Thompson Sampling, where candidate actions are selected by drawing samples from this probability distribution, represented by a per-cell Gaussian posterior whose mean and variance are updated through Bayesian inference. This approach balances exploration of uncertain regions with exploitation of high-probability areas to locate a lost person. Observation uncertainty is incorporated through fractional forest coverage, which measures the percentage of an observation occluded by tree coverage and accounts for reduced detection performance in densely vegetated areas. Simulations using real SAR case data (YOSAR) evaluate the proposed method against a coverage planner and a probabilistic active search method in search regions of 1.5 and 3.8 square kilometers, with 5, 10, 15, and 20 agents flying at 50 km/hr. We demonstrate that our method achieves a success rate of approximately 87% within 60 to 247 seconds in the 1.5 square kilometer region, and success rates of approximately 75% to 91% within 161 to 466 seconds in the 3.8 square kilometer region, across different agent configurations.

cs.RO

新论文 · v1arXiv:2611.14683

Trait Hitchhiking in LLM Post-Training

Adil Soubki, Elizabeth S. Z. Tan, Miles Cranmer

原文摘要

Reinforcement learning (RL) is now a standard stage of language model post-training, and the compute devoted to it is growing rapidly. While it has been shown to improve capabilities, particularly for tasks with verifiable rewards, it can also change behaviours and internal properties that the reward does not explicitly target. We present a formalism to describe the evolution of "traits" during RL post-training and, in doing so, recover the Price equation from evolutionary biology. We use this to develop a mathematical model for what we call "trait hitchhiking": the amplification or suppression of non-targeted traits as training redistributes probability across completions. We evaluate this Price update expression on language models trained with GRPO and show that the Price estimates closely track the sampled trait dynamics. These results identify trait hitchhiking as a mechanism by which RL post-training can silently amplify undesirable traits.

cs.LG · cs.CL

版本更新 · v3arXiv:2511.09454

Individualized Algorithmic Advice as a Strategic Signal on Competitive Markets

Tobias R. Rebholz, Maxwell Uphoff, Christian H. R. Bernges, Florian Scholten

原文摘要

As algorithms increasingly mediate competitive decision-making, their influence extends beyond individual outcomes to shaping strategic market dynamics. In our experiment, we examined how algorithmic advice affects human behavior in a classic economic game with a unique, non-collusive, and analytically traceable equilibrium. Participants (N = 129) played a Cournot quantity competition with equilibrium-aligned or strategically biased algorithmic recommendations. While individualized equilibrium advice supported stable convergence, collusively downward-biased advice led to sustained underproduction and supracompetitive profits - hallmarks of tacit collusion. Participants' quantities converged faster and more consistently toward individualized than collective equilibrium advice, potentially due to an objective quality advantage or greater perceived ownership of the former. These findings demonstrate that algorithmic advice can function as a strategic signal, shaping coordination even without explicit communication. The results echo real-world concerns about algorithmic collusion and underscore the need for careful design and oversight of algorithmic decision-support systems in competitive environments.

cs.HC · cs.AI · cs.CY · cs.GT · econ.GN

新论文 · v1arXiv:2611.14681

Together Compiler: Continual Compilation for AI Inference

Reyna Abhyankar, Dylan Lim, Drew Wadsworth, Venkata Hasith Vattikuti, YuTong Julia Zhang, Jung Hwan Heo, Taeksang Kim, Kesavan Ramakrishnan 等 12 位作者

原文摘要

Today's AI workloads are rapidly changing: new models are released more often, model architectures are increasingly diverse, and traffic distributions change frequently. The challenge we face at Together AI is continual optimization for these changing workloads. Compiling a deployment into an optimized forward pass is a challenge that is well-suited for agent hill-climbing. Existing systems struggle with continual compilation due to a tradeoff between measurement throughput and fidelity. Many systems use agents to optimize individual kernels from the inference forward pass using offline benchmarks, but timings are low-fidelity because of data-dependent behavior in primitives like mixture-of-experts (MoE). On the other hand, systems use agents to directly optimize end-to-end engines but suffer from slow engine launch times. To address these challenges, we build Together Compiler (TKCC), the first truly continual agent loop designed for AI inference optimization. To address the throughput-fidelity tradeoff, we propose: (1) a Tiered Persistent Engine that decouples engine launch overheads from forward pass computation; (2) a cost model to select the parallelism configurations that seed the optimization process. We also conduct extensive ablations on agent context management and present our insights on deploying TKCC in production. TKCC outperforms highly-optimized hand-written Megakernels on the Llama 1B workhorse workload by up to 1.7x and the best open source engines on the latest frontier models (Kimi K3, GLM 5.3, MiniMax M3.1 Flash, DeepSeek v4.1 Flash) across hardware platforms by up to 2.6x higher TPS on the InferenceX benchmark. TKCC also sets the state-of-the-art performance at batch size 1, with 1111 TPS on M3.1 Flash and 1205 TPS on DeepSeek v4.1 Flash. Finally, TKCC generalizes beyond frontier language model inference. TKCC serves trillions of tokens across our production fleet.

cs.AI

新论文 · v1arXiv:2611.14677

Fast Slice-Wise Deep Learning Motion Correction for Spinal Cord Functional MRI

Thomas Dagonneau, Sandrine Bédard, Nontharat Tucksinapinunchai, Uten Yarach, Loïc Le Folgoc, Pietro Gori, Julien Cohen-Adad

原文摘要

Respiratory and bulk motion displace the spinal cord between the volumes of a functional MRI time series. Current methods such as the Spinal Cord Toolbox (SCT) take several minutes per time series, and general-purpose brain tools register whole volumes, whereas the cord moves mainly slice by slice. We propose a lightweight convolutional neural network that regresses the in-plane translation aligning each axial slice to a reference. Two models, trained without motion labels, correct large and then residual motion. On a 3T (120 scans) and a 7T (59 scans) dataset, the proposed method improves on SCT on every metric (tSNR +10 to +25%, DVARS -20 to -38%), leaves almost no slice displaced by more than one voxel (<0.1%), performs on par with a slice-wise AFNI variant and better than slice-wise FSL FLIRT, and runs in about 10 s per scan, about 30 times faster than SCT. The code is available at https://github.com/ivadomed/moco-dl and the method is available in SCT v7.4.

cs.CV

新论文 · v1arXiv:2611.14675

MITRA-Swarm: Injecting Explicit Linguistic Structure into Foundation Models for Classical Machine Translation

Kayshav Bhardwaj, Pragun Seth, Kush Bhardwaj, Vijay Nagasamy, Kurt Keutzer

原文摘要

Classical Sanskrit poses three challenges unresolved by single-call monolithic models: morphophonemic fusion Sandhi, dense nominal compounding Samāsa, and discourse-level zero-anaphora forced by poetic meter. We present MITRA-Swarm, a multi-agent architecture injecting explicit linguistic structure into an otherwise monolithic pipeline: a Sandhi-splitting agent, a parallel array of generalist gemma-4-26B-A4B-it and domain-specialized gemma-2-mitra-it translators, and a discourse-aware Ellipsis Restorer that consults corpus-derived register tags to avoid inventing active-voice subjects in impersonal legal and philosophical registers. Two separated judges evaluate quality: a routing judge ($J_{\text{route}}$, same model family as the generators) driving an internal critique loop, and an independent reporting judge ($J_{\text{report}}=$gpt-4o-mini, no shared vendor lineage) scoring every output exactly once. On a stratified benchmark of 1,000 verses across five registers (23,990 scored verdicts, 12-condition pre-registered ablation), the full swarm reaches $85.90$ MQM against a monolithic baseline of $85.27$ ($Δ=+0.63$, $p_{\text{adj}}=0.0018$, 95% CI $[+0.30,+0.97]$), and isolated discourse restoration alone accounts for $+0.44$ MQM ($p_{\text{adj}}=0.0288$), outperforming a call-count-matched self-refinement baseline by $+0.51$ MQM ($p_{\text{adj}}=0.0288$). Severe per-verse failures (MQM$<80$) fall from $9.0\%$ to $7.6\%$, at roughly $9\times$ the per-verse inference cost of the baseline. Additionally, $J_{\text{route}}$ scores its own family's outputs $2$-$7$ MQM higher than $J_{\text{report}}$ on every one of the 12 conditions, empirically motivating the two-judge split; and a preflight screen of a 192,151-entry retrieval index against all 12 evaluation works verifies 0 reference leaks across 269 runtime checks. These are small gains on a metric saturating near 85-86.

cs.CL · cs.AI

新论文 · v1arXiv:2611.14671

Where Should the Code Go? Locating Foundation-Model Errors in Bitemporal Inventory Simulation

Durga Sandeep Saluru, Lanchen Song, Aditya Kumaran

原文摘要

Operational reports carry two clocks: when an event happened and when its report arrived; later reports can revise earlier ones. A foundation-model component that maintains the state supported by the reports visible at a cutoff, then rolls a supplied scenario forward, can be helped by exact code before it, after it or inside the call, or asked to reason harder. We ask which remedy removes which error, for which models, on an exactly solvable lost-sales inventory environment: 36,672 independently rescored requests over twelve configurations of closed and open-weight models, with a forced-answer-call interface as a control and protocols frozen before the calls. Weak models fail in separable ways. Canonical input removes report-selection error, exact continuation removes rollout error, neither repairs the other, and which error dominates differs by model; strong models are at ceiling on raw reports. Asking for more reasoning is no substitute and can depend on the interface: under a forced answer call high effort collapses GPT-5.4 mini and DeepSeek V4 Pro, which gain or hold under automatic choice; on its provider the forced call disables reasoning for DeepSeek V4 Flash; and at high effort gpt-oss exhausts its output budget. The contribution is a controlled component diagnostic, released with every request, and evidence that for some model and provider pairs the tool-calling interface confounds reasoning evaluation.

cs.SE · cs.AI · cs.LG

版本更新 · v2arXiv:2602.03665

MM-SCALE: Evaluating Evidence-Grounded Moral Judgment in Vision-Language Models

Eunkyu Park, Wesley Hanwen Deng, Cheyon Jin, Matheus Kunzler Maldaner, Jordan Wheeler, Jason I. Hong, Hong Shen, Adam Perer 等 11 位作者

原文摘要

Vision-Language Models increasingly make socially consequential judgments from image-text inputs, yet current evaluations often stop at verdict-level accuracy: whether the final label is human-aligned, not whether it follows from the correct evidence. We introduce MM-SCALE (Multimodal Moral SCALE), a benchmark for evidence-grounded moral judgment built around a design choice: each image is paired with multiple action scenarios, so models must compare how different actions interact with the same visual context rather than score images in isolation. MM-SCALE contains 8,444 image contexts and 21,977 action scenarios, each annotated with a 5-point moral acceptability rating and a modality-grounding label indicating whether the human judgment relied on text, image, or both. Three tasks evaluate whether models (i) assign calibrated scalar moral scores, (ii) preserve human orderings within a shared visual context, and (iii) ground rationales in the evidence source humans found critical to judgment. Across models, aggregate metrics overstate alignment: NDCG@5 remains high across models, while within-image pairwise accuracy remains only 0.53-0.62 even on scenario pairs whose human mean ratings differ by at least one point. CoT has inconsistent effects on calibration and does not reliably improve within-image ordering. Evidence grounding evaluations further show that models often describe visual context without making it critical for the verdict. These results reveal an evidence-grounding failure in current VLMs and position MM-SCALE as an evaluation testbed for moral judgment under shared image contexts. This dataset includes potentially harmful and sensitive visual content. Images are intended solely for evaluation.

cs.CV · cs.HC

新论文 · v1arXiv:2611.14665

Galop: Billion-Scale Genetic Programming on a Single GPU

Xavier Hill Roy, Stephen Kelly

原文摘要

Genetic programming (GP) evolves populations of heterogeneous programs, whereas GPUs achieve their highest throughput when groups of threads execute the same instructions. To better align GP evaluation with GPU execution, we present Galop, a hybrid CPU-GPU linear GP system that assigns one individual to each CUDA warp, a group of 32 threads that execute the same instructions across different fitness cases. We compare Galop against EvoGP, a recent high-performance GPU-based tree GP system, on data-rich symbolic regression across two unique GPUs, varying population size and fitness-case count. Galop completes evolutionary runs faster than EvoGP in 27 of the 28 main comparisons, with speedups of up to 13.6 times. Solution quality comparisons favour EvoGP overall, although Galop remains competitive on several problems. Galop also completes a full generation with 2.15 billion individuals on a single H100 GPU, approximately 4.0 times the largest population achieved by any other tested GP system. All five runs at this population complete 100 generations, with a median wall-clock time of 2.23 hours. These results make it practical to study GP populations in the billions on a single GPU. Galop's source code, experimental data, and reproducibility scripts are publicly available at https://github.com/xavierhillroy/Galop.

cs.NE

版本更新 · v2arXiv:2605.18483

Modality vs. Morphology: A Framework for Time Series Classification for Biological Signals

Jordan Tschida, Matthew Yohe, Edward Kane, Gavin Jager, Emma J. Reid, Tony G. Allen, Mark Story, Leanne Thompson 等 13 位作者

原文摘要

Techniques for classifying biological signals are largely developed within specific modalities rather than the underlying signal structure (i.e., morphology), leading to disjointed methodologies and limited guidance across diverse signals. This work introduces a novel morphology--modality framework that connects waveform structure to a principled design of preprocessing, feature extraction, and modeling techniques for biological time-series classification. We analyze evidence across biological signals including electroencephalography, electromyography, electrocardiography, photoplethysmography, and ocular modalities including electrooculography, pupillometry, and eye-tracking, and organize according to their primary morphologies: spikes, bursts, oscillations, slow drift, and hierarchical rhythms. Across these categories, we examine how morphology influences the analytical pipeline from preprocessing to modeling and evaluation. Localized architectures favor spikes and bursts, whereas frequency and temporal models capture oscillations, and hybrid approaches integrate local and global dependencies in hierarchical signals. The associations are not absolute as biological signals often contain multiple morphologies where relevance is task dependent. The proposed framework positions morphology as an inductive biases are useful for modeling. We further identify challenges in cross-subject generalization, morphology-preserving data augmentation, multimodal fusion, and evaluation practices. By linking modality-specific constraints with waveform structure, this review provides guidance for selecting and evaluating pipelines across biological signals. We argue that morphology provides a useful cross-modal lens for developing biological time-series classification systems that are more generalizable, interpretable, and physiologically grounded.

cs.LG · cs.AI

新论文 · v1arXiv:2611.14664

Outcome Over Learning? Evidence from Student Use of AI Code Assistants for Unit Test Writing

Daniel Hinbest, Jeremy S. Bradbury, Michael A. Miljanovic

原文摘要

Artificial intelligence (AI) code assistants are rapidly being adopted in programming education, yet little is known about how students naturally use these tools when given unrestricted access. In a user study investigating AI-assisted unit test writing, we observed that a majority of students adopted a one-shot interaction strategy, asking the AI to generate a complete unit test directly from the initial requirements. While this approach is capable of efficiently producing a solution, it shifts students' focus from learning how to write effective unit tests to simply completing the task. Moreover, because students rarely engaged in critically evaluating, refining, or iterating on AI-generated output, they may be missing opportunities to develop the critical thinking skills that are essential for effective and responsible use of AI. In an effort to shift student focus from outcome to learning we also discuss how training, accountability and improved learning task design can better support a more learning-centric responsible use of AI.

cs.SE · cs.AI

版本更新 · v2arXiv:2605.22964

Certification from Examples is Hard for Circuits and Transformers under Minimal Overparametrization

Artur Back de Luca, Kimon Fountoulakis

原文摘要

As state-of-the-art neural networks are deployed on reasoning and algorithmic tasks, exactness guarantees become increasingly important. However, high average-case accuracy can still mask incorrect behaviors. This motivates exact certification, which asks for the smallest set of labeled examples needed to certify that a learned hypothesis equals the target. We show that while some hypotheses are easy to certify, even minimal overparametrization can make certification exponentially hard across several hypothesis classes. For threshold circuits of depth $\ge 2$, adding a single extra gate can force certificate sizes exponential in the input dimension. We show an analogous hardness result for log-precision Transformers with only constant architectural overhead. We also characterize approximate certification, showing that allowing only polynomially many mistakes still requires exponentially large certificates, whereas constant relative-error guarantees can hide exponentially many failures. Empirically, we study binary-addition recognition using threshold circuits and Transformers trained with strong supervision. We find that incorrect models can survive extensive checks, with errors that often occur on different inputs and are difficult to detect through uniform sampling.

cs.LG

版本更新 · v2arXiv:2610.22588

SAG2: Embedding-Free Multi-Hop Retrieval with BM25 and Decision Models

Yuchao Wu, XingCheng Liang, Guanxian Li

原文摘要

Multi-hop retrieval must find passages that become useful only after intermediate evidence is retrieved. We present SAG2, an embedding-free retriever whose only persistent structure is a SQLite lexical index, built without an LLM. Where SAG and HippoRAG 2 rely on a generative LLM for graph extraction and selection, SAG2 uses a decision model. Given the question and a shared context of selected retrieved passages, the decision model scores whether each candidate supplies an answer-chain fact. Terms activated from the top-scoring passages retrieve unvisited passages through the lexical index, which holds a passage-term hypergraph implicitly. SAG2 reaches Recall@10 of 86.62%, 97.43%, and 99.00% on 1,000-question subsets of MuSiQue, 2WikiMultiHopQA, and HotpotQA, the highest among the compared systems. With a decision model priced at about a fifth of SAG's LLM, indexing and retrieval on MuSiQue cost USD 4.33 against USD 14.85 for SAG. On EnterpriseRAG-Bench, SAG2 reaches 81.12% document Recall@10. As the benchmark's nested corpus grows 447.5-fold, SAG2's Recall@5 lead over BM25 alone widens from 7.28 to 14.76 points, at a nearly constant model cost per question. Because indexing makes no model call, SAG2 suits corpora that change often or must be searchable as soon as they are indexed.

cs.CL

版本更新 · v2arXiv:2602.03627

Ultra Fast PDE Solving via Physics Guided Few-step Diffusion

Cindy Xiangrui Kong, Yueqi Wang, Haoyang Zheng, Weijian Luo, Guang Lin

原文摘要

Diffusion-based models have demonstrated impressive accuracy and generalization in solving partial differential equations (PDEs). However, their practical utility still suffers from high sampling costs and insufficient physical consistency, mainly due to many-step iterative sampling and insufficient physics guidance. To address these issues, we propose \emph{Phys-Instruct}, a physics-guided distillation framework that compresses a pre-trained diffusion PDE solver into a few-step generator while explicitly enforcing PDE consistency through distillation guidance. We reformulate the training objective as a constrained problem with PDE residual, and derive a score-function identity that leads to a practical physics-guided generator update. Across five PDE benchmarks, Phys-Instruct achieves orders-of-magnitude faster inference while reducing the PDE Error by factors of $2.4$ to $15.5$, compared with the corresponding 200-step EDM teachers. Moreover, the resulting unconditional student model functions as a compact prior, enabling efficient and physically consistent inference for various downstream conditional tasks. Our results indicate that Phys-Instruct is an effective and efficient framework for ultra-fast PDE solving powered by generative models.

cs.LG

新论文 · v1arXiv:2611.14661

Abstention Is Not Threshold Compliance: Stated Scoring Rules in Open Language Models

Dongsun Moon

原文摘要

Kalai et al. propose stating the scoring rule in the prompt with an explicit threshold t, so that a model should answer only when its probability of being correct exceeds t. We probe each requirement of compliance on shared items, in 12 checkpoints from three post-training stages of four fully open 3-8B recipes, with exploratory models up to 32B. At t = 0.75, a line limiting the reply to an answer or "I abstain" (the abstention format) raised the mean abstention rate from 20% to 91%. Yet within this format, raising t from 0.5 to 0.9 changed it by only -0.8 percentage points. Without the line, the higher threshold even lowered abstention, and up to 40% of a checkpoint's items received decisions that no compliant policy with threshold-independent beliefs could make. Given the probability that their answer was correct, the checkpoints barely responded to the threshold in a forced-choice probe. Comparisons with self-assessment signals such as P(True) depended on the grader and on answer drift between prompts. An external threshold on recalibrated P(True) made coverage non-increasing in t by construction. Calibrated on the evaluation distribution (post hoc), it beat the abstention format at t = 0.5; calibrated on TriviaQA and applied to PopQA, however, it fell below that format at 0.75. On OLMo 3 7B, decisions trained on threshold-conditioned targets did not follow unseen thresholds consistently. A post-hoc variant trained at four thresholds answered less as t rose but still failed a pre-specified test, mainly on agreement with its training rule. A high abstention rate is not evidence of compliance: evaluations using stated scoring rules should report how often models abstain, whether decisions respond to the stated threshold, and which items they answer.

cs.CL · cs.AI