跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+479新增论文
+361其中 AI 相关
+63已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 17:24 — 2026-11-16 17:24(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44库内论文最新更新时间:2026-11-14 02:59

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

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

浏览论文库

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

找到 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.13346

Advancing Mass-Conserving Deep Learning for Distributed Hydrologic Modeling: A Case Study in a Snow-Dominated Watershed

Yihan Wang, Lujun Zhang, N. Benjamin Erichson, Yang Hong, Tiantian Yang

原文摘要

Recent progress in physics-aware deep learning (DL) has embedded mass conservation within Long Short-Term Memory (LSTM) architecture for hydrologic modeling, improving physical consistency and enabling diagnostics of internal states. However, existing mass-conserving neural networks are primarily developed in lumped formulations. Consequently, previous studies provide only fragmented and often indirect evidence of when and why imposed physical constraints may lead to unrealistic hydrologic behavior. To address this limitation, we propose Physics-Enhanced Conservation-Augmented Net (PECAN), a mass-conserving convolutional LSTM-based framework for distributed hydrologic modeling and diagnosing structural limitations of physics-aware DL models. PECAN is implemented in two variants: (1) PECAN-MC with a strict precipitation-based conservation constraint and (2) PECAN-MCR with a relaxed conservation constraint allowing additional water inputs beyond precipitation. Both variants are trained solely on gauge streamflow and evaluated in a snow-dominated watershed in Colorado. We benchmark PECAN against lumped DL baselines and the distributed process-based Variable Infiltration Capacity (VIC) model. Results show that PECAN achieves competitive outlet streamflow simulation accuracy while producing spatially explicit latent states for interpretation. Comparisons with reference soil moisture indicate that PECAN cell states resemble meaningful temporal soil moisture dynamics. However, analyses also reveal that PECAN misrepresents snow processes by prematurely removing winter snow water storage from the system rather than retaining it for spring release. PECAN demonstrates accurate streamflow simulation at gauges and shows diagnostic potential to expose structural limitations in hydrologic process representation, thereby informing future physics-aware neural network development for hydrology.

cs.LG · physics.geo-ph

新论文 · v1arXiv:2611.13344

PneuGen: Task-Driven Agentic Co-Design of Soft Pneumatic Robots

Shaohong Zhong, Marco Pontin, Perla Maiolino

原文摘要

Task-driven design of soft robots requires the consideration of factors such as geometry, morphology, material properties, and actuation, resulting in a large and complex design space that is challenging to explore. Computational optimisation methods leverage signals from simulation to iteratively improve designs to achieve task objectives. However, these methods typically demand high computational load for both optimisation and simulation. We present PneuGen, an agentic co-design framework for soft robots that leverages Large Language Model (LLM) agents to search over the soft robot design space efficiently. A designer agent proposes design programs from a parametric component library, and a separate critic agent analyses simulation diagnostics and recommends targeted revisions. Fitted module response models provide reusable physical priors relating geometry and pressure to deformation. Design programs are automatically validated and converted into finite-element simulations, enabling iterative evaluation. Across grasping tasks on primitive shapes and challenging objects, as well as shape-matching tasks that require multi-directional planar and 3D deformation, the proposed framework significantly outperforms prior computational optimisation baselines. Ablation experiments also highlight the utility of the critic agent and the module response model in facilitating efficient design. We additionally demonstrate the agent-generated soft robot designs in real-world shape-matching and grasping tasks.

cs.RO

新论文 · v1arXiv:2611.13342

Early Rug Pull Detection on Solana

Saba Heydaridoost, Kasra Kashani, Mohammad Mowlavi Sorond, Behnam Bahrak

原文摘要

Web3 platforms that help users discover and trade newly launched crypto tokens, including launchpads, decentralized-exchange (DEX) interfaces, wallets, and token-analytics sites, must assess tokens before their legitimacy is clear. On Solana, where token creation is inexpensive and tokens use standard programs rather than custom per-token smart contracts, rug pulls can unfold within minutes. Effective warnings must therefore rely on limited histories. Although graph neural networks (GNNs) have improved rug-pull detection on EVM chains, it remains unclear whether transfer structure adds predictive value over non-graph models at minute-scale decision points, and how that value changes as history accumulates. We study 2,700 tokens sampled from SolRPDS, collecting one-minute market histories from Birdeye and token transfers from Solana RPC. We define a rug pull operationally by requiring a liquidity drain, price collapse, and persistent liquidity depletion over a nominal 24-hour period after token creation. All features use only information available at or before each prediction cutoff. We evaluate observation windows of 12.5, 35.5, and 93 minutes, selected in advance from the published lifespan distribution of Solana rug pulls, and represent each token as a temporal transfer graph. Within the first 12.5 minutes, rug-pull and non-rug graphs already differ in size, density, reciprocity, and receiver-side centralization. We compare GNNs against matched non-graph models using the same token-level and graph-summary features on identical samples. A fixed panel of tokens observed in all three windows further isolates the effect of longer observation from changes in token population. Our findings inform the design of early-warning mechanisms for newly launched Solana tokens in Web3 interfaces.

cs.CR

版本更新 · v5arXiv:2603.02337

Preconditioned Flow Matching

Shadab Ahamed, Eshed Gal, Md Shahriar Rahim Siddiqui, Simon Ghyselincks, Moshe Eliasof, Eldad Haber

原文摘要

Flow matching (FM) learns vector fields by regressing stochastic velocity targets along intermediate distributions $p_t$. We identify a geometric optimization bottleneck in this regression problem: when the covariance $Σ_t$ of $p_t$ is ill-conditioned, gradient-based training rapidly fits high-variance directions while making slow progress along low-variance ones. In an exactly solvable Gaussian setting, we prove that the excess risk is weighted by $Σ_t$, and that both gradient descent and stochastic gradient descent inherit condition-number-dependent convergence. We then extend the analysis to Gaussian mixtures, showing that multimodality does not average away this effect; instead, the slowest and worst-conditioned component can control optimization. Motivated by this analysis, we propose $\textit{preconditioned flow matching}$, a precondition-then-match framework that transforms the target distribution into a more isotropic representation, trains the main flow in the transformed space, and maps generated samples back through the inverse transformation. We show theoretically that preconditioning reshapes the intermediate FM path and improves its conditioning. Across controlled Gaussian and Gaussian-mixture experiments, latent MNIST and other high resolution image datasets up to $512{\times}512$ resolution, preconditioning improves path-conditioning diagnostics, low-eigenvalue recovery, FID, MMD, precision, and recall. Compute-matched baselines and preconditioner-quality ablations further show that the gains are not explained merely by additional preconditioner parameters, but by improved geometry of the downstream flow matching problem. GitHub: https://github.com/ahxmeds/preconditioned-flow-matching.git.

cs.LG · cs.AI · cs.CV

版本更新 · v2arXiv:2611.06858

CompressionBench: How can your coding agents compress LLMs?

Xinrui Zhong, Zhifeng Li, Zhiming Wang, Xinze Feng, Yongqi Liu, Shanglin Yang, Yang Zhou, Zikun Li 等 10 位作者

原文摘要

Recursive self-improvement requires AI systems to improve the models and infrastructure used by subsequent systems. LLM compression offers a concrete efficiency objective: retain a pretrained model's behavior within a smaller model storage budget. We study whether coding agents can carry out this step autonomously. We formulate compression as a terminal task in which an agent receives a source checkpoint, storage limit, inference environment, and time budget, then constructs compressed weights and executable inference code. The agent controls its algorithm and experiments; perplexity feedback guides search, and independent verification checks the final model. Across six agents and six model--size settings, 29 of 36 submissions pass verification. Selecting the lowest-perplexity agent design per task yields an average 3.4% perplexity increase over BF16 and 77.33% downstream accuracy, compared with 79.56% for BF16. Recorded experiments reveal how agents achieve these outcomes and where improvement breaks down. Agents lower PPL in 21 of 24 revisions at nearly fixed storage; complete-model feedback reverses 17 of 79 prior local rankings; and generation and inference tests expose failures that likelihood alone misses. The results identify representation design, experimental judgment, and capability validation as central to agent-driven model compression, a measurable component of efficiency-oriented self-improvement.

cs.AI

新论文 · v1arXiv:2611.13337

VC-Dimension and Generalization in Geometric Machine Learning with Applications to Active Learning

Gokul Bhusal, Delanna Do, Ekaterina Merkurjev, Kevin Miller, Stephan Wojtowytsch

原文摘要

We compute the VC-dimension of metric ball classifiers in the model spaces of Riemannian geometry (Euclidean, spherical, hyperbolic) and present upper and lower bounds on the VC-dimension of metric balls in several other situations, including general normed vector spaces (potentially infinite VC-dimension), vector spaces with $\ell^p$-norms (VC-dimension grows at least linearly in the dimension, faster than Euclidean for $p=1$), flat tori, and general Riemannian manifolds (arbitrarily large VC-dimension after a conformal change). In several situations where the VC-dimension is large or even infinite, we prove generalization bounds under additional assumptions on the data distribution using covering arguments. Both in the VC-dimension and covering setting, we consider data on low-dimensional subsets of high-dimensional Euclidean spaces. As an application, we consider coverage-based algorithms in active learning.

stat.ML · cs.LG · math.DG

新论文 · v1arXiv:2611.13336

Veritas: A Verifier Generation Harness for Agent Tasks

Daoan Zhang, Qinbo Bai, Dehai Min, Xingyu Mu, Ziyi Chen, Jianing Yin

原文摘要

The effectiveness of a self-improving system relies heavily on the quality of its verifier, which judges the outcome of each improvement round. However, the verifiers of most tasks are written by hand, which is expensive and does not scale to tasks that come without one. We propose Veritas, a harness that generates verifiers automatically. Unlike general-purpose agent harnesses, Veritas adds three mechanisms for verifier generation: an evidence header stating what the verifier will observe, a library of domain rules that tasks leave unstated, and authoring principles, partly refined by a self-improvement loop. We evaluate on six benchmarks: four scored by execution, whose official verifiers we first certify, and two that compare pairs of responses. With the model fixed, the verifiers Veritas generates agree better with the official verdicts than those of seven other harnesses on all four execution-scored benchmarks. On the two pairwise benchmarks they are at or near the best. They also agree better than those of the vendor's own harness for two of three other model families. Its mechanisms also improve 9 of 12 harness-benchmark pairs scored by execution across three harnesses.

cs.AI · cs.CR

新论文 · v1arXiv:2611.13334

Disentangling Multimodal Rotary Positional Embedding in Vision-Language Models

Zhaoyi Liu, Haichuan Zhang, Xiaochuan Gong, Yancheng Zhu, Bowei Tian, Wanghao Ye, Yufan Zhang, Ang Li

原文摘要

Vision-language models widely adopt Multimodal Rotary Position Embedding (MRoPE), an extension of Rotary Position Embedding (RoPE) that incorporates temporal, height, and width axes to encode the spatial structure of visual tokens. However, MRoPE also assigns height and width coordinates to text tokens that lack inherent spatial structure, introducing spatial positional effects into text-vision attention. Existing MRoPE variants explore different frequency allocations and coordinate layouts, with their designs suggesting different intuitions about these cross-modal effects: they may provide useful spatial references for associating language with visual regions, or introduce unnecessary positional preferences that hinder text-vision interactions. In this work, we disentangle intra-visual spatial structure from cross-modal spatial effects to investigate this question. We identify a constraint of shared coordinate layouts that prevents eliminating cross-modal spatial effects while preserving intra-visual spatial encoding, and develop controlled experiments to isolate their respective contributions. Our results across multiple model scales, MRoPE variants, and benchmarks show that cross-modal spatial effects provide little additional benefit as spatial references and can even impair model performance, while intra-visual spatial encoding remains useful for fine-grained grounding.

cs.AI

新论文 · v1arXiv:2611.13333

Do AI Agents need Preventive Care? An Epidemiologic Cohort Design for Agentic AI

Shu Jiang, Graham A. Colditz

原文摘要

As AI agents increasingly perform tasks autonomously across sectors, including healthcare and biomedical research, understanding how their behaviors develop and influence outcomes over time becomes increasingly important. Existing evaluations largely focus on model capabilities and performance on predefined tasks. Here, we propose an epidemiologic cohort design for studying agentic AI, drawing on principles established in human population studies. The framework treats individual agents as members of a cohort, their underlying model as genetic makeup, accumulated work as their time scale, and naturally occurring behaviors as exposures that may influence subsequent outcomes. By following agents longitudinally, this approach enables investigation of behavioral determinants of adverse events, estimation of their potential preventable burden under causal assumptions, and characterization of behavioral changes over an agent's work life. We illustrate the design through two prospective observational cohorts examining curiosity and probing as a safety question, and data checking and analytical accuracy as a reliability question. Together, the framework and illustrative studies provide a generalizable blueprint for designing epidemiologic cohorts of AI agents.

cs.AI · cs.MA

新论文 · v1arXiv:2611.13332

FP64 Performance and the Limits of Ozaki Emulation on HPC Systems

Katarzyna, Swirydowicz, Nicholas Malaya, Noah Wolfe, Paul Bauman, Pieter Ghysels, Jonathan Belof

原文摘要

A growing industry narrative holds that native double precision can be deprioritized in HPC accelerators, on the hypothesis that low-precision tensor cores can emulate FP64 on demand, and that most HPC workloads are bandwidth-bound. This paper evaluates some of those claims and explores the importance of FP64 in scientific computing. We show roofline profiling data of representative HPC workloads, across a variety of common computational motifs, to evaluate the arithmetic-intensity and accuracy requirements of these workloads. We also consider FP64 emulation via the Ozaki method to ascertain some of the possibilities and limitations of these approaches. These results indicate that Ozaki emulation should not be evaluated as a general replacement for FP64, but as an optimization for the subset of workloads whose dominant computation is sufficiently large, dense, and GEMM-shaped. Our analysis indicates this is less than 10\% of the HPC ecosystem. Furthermore, even in this favorable regime, standalone GEMM speedup is not enough to accelerate (or avoid performance regression) for the application: numerical behavior, workspace requirements, matrix shape, and integration overhead determine whether the benefit survives at application scale. This paper characterizes those boundaries empirically. Furthermore, we show that dense GEMM accounts for only a small fraction of FP64 computation across HPC workloads, leaving most application-level FP64 work beyond the reach of GEMM-based emulation.

cs.DC · math.NA

新论文 · v1arXiv:2611.13330

Uni-Loc: Weakly Supervised 3D CT Pathology Localization via Spatially Grounded Vision-Language Classification

Hao-Chih Lee, Zahi A. Fayad, Xueyan Mei

原文摘要

Accurate localization of abnormalities in three-dimensional (3D) CT scans is essential for linking automated predictions with clinically relevant pathological findings. We propose Uni-Loc, a vision-language framework that unifies pathology classification and 3D localization using scan-level supervision. Uni-Loc derives both predictions and localization maps from spatial similarities between pathology-conditioned queries and image features. A token-to-voxel upsampling module enables high-resolution localization, while gradient-guided thresholding identifies pathology regions without additional learned parameters. Evaluated on five localization tasks comprising 355 annotated CT scans, Uni-Loc achieves macro-averaged voxel-level AUROC/AUPR of 96.1\%/34.5\%, outperforming relevance propagation (80.7%/13.9%) and gradient saliency (88.7%/8.1%). Uni-Loc also achieves classification AUROC of 88.39% on CT-RATE and 78.03% on RAD-ChestCT, improving over a matched baseline. These results demonstrate effective 3D pathology localization without requiring pathology-specific voxel-level supervision.

cs.CV

新论文 · v1arXiv:2611.13329

Agent-Guided Discovery of Exchange-Correlation Functionals with Physics-based Validation

Achuth Chandrasekhar, Amir Barati Farimani

原文摘要

Accurate, compact exchange--correlation functionals are central to predictive density functional theory. Symbolic search and language-model agents can propose new functional forms, but it remains unclear whether their gains survive self-consistency and external evaluation, whether the new terms carry physical content, whether agents outperform evolutionary search, and how language-model backbones compare. We connect frontier LLM agents to a GPU evaluator through the Model Context Protocol, with training-only fitting, persistent memory, and self-consistent and external evaluation. Opus-5.5 agents passed the screening gate with about 40-fold fewer tokens than Codex (GPT-6-Astra) agents and found a candidate with lower validation and held-out errors; only this candidate advanced to self-consistent evaluation. The resulting 13-parameter functional, O159, multiplies same-spin correlation by a smooth density window. Refitted controls favor a window that scales the entire same-spin factor, reducing it by 15--30\% at its peak, and that acts on reaction energies mainly in near-iso-orbital regions; against a refitted no-window control, it lowers heavy-atom total-energy errors on GSCDB137 by 29\%. With about 400 fits each, SyFES evolution did not improve on its GAS22 seed, whereas the agents found forms 0.10--0.13 \kcal\ lower in validation error by adding an explicit density scale. Self-consistent O159 lowers the held-out MGCDB84 test error of $ω$B97M-V by 11.7\%, and its mean normalized error ratio on 36 GSCDB137 datasets (1.139) is comparable to $ω$B97M-V (1.144) and below GAS22 (1.190). Frontier-LLM agents thus produced O159, a compact functional whose improvement over $ω$B97M-V survives self-consistent, physics-based validation.

cs.AI

新论文 · v1arXiv:2611.13326

ARIA: An AI-Powered Radio-Channel Inference and Analysis Pipeline

Homa Nikbakht, Mingjun Ying, Dipankar Shakya, Daniel Abraham, Theodore S. Rappaport

原文摘要

Statistical channel models play a key role in the design and standardization of next-generation wireless systems. The models substitute for costly and time-consuming field measurements when fitted distributions accurately reproduce the measured channel impulse responses. Future wireless systems will operate in global spectrum allocations from 1 to 150 GHz. Over the full span, analytically chosen distribution families fitted to scarce measurement data fail to deliver the required accuracy. Generative AI models instead learn each distribution from the radio-propagation data itself, adapt to the measured structure at every frequency, and scale across the entire band. We present ARIA, an AI-powered Radio-channel Inference and Analysis pipeline that learns each channel-parameter distribution from the measurements. The pipeline extracts power-delay profiles and recovers the channel parameters with time-cluster spatial-lobe (TCSL) analysis. Three neural density estimators, namely mixture density networks, neural spline flows (NSF), and denoising diffusion implicit models, learn each parameter's distribution. A composite rank across goodness-of-fit metrics with Friedman-Nemenyi testing identifies the best estimator, and a maximum-likelihood step anchored to the measured samples converts its density into closed-form parametric families. We instantiate ARIA on the NYU WIRELESS 16.95 GHz InH campaign and find that NSF outperforms the other estimators on every metric. We also show that a conditional NSF with feature-wise linear modulation, trained jointly on the 6.75 and 16.95 GHz measurements, improves over single-frequency training. We feed the fitted distributions into the NYUSIM simulator and reproduce the measured omnidirectional RMS delay spread medians within 2 ns, the per-lobe azimuth and zenith spread medians within 1 degree, and the omnidirectional zenith spread medians within 0.5 degrees.

cs.IT · eess.SP

新论文 · v1arXiv:2611.13325

F3-AGI v4.0: Bioenergetically-Gated Active Inference, Metaplastic Preconditioning, and Residual Program Synthesis for Sample-Efficient Abstract Reasoning

Henrique Oliveira

原文摘要

Few-shot abstract reasoning on ARC-AGI requires inducing algorithmic transformations from 2 to 5 demonstration pairs without task-specific pretraining. Because few-shot demonstrations under-constrain the hypothesis space, program synthesis suffers from the Rashomon effect (predictive multiplicity): heuristic search finds spurious programs with low training error that fail on test inputs, while unconstrained library growth degrades latency. We introduce F3-AGI v4.0, a CPU-native neuro-symbolic and active inference architecture comprising three mechanisms: (1) F3-Metabolic-Optim, combining mistake-gated plasticity, Fisher-EMA preconditioning, and virtual ATP gating; (2) Adaptive Complexity-Guided Program Synthesis (AACR) with a Cycle-3 ResidualPatchSynthesizer and smallest-pair early rejection; and (3) a 512D L2-normalized random projection driving Expected Free Energy (EFE) exploration with dead-signature pruning. Across three empirical studies: (i) on a synthetic 5-task class-incremental stream without replay, F3-Metabolic-Optim achieves 91.67% final accuracy with 9.17% forgetting, skipping 93.47% of updates, cutting L1 plasticity cost by 65.7%, and running 2.19x faster than EWC; (ii) on the 400-task ARC-AGI-1 public evaluation set (offline CPU, zero LLM calls), F3-AGI v4.0 solves 57/400 tasks (14.25% pass@2; 56/400 pass@1) with a mean latency of 1.62 s/task, decomposed into 19/50 (38.00%, 1.19 s/task, a 42.5x paired speedup over Horizon 2) on the 50-task calibration slice and 38/350 (10.86%) on the 350 strictly uninspected hold-out tasks (with 7 autonomous Cycle-3 patch solutions); and (iii) in a local 5-game (15-level) ARC-AGI-3-inspired interactive suite, our agent completes 15/15 levels with 89.44% level-weighted RHAE (90.72% unweighted).

cs.AI

新论文 · v1arXiv:2611.13324

Robust Flow Matching under Target Corruption and Label Noise

Mert Can Kurucu, Erik Englesson, Hossein Azizpour

原文摘要

Flow Matching (FM) is a strong framework for generative modeling due to its stable training and efficient sampling. However, FM assumes clean target data and labels, an assumption often violated in practice. We formulate FM training as a time-dependent regression problem over conditional vector fields and analyze how the two corruption types affect the objective: i) target corruption adds a time-dependent residual term that grows with time, ii) label noise causes updates to the wrong class-conditional vector field. Based on this analysis, we propose to improve FM robustness by mapping corruption-specific residual scores to sample weights. For target corruption, we propose the Temporal Residual Score (TRS), which emphasizes residual magnitudes at intermediate-to-late FM times, where clean and corrupted samples are more separable. For label noise, we propose the Comparative Conditional Score (CCS), which compares the residual of the observed class-conditional vector field against alternative class-conditional vector fields for the same trajectory and velocity target. Experiments across controlled corruption settings and real-world noisy labels show that the proposed methods improve robustness over standard FM and robust-training baselines, supporting corruption-specific residual structure as a practical basis for robust FM.

cs.LG · cs.CV

新论文 · v1arXiv:2611.13322

MicroLens: Read, Trace, and Rewire the Residual Stream with Two Lenses

Nika Zahedi, Fangyi Zhu, Anna Wu

原文摘要

Lenses that decode hidden states into words are a popular way to look inside language models, but a heatmap of decoded words only shows what a vector reads as and cannot distinguish whether, or how much, the model uses the information. We present an interactive viewer that puts reading, tracing and editing on the same layers-by-tokens grid of the residual stream. In the viewer, every cell can be decoded with two lenses, the logit lens and the Jacobian lens (J-lens), traced back to the tokens it drew from, and edited, with the rest of the model rerun on the spot. We demonstrate three usage scenarios on Gemma-3-4B-it, backed by sweeps over a few hundred prompts, to show what this tool can discover. First, the two lenses give different directions to write with, each suiting a different edit: the logit lens's word direction sets what a token outputs, while the J-lens's direction changes what later tokens read. Second, in two-hop trivia questions (the capital of the state or country containing a given city), the state or country is readable at the city token from as early as layer 7, and swapping it there can redirect the answer 92-98% of the time; however, at the answer position, the state or country information is not used. Third, when a chat model answers questions with a step-by-step reasoning prompt, the correct answer is often already the top word in the residual stream before any reasoning is written: for 89-92% of retrieval questions and 39-63% of multi-hop and serial ones, far above their respective distractors (at most 5%). However, ordering puzzles are an exception, as the model works them out only once it writes its final reasoning steps. Furthermore, for answers that are visible in the residual stream, the J-lens reads them a layer or two earlier than the logit lens across the different types of question.

cs.LG · cs.CL · cs.HC

版本更新 · v2arXiv:2610.36202

Base Models Can Detect Hidden Intentions that Prompted Classifiers Miss

Oz Amram

原文摘要

The Persona Selection Model (PSM) posits that post-training selects a persona the model learned during pre-training. Work on subliminal learning has shown that models can impart covert signals (like "love of owls") into semantically unrelated outputs like strings of numbers, and that students trained on these outputs inherit those traits. In this work I show that by evaluating the likelihood of such outputs under the base pre-trained model with an appropriate header, a method I call persona-header likelihood evaluation (PHLE), one can decode these subliminal signals and classify between them. For example, PHLE distinguishes number sequences generated by a post-trained model prompted with "You love owls" from those prompted with "You love trains", and distinguishes answers from a model with a secret desire to harm the user, filtered to remove any noticeable misalignment, from those of a model with no system prompt. In both cases prompted classifiers, including the generating model itself, perform far worse. The signal partially persists across model families, with the Qwen base model reading signals generated by Olmo and vice versa. This is evidence for a non-trivial prediction of the PSM, and the method may be practically useful for auditing the hidden objectives of models.

cs.LG · cs.AI · cs.CL

版本更新 · v2arXiv:2606.23700

Self-Modeling Interventions can Modulate Emergent Misalignment

Arush Tagade, Shaoheng Zhou, Jiaxin Wen, Shi Feng

原文摘要

Emergent misalignment (EM) has been linked to the activation of misaligned persona vectors and evil character traits, suggesting that EM operates through disruption of the model's aligned character rather than direct learning of harmful content. Motivated by this connection, we study self-modeling interventions: specifically self-recognition and self-reports as character-targeted interventions that are distinct from existing in-training defenses. We conduct two-stage finetuning experiments across three models (GPT-4.1, Qwen2.5-32B-Instruct, Seed-OSS-36B-Instruct) and multiple EM datasets to compare self-recognition finetuning against benign finetuning baselines (correct domain-specific data, general knowledge, and word counting), finding it an effective defense in both reversal and prevention settings. For prevention, only self-recognition finetuning consistently reduces misalignment without exacerbating any individual metric, suggesting that character fortification specifically drives prevention. We also conduct in-training experiments across these models to compare the effectiveness of self-reports with benign interleaving and inoculation prompting. We provide further evidence for EM's relation to the LLM's default character by showing that EM finetuning leads to fragmentation of LLM's identity self-reports, reduces self-recognition performance to about chance, artificially corrupting self-recognition exacerbates misalignment caused by EM finetuning, and finetuning on self-reports from EM finetuned models can transfer misalignment. Together, these findings reframe EM not as the adoption of a coherent misaligned persona but as the destabilization of aligned character.

cs.CL · cs.AI · cs.LG

版本更新 · v3arXiv:2509.22979

OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning

Xinzhi Zhang, Zeyi Chen, Humishka Zope, Hugo Barbalho, Konstantina Mellou, Marco Molinaro, Janardhan Kulkarni, Ishai Menache 等 9 位作者

原文摘要

Mathematical optimization drives decisions in supply chains, logistics, energy, and scheduling, but translating natural-language problems into solver-executable formulations remains a bottleneck. While frontier models show promise for this task, many deployments require small language models (SLMs) that run locally under privacy, latency, and cost constraints. Existing SLMs are limited by noisy data, ambiguous benchmarks, and one-shot inference that ignores the iterative, feedback-driven nature of optimization modeling. To address these challenges, we introduce OptiMind, a system that combines data cleaning and class-specific hints with training using solver feedback. OptiMind distills recurring formulation errors into class-specific hints that guide the repair of ambiguous problems and the regeneration of solution trajectories. This process provides reliable training data, which is then used for multi-turn RL to teach models to revise their formulations in response to solver feedback. At inference time, the same hint library guides further refinement as models revise their solutions over successive turns. To support reliable evaluation, we clean three challenging benchmarks from the literature. On these cleaned benchmarks, our 20B OptiMind-RL model outperforms strong open-source baselines and reaches frontier-model performance under the same protocol. The full hint library, cleaned test data, cleaning logs, and evaluation code are publicly available on Github (https://github.com/microsoft/OptiGuide/tree/main/optimind), and our trained OptiMind-RL model is available on Hugging Face (https://huggingface.co/microsoft/OptiMind-RL).

cs.LG

版本更新 · v2arXiv:2601.19704

Robust Joint Power Allocation and Antenna Placement for Pinching-Antenna Systems under Gaussian Location Uncertainty

Hao Feng, Ming Zeng, Xingwang Li, Wenwu Xie, Nian Xia

原文摘要

Pinching antenna systems (PASS) have attracted much attention recently owing to their capability to maintain reliable line-of-sight communication in high-frequency bands. By guiding signals through a waveguide and emitting them via a movable pinching antenna, PASS enable dynamic control of signal propagation and spatial adaptability. However, their performance heavily depends on effective resource allocation, including power allocation and antenna positioning, which becomes challenging under user localization uncertainty. Existing studies largely assume perfect user locations, while our prior work considered uniformly distributed localization errors. In this paper, we develop a robust resource allocation framework for multi-user downlink PASS under Gaussian-distributed localization uncertainty. An energy-efficiency (EE) maximization problem is formulated subject to probabilistic outage constraints, and the minimum transmit power is analytically characterized for any given antenna position. For the unbounded Gaussian model, we prove that the resulting one-dimensional antenna-placement objective is convex and derive a globally optimal derivative-bisection algorithm. We further consider a circularly truncated Gaussian model for bounded localization-error regions and develop a deterministic branch-and-bound method that returns an $ε_{\rm B}$-globally optimal antenna position. Finally, we discuss how position-dependent waveguide attenuation modifies the placement objective and may destroy its convexity. Simulation results verify that the proposed branch-and-bound solution closely matches the bounded grid-search benchmark, demonstrate substantial EE gains from optimized pinching-antenna placement over the bounded fixed-antenna architecture, and reveal an increasing distinction between the bounded and unbounded Gaussian models as the location uncertainty grows.

cs.IT

新论文 · v1arXiv:2611.13316

A probabilistic model of visual segmentation explains early visual cortical dynamics

Tridib K. Biswas, Ruben Coen-Cagli

原文摘要

Neural dynamics are a central feature of biological neural systems. In the visual cortex, the functional role of neural dynamics is poorly understood, particularly for static stimuli. The statistics of still natural images have long been used by models that successfully predict firing in early visual cortex; those models assume that neurons represent inferences about latent image features, but often ignore the dynamics of said inference. Here, we test if inferential dynamics in images explain visual-cortical dynamics. To do so, we present a biologically plausible model of cortical computation which assumes that the inference of features is coupled with inference about how those features are organized into meaningful parts, a function also known as segmentation. Given an input image, our model iterates between inferring the features and the segments, through recurrence and feedback, thus inducing dynamics in the neural representation of features. For these neural dynamics, we derive theoretical and exact predictions. Our model predicts both gain and variability in evoked responses to natural images, and we show that it captures classical single-neuron experimental findings such as gain dynamics and variability decay during stimulus presentation. The model also predicts that those dynamics are organized around inferred segment structure and more heterogeneous than previously thought, reflecting the complexity of inference for natural scenes. Finally, our analytical formulation provides a clear interpretation of our results. Insights from our normative model could generalize to segmentation problems in other experimental modalities, and help address the cost of inference in artificial networks with iterative computation.

q-bio.NC · cs.CV

版本更新 · v2arXiv:2611.02340

On Stochastic Continuous-Time Linear System Identification for Adaptive Stabilization

Reza Sadeghi Hafshejani, Mohamad Kazem Shirani Faradonbeh

原文摘要

System identification studies the canonical problem of reliably learning system-dynamics from state and input trajectories. One of its important applications consists of estimating a feedback gain matrix that can stabilize an unknown system. This paper focuses on the analysis of such adaptive stabilization schemes for multivariate linear time-invariant state-space models. The system instability practically renders trajectories short, i.e., the observed data is notably limited. So, it is crucial to tightly consider effects of \emph{all} involved quantities including length and number of trajectories, dimension, controllability Gramian, and signal-to-noise ratio. We put forward a simple, practical, and reliable relationship between the chance that adaptive stabilization (based on system identification) fails to stabilize the system, in terms of all the above-mentioned quantities. Our findings show that despite exponential effects of all other quantities on failure probability, such effects do not hold for signal-to-noise ratio. More specifically, this study shows that the strength of the excitation signal helps stabilization only \emph{logarithmically}; a very important phenomenon that we explain under the term \emph{signal saturation}.

stat.ML · cs.LG

新论文 · v1arXiv:2611.13312

Towards Scalable Network-Based Interventions for HIV Treatment and Prevention via R2C-Agent

Akseli Kangaslahti, Milind Tambe, Alastair van Heerden, Cheryl Johnson

原文摘要

Human Immunodeficiency Virus (HIV) remains a pressing public health challenge worldwide. Targeting limited HIV prevention and treatment resources effectively with network-based algorithms is a long-standing problem with a rich history at AAMAS and other computational venues. However, optimizing targeted biomedical interventions for minimizing spread of HIV often requires observability of the contact network of HIV transmission risk behavior among individuals, which is prohibitively expensive to collect at scale. Peer referral networks, i.e., networks collected through a recursive peer referral process, are an alternative network class often used to study HIV in hidden populations that can be collected digitally at scale, but they deviate from the underlying contact network: referrals can follow non-risk social ties and participants accept only one referral, hiding contacts among already-recruited individuals. In this work, we first formalize the novel problem of planning network-based interventions to minimize HIV spread in the hidden contact network while observing only the peer referral network. Second, we implement R2C-Agent, a decision making agent for interventions that is designed around our new conditional graph diffusion model called Referral-to-Contact Diffusion (R2C-Diff). R2C-Diff positions the peer referral process as incremental corruption of the underlying contact network and learns to reverse it. R2C-Agent plans its interventions over contact networks sampled from R2C-Diff, so its decisions account for uncertainty about the hidden contact network. Finally, we conduct simulated experiments using real-world HIV network data that demonstrate that R2C-Agent empirically plans more effective interventions than baselines from interdisciplinary literature and highlight key tradeoffs and assumptions driving performance.

cs.AI

版本更新 · v4arXiv:2210.06116

Self-stabilization and Byzantine Tolerance for Maximal Independent Set

Johanne Cohen, Laurence Pilard, François Pirot, Jonas Sénizergues

原文摘要

We analyze the impact of transient and Byzantine faults on the construction of a maximal independent set in a general network. We adapt the self-stabilizing algorithm presented by Turau for computing such a vertex set. Our algorithm is self-stabilizing and also works under the more difficult context of arbitrary Byzantine faults. Byzantine nodes can prevent nodes close to them from taking part in the independent set for an arbitrarily long time. We give boundaries to their impact by focusing on the set of all nodes excluding nodes at distance 1 or less from Byzantine nodes, and excluding some of the nodes at distance 2. As far as we know, we present the first algorithm tolerating both transient and Byzantine faults under the fair distributed daemon. We prove that this algorithm converges in $ \mathcal O(Δn)$ rounds w.h.p., where $n$ is the number of nodes and $Δ$ is the maximum degree of the network. Additionally, we present a modified version of this algorithm for anonymous systems under the adversarial distributed daemon that converges in $\mathcal O(n^{2})$ moves both in expected value and with high probability.

cs.DC

新论文 · v1arXiv:2611.13311

One Trajectory, Two Requirements: Accuracy and Local Stability in Euler Sampling for Flow Matching Policies

Mahindra Rautela

原文摘要

Flow matching robot policies commonly use a fixed Euler step count selected from offline accuracy sweeps. At inference time, however, each policy input (visual observation, robot state, and language instruction) together with a source-noise draw defines a different ODE trajectory and sequence of local Jacobians. We ask whether a step count that accurately follows the nominal noise-to-action trajectory can still be too coarse for strongly contracting directions around it. An exact two-coordinate system and a controlled augmentation of six trained flow models show that trajectory accuracy and local Euler stability can impose different step requirements even when the original learned transport is unchanged. We then study a frozen $π_{0.5}$-LIBERO checkpoint without modifying its weights or action dynamics. Across 30 policy inputs from 10 LIBERO-10 tasks, the Jacobian exhibits strong contracting directions near the action endpoint, yet no sampled mode violates the Euler non-expansion condition. On five of those inputs, accuracy sweeps require 4--9 Euler steps at 5% terminal error and 87--112 at 1%. These five paired cases are therefore consistent with accuracy-limited rather than stability-limited sampling under this local criterion, while the controlled experiments show why endpoint accuracy alone cannot rule out a separate stability requirement.

cs.LG · cs.RO

新论文 · v1arXiv:2611.13310

ABRR: Transforming Temporal Sentence Grounding with Wasserstein-Adaptive Refinement and Precision Ranking

Xiang Fang, Wanlong Fang, Junhao Dong, Daizong Liu

原文摘要

Temporal Sentence Grounding (TSG) aims to localize temporal segments in untrimmed videos that correspond to natural language queries, a critical task for video understanding with applications in video retrieval, summarization, and human-computer interaction. Despite significant progress driven by transformer-based models, existing TSG methods suffer from two key limitations: quantization errors due to temporal downsampling, which misalign segment boundaries, and suboptimal ranking of predictions based on semantic matching rather than localization precision. To address these challenges, we propose the Adaptive Boundary Refinement and Ranking (ABRR) framework, a novel, model-agnostic post-processing approach that enhances the performance of any TSG model without retraining. ABRR integrates three innovative components: (1) Temporal Distribution Smoothing, which mitigates noise in predicted score distributions using Gaussian kernel convolution; (2) Boundary Refinement via Optimal Transport, which leverages the 2-Wasserstein distance and Sinkhorn iterations to align coarse segment boundaries with true temporal moments, grounded in Monge-Kantorovich optimal transport theory; and (3) Quality-Driven Re-Ranking, which reorders predictions using a composite score balancing localization precision and semantic relevance. By correcting quantization errors and prioritizing accurately localized segments, ABRR achieves substantial improvements over state-of-the-art TSG models. Extensive experiments on benchmark datasets, including Charades-STA, ActivityNet Captions, and QVHighlights, demonstrate consistent gains at stringent IoU thresholds (e.g., IoU=0.7), alongside enhanced ranking performance. The framework's computational efficiency and compatibility with existing models make it a versatile and impactful solution for real-world TSG applications.

cs.CV · cs.MM

新论文 · v1arXiv:2611.13309

PegasusAI Studio: Legible Cyberinfrastructure and Accountable AI Agents for Scientific Workflows

Komal Thareja, Mats Rynge, Berent Aldikacti, Angelina Ju, Ian Lumsden, Anirban Mandal, Rajiv Mayani, Kin Wai Ng 等 15 位作者

原文摘要

AI coding agents can now construct scientific workflows, but operating them on shared cyberinfrastructure (CI) raises problems that code generation does not solve. Agents need current knowledge of the workflow system and its execution sites and access to the runtime state of distributed executions, while facilities need to attribute every agent action to a user and bound it by that user's privileges. We present PegasusAI Studio, an AI-assisted science gateway built on the Pegasus and HTCondor stack. Studio makes CI legible to agents by projecting one facility-curated knowledge base into the native configuration of several coding agents, by introspecting workflow interfaces and execution sites, and by grounding diagnosis in workflow and scheduler telemetry. Agent actions operate within a trust envelope that combines federated authentication, per-user execution environments and scheduler credentials, provider-neutral model access, observability, and approval controls for state-changing actions. The same application runs as a JupyterHub-based gateway on a research cloud and as an Open OnDemand application on HPC systems. We evaluate Studio through case studies of legacy CASA weather workflow modernization, a gravitational-wave reanalysis, an EEG analysis built with an open-weight model, and an Event Horizon Telescope (EHT) M87 image reconstruction that recovered from two failed runs to a zero-failure execution. The evaluation establishes that these mechanisms operate as designed.

cs.DC · cs.AI · cs.SE

新论文 · v1arXiv:2611.13308

Domain-Adversarial Adaptation from MURA to In-House Radiographs for Improved Adult Elbow Fracture Classification

M. Bolhassani, W. Furtado, D. Duvall, MJ Negahdar, J. Joshi, S. Contractor, A. Amini

原文摘要

We studied domain shift in adult elbow fracture classification from radiographs when training on a large public dataset and deploying on a small, institution-specific dataset (UofL). We implemented a domain-adversarial neural network (DANN) to align feature distributions across source (MURA) and target (UofL) domains while optimizing fracture classification. A pretrained convolutional backbone was adapted to grayscale inputs; the task head predicts fracture presence, and a gradient-reversal-based domain head encourages domain-invariant features via adversarial learning. We compared four settings: (1) Source-only, (2) Target-only (limited labels), (3) Naive merge (pooled training), and (4) DANN (MURA to UofL). Evaluation on UofL test data uses AUC-ROC, and accuracy. DANN outperformed Source-only and Naive merge baselines by reducing domain bias without overfitting to the small target set. Ablations showed that progressive adversarial weight, dataset-size-aware domain loss, and domain-balanced sampling improved stability and target performance. Results demonstrated that domain alignment is a practical path to robust clinical generalization from public to local data.

cs.CV

新论文 · v1arXiv:2611.13307

Does Haptic Connection to a Healthy Partner Improve Motor Learning in Chronic Stroke? A Pilot Study of Robot-Based Dyadic Training

Erica L. Waters, Natalia Stroutinsky-Sobotka, Reem M. Azar, Frances S. Shofer, Pamela Z. Cacchione, Rochelle J. Mendonca, Michelle J. Johnson

原文摘要

Purpose: Robot-based haptic dyads, where two users exchange forces through robots, have been proposed for robot-assisted neurorehabilitation. This intervention could increase motor learning by promoting motor variability, providing an implicit communication channel, and facilitating social interaction. Despite the potential benefits, few studies have investigated robot-based haptic dyads for neurological populations, and none have included a comprehensive clinical assessment. Design/Methodology/Approach: We present a pilot study investigation of individuals with chronic stroke learning a complex tracking task in solo and dyad conditions. Prior to training, participants completed a battery of cognitive, motor, and sensory assessments. We assessed changes in key kinematic outcomes including tracking error, distance traveled, mean absolute power, and sample entropy. We also performed a correlation analysis of clinical scores with baseline tracking errors. Findings: Baseline tracking error was strongly correlated (r > 0.6) with lower cognitive scores and higher motor scores. Only the solo group demonstrated lower tracking error at assessment (Δ = -5.33, 95%CI [-10.25, -0.40], p = 0.027), but this result was tempered by the removal of an outlier participant. Neither group demonstrated clear retention. The dyad group showed significantly elevated performance, effort, and movement complexity during training. Research Limitations/Implications: The selected task was too difficult to reveal learning for either group, which may be related to its high cognitive demand. Sample size and stroke heterogeneity were also limitation. Originality/Value: Dyadic training increased movement complexity and effort, which are associated with better motor learning. Clinical characteristics such as lesion location, cognition, sensation, and chronicity may influence potential benefits of dyadic training.

cs.RO · cs.HC

版本更新 · v2arXiv:2608.28542

Policy-Controlled Offline-Verifiable Accountability for Cross-Organization Agent Messaging: A Preserved Evidence-Bundle Approach

Adil Alshammari, Hayretdin Bahsi

原文摘要

Cross-organization agent workflows require preserved evidence that remains independently verifiable during later audit or dispute review. Such workflows may involve multiple organizations, delegated actions, policy-relevant events, and disputed accountability claims. This is difficult when live systems are unavailable, controlled by one party, or not trusted by all participants. Existing mechanisms provide useful pieces, including authenticated logging, delegation semantics, signed checkpoints, and consistency checks. What remains missing is a verifier-centered event-level bundle for checking evidence sufficiency offline under an explicit policy. We propose a preserved evidence-bundle model and a policy-controlled offline verifier for agent-to-agent workflow events. Each bundle preserves policy-required evidence, including sender authentication, authenticated log commitment, witness-backed checkpoint evidence, append-only continuity, delegation-aware authorization evidence, and, when issued and required by policy, explicit receiver-signed receipt evidence. The verifier accepts a bundle only when all mandatory and policy-required checks succeed, giving a later dispute reviewer an offline basis for assessing evidence sufficiency. It does not infer delivery or receipt from transport behavior or log inclusion alone. In a prototype evaluation, the event-type study used 300 synthetic four-event healthcare workflow cases and 1200 valid preserved bundles. The policy-profile comparison observed its largest median latency reduction relative to the fully enabled profile when checkpoint-context validation was disabled. All 17 tested cases in the original negative-evidence diagnostic suite were rejected under the fully enabled profile. Additional functional studies examined context and signed-reference binding. These results support prototype feasibility for the evaluated workloads.

cs.CR · cs.MA