跳到正文
研踪PaperTrail

论文库

检索计算机领域论文，按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描：2026-11-16 01:34 · 全站最近入库：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 06:51 — 2026-11-16 06:51（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-16 01:34最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 02:59

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

23,348 已收录论文19,580 AI 相关6,729 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 23,348 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33（北京时间）
新论文 · v1arXiv:2611.15578

Constructing and Validating Memorisation Audits for EHR Foundation Models

Inigo Stibbe, Joshua Placidi, Padmanabhan Ramnarayan, A. Aldo Faisal

原文摘要

Autoregressive electronic health record (EHR) foundation models may disclose training information at inference, yet clinical predictability makes patient-specific memorisation difficult to distinguish from generalisation. We evaluate fixed-window token reconstruction, sensitive-attribute disclosure, and random patient-level canaries in GPT-2-style models trained on MIMIC-IV, across early, best-validation, and final checkpoints. Reconstruction improves with additional context, but training--held-out differences remain small. Trajectory-unique prompts containing limited clinical information produce no excess sensitive disclosure for training patients. In a matched model with random binary patient-level canaries, training-patient label-recovery AUROC increases from 0.512 to 0.549 while held-out recovery remains at chance. An overfit 1,000-patient positive control achieves near-perfect recovery, confirming sensitivity to strong memorisation. These results reveal weak cohort-level memorisation but no reliable patient-level disclosure under the evaluated attacks. They motivate clinically grounded inference-time audits that can detect patient-specific memorisation in existing models without retraining with canaries.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.21359

Graph-Free Root Cause Analysis

Luan Pham

原文摘要

Failures in complex systems demand rapid Root Cause Analysis (RCA) to prevent cascading damage. Graph-free RCA methods typically assume that the root cause has the highest anomaly score. This assumption fails when faults propagate, because a small deviation at the root cause can grow into a larger anomaly downstream. Our key observation is that a root cause deviates in both its internal properties (e.g., resource usage) and external properties (e.g., latency), whereas components affected by propagation deviate only in external properties. We propose CIE, a framework that ranks components by combining their internal and external anomaly scores. We formalize a class of component-based systems and state conditions under which CIE provably ranks the root cause first. The guarantee holds under arbitrary amplification for a conjunctive score, and under bounded amplification and a stronger root-cause condition for the default additive score. On 735 failures in nine datasets from three microservice systems, CIE achieves 68% Top-1 accuracy averaged over 11 fault types, a 21% relative improvement over the best of twelve baselines, while requiring 8 ms per diagnosis.

cs.LG · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.25507

Lightweight GenAI for Network Traffic Generation: Fidelity, Augmentation, and Classification

Giampaolo Bovenzi, Domenico Ciuonzo, Jonatan Krolikowski, Antonio Montieri, Alfredo Nascita, Antonio Pescapè, Dario Rossi

原文摘要

Network Traffic Classification (NTC) increasingly relies on data-driven models, yet its practical deployment is often constrained by limited labeled data, strict privacy requirements, and the cost of collecting representative traffic traces. While Network Traffic Generation (NTG) provides an effective means to mitigate data scarcity, conventional generative methods struggle to model the complex temporal dynamics of modern traffic and often incur high computational costs. In this article, we investigate lightweight Generative Artificial Intelligence (GenAI) architectures for practical NTG. Rather than generating raw packet bytes or relying on large foundation models, we synthesize compact flow-level traffic representations derived from early packet-header information, enabling transformer-based, state-space, and diffusion models with only a few million parameters. We present a modular GenAI pipeline for NTG and evaluate it along four complementary axes: (i) synthetic traffic fidelity, (ii) synthetic-only training for reduced raw-data sharing in NTC, (iii) data augmentation under low-data regimes, and (iv) computational efficiency. Experiments on two heterogeneous datasets show that lightweight transformer-based and state-space models preserve both static and temporal traffic characteristics, while providing useful synthetic data for downstream NTC. Among them, transformer-based models offer the best fidelity-efficiency trade-off, combining high-quality traffic generation with moderate computational overhead.

cs.NI · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15577

Orthogonal Code-Based Parallel Signaling for PLCA in Shared-Medium Ethernet

Mohamed Elattar, Ahmed Abdelkader, Zhe Lou, Georg Carle

原文摘要

Physical Layer Collision Avoidance (PLCA) enables collision-free channel access in shared-medium Ethernet by granting each node an exclusive transmission opportunity (TO) in a sequential, cyclic manner. This sequential, node-based access structure, however, is the root cause of PLCA's fundamental limitations, causing access latency to grow with network size and idle TOs to accumulate when traffic is sparse, a limitation inherited by existing PLCA extensions. To address this, we propose OC-PLCA, an orthogonal code-based parallel signaling mechanism for PLCA. Rather than signaling sequentially, all nodes with pending traffic transmit their unique Walsh-Hadamard code simultaneously to signal their intent to transmit. Since these codes are mutually orthogonal, each node independently identifies the complete set of active nodes, allowing the transmission cycle to include only active nodes and eliminating idle TOs entirely. We further investigate the impact of quantization on active node detection, and propose a grouping-based extension that preserves unambiguous detection for networks of an arbitrary number of nodes. Theoretical analysis shows that OC-PLCA reduces signaling overhead by 88% for an 8-node network, with the reduction growing as network size increases. Simulation results confirm significant reductions in observed access latency across a range of network loads and heterogeneous node activity.

cs.NI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15576

Can Model Answer Probabilities Represent Survey Populations? Conditional Prediction and Joint Validity in Jev Survey Simulation

Zengqing Wu, Chuan Xiao

原文摘要

Survey simulations require realistic combinations of answers, but predictive accuracy alone does not establish that a model can generate them. We evaluate the option probabilities returned by Jev, a TypeSafe decision model, using linked responses to 20 binary items from five archived survey waves. We compare population-only prediction, prediction given recorded answers, and sequential completion that uses generated answers to predict later responses. Joint comparisons hold the starting population information fixed, and two three-question cases are completed in both question orders. We evaluate predictive scores, answer frequencies, and associations against the survey records. Recorded answers can improve predictive scores while associations remain distorted. Large conditional errors also occur. For example, among men who described themselves as having traditional values, the model predicted that 16% would see men and women as similar in workplace abilities, compared with 56% in the survey. Sequential completion has mixed effects on joint validity, and reversing question order produces different joint distributions in both tested cases. Order checks and classical marginal bounds clarify what can be assessed before linked validation answers are available. The findings support validating the joint events a simulation uses and separating empirical constraints from model assumptions. The evidence concerns selected binary tasks and one model version.

stat.AP · cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15575

Does Confusing Code Confuse LLMs? A Pilot Study on C++

Tim van de Wetering, Lola Solovyeva, Fernando Castor

原文摘要

Large language models (LLMs) are increasingly deployed for software maintenance tasks that depend heavily on code comprehension. While atoms of confusion, minimal code patterns empirically shown to impair human program comprehension, are well studied, it remains unclear whether these same patterns affect LLMs, and whether their impact varies across maintenance tasks. We present a pilot study evaluating the impact of atoms of confusion on LLM performance on C++ code drawn from three production libraries, using ChatGPT and GitHub Copilot on three software development tasks: atom injection and removal, output prediction, and code explanation. Our results reveal three preliminary findings: (i) the impact of atoms on LLMs is strongly task-dependent; (ii) atoms requiring reasoning about surrounding code are the most resistant to transformation, while localized syntactic atoms are handled reliably; and (iii) LLMs remove atoms of confusion more reliably than they inject them, suggesting that removal succeeds through pattern matching while injection requires deeper comprehension.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15574

RipBench: A Unified Benchmark for Multi-Level Rip Current Detection, Classification and Segmentation

Andrei Dumitriu, Aakash Ralhan, Florin Miron, Florin Tatui, Radu Tudor Ionescu, Radu Timofte

原文摘要

Rip currents are a serious and often under-addressed threat to beach safety and the leading cause of coastal drownings worldwide. They are difficult to detect due to their amorphous structure, similarity to the background, and large variability in viewpoints and environments. Despite their dangers and growing interest in automated detection, existing research remains fragmented across datasets, metrics, models, and approaches, leading to an incomplete understanding of model performance. We introduce RipBench, a unified benchmark that enables controlled evaluation of rip current detection spanning multiple tasks, including classification, axis-aligned and oriented object detection, and instance, semantic, and panoptic segmentation, on the same data with standardized splits. This allows direct comparison of model performance on all levels of visual abstraction. Across $304$ videos ($303{,}491$ frames, $51{,}011$ of them annotated for all six tasks) collected from diverse coastlines, our results expose a clear performance gap between coarse recognition and precise spatial understanding: frame-level classification reaches $F_2 = 0.93$, while the best detector and the best instance segmenter reach $0.72$ and $0.66$, with model rankings that change from task to task. Video-level confidence intervals, a blind inter-annotator study of the spatial labels, stratified analyses by viewpoint and visual signature, and video views with temporal baselines (single-seed, short-schedule reference runs) accompany the benchmark. All tasks are supported with carefully curated annotations and evaluated using standard metrics, with a focus on the $F_2$ score to emphasize recall in this safety-critical setting. RipBench, along with multiple baselines per task, is publicly available at https://RipBench.ai to support progress in real-world, multi-task vision for beach safety.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.02753

The Import Tax: A Longitudinal Measurement of Startup Cost in the Python Ecosystem

Trinath Sai Subhash Reddy Pittala

原文摘要

Python programs pay for their imports at every process start, a cost that is invisible in steady-state benchmarks but dominant for command-line tools, test workers, and serverless cold starts. Python 3.15 adds explicit lazy imports (PEP 810) on largely anecdotal evidence. We measure the import cost of the 500 most-downloaded PyPI packages, every quarterly release since mid-2021, under six CPython versions (3.9-3.14) on two platforms (Apple M5/macOS and Intel Xeon/Linux), 66,816 cells in all, with targeted experiments that isolate individual effects. Values are for macOS (Linux in parentheses). Import cost is heavily skewed (median 12.3 ms, 99th percentile 400 ms). Among packages that import in more than 2 ms, namespace distributions excluded, the median package spends 68% of its import time in the standard library (68% on Linux with the interpreter on local storage, 79% on network storage). Precompiling bytecode removes almost all of the cold-start penalty on Linux and 92% of it for the median package on macOS, but only a third of the summed macOS penalty: packages with native libraries pay a security assessment of each library that the system has not seen before, again in every fresh environment. A package's own import code grows by a median 4.0% (5.0%) per year; installing each release with the dependencies of its time changes its trend by a median of only 0.15 (0.35) percentage points (CPython 3.9). CPython 3.14 runs package code faster than 3.9 but imports more and slower standard-library modules, a net 1.16x (1.07x) slowdown. Submodules that dependents import beyond the top level add nothing for the median package and at most 11.7 (49.5) ms for nine packages in ten. On CPython 3.15, global lazy mode cuts the imports that dependents perform to 0.41x (0.39x) of their cost, and 38 of 461 packages fail under it, many only on first use of a name. Harness, code, and dataset are public.

cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.28910

Backtracking Direct, Indirect and Total Effects

Jose M. Peña

原文摘要

Natural direct and indirect effects are defined through cross-world interventional counterfactuals. We propose an alternative construction based on backtracking counterfactuals. Rather than intervening on the treatment or mediator and change the structural equations, we use a backtracking conditional distribution to construct an alternative exogenous state satisfying a desired treatment-mediator constraint and then evaluate the unchanged structural equations on that state. This yields the backtracking direct and indirect effects, and also the backtracking total effect. Likewise, we adapt the population intervention effects.

stat.ME · cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.24763

MoTE: Mixture of Task Experts for Multi-Task Video Understanding

Muhammad Asad Ali, Umar Khan, Nadia Robertini, Didier Stricker

原文摘要

Procedural video-language models must solve heterogeneous tasks from the same visual evidence, including action recognition, forecasting, and procedure prediction. Dense transformer decoders share the same feed-forward networks across tasks, which can entangle task behavior and make controlled capability expansion difficult. Sparse Mixture-of-Experts (MoE) decoders provide conditional computation, but token-level learned routing is not naturally aligned with task-level procedural objectives. We propose MoTE (Mixture of Task Experts), a decoder architecture that converts large language model feed-forward networks into task-specific experts while keeping the multimodal backbone shared. Each example follows one sample-level task route, so active task-expert computation remains independent of the number of stored task experts. We instantiate this design as VideoLLM-MoTE and evaluate it on five COIN benchmarks using explicit task routes. The five-expert model activates ~2B LLM parameters per sample and achieves higher average top-1 accuracy than recent VideoLLM baselines. Under the same expert topology, it improves over dense all-expert activation and learned sparse-routing controls. These results show that task-structured routing provides an interpretable and compute-efficient decoder alternative for multi-task video-language learning.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.07665

Debiased Counterfactual Generation via Flow Matching from Observations

Hugh Dance, Johnny Xi, Peter Orbanz, Benjamin Bloem-Reddy

原文摘要

Estimating the full counterfactual distribution under an intervention is central to treatment risk assessment and counterfactual generation tasks. Existing approaches model the counterfactual distribution as a standalone generative target, without exploiting its relationship to the observational data. In this work, we show that under standard assumptions, observational distributions and marginal counterfactual distributions over outcomes are tightly linked: they have identical support and tail behavior, remain statistically close under weak confounding, and share any outcome features which are invariant to confounders. These properties motivate learning counterfactual distributions not from scratch, but via a deconfounding flow from the observational distribution. We formulate this problem via flow-matching and derive a semiparametrically efficient estimator based on a novel efficient influence function correction. We subsequently extend our estimator to target minimal-energy flows in high-dimensions, which we show can be especially simple targets between observational and counterfactual distributions. In experiments, deconfounding flows outperform existing debiased counterfactual distribution estimators, while also mitigating known failure modes of flow-based methods.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15572

Learning a calibrated decision head from logged bandit feedback

Ye Yuan

原文摘要

A decision head reads a state and a list of options and returns a probability per option in one forward pass. Once deployed, it usually observes only whether the option it chose was right: logged bandit feedback. We adapt such a head, LoRA on Qwen3-0.6B-Base and 1.7B-Base, from that feedback and report three results. First, the Brier or log score of the sampled action's own probability is not a usable REINFORCE reward: every wrong action earns at least gold's reward, with a mean baseline the lowest-probability wrong action gets the largest advantage, and at two options the signal is zero; in one run it cut accuracy on ordered-scale questions from .636 to .111. Scoring the probability as a loss by the pathwise gradient avoids the collapse, as do the REINFORCE rewards r and r minus p. Second, with full labels, none of four tested bandit arms beat cross-entropy plus one temperature on mean expected calibration error (ECE) over four unseen label schemas. Third, from logged feedback alone, Chosen-Action Proper Scoring (CAPS), the direct method with a proper score on the chosen action's probability, beats fine-tuning on confirmed answers only, which discards negatives: on Banking77 by 2.6 accuracy points, .053 lower ECE and lower selective risk (three seeds against one baseline seed), and by 21.7 points on one seed on emotion data with an often-wrong logger. At N 5000, CAPS stays 1.5 points below full-label training at 0.6B and .6 points at 1.7B against one full-label seed, and propensity weights add nothing on this log. Under feedback flipped at a known rate, one seed per rate, CAPS's confidence tracks the noisy channel on average, backward correction recovers most of the clean calibration, and early stopping on held-out logged outcomes prevented memorising noisy draws in all three runs. Code, adapters, logs and per-record results are public.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15569

TraceKV: Policy-Preserving Low-Rank KV Cache Compression for Reasoning Vision-Language Models

Ke Li, Zishan Shao, Yiran Chen

原文摘要

Reasoning vision-language models (VLMs) impose substantial KV cache demands from both large multimodal contexts and growing reasoning traces. Low-rank KV compression has emerged as a promising paradigm that stores low-dimensional latents of KV states and can be combined with quantization. However, existing low-rank methods often induce growing predictive policy drift from the dense model when compressing reasoning KV states, resulting in reasoning failures. We identify two key causes of this degradation: calibration-state mismatch between static contexts and on-policy reasoning states, and unequal error sensitivity across KV states. To address these challenges, we propose TraceKV, a training-free low-rank KV compression framework that unifies on-policy calibration, sensitivity-aware SVD, and global rank allocation under a single policy-preserving principle, substantially reducing policy-KL divergence during reasoning. Experiments across multiple VLMs and visual reasoning benchmarks demonstrate superior accuracy--memory trade-offs, achieving near-lossless reasoning accuracy with 5.64$\times$ KV cache compression when combined with quantization. Optimized low-rank attention kernels further deliver up to 1.83$\times$ end-to-end decoding speedup. Code will be available at https://github.com/AK-DREAM/TraceKV.

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15568

Can We Make an LLM Dumber, or Is It Just Playing Dumb? An Empirical Study of Believable Performance Throttling

Chengguang Gan, Yunhao Liang, Hanjun Wei, QingHao Zhang, Shiwen Ni

原文摘要

A benchmark score is commonly read as a proxy for model capability. We study the inverse problem: can a model be driven to a target score, and do its failures resemble those of a naturally weaker model? We operationalize believable performance reduction along three axes: target calibration, item-difficulty structure, and error-distribution similarity to a real weak reference. We introduce CapLadder, an IRT-calibrated suite of 1,985 items spanning mathematics, code, multiple-choice reasoning, and tool use. A simple weak-teacher LoRA dial reaches unseen target levels on reasoning with a 1.9-point held-out calibration error, whereas prompting, temperature, and weight noise cannot combine comparable range and precision. Yet on multiple choice, the dial converges to an answer-token attractor: up to 97% of its newly introduced errors land on one letter, with the attractor changing from D in Qwen to A in Llama. Logit interventions identify a dominant near-constant shift: subtracting the estimated shift on held-out items recovers 52 to 59% of lost accuracy and removes the dominant attractor, while option permutation confirms that the bias tracks token position rather than option content. With high inter-annotator agreement ($κ=0.94$), human-coded error-category distributions nonetheless match the weak reference on reasoning (JS = 0.00), showing that local plausibility and aggregate detectability differ. Structured tool calls exhibit more natural degradation in the Qwen family (JS = 0.09), while a globally calibrated dial transfers poorly across benchmarks (14.2-point error on two usable benchmarks). Precise score control, therefore, does not imply a portable or believable reduction in skill.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15566

Observations Drift, Structures Remain: Structural Pretraining with Time Alignment for Electromagnetic Signals

Wenjin Gui, Junyu Shen, Haibo Xu, Yuchuang Sun, Luqing Luo, Wupeng Xie, Qian Huang, Fengxiang Wang 等 10 位作者

原文摘要

Electromagnetic signal modeling is increasingly moving toward self-supervised pretraining on heterogeneous I/Q observations. However, an observed waveform is jointly shaped by signal generation, propagation environments, and acquisition processes, which mix reusable structural regularities with observation-specific variations. Existing methods usually pursue unified pretraining with reconstruction objectives on mixed observations. This heterogeneity creates two key mismatches for reconstruction pretraining: (1) appearance mismatch, induced by propagation-dependent waveform variations; and (2) temporal mismatch, induced by acquisition-dependent sampling coordinates. These mismatches make observation-specific appearances and sampling coordinates easier to reconstruct than stable signal structures, inducing observational shortcuts. We identify this failure mode as observation-biased pretraining. To address this, we propose Structural Pretraining with Time Alignment for heterogeneous EM signals. It mitigates temporal mismatch with RoPE-fs, which maps token positions to sampling-rate-normalized physical-time positions, and reduces reliance on appearance shortcuts by replacing waveform reconstruction with masked prediction of discrete structural units. These units are organized into atomic structural units and emergent structural units that capture variable-length compositional patterns beyond fixed patch boundaries. Across diverse EM benchmarks, our method improves both full-supervision and few-shot adaptation over existing EM pretraining baselines, showing that the learned representations better preserve structural consistency when observations drift in waveform appearance and temporal scale.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2602.12316

GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory

Pepijn Cobben, Xuanqiang Angelo Huang, Thao Amelia Pham, Isabel Dahlgren, Bernhard Schölkopf, Terry Jingchen Zhang, Zhijing Jin

原文摘要

Frontier AI systems are increasingly capable and deployed in high-stakes multi-agent environments. However, existing AI safety benchmarks largely evaluate single agents, leaving multi-agent risks such as coordination failure and conflict poorly understood. We introduce GT-HarmBench, a benchmark of 1,535 high-stakes scenarios spanning game-theoretic structures such as the Prisoner's Dilemma, Stag Hunt and Chicken. Scenarios are drawn from realistic AI risk contexts in the MIT AI Risk Repository. Across 15 frontier models, agents fail to choose socially beneficial actions in 39% of high-stakes cases, such as military escalation, election manipulation, and medical malpractice. We measure sensitivity to game-theoretic prompt framing and ordering, and analyze reasoning patterns driving failures. We further show that game-theoretic interventions improve socially beneficial outcomes by up to 31%. Our results highlight substantial reliability gaps and provide a broad standardized testbed for studying alignment in multi-agent environments. The benchmark and code are available at https://github.com/Flecart/gt-harmbench.

cs.AI · cs.CL · cs.CY · cs.GT · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.21820

A Closed Form Depth-Width Law for Neural Collapse in Deep Linear Networks

Pankhil Gawade, Kirsten Fischer, Guy Wolf, Ewa Szczurek

原文摘要

How the depth and width of neural networks shape learned representations is difficult to predict from the data and architecture. We use neural collapse (NC) as a probe of the representation geometry and express its first three properties, within-class variability collapse (NC1), simplex class means (NC2) and classifier alignment (NC3), through the learned feature kernel, extending a known identity for NC1 to NC2 and NC3. For deep linear networks with an exchangeable input kernel, the kernel equations yield a geometric law, exact within this theory, for the layerwise decrease of NC1. At large width $N$ the accumulated decrease becomes a function of the depth-to-width ratio $L/N$, with its rate determined self-consistently by the data and architecture, yielding a scaling law for representation geometry.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15565

Generalized Inverse Kinematics via Conditional Flow

Kaitlyn Zhang, Tomás Lozano-Pérez, Leslie Pack Kaelbling

原文摘要

Inverse kinematics (IK) is a foundational primitive in robotics, mapping the task-space objectives expressed by higher-level planners to robot configurations that realize them. Traditional IK methods generally treat each query as an isolated pose-to-configuration problem, but planners often need a distribution over valid realizations that accounts for future reachability and preferences such as collision avoidance and stability. We introduce GenGenIK, a generative modeling approach that supports mobile bases, multiple end-effectors and targets, scene awareness, and preferences over robot behavior within a common interface. Experiments show that GenGenIK outperforms existing methods in both solve rate and runtime across tasks such as bimanual lift and flip-up, while allowing flexible control over the sampled distribution and remaining effective under partial scene observations. Website: https://icra-2027-gengenik.github.io/.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15561

Immersive Sight-Restriction-Based Collision Prevention Using Generic Particle Systems in Virtual Reality

Annalisa Degenhard, Annika Stampf, Michael Rietzler, Enrico Rukzio

原文摘要

Collision prevention systems (CPS) help VR users navigate their physical surroundings safely. Most approaches overlay conceptually distinct grids or add solid virtual counterparts of physical obstacles; both can reveal the physical space, as they either stand out visually or behave inconsistently during locomotion. We explore sight restriction as an alternative: a standard particle system visualizes the play area boundary as a fog-like cloud whose intensity scales with proximity and viewing direction. A pre-study (N=10) determined the distance at which the visualization must appear. In a main study (N=11), we compared this particle-based CPS with a grid-based solution, focusing on locomotion behavior: across 253 approach episodes, users interrupted their approach after a comparable distance once either visualization appeared. Although the particle boundary was visible three times as often, participants reported higher presence. We release our implementation as open source to support further work on immersive collision prevention.

cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.29467

Co-Evolutionary Prompt Optimization with Cross-Category Transfer for Zero-Shot Anomaly Detection

Sisi Zhu, Changwei Yu, Renshuai Tao, Zhenliang Ni

原文摘要

Zero-shot anomaly detection (ZSAD) has gained significant attention for its practical value in industrial inspection. Recently, CLIP-based approaches have been widely adopted in ZSAD due to their strong vision-language generalization capabilities. However, existing methods commonly employ continuous prompt embeddings for prompt optimization and encode semantics in latent vectors, which lack interpretability and scalability. To this end, we propose CoEvoAD, a co-evolutionary framework for discrete prompt selection. CoEvoAD performs prompt search in the discrete natural-language space using an evolutionary algorithm. Candidate prompts are iteratively generated, evaluated, and selected throughout population evolution, thus preserving the interpretability and composability of natural language. Furthermore, we introduce a Cross-Category Transfer Objective (CCTO), which treats held-out source categories as proxies for unseen categories and scores prompt rules based on their estimated cross-category transferability, effectively improving cross-category generalization. Extensive experiments are conducted to validate the effectiveness of CoEvoAD, and the results show that it achieves state-of-the-art performance across multiple anomaly detection datasets. The code is available at https://github.com/rstao-bjtu/CoEvoAD.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2507.04575

Lilith: Developmental Modular LLMs with Chemical Signaling

Mohid Farooqi, Alejandro Comas-Leon

原文摘要

Current paradigms in Artificial Intelligence rely on layers of feedforward networks which model brain activity at the neuronal level. We conjecture that expanding to the level of multiple brain regions with chemical signaling may be a productive step toward understanding the emergence of consciousness. We propose LILITH, a novel architecture that combines developmental training of modular language models with brain-inspired token-based communication protocols, mirroring chemical signaling in the brain. Our approach models distinct brain regions as specialized LLM modules including thinking, memory, sensory, and regulatory components that communicate through emergent token-based signaling protocols analogous to neurotransmitter networks. Unlike traditional pre-trained systems, LILITH would employ developmental training where untrained LLM architectures learn through simulated life experiences, developing communication pathways and cognitive abilities through environmental interaction and evolutionary optimization. This framework would enable direct empirical investigation of consciousness emergence using Integrated Information Theory metrics while providing unprecedented insight into inter-module signaling patterns during development. By optimizing for consciousness emergence rather than task performance, LILITH could provide insight into different emergent phenomena at multiple levels of neural correlates, contrasting neuronal-level processing with multi-region coordination dynamics. The goal of this paper is to put the idea forward while recognizing the substantial challenges in implementing such a system.

q-bio.NC · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.03767

Quantifying out-of-distribution data severity with Wasserstein distances: benchmarking large language models for alloy property prediction

YuJie Liu, Dezhen Xue, Jun Sun, Xiangdong Ding, Zhibin Gao, Turab Lookman

原文摘要

General-purpose Large Language Models (LLMs) increasingly rival domain-specific pipelines on scientific prediction, but their performance under distribution shift is untested. Across six alloy and crystal-structure datasets, we benchmark LLMs against traditional, BERT-based, TabPFN, and text-regression baselines under random cross-validation and six out-of-distribution (OOD) protocols shifting input and target distributions, with severity quantified via a standardized Wasserstein distance. We isolate the LLM's advantage over k-nearest-neighbor (k-NN) retrieval: it beats k-NN on all eight tasks at a fixed 5% reference budget, on seven of eight when independently optimized, and in 72.5% of 120 OOD task--protocol configurations against an optimized baseline. No model family is uniformly best; the LLM is often strongest under severe shift, and error increases with target-space but not representation-space severity. Self-reported LLM confidence tracks both shift and error, more consistently than a density-only control from the same retrieved samples, and a matched-cohort check finds no substantial evidence of memorization.

cs.LG · cond-mat.mtrl-sci

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.30104

BatchBench: Benchmarking AI Robustness to Batch Effects and Domain Shift in Biomedical Images - A JUMP Cell Painting Leaderboard

Sonja Topf, Ana Sanchez-Fernandez, Günter Klambauer

原文摘要

Despite recent advances, current AI systems remain highly susceptible to domain shifts, particularly in biomedical imaging, where images are usually acquired under substantially different experimental conditions. Although recent domain adaptation methods have made substantial progress, significant performance gaps under domain shift persist. To measure progress in this regard, we introduce BatchBench, a leaderboard that evaluates and compares the robustness of AI systems on biomedical images from unseen experimental batches and data sources. BatchBench is built on JUMP-CP, one of the largest publicly available biomedical imaging datasets. Generated using the Cell Painting assay, JUMP-CP exhibits pronounced batch effects and domain shifts, making it a challenging testbed for evaluating robustness to distributional changes. The leaderboard is open for submissions on https://huggingface.co/spaces/ai-lab-jku/jumpcp-challenge .

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15555

What Conformal Selection Can Certify in CRISPR Off-Target Design:Benchmark Leakage, Free Baselines, and a Finite-Sample Cohort Requirement

Mohammad Malekpouri, Somayeh Lotfi

原文摘要

Conformal selection promises distribution-free, finite-sample control of the error rate of a decision, and has been proposed as a safety layer for machine-learning CRISPR guide design. We ask whether such a certificate is attainable from the validated off-target data that exist. The constraint is arithmetic: a conformal p-value cannot fall below one divided by the calibration cohort size plus one, so a Benjamini-Hochberg selection certifies a single candidate only when that cohort is at least the candidate pool size divided by the tolerated error rate. Public cohorts supply ten validated guides, whereas a pool of two thousand at a ten percent error rate needs twenty thousand; the accepted set is consequently empty in over ninety-six percent of splits. Two benchmarking findings explain why this went unnoticed. The standard CIRCLE-seq file lists ten guides under eighty on-target strings, so grouping cross-validation on the sequence column trains and tests on one guide; corrected, pair-level discrimination and per-guide fidelity collapse. With that leakage removed, a training-free position-weight score and a bare count of near-match genomic sites are not beaten by a trained oracle. We give the corrected protocol, the baselines a new model must beat, and the cohort size a certified pipeline needs.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.06182

Fano's Inequality and Channel Capacity in the Individual-Sequence Regime

Neri Merhav

原文摘要

We derive an individual-sequence analogue of Fano's inequality, replacing entropy by Lempel--Ziv (LZ) complexity and probability of error by empirical error frequency. In the setting considered, an arbitrary encoder maps a message to a channel input sequence $\{x_t\}$, the channel maps the input to an output $\{y_t\}$ in a completely arbitrary manner, and a block finite-state decoder produces an estimate of the channel input from the output. The individual-sequence Fano inequality lower-bounds the empirical symbol-error frequency in terms of the LZ complexity of the channel input conditioned on the channel output. This leads to a channel coding converse: reliable communication at a given rate is possible only if that rate does not exceed the individual-sequence LZ channel capacity, defined as the LZ mutual information maximized over channel inputs and minimized (worst-case) over a noise set. We also prove a matching achievability theorem for the class of \emph{symbol-wise invertible} channels, in which the channel output at each time $t$ is $y_t = f(x_t, v_t)$, $v_t$ being a `noise' variable, and $f(\cdot,v)$ is a bijection for every fixed $v$. This class includes group-additive channels $y_t = x_t \oplus v_t$ studied by Feder and coworkers. For such a channel, any rate below the LZ capacity is achievable via a randomized code (with shared randomness between encoder and decoder) with vanishing \emph{expected} per-message error frequency, simultaneously for every $v^n$ in a given noise set $\mathcal{N}$, provided $\mathcal{N}$ is closed under block permutations; this condition is satisfied by any noise set that depends on $v^n$ only via its type class with respect to such blocks. The achievability uses a universal decoder that requires no knowledge of the channel and no feedback.

cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15548

DafnyCert: Certifying Specification Strength in Dafny

Álvaro Silva, Isabel Amaral, Ruben Martins, Alexandra Mendes

原文摘要

Formally verifying a method with Dafny guarantees correctness relative to its specification. However, a specification may be too permissive, allowing multiple outputs for the same input, even when the implementation produces only one. In this paper, we propose checkable certificates that provide independently verifiable evidence of whether a specification is weak or strong. A certificate of weakness contains an alternative implementation that verifies against the original specification, together with a witness input on which the original and alternative implementations produce different results. A certificate of strength is produced by constructing a harness around the original method such that successfully verifying the harness guarantees that the specification allows at most one possible output for any given input. We present DafnyCert, a tool that automatically produces these certificates. Strength is established by constructing and verifying the harness. Weakness is demonstrated by using the MutDafny mutation tool to find mutants that verify against the original specification, and by using the Hypothesis property-based testing framework to generate inputs that produce different outputs for the original program and the mutant. The resulting mutant and witness form a recheckable certificate of weakness. On a dataset of 3,910 verified Dafny methods from Dafny-Synthesis and VeriEquivBench, DafnyCert automatically certifies 3,570 methods (91.3%). We also provide certificates for the remaining 340 methods. To our knowledge, this is the first dataset in which every specification is backed by a checkable certificate of strength or weakness. These labels disagree with the benchmarks' original labels for 16.3% of the methods. These findings highlight the importance of supporting specification strength labels with independently checkable evidence.

cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2601.21688

XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision

Alexandre Myara, Nicolas Bourriez, Thomas Boyer, Thomas Lemercier, Ihab Bendidi, Auguste Genovesio

原文摘要

Disentangled representation learning aims to map independent factors of variation to independent representation components. On one hand, purely unsupervised approaches have proven successful on fully disentangled synthetic data, but fail to recover semantic factors from real data without strong inductive biases. On the other hand, supervised approaches are unstable and hard to scale to large attribute sets because they rely on adversarial objectives or auxiliary classifiers. We introduce \textsc{XFactors}, a weakly-supervised VAE framework that disentangles and provides explicit control over a chosen set of factors. Building on the Disentangled Information Bottleneck perspective, we decompose the representation into a residual subspace $\mathcal{S}$ and factor-specific subspaces $\mathcal{T}_1,\ldots,\mathcal{T}_K$ and a residual subspace $\mathcal{S}$. Each target factor is encoded in its assigned $\mathcal{T}_i$ through contrastive supervision: an InfoNCE loss pulls together latents sharing the same factor value and pushes apart mismatched pairs. In parallel, KL regularization imposes a Gaussian structure on both $\mathcal{S}$ and the aggregated factor subspaces, organizing the geometry without additional supervision for non-targeted factors and avoiding adversarial training and classifiers. Across multiple datasets, with constant hyperparameters, \textsc{XFactors} achieves state-of-the-art disentanglement scores and yields consistent qualitative factor alignment in the corresponding subspaces, enabling controlled factor swapping via latent replacement. We further demonstrate that our method scales correctly with increasing latent capacity and evaluate it on the real-world dataset CelebA. Our code is available at \href{https://github.com/ICML26-anon/XFactors}{github.com/ICML26-anon/XFactors}.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.12476

Routers Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-Experts

Sagi Ahrac, Noya Hochwald, Mor Geva

原文摘要

Sparse Mixture-of-Experts (SMoE) models enable scaling language models efficiently, but training them remains challenging, as routing can collapse onto few experts and auxiliary load-balancing losses can reduce specialization. Motivated by these hurdles, we study how routing decisions in SMoEs are formed mechanistically. First, we reveal a geometric coupling between routers and their corresponding experts. For a given token, the router weights for the selected expert and the expert weights processing it receive gradients along the same input direction, differing only in scalar coefficients. Thus, matched router--expert directions accumulate the same routed token history. This theoretical coupling also appears empirically in routing dynamics. In a $1$B SMoE trained from scratch, higher router scores predict stronger expert neuron preactivations, showing that routing decisions are mirrored inside the selected expert. Next, we analyze the effects of auxiliary load balancing on the router--expert geometric coupling, showing that such losses break this structure by spreading input-directed gradients across router weights, making distinct router directions nearly three times more similar to each other. Last, we demonstrate the centrality of geometric coupling for effective routing with a parameter-free online K-Means router, in which each expert maintains a running average of the hidden states routed to it and tokens are assigned based on cosine similarity. Compared with auxiliary-loss and loss-free balancing, this router achieves the lowest load imbalance with only a modest perplexity increase, indicating that geometric coupling captures a substantial part of what the router learns. Overall, our results explain how routers form assignment geometry that supports an effective division of labor.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15543

Testing Conversation Preservation Across LLM APIs: A Rule-Based Oracle for Detecting Silent Information Loss

Xin Liu, Xu Han, Yuxin Wang, Haoran Song, Mingjian Zhao, Lei Wang

原文摘要

LLM applications increasingly rely on translators and compatibility layers to move conversations across APIs. Yet a translated request can be accepted by the target API while silently losing information about instruction roles, tool interactions, error states, or generation controls. We introduce isloss, a deterministic oracle for testing conversation-information preservation across LLM API translations. It maps source and translated requests and replies to a shared intermediate representation, ConvIR, and applies explicit rules to distinguish legitimate representation changes from information loss. Unlike schema validation or reference-based differential testing, isloss requires neither a reference translation nor additional model calls. It also distinguishes avoidable loss from degradation caused by target API limitations. We evaluate isloss using specification-based fault injection, human review, and experiments on translators, gateways, and client libraries. On held-out tests, it detects 95/125 planted faults (76.0%) with 2/100 false alarms (2.0%). Across a synthetic request suite spanning six configurations of five translator codebases, 127/685 completed translations (18.5%) pass static target checks while silently changing prompt, role, or tool information in ways the target API could have preserved. In translated replies, 203/558 streams (36.4%) cause exceptions or silent corruption in at least one tested official OpenAI SDK. Targeted experiments across six models show that translation-induced changes can alter model behaviour when tasks depend on the affected information. These results establish conversation preservation as a distinct correctness requirement for reliable LLM interoperability, agent execution, and model evaluation.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.09854

When Does Low-Bit Quantization Preserve the Decisions of Vector Search?

Wenxuan Xiao, Xu Cao

原文摘要

An orthogonal rotation improves the distance rank correlation of two-bit Cohere codes from 0.75 to 0.91, yet increases nearest-neighbour comparison flips by 51%. We analyse quantization through the comparisons made by graph search. A comparison changes only when its quantization error exceeds its exact margin, giving a flip bound that separates close calls from large errors. Shared endpoints induce correlated distance errors that partly cancel within a comparison. An exact replay identity connects candidate-level actions to the output of neighbour selection. A Gaussian model gives coordinate-code errors in closed form, and a rare-spike construction exposes heavy tails in the population-radius error. Held-out blocks give model-free certificates for acceptance rules based on exact or quantized margins. Across 24 dataset-code configurations, calibration-estimated risk correlates with held-out ranking and pruning flips at 0.97 and 0.99, compared with 0.91 and 0.99 for a margin-to-noise summary and 0.74 and 0.05 for distance rank correlation. Paired builds of 200,000-vector graphs connect rotation, query scoring, and topology to end-to-end recall and search work.

cs.DB · cs.IR · cs.LG

查看论文
arXiv ↗PDF ↗