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

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 03:21 — 2026-11-22 03:21(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 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 1,939 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
版本更新 · v2arXiv:2602.04364

任意时间有效的保形风险控制

Anytime-Valid Conformal Risk Control

Bror Hultberg, Dave Zachariah, Antônio H. Ribeiro

AI 速读 基于摘要

该论文将保形风险控制的错误控制从固定校准集上的平均有效性扩展为在累积增长的校准集上任意时刻以高概率有效。

stat.ML · cs.LG

查看原文摘要

Prediction sets provide a means of quantifying the uncertainty in predictive tasks. Using held out calibration data, conformal prediction and risk control can produce prediction sets that exhibit statistically valid error control in a computationally efficient manner. However, in the standard formulations, the error is only controlled on average over many possible calibration datasets of fixed size. In this paper, we extend the control to remain valid with high probability over a cumulatively growing calibration dataset at any time point. We derive such guarantees using quantile-based arguments and illustrate the applicability of the proposed framework to settings involving distribution shift. We further show that our guarantees are asymptotically tight, in the sense that the risks converge to the target level from below, and that the rate of our correction cannot be improved. Finally, we demonstrate the practical performance of our methods through both simulations and real-world numerical examples.

新论文 · v1arXiv:2611.26336

一个框架诊断所有:孟加拉语大语言模型幻觉的分层基准

One Framework to Diagnose Them All: A Stratified Benchmark for Bengali LLM Hallucination

Asif Shahriyar Sushmit, Shefayat E Shams Adib, Abdullah Al Jubaer Gem, Ahmed Shafin Ruhan, MD. Nazmuddoha Ansary, Biplab Kumar Sarkar, Syed Rifat Raiyan, Ajwad Abrar 等 19 位作者

AI 速读 基于摘要

作者提出并社区验证了孟加拉语幻觉检测基准Alikbachan,通过文化距离、任务类型和幻觉分类三轴分层,揭示零样本LLM评判与竞赛系统在不同分层上的性能差异。

cs.CL · cs.AI

查看原文摘要

Hallucination research in low-resource languages fragments easily: each newly named failure mode prompts its own dataset, spending scarce annotators on incomparable resources. We argue for consolidation and test it at community scale. Alikbachan is a Bengali hallucination-detection benchmark stratified along three crossed axes: a human-validated cultural-distance band, six task types, and a five-family, 32-mode hallucination taxonomy. It comprises a harvested 2,516-item test set (Phase 1) and a quota-constructed, gold-labeled 5,000-item set (Phase 2). The stratification is diagnostic. Four zero-shot LLM judges vary by over 30 macro-F1 points across strata, and the item-level predictions of 99 Phase-1 and 32 Phase-2 competition systems reproduce the profile: discourse-level omission defeats judges and most teams alike, whereas only a minority over-flag negative controls. The judges' verdict probabilities rank items well (ROC-AUC 0.74-0.95) but are overconfident (ECE 0.04-0.29). An open competition on Alikbachan drew 222 teams and 3,566 submissions, and a single-prompt 32B judge reaches the 57th percentile. Of the 25 teams in both phases, 24 regress on Phase 2 (mean $-17.6$ points) while every zero-shot judge improves, and Phase-1 rank barely predicts Phase-2 rank (Spearman $ρ=0.35$), so a Phase-1 leaderboard alone would have crowned a different winner.

版本更新 · v2arXiv:2610.36691

自适应相干性的差分隐私预处理幂迭代主成分分析方法

Differentially Private Preconditioned Power Iteration Method for Principal Component Analysis that Adapts to the Coherence

Duy V. Le, Ta Duy Nguyen, Alina Ene, Huy L. Nguyen

AI 速读 基于摘要

提出一种基于预处理幂迭代的差分隐私PCA算法,其效用保证随输入矩阵的相干性提高而改善。

cs.DS

查看原文摘要

In Principal Component Analysis (PCA), we are given as input a matrix $A\in\mathbb{R}^{n\times d}$ and an integer $k\leq d$, and the goal is to find the top $k$ right-singular vectors of $A$. We consider the setting where each row of $A$ is the private data of an individual, and we design an $(ε,δ)$-differentially private algorithm whose utility guarantee improves with the coherence of the input matrix. Prior works were either restricted to the case $k=1$ or ensured significantly weaker privacy protections. Our algorithm is based on a preconditioned variant of the power iteration method that is designed to significantly reduce the noise needed to ensure privacy.

新论文 · v1arXiv:2611.26335

ClosureBench:面向闭包假设下推理的基准

ClosureBench: A Benchmark for Reasoning under Closure Assumptions

Francesco Belardinelli, Flavio Corradini, Matteo Leonesi

AI 速读 基于摘要

作者提出 ClosureBench,用同一基础场景在 OWA、CWA、LCWA 三种缺失信息处理规则下测试 LLM 是否遵循给定规则,并发现总体准确率会掩盖大量闭包判断错误。

cs.AI

查看原文摘要

AI agents built on large language models (LLMs) often answer questions from incomplete records. Missing information might be interpreted as unknown or false, depending on the completeness of the source. Current evaluations fail to distinguish these two aspects, as they are usually interwoven with other reasoning demands. We present ClosureBench, a benchmark that tests whether LLMs follow the stated rules for dealing with missing information. Every base scenario is tested under OWA, CWA, and LCWA, and only the treatment of missing information changes between variants. ClosureBench provides a verified base benchmark as well as agent extensions for action choice, source scope, and updates. A model is considered correct on a base scenario only if it provides correct answers in all of its closure variants. Across 960 instances, overall accuracy can mask substantial closure mistakes. Models achieve overall accuracy from 71.18% to 99.86% across replicated runs, but their core switch accuracy, measured on the scenarios whose gold label actually changes with the contract, varies between 18.23% and 99.31%. Large discrepancies emerge under LCWA. For example, some agents choose unknown despite the prompt indicating that missing information should be treated as false. Our findings demonstrate that evaluations of AI agents should not only measure whether agents can reason over existing facts but also whether they use the appropriate assumption when information is absent.

新论文 · v1arXiv:2611.26334

视频扩散Transformer中2比特KV缓存量化的在线时间旋转

Online Temporal Rotations for 2 Bit KV-Cache Quantization in Video Diffusion Transformers

Ryan Lucas, Petros Prastakos, Rahul Mazumder

AI 速读 基于摘要

TRQ通过对时间相邻的KV缓存向量拟合轻量正交旋转,降低2比特量化误差,提升视频生成质量。

cs.CV · cs.AI

查看原文摘要

Video diffusion transformers reuse key--value (KV) caches across denoising steps, which quickly becomes a bottleneck for long video generation. We find that quantizing temporally distant cache vectors leads to a large range and high quantization error, but that nearby video tokens in the KV-cache share a persistent pattern per channel. These patterns also vary across videos, motivating rotations that are adapted to each video's unique cache. We propose Temporal Rotation Quantization (TRQ), a method that rotates frames in the cache that are adjacent in time before quantization. For each block of temporally adjacent cache vectors, TRQ fits an orthogonal transform that maps the block's per-channel means to a vector that is close to a constant across channels. To keep the quantization format lightweight, we parameterize this rotation as a tree of $2 \times 2$ planar rotations, each stored with only two bits, followed by a fixed Hadamard transform shared across all blocks. The rotations are fit without gradients or changes to model weights, and we prove that a simple greedy fit is globally optimal for our 'mean-flattening' objective. The transforms are fit online for each new video, and we release fused Triton kernels to make this process efficient at inference. At 2-bit precision and matched compression, TRQ improves VBench subject consistency over the state-of-the-art method QVG from 90.38 to 92.02 on LongCat-Video-13B and from 86.33 to 87.61 on HY-WorldPlay-8B, as well as improving other metrics.

版本更新 · v2arXiv:2604.03257

有界不良评判下的稳健LLM评估:一种约束最大似然方法

Robust LLM Evaluation with Boundedly Bad Judges: A Constrained Maximum Likelihood Approach

Minghe Shen, Ananth Balashankar, Adam Fisch, David Madras, Miguel Rodrigues

AI 速读 基于摘要

提出约束最大似然估计(CMLE)及其分层变体(SCMLE),通过数据驱动的约束建模代理标签错误率,在有限可靠标签下降低LLM评估的均方误差。

cs.CL · cs.AI

查看原文摘要

Evaluating language models at scale often involves reconciling costly, but reliable, labels (e.g., from human raters) with cheap, but noisy, proxy labels (e.g., from LLM-as-a-judge autoraters). This paper proposes constrained maximum likelihood estimation (CMLE), a likelihood-based approach to large language model (LLM) evaluation that explicitly models the error in the proxy labels via their true-positive and false-positive rates, subject to data-driven constraints. Functionally, these constraints act as an adaptive regularization that restricts the feasible judge error rates, particularly when the available number of reliable labels is limited. In contrast to asymptotically unbiased estimators (such as those based on prediction-powered inference), this formulation accepts a controlled bias under misspecified constraints in exchange for variance reduction relative to various baselines including unconstrained maximum likelihood estimation (UMLE); we characterize this bias--variance tradeoff analytically under point constraints. We identify the regimes in which CMLE outperforms UMLE and prediction-powered baselines in mean squared error. We further extend the framework to heterogeneous settings using a stratified variant involving stratum-specific constraints based on judge confidence. Empirically, on synthetic and real-world LLM evaluation tasks, CMLE achieves up to roughly 9\% lower mean squared error (MSE) than non-stratified baselines, and its stratified variant (SCMLE) achieves up to roughly 30\% lower MSE than the strongest baseline considered, with the largest gains in low-label regimes.

新论文 · v1arXiv:2611.24941

UltraTex:对齐物理知识的高保真PBR纹理生成

UltraTex: Aligning Physical Knowledge for High-Fidelity PBR Texture Generation

Jingzhi Bao, Xiaohe Ma, Hong Li, Yuanming Hu, Xiaoguang Han

AI 速读 基于摘要

UltraTex 通过级联多视图扩散框架,将物理知识与材质语义先验注入 PBR 纹理生成,以提升金属度和粗糙度预测的物理合理性。

cs.CV

查看原文摘要

Generating physically based rendering (PBR) texture maps for a 3D mesh from a single reference image is highly ambiguous, as the observed appearance entangles material identity, surface reflectance, and illumination. While current generative methods produce realistic albedo maps, they still struggle to infer accurate metallic and roughness attributes for relighting. We present UltraTex, a cascaded multi-view framework that moves beyond appearance matching by integrating physical knowledge into multi-view diffusion-based PBR generation. UltraTex first jointly predicts albedo and world-space shading normals to generate more detailed albedo maps, and then predicts metallic-roughness (MR) maps conditioned on the generated albedo, reference image, and material semantic priors. To inject material semantics, a lightweight adapter transforms hidden-layer features of a vision-language model (VLM) into intrinsic material representation tokens, providing part-level knowledge anchors for MR estimation. To model material-light interaction, photometric representation alignment guides intermediate diffusion features toward ground-truth material renderings under controlled lighting. This makes metallic and roughness variations observable through highlight intensity, specular sharpness, and local reflectance contrast, providing stronger guidance for fine-grained material prediction without explicit lighting supervision. Extensive experiments show that UltraTex generates high-quality textures and outperforms existing open-source and commercial methods in visual fidelity, material accuracy, and physical plausibility.

新论文 · v1arXiv:2611.24940

Z-sight:统一视觉-语言-动作与潜在世界建模

$Z$-sight: Unifying Vision-Language-Action and Latent World Modeling

Junjie Ye, Yiqi Zhao, Muchen Xu, Celina Shiyu Wang, Hao Dong, Ruohai Ge, Rong Xue, Benjamin J Kolligs 等 15 位作者

AI 速读 基于摘要

Z-sight 将视觉-语言-动作模型与生成式潜在世界建模统一起来,在 VLM 自身的视觉 token 空间中联合预测未来与动作,无需像素重建或外部编码器。

cs.RO · cs.CV

查看原文摘要

We introduce $Z$-sight, a unified robot foundation model that couples vision-language-action (VLA) and generative latent world modeling. Video-based world action models (WAMs) show the value of joint future-and-action generation for control, yet inherit the heavy cost of video generators. Recent latent-space policies avoid pixel generation, yet typically align intermediate features or rely on frozen target encoders, decoupling future prediction from the VLM's native feature space. $Z$-sight instead predicts the future directly in the visual token space in which its VLM perceives the present. Coupling a foresight expert and a continuous action expert with the VLM in a mixture-of-transformers, $Z$-sight jointly denoises future spatial tokens and actions at inference without pixel reconstruction or external encoders. Trained on human video and robot trajectories, $Z$-sight achieves 81.9% success on SIMPLE (+9.6 points over the strongest baseline) and 73.3% across six Unitree G1 tasks (+20.0 points) at 110 ms per chunk, while remaining competitive on tabletop benchmarks.

新论文 · v1arXiv:2611.24938

Phoenix:学习场景结构表示以构建可泛化的世界-动作模型

Phoenix: Learning Scene Structure Representations for Generalizable World-Action Models

Yupeng Zheng, Chaoyue Li, Linbo Wang, Xiang Li, Yuhang Zheng, Xiaotong Su, Songen Gu, Yichen Zhang 等 18 位作者

AI 速读 基于摘要

Phoenix 通过双教师蒸馏学习场景结构表示,并结合因果聚合的 CS-VAE 与世界-动作联合预测,在多种操作基准上取得领先性能。

cs.RO

查看原文摘要

World-action models jointly predict future observations and actions, yet reconstruction-oriented visual representations do not explicitly emphasize the spatial relationships and object-state changes needed for manipulation. We introduce Phoenix, which learns representations of scene structure for world-action modeling. Specifically, Phoenix Encoder enriches DINOv3's general visual semantics through dual-teacher distillation of geometric and spatiotemporal semantic knowledge. Next, CS-VAE causally aggregates and compresses Phoenix Encoder features into generative latents while preserving scene information and spatial layout. Finally, Phoenix jointly predicts these latents, complementary appearance latents, and robot actions, linking scene evolution with action generation. To study pretraining data efficiency, we curate approximately 39,000 hours of egocentric and robot manipulation data for representation learning and use the robot demonstration subset for WAM pretraining. Following benchmark-specific post-training, Phoenix achieves state-of-the-art performance across simulation and real-robot benchmarks spanning single-arm, bimanual, and dexterous manipulation. It demonstrates strong robustness to perturbations, achieving success rates of 94.8% on LIBERO-Plus and 72.4% on RoboTwin 2.0 C2R, alongside strong cross-embodiment transfer and real-world manipulation performance on Bench2Dex and RoboDojo-RealWorld, respectively. Pretraining-scale analysis shows larger performance gains from data scaling than a video-VAE-only baseline, indicating stronger scaling benefits and more effective data utilization. Moreover, Phoenix maintains high success rates when adapted with limited downstream demonstrations, demonstrating strong few-shot adaptation. Our code, pretraining data, and models are available on the project page to help the community reproduce our results.

版本更新 · v3arXiv:2605.00778

可观测表现并不完全反映适应性系统组织:咬合约束下步态动力学的多层次分析

Observable Performance Does Not Fully Reflect Adaptive System Organization: A Multi-Level Analysis of Gait Dynamics Under Occlusal Constraint

Jacques Raynal, Pierre Slangen, Elsa Raynal, Jacques Margerit

AI 速读 基于摘要

作者以单例帕金森病患者在六种咬合探针下的重复步态观测为例,说明聚合表现分数与低维嵌入都无法唯一识别特定咬合条件对应的系统状态。

cs.LG · q-bio.NC

查看原文摘要

In biomechanical systems, observable performance is often used as a proxy for underlying organization, although similar outputs may arise from different adaptive configurations. This study considers the vertical dimension of occlusion (VDO) as a constraint applied to an adaptive neuromechanical system. A single-case design in a patient with Parkinson's disease enabled repeated intra-individual gait observations under six occlusal probes. Three complementary analytical levels were examined: (i) an aggregated scalar score of observable performance, (ii) a conceptual dynamical systems framework, and (iii) an exploratory UMAP representation of 55 standardized biomechanical variables from 270 M1 observations. The revised Level 1 analysis showed that the relative ranking of OC2.5 and OC3 depended on score construction, while their scalar distributions remained close. The Level 3 embedding showed substantial overlap among all six probes and did not identify independently separated condition-specific clusters. OC2.5 and OC3 displayed limited centroid displacement but broad observation-level overlap. The principal result is therefore representational non-identifiability: neither the aggregated score nor the selected low-dimensional embedding uniquely identifies an occlusal-condition-specific system state. VDO is interpreted as a constraint parameter rather than a causal determinant. The findings are exploratory, model dependent, and non causal. They do not establish distinct physiological states, an optimal VDO, clinical thresholds, or diagnostic, predictive, mechanistic, or prescriptive validity.

版本更新 · v3arXiv:2607.07085

自适应数据分析中随机性是必要的吗?

Is Randomness Necessary for Adaptive Data Analysis?

Edith Cohen, Haim Kaplan, Yishay Mansour, Shay Sapir, Uri Stemmer, Eliad Tsfadia

AI 速读 基于摘要

该论文研究自适应数据分析(ADA)中随机性是否必要,证明在分析师计算能力无界时,任何确定性机制在约 n 个查询后就会失败,从而表明随机性是严格必要的。

cs.CR · cs.DS · cs.LG

查看原文摘要

The Adaptive Data Analysis (ADA) problem formalizes the challenge of preventing false discovery and overfitting when a dataset is repeatedly reused. Formally, our input is a dataset containing $n$ i.i.d. samples from an unknown distribution $\mathcal{P}$ over a domain $\mathcal{X}$, and our goal is to answer a sequence of $k$ adaptively chosen statistical queries with respect to $\mathcal{P}$. The main question is how many queries we can support (i.e., how large $k$ can be), primarily as a function of the number of samples $n$. This question has been intensively studied and is relatively well-understood for randomized mechanisms: there are computationally efficient mechanisms that support $k \approx n^2$ queries, and no computationally efficient mechanism can answer $k \gg n^2$ queries. In this paper, we address a fundamental question: is randomness necessary for ADA? Despite a decade of work on ADA, this question remains open. A folklore observation dating back to the initial works on ADA is that randomness is {\em not} necessary when the analyst is computationally bounded. Yet, the necessity of randomness against computationally unbounded analysts has remained elusive. Our main contribution resolves this gap in the information-theoretic setting. Perhaps surprisingly, we show that randomness is {\em strictly necessary} to answer a non-trivial number of adaptive queries: when the analyst is unbounded, any deterministic mechanism can be forced to fail after just $k = \tilde{O}(n)$ queries.

版本更新 · v2arXiv:2610.38355

面向LLM服务的扁平化KV缓存存储架构

A Flat KV Cache Storage Architecture for LLM Serving

Xin Huang, Teng Ma, Zhuoran Li, Yibo Zhao, Zhaoshi Li, Qianchao Zhu, Wei Yang, Chenxi Wang 等 10 位作者

AI 速读 基于摘要

FlatCake将主机DRAM与NVMe SSD作为统一64位地址空间中的对等介质,按会话连续、层优先顺序直接放置不可变KV块,以缓解分层缓存在生产负载下的失效。

cs.DC · cs.OS

查看原文摘要

KV cache reuse accelerates LLM serving, but existing systems manage host DRAM and NVMe SSD as a tiered hierarchy where DRAM acts as an intermediate cache. Production LLM workloads break both premises of this hierarchy. First, bimodal reuse defeats DRAM temporal filtering, since workloads are dominated either by one-shot blocks with long reuse distances or by multi-gigabyte agentic sessions that exceed DRAM capacity, putting SSD on the critical read path. Second, DRAM staging and eviction-ordered layout bottleneck SSD restoration. Holding host staging buffers for in-flight prefixes causes contention under load that aborts prefetches, while incremental eviction scatters a session's blocks across the SSD and prevents large sequential reads. We present FlatCake, a flat KV storage architecture that exposes host DRAM and NVMe SSD as peer media in a unified 64-bit address space. Exploiting the fact that KV blocks are write-once, immutable, and reused together within a prompt or session, FlatCake places each block directly onto its target medium in session-contiguous, layer-major order at creation time and never migrates it. FlatCake streams coalesced SSD reads directly into a bounded GPU window via GPUDirect Storage and decouples DRAM and SSD request queues to prevent head-of-line blocking. We implement FlatCake in SGLang and compare it against host-staged (Mooncake) and GDS-enabled (Mooncake-GDS) tiered storage, as well as SSD-direct storage (Tutti). Across three production agentic, coding, and conversational traces with DeepSeek-V4-Flash, FlatCake reduces mean TTFT near the baselines' latency knees by $1.40\times$--$2.42\times$ over the fastest baseline. On the agentic Claude Code trace, FlatCake sustains a 91.6% cache hit rate under load (versus 71.1% for all three baselines) and delivers up to $2.16\times$ higher token throughput.

版本更新 · v2arXiv:2611.15789

VibePrevisBench:评估Blender中4D场景生成的智能体编码

VibePrevisBench: Evaluating Agentic Coding for 4D Scene Generation in Blender

Yuzhe Chen, Muxi Diao, Lele Yang, Wenbin Xu, Xuyang Liu, Qile Su, Changyi Liu, Jiankang Chen 等 21 位作者

AI 速读 基于摘要

提出VibePrevisBench基准,用于评估编码智能体根据简要说明生成可执行的Blender 4D场景并渲染代理视频的能力。

cs.CV · cs.AI

查看原文摘要

Controllable real-world video generation models can condition on a rendered graybox proxy video, which fixes layout, motion and camera. Coding agents can build such videos by generating a 4D scene in Blender, yet no benchmark checks both these rendered proxy videos and the complex, multi-shot scenes behind them. We introduce VibePrevisBench, a benchmark for 4D scene generation: an agent turns a brief into an executable 4D scene and renders its proxy video. Its 242 tasks span four input kinds, including scripts, photos, continuations, and reference videos. Each delivery is scored along two evaluation dimensions. Rule-based Scene Check re-runs the code and compares the exported 4D scene with hidden ground truth facts in nine dimensions. VLM-based Screen Check asks a VLM judge whether facts that pass the rules are recognizable in the proxy video. We analyze the evaluation results and trajectories of 11 frontier coding agents and identify three key observations. First, multimodal understanding separates the agents, especially in understanding space and camera motion. Second, all agents seem to already master basic camera work and staging, and fail at challenging requests. Third, agents inspect their own renders but fail to correct their errors. Agents thus need better visual understanding of space and camera, explicit checks for challenging requests, and item-by-item verification of renders against the brief.

新论文 · v1arXiv:2611.24936

基于对比原型结构的大语言模型越狱检测

Jailbreak Detection on Large Language Models via Contrastive Prototype Structures

Yan Qiu, Yuanyuan Li

AI 速读 基于摘要

JDPI利用对比学习表示和原型距离进行越狱检测,无需额外下游分类器,在多个基准上表现优于基线。

cs.CL

查看原文摘要

Jailbreak attempts and harmful prompts remain a challenge for the safe deployment of large language models. We study whether contrastively learned representations can support safety detection without training an additional downstream classifier. We propose Jailbreak Detection with Prototype Inference (JDPI), which uses binary safety labels to construct harmful and benign prototypes and makes predictions from relative prototype distances. JDPI uses only binary safety labels for encoder adaptation, prototype construction, and validation. In our setup, it uses fewer labeled examples than the classifier baseline (Method A) by avoiding the separate split used to train the downstream classifier. Across four benchmarks covering different input formats, contrastive fine-tuning improves JDPI's detection accuracy by 9.1-18.0 percentage points. Using the same encoder, JDPI achieves slightly higher ROC-AUC on one benchmark and stays within 0.017 of the baseline across all four. With dataset-specific adaptation, JDPI exceeds the released Llama Guard 3-8B baseline by 0.173-0.310 in ROC-AUC across the four benchmarks. In multi-turn replay on TomGibbs, JDPI uses accumulated user history as the conversation unfolds, achieving higher conversation-level accuracy than when it uses the current turn alone. Across 12 directed transfers, JDPI outperforms the classifier by an average of 1.59 percentage points in accuracy, demonstrating stronger cross-dataset robustness.

新论文 · v1arXiv:2611.24932

知道自己知道什么:人机认知系统中审阅者价值的特质理论

Knowing What You Know: A Trait Theory of Reviewer Value in Human-AI Cognitive Systems

Priyanka Sinha, Sugam Pandey

AI 速读 基于摘要

作者提出审阅者价值由元认知校准(而非活动、速度、一致性或资历)决定,并用AI辅助会计系统的生产数据验证该特质理论。

cs.AI · cs.CE · cs.HC · cs.LG

查看原文摘要

When a capable model and a human reviewer cooperate on the same decision, which human still adds value? We argue this is a question about a single cognitive trait, metacognitive calibration: the alignment between a reviewer's behavioral confidence and the actual correctness of their judgments. We develop a trait theory of reviewer value to make it precise. The theory makes five claims: value is governed by calibration rather than by activity, speed, agreement, or tenure; calibration leaves observable traces in behavioral telemetry; those traces are non-diagnostic on their own, because the fast, low-revision signature of a calibrated expert is indistinguishable from that of a confident novice until it is gated by outcomes; human calibration and a model's self-knowledge are the same construct, so the joint system should defer to whichever agent is better calibrated on each item; and individual calibration is causally identifiable only above the level of the single judgment. We ground each claim in a six-month production window of an AI-assisted accounting system (541621 reviewer events, 483 reviewers), and find that a purely behavioral expertise profile inverts the ground truth, scoring an overconfident cohort (5.2 percent correction survival) higher than genuine experts (99.2 percent); that reviewer quality is flat across tenure, so the trait is not learned on the job; and that the same calibration logic that separates good from bad reviewers, applied to the model, concentrates 92.5 percent of human effort on genuine errors. We close with the boundary the theory must respect: under majority-vote aggregation, individual causal value is unidentifiable.

新论文 · v1arXiv:2611.24931

网络古诺竞争的精确复杂性阈值

Sharp Complexity Thresholds for Network Cournot Competition

Mohammad Hajiaghayi, Mohammad Mahdavi

AI 速读 基于摘要

作者确定了网络古诺均衡近似复杂度随需求多项式的次数和每个市场中的企业数量变化的精确阈值。

cs.GT · cs.CC

查看原文摘要

We determine the approximation complexity of network Cournot equilibrium as a function of demand degree and the number of firms sharing a market. For common, nonincreasing concave polynomial inverse demands, convex quadratic costs of firms' allocation vectors, and rational total capacities, high-precision approximation is polynomial-time solvable for cubic demands, regardless of market size. Quartic demands remain tractable when each market has at most three firms, and quintic demands remain tractable with at most two. These thresholds are exact: approximation at a fixed positive profit-regret tolerance is PPAD-hard for quartic demands with four firms per market, quintic demands with three, and sextic demands with two. Each hardness result uses one fixed demand curve in every market, a constant number of markets per firm, and globally nondecreasing strongly convex quadratic costs. We also give a polynomial-time algorithm for arbitrary-degree nonincreasing concave polynomial demands when each firm's convex polynomial cost depends only on its total production. The algorithm applies to arbitrary access graphs and permits firm-specific inverse demands. Its running time is polynomial in the input size and the logarithm of the inverse accuracy. The algorithm assigns one marginal charge to each firm and adjusts the charges until each firm's total sales approximate the quantity it would produce at that charge.

新论文 · v1arXiv:2611.24927

绘制AI供应链:AI生态系统中的依赖关系、脆弱性与市场集中度

Mapping the AI Supply Chain: Dependencies, Vulnerabilities, and Market Concentration in the AI Ecosystem

Sarah H. Cen, Lindsey A. Gailmard, Joohan Kim, Rishi Bommasani, Daniel E. Ho, Percy Liang

AI 速读 基于摘要

作者构建了一个多层级、大规模的数据集,系统映射AI供应链中的组织与关系,并据此分析中心性、网络集中度、社区与瓶颈。

cs.CY · cs.AI

查看原文摘要

AI systems are built across many organizations that contribute models, data, compute, capital, talent, and other assets. While the layers of the AI stack are relatively well understood, the relationships between actors and components across layers remains sparsely documented. In this work, we focus on the organizations that make up the AI supply chain: the complex network of actors that contribute to the development and deployment of AI. We motivate the examination of the organizational AI supply chain---highlighting concerns about concentration, power, chokepoints, cascading failures, fragmented accountability, and risk---then describe our pipeline for mapping the AI supply chain. Our pipeline yields our main contribution: a multilayered, large-scale dataset of actors and relationships in the AI ecosystem, annotated with dates, descriptions, types, tags, and more. This work takes a step toward systematically mapping and measuring the AI supply chain and its properties, cataloging how models, data, chips, infrastructure, capital, and even talent flow between organizations. This data enable critical examinations of industry relationships and yield insights into the political economy of AI development and concentration. We provide several illustrative analyses, including studying the most central actors, analyzing network concentration, and identifying communities and chokepoints. While our dataset is fairly comprehensive, it is also necessarily incomplete: public documents omit private deals, and coverage is shaped by search design. Together, the approach, data, and findings aim to serve as a resource for studying the AI ecosystem. The dataset is publicly available at https://huggingface.co/datasets/sarahcen/ai-supply-chain and can be explored interactively at https://aisupplychains.org/.

新论文 · v1arXiv:2611.24926

Grana:面向长时程机器人操作的可组合奖励建模

Grana: Compositional Reward Modeling for Long-Horizon Robot Manipulation

Zi-ang Cao, Kaiyuan Zheng, Yinzhen Xu, Haonan Duan, Jiasheng Gu, Fengyuan Hu, Nan Zhu, Kun Lei 等 17 位作者

AI 速读 基于摘要

Grana 是一种视觉-语言机器人奖励模型,通过开放词汇子任务描述识别未完成子任务并估计其连续进度,再组合子任务进度与已完成子任务信用来估计长时程任务的整体进度。

cs.RO

查看原文摘要

Robot reward modeling faces two challenges: generalizing across tasks and accurately tracking progress in long-horizon manipulation. General-purpose reward models demonstrate broad task transfer, but transfer from short-task pretraining to long-horizon tasks remains underexplored. Long-horizon progress models often rely on task-specific subtask classifiers or fixed action vocabularies, limiting the reuse of learned progress knowledge when adapting to new tasks. To address these challenges, we introduce Grana, a vision-language robot reward model that learns to identify unfinished subtasks and estimate their continuous progress using open-vocabulary subtask descriptions. We train a language-conditioned model to estimate progress in short-horizon tasks and individual subtasks of long-horizon tasks. For long-horizon tasks, we combine the selected subtask's predicted progress with credit for preceding completed subtasks to estimate whole-task progress. General progress prediction requires training the model across diverse tasks with progress supervision that accounts for imperfect execution. Elapsed-time proxies can misrepresent progress when relative subtask durations vary, or failures reverse local progress. We therefore introduce an annotation protocol that converts sparse subtask boundaries and action-quality annotations into dense progress targets, without requiring annotators to assign numerical progress scores. Pretraining with this supervision on 200 diverse, mostly short-horizon manipulation tasks enables zero-shot reward prediction on unseen tasks and improves progress prediction after adaptation to multi-minute, long-horizon tasks. Experiments demonstrate (i) generalizable reward prediction, including adaptation to five long-horizon tasks, (ii) benefits from pretraining and composing subtask progress estimates, and (iii) improved downstream policy performance.

版本更新 · v2arXiv:2611.22268

预见还是臆测?让未来在AI伦理中发挥作用

Anticipating or Speculating? Making Futures Pay in AI Ethics

John P. Nelson

AI 速读 基于摘要

作者主张区分“预见”与“臆测”,并据此批评为医生与医疗AI判断分歧制定统一决策规则的做法。

cs.CY · cs.AI

查看原文摘要

Philosophers have recently been trying to develop uniform decision rules for instances in which physicians' judgments diverge from the recommendations of medical artificial intelligence (AI) systems. I argue that this effort is fatally flawed because the performance and appropriate use of algorithmic recommendation systems by physicians are highly context-specific, empirical medical matters rather than epistemological ones. In such instances, general decision rules can be stipulated only to the extent that they abstract away from relevant, indeed determinative, contextual circumstances. The alleged problem of physician-AI disagreement, and others like it, play into longstanding disputes in technology ethics about the viability and utility of envisioning possible futures: is this useful "anticipation" or wasteful "speculation"? I suggest that the two may be distinguished. Anticipation explores plausible futures to help inform present actions under irreducible uncertainty. Speculation abstracts away uncertainty, developing formal solutions to stipulated circumstances whose relationship to the real present is often quite unclear. Efforts to develop crisp philosophical solutions to physician-AI disagreement, among other problems, fall into the latter category. Technology ethics should remember that fruitful futures thinking must both begin from and return to the messy, uncertain present.

新论文 · v1arXiv:2611.24925

渲染机器人,生成世界:跨具身形态的统一视频世界模型

Render the Robot, Generate the World: One Video World Model Across Embodiments

Yash Jangir, Karan Mirakhor, Renos Zabounidis, Muhammad Zubair Irshad, Sergey Zakharov, Yonatan Bisk, Homanga Bharadhwaj

AI 速读 基于摘要

Doppel 用相机对齐的未来身体渲染图加数值动作轨迹作为条件,训练一个跨八种机器人/人体形态的共享视频世界模型,让模型专注于预测物体运动与环境交互变化。

cs.RO

查看原文摘要

Predicting the consequences of an agent's actions requires modeling both the body's motion and the environment's response. Most video world models attempt to learn both from numerical actions, even though geometry and kinematics already specify the intended motion. We introduce Doppel, an embodiment-agnostic video world model conditioned on camera-aligned renderings of future body configurations and numerical action trajectories. By explicitly providing the intended motion, Doppel can focus on predicting object motion and interaction-driven changes in the environment. Rendered motion also provides a common visual interface across different embodiments and action spaces. To train on robot datasets without camera extrinsics, we recover camera poses and align rendered trajectories with recorded observations. We jointly train a single shared video backbone and conditioning adapter on eight datasets spanning eight robot and human embodiments, from single- and bimanual robot arms to a dexterous humanoid and human hands and bodies, using about 600 hours of video without embodiment labels. Across three robot-arm datasets, Doppel improves PSNR over action-only baselines by 1.00 dB on held-out trajectories and 1.20 dB under out-of-distribution evaluation, while predicting more consistent object motion. Training on all eight embodiments (Doppel-8) improves robot predictions over the three-robot model (Doppel-3) on four of six evaluation sets. Project page: https://doppelwm.github.io/.

新论文 · v1arXiv:2611.24924

Agentic Harness Engineering Beta:以需求为中心的智能体框架演化

Agentic Harness Engineering Beta: Requirement-Centered Evolution of Agent Harnesses

Jiahang Lin, Jiahao Chen, Yiding Wang, Shichun Liu, Chengjun Pan, Shihan Dou, Honglin Guo, Yuyang Hu 等 14 位作者

AI 速读 基于摘要

作者提出以用户需求为中心的智能体框架演化闭环 AHE-Beta,并在留出任务与盲测中报告了优于基线及若干对比系统的表现。

cs.SE · cs.AI

查看原文摘要

Real-world harness engineering is driven by explicit and implicit user requirements, which guide development and validation. However, existing harness evolution methods often overlook implicit requirements and interaction needs, while using a single evolution agent to modify the harness and benchmark scores to select changes. This process often produces narrow patches and leads to benchmark-specific local optima. We introduce Agentic Harness Engineering Beta (AHE-Beta), a requirement-centered loop that brings real-world engineering practices into harness evolution. The loop consists of three steps: (1) User-driven evaluation lets simulated users raise their requirements as issues while they work with the harness over multiple turns. (2) Team-based modification implements those requirements as generalizable changes rather than task-specific patches. (3) Requirement-driven selection merges a change only when it resolves a verified requirement and passes review. Empirically, on held-out tasks, AHE-Beta raises pass@1 from 21.9% to 33.3% while using 40.8% fewer tokens than Base Harness, and achieves higher pass@1 than Claude Code, Meta-Harness, and AHE. In a blind human A/B test, real users prefer AHE-Beta in 31 of 48 valid pairs and rate it higher on all five dimensions, matching the directional preference of the user simulator. The human A/B results show that AHE-Beta achieves its goal of aligning harness evolution with real-world user requirements. Without further evolution, the gains transfer to GLM-5.3 and DeepSeek-V4.1-Flash with pass@1 improvements of 15.8% and 5.3% over Base Harness. Together, these results show that requirement-centered harness evolution is a more general method for improving agent capabilities.

新论文 · v1arXiv:2611.24920

次可加在线组合拍卖的最优竞争比小于1/2

The Optimal Competitive Ratio for Subadditive Online Combinatorial Auctions is Less Than 1/2

Andrés Cristi, Jiechen Zhang

AI 速读 基于摘要

作者构造了一个四买家在线组合拍卖实例,证明任何在线规则都无法达到1/2的竞争比,而三个买家时1/2的保证总是成立。

cs.GT

查看原文摘要

We construct a four-buyer online combinatorial auction with independent subadditive valuations and a fixed, known arrival order in which every online rule earns strictly less than $1/2$ of the expected offline optimum. A common partition, revealed at the third arrival, gives the first three buyers one unit of welfare per item. If the rule uses three distinct partitions, either an item allocated early contributes zero or the fourth buyer's expected value for the remaining bundle is one less than its size. We compute the optimal online and offline welfare exactly and show that a $1/2$ guarantee always holds with at most three buyers.

新论文 · v1arXiv:2611.24918

《Infinite Energy》谜题的难度

Hardness of "Infinite Energy" Puzzles

Utkarsh Tiwari, Utkarsh Thanvi, Armaan Sethi, Aalok Thakkar, Neeldhara Misra

AI 速读 基于摘要

论文研究单机解谜游戏 Infinite Energy 及其多个变体的判定复杂度,证明多数变体为 NP-hard,部分变体可精确刻画到 TC^0 完全或 PSPACE 上界。

cs.CC

查看原文摘要

Infinite Energy (by Light Potato, 2025) is a single-player puzzle in which one wires a network of sockets so that, after every power source is unplugged, energy keeps circulating and leaves every board energized. We study several variants of the game and the complexity of deciding whether an instance can be won. The variants can be played at https://infinite-energy-peer-review.netlify.app, which also has worked examples of the reduction techniques. The colorless game, with connectability given by an arbitrary matrix, is NP-hard (by reduction from Hamiltonian Path) and lies in PSPACE. We give a seven-socket instance winnable only by charging a temporary battery loop and then breaking it, so the natural "charge and keep" strategy fails. We reduce NP-membership to one conjecture: that every winnable instance has a winning play in which no socket is charged twice. Two variants bound the complexity more tightly. The unconstrained variant, in which connectability is unrestricted, is $\mathsf{TC}^0$-complete under $\mathsf{AC}^0$ Turing reductions (hence in L). The geometric variant, in which connectability is set by proximity of points in $\mathbb{R}^k$, stays NP-hard for every fixed $k \ge 2$ via reduction from Hamiltonian Path over grid graphs. The one-dimensional case is open. The colored variant is NP-hard, though a matching upper bound remains open.

版本更新 · v3arXiv:2608.29497

布尔估值下的公平分配:超越归一化

Fair Division Under Boolean Valuations: Beyond Normalization

Nisarg Shah, Paritosh Verma

AI 速读 基于摘要

研究在智能体具有任意两级(布尔)偏好且不要求归一化时,EF1和EFX多种变体的存在性及其与效率、激励兼容等性质的兼容性。

cs.GT

查看原文摘要

We study fair division of indivisible items when agents have arbitrary two-level preferences: the value of each agent for any set of items is Boolean, which need not be monotone or additive. Notably, we do not impose the standard assumption of normalization, i.e., different agents may value the empty set at different Boolean levels. Since the preferences are nonmonotone, envy-freeness up to one item (EF1) and envy-freeness up to any item (EFX) each admit several variants, depending on which items are tested for removal and whether they are removed from the envious agent's bundle or the envied agent's bundle. This paper investigates the existence of these variants of EF1 and EFX, on their own and together with economic efficiency, incentive compatibility, feasibility constraints, and lottery-based randomization. Our paper presents a wide range of positive and negative results that collectively highlight an interesting phenomenon: the landscape of achievable guarantees depends crucially on the number of normalized agents, who value the empty bundle at the lower Boolean level.

新论文 · v1arXiv:2611.24915

PrismRestore:面向智能体图像恢复的紧凑恢复工具箱

PrismRestore: A Compact Restoration Toolbox for Agentic Image Restoration

Zhaocheng Yu, Kui Jiang, Jing Cao, Yiang Chen, Xiaocheng Feng, Junjun Jiang, Xianming Liu

AI 速读 基于摘要

PrismRestore 从单个冻结的全能模型中构建紧凑的可调用恢复动作库,并用状态条件策略组合动作,以单骨干实现智能体图像恢复。

cs.CV

查看原文摘要

Agentic image restoration composes operations to handle mixed degradations, yet its toolbox often requires storing multiple restoration networks. We propose PrismRestore, which constructs a compact bank of callable restoration actions from a single frozen all-in-one model. Our approach builds on task-dependent yet overlapping channel responses in the shared model. An offline task-prior search uses activation and gradient statistics to group channels with similar response profiles, then searches task-specific modulation coefficients over non-representative channels while leaving representative channels unmodulated. The resulting prior bank enables explicit action selection and composition without additional restoration backbones or task-specific adapter modules. A state-conditioned policy learns to compose these actions using Group Relative Policy Optimization. Its objective separately normalizes fidelity and perceptual feedback within groups of trajectories sampled for the same input, and combines terminal evaluation with return-to-go derived from stepwise quality changes. Experiments on synthetic composite-degradation and real-world multi-task benchmarks show improvements over the evaluated all-in-one baselines and restoration quality competitive with multi-model agents. PrismRestore achieves these results with a single restoration backbone and faster inference than the evaluated agentic baselines.

版本更新 · v2arXiv:2608.00799

CADENA:逐步式CAD逆向工程

CADENA: Stepwise CAD Reverse Engineering

Soslan Kabisov, Gennadiy Savrasov, Maksim Elistratov, Antonio Rodriguez, Daniil Ignatiev, Nikita Gavrilov, Rustam Uzdenov, Alexey I. Boyko 等 12 位作者

AI 速读 基于摘要

CADENA 以逐步生成并每步比对当前几何与目标的方式,将3D网格重建为参数化CAD程序,并引入按机械零件类别评测的 CADENA-Bench。

cs.CV

查看原文摘要

Computer-Aided Design (CAD) underpins modern engineering, yet converting existing shapes into editable models still demands substantial expert effort. Most AI systems emit the entire CAD program in a single pass, never inspecting the intermediate geometry. In contrast, human engineers build a part feature by feature, checking after each operation what remains to be modeled. We introduce CADENA (Spanish for "chain"), a model that reconstructs a 3D mesh as a parametric CAD program, growing its sequence of operations one at a time and comparing the target with the currently predicted geometry at every step. We also address the lack of benchmarks for evaluating reverse-engineering methods on mechanical parts, introducing CADENA-Bench, a benchmark that measures performance across categories of mechanical parts. CADENA outperforms prior methods on CADENA-Bench and on the DeepCAD, Fusion 360, and MCB datasets. Code is available at https://github.com/zhemdi/cadena, model weights at https://huggingface.co/kulibinai/cadena, and CADENA-Bench at https://huggingface.co/datasets/kulibinai/cadena-bench.

版本更新 · v3arXiv:2505.16959

更大并不总是记忆:早停过参数化扩散模型

Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models

Alessandro Favero, Antonio Sclocchi, Matthieu Wyart

AI 速读 基于摘要

作者报告在高度过参数化的扩散模型中,泛化在记忆发生前随训练逐步实现,且记忆时间与数据集大小成正比,支持基于数据规模的原则性早停准则。

cs.LG · stat.ML

查看原文摘要

Diffusion probabilistic models have become a cornerstone of modern generative AI, yet the mechanisms underlying their generalization remain poorly understood. In fact, if these models were perfectly minimizing their training loss, they would just generate data belonging to their training set, i.e., memorize, as empirically found in the overparameterized regime. We revisit this view by showing that, in highly overparameterized diffusion models, generalization in natural data domains is progressively achieved during training before the onset of memorization. Our results, ranging from image to language diffusion models, systematically support the empirical law that memorization time is proportional to the dataset size, consistent with a kernel-regression bound on the time required to fit the empirical score at low noise. Generalization vs. memorization is then best understood as a competition between time scales. We show that this phenomenology is recovered in diffusion models learning a simple probabilistic context-free grammar with random rules, where generalization corresponds to the hierarchical acquisition of deeper grammar rules as training time grows, and the generalization cost of early stopping can be characterized. We summarize these results in a phase diagram. Overall, our results support that a principled early-stopping criterion - scaling with dataset size - can effectively optimize generalization while avoiding memorization, with direct implications for hyperparameter transfer and privacy-sensitive applications.

版本更新 · v2arXiv:2605.15085

从数据到行动:利用人工智能加速炼油厂优化

From Data to Action: Accelerating Refinery Optimization with AI

Dániel Pfeifer, Ábrahám Papp, Tibor Bernáth, Tamás Zoltán Varga, Márk Czifra, Botond Szilágyi, Edith Alice Kovács

AI 速读 基于摘要

作者提出一种带记忆的线性规划求解器增强方案,通过三种异常检测方法识别输入数据错误和异常关系,以改进炼油厂调度与计划中的后续优化。

stat.ML · cs.LG · stat.AP · stat.ME

查看原文摘要

Nowadays refinery optimization utilizes sheer amounts of data, which can be handled with modern Linear Programming (LP) software, but the interpreting and applying the results remains challenging. Large petrochemical companies use massive models, with hundreds of thousands of input matrix elements. The LP solution is mathematically correct, but simplifications are made in the model, and data supply errors may occur. Therefore, further insight is needed to trust the results. The novelty of the paper consists of enhancing the LP solver with a memory, which makes possible to find potential errors in the input data, finding unusual relations in the data on different decision levels, by introducing an anomaly detection tool. Analyzing the potential "anomalies" in the input and output of LP, the subsequent LP solutions can be improved. The Anomaly Detection tool proposed comprises three methodologies. A transformed version of the popular ECOD methodology is applied. New methods are proposed to handle high-dimensional data: choosing the most informative pairs. Then, this is used alongside two 2D Anomaly Detection algorithms, revealing several business opportunities and data supply errors in the MOL refinery scheduling and planning architecture. The proposed tool learns connections in past data and runs very efficiently on present data revealing unusual connections sorted by their importance. Up to this step, optimization and Anomaly Detection happened automatically, and thereafter, decision makers may take a look at the most relevant anomalies found, and decide how to further improve the subsequent LPs. The tool also has periodic retraining built in.

新论文 · v1arXiv:2611.24908

分解神经网络中的SGD动力学:教师诱导尖峰与方差膨胀

Decomposing SGD Dynamics in Neural Networks: Teacher-Induced Spikes and Variance Inflation

Samet Demir, Zafer Dogan

AI 速读 基于摘要

作者通过将两层网络第一层权重分解为教师信号分量与正交补分量,分析其与第二层的联合SGD动力学,揭示正交补中教师依赖的谱尖峰如何放大表示方差并损害泛化。

stat.ML · cs.LG

查看原文摘要

We study two-layer neural networks trained by stochastic gradient descent (SGD) on a multi-index teacher model, focusing on how first-layer parameters orthogonal to the teacher subspace affect generalization. We decompose the first-layer weights into a signal component aligned with the teacher and an orthogonal complement, and analyze their joint SGD dynamics together with the second layer in the proportional limit. We show that although SGD updates to the complement are initially isotropic, the training dynamics induce teacher-dependent spectral spikes in the complement Gram matrix. This emergent anisotropy provides a concrete mechanism by which representation variance is amplified, and generalization degrades. To isolate this effect, we introduce Decomposed Dynamics, an analytically tractable surrogate whose asymptotic test-error dynamics coincide with those of SGD. In simulations with a ReLU student, freezing the directions of the orthogonal complement improves generalization relative to training them. Finally, we show that the signal component rapidly aligns with the second-layer weights, revealing strong cross-layer coupling even in this shallow setting. Together, our results provide a dynamical explanation for how feature learning outside the teacher subspace harms generalization.

版本更新 · v2arXiv:2610.09127

CADFather:通过协同工具使用实现自主CAD重建

CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use

Gennadiy Savrasov, Maksim Elistratov, Nikita Gavrilov, Albert Garifullin, Oleg Pavlov, Soslan Kabisov, Vladimir Frolov, Anton Konushin 等 10 位作者

AI 速读 基于摘要

CADFather是一个无需额外训练的自主智能体系统,通过协调多种工具从3D网格重建参数化CAD程序。

cs.AI · cs.LG

查看原文摘要

Reconstructing an editable CAD model from a 3D shape remains a challenging engineering task. Existing methods can propose CAD operations, but no single source of proposals works equally well across different part geometries and stages of reconstruction. We introduce CADFather, an autonomous agentic system that coordinates complementary tools to recover parametric CAD programs from 3D meshes. A vision-language assistant inspects renders of the target and intermediate reconstructions, then decides which candidate CAD programs to extend, which tools to invoke, how many proposals to generate, and when to finish. Learned and algorithmic tools propose CAD operations, while numerical optimization refines the parameters of existing programs. Proposed or refined programs are executed and evaluated to provide feedback for subsequent decisions. The agent maintains alternative candidate programs for each target part and preserves the best valid result throughout reconstruction. CADFather uses pretrained generation and assistant models without additional training. We evaluate reconstruction quality and execution validity on the full DeepCAD, Fusion360, and MCB test sets, as well as on CADENA-Bench, CADBench, and BenchCAD. We additionally analyze computational cost and the trade-off between cost and reconstruction quality.