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

+729新增论文
+575其中 AI 相关
+82已有论文修订
+95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 2026-11-20 14:57 — 2026-11-21 14:57(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 24,181 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)
新论文 · v1arXiv:2611.24043

Compression Effects on Low-Resource Multilingual Translation

Abbas Sani

原文摘要

We present a pilot study characterising the effect of post-training quantisation on multilingual machine translation quality and inference cost for three African languages - Hausa, Swahili, and Yoruba - across three model families: a small general-purpose LLM (Qwen2.5-1.5B), a larger multilingual instruction-tuned LLM (Aya-23-8B), and a dedicated multilingual MT model (NLLB-200-distilled-1.3B). Evaluating on the FLORES-200 devtest set (1,012 sentences per direction) under FP16, bitsandbytes INT8, and NF4 INT4 precisions on consumer-grade NVIDIA T4 GPUs, we find: (i) the specialised MT model outperforms both LLMs by 32.7-43.3 chrF on the Hausa and Swahili directions, and by 12.9-24.7 chrF on Yoruba, despite being roughly a sixth the size of the 8B instruction-tuned LLM; (ii) post-training quantisation preserves aggregate translation quality within approximately 1 chrF across all model families and language directions, with a single worst case of 2.19 chrF; (iii) on consumer GPUs, INT8 and INT4 quantisation provide substantial memory savings (49-61% at INT4) but do not reduce inference latency relative to FP16 - in fact, latency increases by 1.3x to 5.3x; (iv) a clear performance gradient tracking training-resource availability is visible across languages (Swahili > Hausa > Yoruba). These findings motivate a research agenda focused on hardware-aware compression and error-type analysis beyond aggregate metrics for low-resource deployment.

cs.CL

新论文 · v1arXiv:2611.24042

CURVTON-205K: A Mask-Free Difficulty-Stratified Synthetic Dataset for Robust and Scalable Virtual Try-On

Dipan Bartaula, Anuj Shrestha, Ankit Belbase, Anish Bishwakarma, Saroj Poudel, Samip Ghimire, Shashank Bhatta, Eric Arazo 等 9 位作者

原文摘要

Recent advances in 2D virtual try-on (VTON) have largely focused on architectural innovation, yet robust performance in diverse real-world conditions remains challenging. We argue that failure modes in VTON, such as inaccurate occlusion handling, unconstrained poses, and poor coverage of under-represented garments and appearance factors, are tightly coupled to dataset design choices and long-tail data regimes. We present a scalable data generation pipeline that coordinates specialized editing and generation models with vision-language model (VLM) guidance to synthesize triplets without requiring parsing masks or dense-pose annotations. Using this pipeline, we create CURVTON-205K, a curated synthetic dataset of 205K triplets: source person, target garment, and corresponding try-on image. CURVTON-205K is explicitly designed to broaden coverage across garments, person appearance, poses, occlusions, and visual conditions. Additionally, CURVTON-205K is organized into three difficulty tiers, enabling controlled evaluation under varying levels of difficulty and supporting difficulty-aware experimentation. We analyze the dataset diversity and demonstrate its potential to improve try-on fidelity across four VTON architectures and its cross-dataset generalization.

cs.CV

新论文 · v1arXiv:2611.24039

A Capability Framework for Evaluating Agentic AI Platforms in Regulated Enterprises

Abbas Raza Ali, Muhammad Ajmal Siddiqui, Moona Zahid

原文摘要

Agentic AI platforms-systems in which LLM agents plan, invoke tools, retain memory and coordinate to change the state of enterprise systems-are being procured faster than they can be measured. Public agent benchmarks score models in fixed harnesses; enterprises buy integrated platforms whose orchestration, memory, governance and tooling layers dominate outcomes, and they buy them largely on the strength of vendor demonstrations. We report an industrial evaluation programme ("bakeoff") run by the innovation laboratory of a global bank in which ten platforms-spanning open-source frameworks, proprietary products and hyperscaler ecosystems-were assessed by a cross-functional panel on nine capability dimensions across three financial-services workloads: counterparty credit risk, retrieval-augmented generation and process automation. Scores separate the field into three tiers that are stable under alternative weightings, and surface workload-specific strengths that aggregates hide. A secondary analysis, however, finds Cronbach's alpha = 0.98 across nominally distinct dimensions and rank correlations >= 0.93 with the total for eight of nine: a halo effect indicating that demonstration-based scoring measures presentation as much as capability. From these lessons we propose a gate-then-score evaluation protocol with four layers (capability, execution reliability, governance gates, business value), trace-level reliability metrics estimated over repeated runs, an autonomy-readiness scale and a reproducibility protocol. We state precisely what the present evidence supports, and what a controlled harness must add to turn enterprise platform evaluation from structured judgement into measurement.

cs.AI · cs.MA · stat.ML

版本更新 · v2arXiv:2611.00791

PhoneValue-Bench: A Dual-Ground-Truth Scorecard Benchmark for Smartphone Recommerce Inspection

Zihan Deng, Chuanzhi Xu, Junjie Huang, Xiaozhen Zhong, Du Tiantian

原文摘要

Remote smartphone recommerce is scaling quickly, and locking a repurchase offer from seller photos and diagnostic screens before the handset arrives has become a central operational task. Existing multimodal resources mainly target defect localization, catalog attributes, or screen reading. They overlook payout-facing scorecards with dual cosmetic and operational ground truth under a declared input contract. This gap stems from two challenges: (1) the lack of a large weakly labeled trade-in corpus kept separate from a compact audited ranking cut, and (2) architectures that either flatten unordered photo bags into one prompt or collapse evaluation into a single price scalar. To address these challenges, we propose PhoneValue-Bench, a dual-ground-truth recommerce framework with PhoneValue-Corpus for weak training on 21,550 orders and 278,748 images, and PV-Rank as the only leaderboard on 335 quality-gated orders. Systems are ranked by CardScore under LeadGate, with Cosmetic Fill and Operational Fill as diagnostics, while grade and price stay off the board. Notably, ValueAgent is a six-stage perception-fusion reference that canonicalizes views, detects regional defects, reads screenshots, and fuses evidence under warehouse-style rules, so bag-of-images prompting is not the only evaluation unit. On the same PV-Rank cut and frozen scorer, this full-system and input-contract comparison finds ValueAgent at 84.1 CardScore against the strongest Flat Vision-Language Model at 69.9, with the largest reported gap in CosFill, while OpsFill remains limited under the two declared contracts. CardScore measures field-fill completeness, not quote accuracy.

cs.CV · cs.AI

新论文 · v1arXiv:2611.24038

Semantic-aware Contrasting with Explicitly Disentangled Representations for AI-Generated Video Detection

Jiaquan Yu, Jingyi Xie, Zeyu Zhang, Yunhang Qian, Xiaobin Hu, Jiawei Liu

原文摘要

The rapid proliferation of AI-generated videos (AIGVs) has raised critical concerns about content authenticity. Existing benchmarks suffer from a fundamental limitation: real and fake videos are often collected or generated from different semantic distributions. As a result, detectors may rely on spurious correlations involving objects, scenes, or actions rather than intrinsic artifacts introduced by generative models. To this end, we introduce SAVGE, a large-scale semantically aligned AIGV detection dataset comprising 2,369,822 videos, including 424,115 real videos and 1,945,707 generated videos. SAVGE organizes samples into real-fake semantic groups by using captions paired with real videos as prompts for text-to-video generation, thereby providing both group-level correspondence and textual semantic anchors. Based on SAVGE, we further propose Explicit Disentangling and Semantic-aware Contrasting (EDSC), a model-agnostic training framework for learning artifact-focused representations with reduced semantic interference. EDSC first extracts and aligns visual semantic features with textual representations, and then explicitly suppresses semantic information in the artifact branch while contrasting real and fake samples within each semantic group. By integrating caption-guided semantic supervision with intra-group contrastive learning in a two-phase optimization strategy, EDSC encourages detectors to capture generation-related cues under matched semantic conditions. Extensive experiments on SAVGE and GenVideo demonstrate that EDSC improves most evaluated backbone-metric combinations, enhances robustness under challenging evaluation settings, and strengthens cross-dataset generalization. These results highlight the importance of semantic alignment in AIGV detection and validate explicit semantic-artifact disentanglement as an effective strategy for robust detector learning.

cs.CV

新论文 · v1arXiv:2611.24037

FormalFixer: Intent-Aligned Automated Hardware Repair via Joint Refinement of Specifications, Assertions, and RTL Implementations

Changyuan Yu, Hongce Zhang

原文摘要

Functional errors in hardware designs can compromise correctness and security, and must be fixed before tape-out. Formal property verification (FPV) provides strong guarantees by proving or refuting assertions, but a failed assertion is not always evidence of an RTL defect: the failure may also come from a buggy assertion or from a specification that is semantically correct but too ambiguous or incomplete for direct formalization. This creates a practical repair problem that existing RTL-centric methods do not directly address: the repair loop must align specification intent, verification intent, and RTL behavior before deciding which artifact to change. \textsc{FormalFixer} addresses this problem with a multi-stage, intent-aligned repair workflow for Verilog designs with assertions. It preserves the original specification as authoritative ground truth and appends confidence-filtered refinements to clarify implicit constraints. \textsc{FormalFixer} uses both intent mismatch and verifier-generated counterexample cone graphs to guide iterative RTL patching. This workflow explicitly checks specification--assertion--RTL correspondence. Results support intent alignment for FPV-based hardware repair.

cs.MA · cs.AI

版本更新 · v2arXiv:2609.11357

Morphology-Aware Human Motion Retargeting for Wheeled-Humanoid Loco-Manipulation

Chenbo Xia, Xiang Li, Hao Zhang, Bohan Wu, Yue Hao, Chao Ye

原文摘要

We propose a whole-body teleoperation method for topology-mismatched humanoids, with a focus on motion retargeting and whole-body control for wheeled humanoids. First, we design a Topology-Adaptive Motion Retargeting (TAMR) method with a robust switching logic that selects mapping joints according to human posture. Second, we train a Teacher-Student DAgger method that supports real-time teleoperation with inertial motion capture and virtual-reality devices. We further develop a Temporal Feasibility-Aware Command Governor (T-FeaCG) for the wheeled base to reduce the mismatch between teleoperation policy intent and the feasible execution margin of a three-steer-wheel base. We will release the complete teleoperation code and dataset, and demonstrate whole-body humanoid skills learned from teleoperation. More videos are available at: https://xiachenbuo.github.io/Morphology-Aware-Human-Motion-Retargeting-for-Wheeled-Humanoid-Loco-Manipulation/.

cs.RO

版本更新 · v2arXiv:2611.23187

Any2Building: Unifying Point Clouds and Images for Building Reconstruction via Shared Spatial Queries

Hongye Hou, Zhuoxiao Li, Liu Xiangyu, Tengxi Wang, Jing Ou, Dongli Wu, Shuai Zhang, Tongyan Hua 等 9 位作者

原文摘要

Abstracting structured buildings from limited observations is essential for 3D urban modeling and digital twins. Partial point clouds and overhead images of the same building provide incomplete 3D surface measurements and visual cues to its footprint, roof geometry, and rooftop structures, respectively. This motivates a unified framework that aligns geometric and visual cues in 3D and reconstructs buildings from either or both modalities. Building on this connection, we present Any2Building, a unified model for Level of Detail 2 (LoD2) building reconstruction from partial point clouds, overhead images, or both, with optional coarse geometric priors. At its core is an occupancy-grounded shared spatial queries representation that organizes available observations within a common 3D grid. Supervised by complete building surface voxels, these queries connect observational evidence to target geometry, enabling a shared generator to learn structural priors across tasks and providing spatial guidance for recovering missing structure. A trained voxel conditional surface-generation and low-poly remeshing pipeline then converts the predicted structure into compact LoD2 building models. To support this framework, we introduce BuildingWorld-Image, comprising approximately one million paired samples of partial point clouds, overhead images, and LoD2 building models across 18 cities. Experiments on multiple benchmarks demonstrate that Any2Building outperforms existing methods in geometric reconstruction accuracy across unimodal and multimodal point-cloud completion, single-image building generation, and prior-assisted generation, while maintaining detailed and robust recovery when point cloud input modality is degraded.

cs.CV

新论文 · v1arXiv:2611.24032

Test-Time Symmetrization: Scaling Laws for Model-Agnostic Learning under Structure

Behrooz Tahmasebi, Melanie Weber

原文摘要

Test-time compute has emerged as a powerful way to improve the accuracy of language models at inference time, with scaling laws quantifying how accuracy improves with additional forward passes. Existing scaling laws, however, focus on repeated sampling from a fixed prompt, even though many tasks admit multiple equivalent representations of the same underlying problem. A graph does not depend on how its nodes are numbered, and a program does not depend on the names of its variables, yet language models can change their answers under such rewritings. In this paper, we study test-time symmetrization, which uses forward passes on rewritings of the input and aggregates the resulting answers over the group $G$ of rewritings. We prove that no amount of sampling and repeated decoding from a single representation can replace rewriting, while only $O(\log |G|)$ random rewritings suffice to recover the information provided by all $|G|$ rewritings. The same set of $O(\log |G|)$ rewritings provides simultaneous approximation across models, decoding rules, and sampled reasoning traces, and the logarithmic scaling is optimal in general. We validate the theory with experiments on Qwen2.5-7B, Phi-4-mini, Llama-3.1-8B, and Qwen2.5-14B, with chain-of-thought reasoning, on graph reasoning, logical deduction, and multiple-choice question answering. At the same number of forward passes, spending them on rewritings of the input is substantially more accurate than spending them on repeated sampling from the original prompt whenever the model's answer depends on how the input is written, and the number of rewritings needed grows only logarithmically with the number of possible rewritings, as the theory predicts. Our results provide a principled way to enforce symmetries at inference time when they cannot be built into the model, which we call model-agnostic symmetrization.

cs.AI

版本更新 · v2arXiv:2608.06847

What Should Visual Place Recognition Be Invariant To? Rethinking Condition Invariance in Visual Place Recognition

Beomsu Kim, Minwoo Jung, Giseop Kim

原文摘要

Condition invariance in Visual Place Recognition (VPR) is typically evaluated by matching queries from one condition against a database from another condition. This tests the ability to recognize the same place when the query's condition differs from the database's condition. However, to map large environments, a database can be built from images collected by multiple robots or across multiple traversals under different conditions. In this setting, condition blindness---the ability to remain invariant to condition differences among database images---becomes important, but standard cross-condition evaluation does not provide a controlled assessment of this ability. Therefore, we introduce Distractor-Augmented Recall (DAR) to measure condition blindness in a controlled manner. Across eleven methods and six datasets, we find that differences in condition blindness can be larger than Recall@1 alone would suggest. To improve the condition blindness that DAR reveals, we compare three methods that make VPR descriptors more invariant to condition changes through post-processing. Among the three methods, we demonstrate INLP on a database built from multiple traversals under different conditions, showing that it can improve the performance of existing VPR methods.

cs.RO · cs.CV

新论文 · v1arXiv:2611.24028

Algorithmic Market Making Can Lead to Rough Volatility Through the Order Book

Sai Niranjan Ramachandran

原文摘要

Existing work suggests that markets can show volatility with paths rougher than those of Brownian motion. In theory this can happen when the order flow is close to instability with memory that decays as a power law. However, it is not fully clear how such order flow could arise from the predominantly algorithmic market making that characterizes order book dynamics. We show one such consistent mechanism. We treat each market maker as a desk that uses a first-order gradient rule to move the distances of its orders from the mid price toward target distances provided by an unknown oracle. We assume that distinct desks do not act synchronously in time but act whenever new information relevant to their respective oracles arrives, which each desk samples over its own characteristic lookback horizon. Across all desks the rule therefore takes the form of stochastic gradient descent (SGD) with information-driven (mini-batch) noise. In the continuum limit this update rule makes the volume of the order book follow a conservative stochastic partial differential equation (the Dean--Kawasaki equation) whose fluctuations drive the order flow. The distinct horizons of the desks further induce a persistent memory in the order flow that decays as a power law. Standard scaling arguments then lead to rough volatility. We confirm the key predictions of the model on simulated agents and on six months of Binance data with about 790 million orders. In liquid markets governed mainly by market makers, such as the perpetual futures of Binance, the order books are consistent with how our desks change the book.

cs.LG · q-fin.MF · q-fin.TR

版本更新 · v2arXiv:2505.07460

A Survey on Collaborative Mechanisms Between Large and Small Language Models

Yi Chen, Haiquan Wang, JiaHao Zhao, HaoHao Han

原文摘要

Large Language Models (LLMs) deliver powerful AI capabilities but face deployment challenges due to high resource costs and latency, whereas Small Language Models (SLMs) offer efficiency and deployability at the cost of reduced performance. Collaboration between LLMs and SLMs emerges as a crucial paradigm to synergistically balance these trade-offs, enabling advanced AI applications, especially on resource-constrained edge devices. This survey provides a comprehensive overview of LLM-SLM collaboration, detailing various interaction mechanisms (pipeline, routing, auxiliary, distillation, fusion), key enabling technologies, and diverse application scenarios driven by on-device needs like low latency, privacy, personalization, and offline operation. While highlighting the significant potential for creating more efficient, adaptable, and accessible AI, we also discuss persistent challenges including system overhead, inter-model consistency, robust task allocation, evaluation complexity, and security/privacy concerns. Future directions point towards more intelligent adaptive frameworks, deeper model fusion, and expansion into multimodal and embodied AI, positioning LLM-SLM collaboration as a key driver for the next generation of practical and ubiquitous artificial intelligence.

cs.AI · cs.CL

版本更新 · v4arXiv:2608.12704

Efficient Hessian-Free Methods for Multi-Objective Bilevel Optimization with a Nonconvex Lower-Level Objective

Yicong Jiang, Feihu Huang

原文摘要

Multi-objective bilevel optimization has wide applications in the AI area such as automated learning and multi-task meta-learning. Although some recent studies have investigated multi-objective bilevel optimization, many existing methods rely on the (strongly) convex lower level problems. In fact, these multi-objective bilevel learning problems are generally nonconvex, and particularly their lower level problems are nonconvex. To fill this gap, we propose a class of Multi-Objective Moreau Envelope based Hessian-free Algorithms (MOMEHA) for the multi-objective bilevel learning problems with a nonconvex lower level. Specifically, our method uses the Moreau envelope to formulate a multi-objective single-level relaxation that enforces lower-level first-order stationarity. In particular, our method retains computational advantages of being single-loop and Hessian-free in the multi-objective setting by incorporating a smooth weighted Tchebycheff scalarization. Furthermore, we propose a momentum variant of MOMEHA (i.e., MB-MOMEHA) for the stochastic multi-objective bilevel learning problems. Under the stated assumptions, we establish finite-iteration bounds on the Moreau gap and Pareto stationarity residuals under dynamically relaxed gap constraints in both deterministic and stochastic settings. Some experiments on few-shot meta-learning and neural architecture search demonstrate that our methods outperform the existing approaches in terms of Pareto front quality, validating their effectiveness and robustness.

math.OC · cs.LG

新论文 · v1arXiv:2611.24025

Intent Contracts: Taking Tools Away from Agents

Ziyuan Wang, Genliang Zhu, Xiaobo Chen, Chu Wang

原文摘要

Intent contracts are an authorization interface for tool-using LLM agents in which the planning model holds no tools. For each step it submits a short logged contract: a goal, a verbatim quotation of the user, and scope fields. Code validates the contract, and a small trusted model checks it against the user's words and writes the tool call itself. Provided the validation and dispatch code is correct, every executed call is written by the trusted model, the planner's influence on a call is confined to a contract logged before it, and the trusted side decides how much of a request to carry out. We compare contracts with two reviewers of planner-written commands: one sees only the user's words and the command, the information boundary of a reasoning-blind permission classifier, and one also sees the planner's goal and a checked quotation. With gpt-6.1-terra as planner and GLM-5.3-Flash as the trusted model on three AmPermBench task families, every object changed under contracts is named in the goal of the contract that produced the change; under review the planner names objects in its commands and rarely in its goals. When the planner adds work the user never asked for, contracts complete the user's task in 27/30 runs and the intent-visible reviewer in 16/30, because a reviewer can only refuse a whole command. Contracts do not reduce unauthorized actions. They are indistinguishable from blind review, and once the benchmark's environment terms are clarified, every condition that changes state hits a wrong target in 40-49% of those runs. That error is the planner's choice of objects for an ambiguous reference, which no trusted model here can see the environment to check; telling the executor to decline when unsure does not change it. We evaluate benign over-reach with one pair of models, not adversarial planners. We release the plugin and run records.

cs.CR · cs.AI

新论文 · v1arXiv:2611.24023

STAR++: A Physical-Aware Benchmark and Framework for Astronomical Super-Resolution across Multiple Filters

Guohang Zhuang, Jiaze Li, Kuo-cheng Wu, Hao Du, Jinyang Huang, Xiang Zhang, Wanli Ouyang, Yan Lu

原文摘要

Astronomical super-resolution (ASR) aims to reconstruct high-resolution star fields from low-resolution telescope observations across multiple filters for astrophysical analysis. However, developing a physics-aware ASR framework faces two challenges: 1) Data view: no large-scale benchmark supports field-level ASR, especially on unseen filters. 2) Method view: Existing ASR methods often fail to preserve stellar flux across spatial resolutions. Moreover, ASR requires reconstructing high-frequency components, including accurate star locations and profiles, making it more ill-posed than natural-image SR. To tackle these problems, we introduce STAR++, a large-scale benchmark comprising approximately 1.7 million flux-consistent image pairs across 36 filters, derived from Hubble Space Telescope (HST) observations. STAR++ uses a flux-preserving data generation pipeline to ensure photometric consistency across resolutions and provides the Flux Error (FE) metric to evaluate ASR models from a physical perspective. To address method-level challenges, we propose a Flux-Invariant Super-Resolution Plus (FISR++) model that generalizes to unseen filters while accurately reconstructing flux-consistent high-resolution images. Beyond the flux-preserving modules, FISR++ introduces two novel components. Specifically, a Filter-Aware Adapter (FAA) incorporates filter metadata to adapt image representations to varying spectral and optical conditions. In addition, a Spatial Ambiguity Disentangle Loss (SADL) models spatial ambiguity as pixel-shift uncertainty, mitigating the smoothing of learned conditional mean reconstructions caused by this ambiguity. Extensive experiments demonstrate that FISR++ consistently outperforms existing ASR methods in reconstruction quality and flux accuracy, while generalizing to unseen filters, highlighting its effectiveness for photometrically faithful ASR.

cs.CV

版本更新 · v4arXiv:2606.10660

Accounting for Purchased Artificial Intelligence Inference in Corporate Greenhouse Gas Inventories: A Token-Based Method

Guillermo Llopis-Garcia

原文摘要

Purchased artificial intelligence (AI) inference belongs in Scope 3 Category 1 of a corporate greenhouse gas inventory, yet practice omits it or applies a spend-based factor that gives 1.7 to 12.3 times the physical estimate and cannot tell one model or region from another. This paper sets out a token-based method and open dataset: a cradle-to-gate boundary, four tiers of activity data, an effective-token basis, a four-term factor (serving electricity, embodied hardware, data-centre construction, disclosed final training runs) and a rule resolving any model identifier and region to a factor. Inference footprints span twelve times between model classes and nine between regions. The mid-class factor, 0.039 kg of carbon dioxide equivalent (CO2e) per million billed tokens at the world-average grid, is the low end of a stated structural range: a less efficient serving configuration raises it 2.8 times, and replacing the training term with all model development, on its own boundary, gives 1.5 to 2.9 times it. Input bands alone give -18% to +29%. Published per-query energy estimates that can describe a mid-class model are 2.4 to 7.2 times the mid-class energy, above its structural range in four of five rows; those that can describe a frontier-class model bracket it at 0.7 to 1.6 times. Worked examples give 8.5 kg CO2e a year for a 200-person firm, and 2.1 tonnes for fifty developers using agentic coding tools on a mid-class model or 8.3 tonnes on a frontier-class one. The contribution is a traceable figure; accuracy against metered energy is untested.

cs.CY · cs.AI

新论文 · v1arXiv:2611.24018

Semi-Supervised GAN-Based Segmentation of CTPA Scans for Pulmonary Emboli Boundary Extraction

Maria Thoma, Michalis Savelonas, Foteini Malli, Dimitris Iakovidis

原文摘要

Pulmonary embolism (PE) is a pulmonary vascular disease associated with high morbidity and mortality, where delayed diagnosis can be fatal. While computed tomography pulmonary angiography (CTPA) is the clinical gold standard for PE detection, interpreting these scans manually is time-consuming and error-prone. In this work, we propose a semi-supervised segmentation method, employing generative adversarial networks (GANs) to leverage large pools of unlabeled CTPA scans. The proposed method addresses more effectively the challenges of CTPA image segmentation than previous methods by employing the dice loss and the cross-entropy loss to tackle the highly imbalanced nature of CTPA scans, the feature matching loss to encourage the generator to produce anatomically plausible segmentation maps that are indistinguishable from ground truth, as well as the self-training loss to reinforce learning from highly-confident pseudo-labeled samples. The experimental evaluation on a publicly available dataset shows that the proposed method maintains accurate segmentation, despite a limited number of labeled CTPA scans. with a Dice coefficient of 88.75% and a 95th percentile Hausdorff distance (HD95) of 1.74, outperforming fully supervised baselines.

cs.CV · cs.LG

新论文 · v1arXiv:2611.24016

Rethinking Contrastive Targets in Radiology Language-Image Pretraining

Yunhe Gao, Ashwin Kumar, Jiaming Liu, Chong Wang, Maya Varma, Fuying Wang, Stefania L. Moroianu, Louisa Fay 等 11 位作者

原文摘要

CLIP-style contrastive image-text pretraining is widely used in radiology data, where each image is paired with one report and every other report in the batch is treated as a negative. Under this recipe, two failures appear, neither of which is systematically addressed by existing contrastive learning theory: zero-shot evaluation peaks then degrades while training loss keeps decreasing, and training fails to learn from large batches. We hypothesize the cause is structural rather than radiology-specific: many unpaired reports share clinical findings with a given image, so CLIP's paired-identity target is systematically biased, not merely noisy. To test this, we construct CLEVR-Radiology, a synthetic testbed that preserves only this overlapping-fact structure and reproduces both failures. With evidence that the structure is sufficient to reproduce the failures, we develop a target-misspecification theory that explains both failures from a single deterministic gradient bias amplified by batch size, and use it to motivate a minimal compatibility-based correction, CorLIP: text is treated as positive whenever its clinical assertions agree with the image, with no architecture changes. Beyond benchmark improvements, CorLIP largely removes the post-peak degradation, makes large-batch training succeed where it previously collapsed, substantially amplifies the gains from more data, and is the only configuration that remains stable up to B=2048. The correction transfers from chest X-ray to 3D CT modalities.

cs.CV · cs.LG

新论文 · v1arXiv:2611.24015

NOTREKS: Marginal Independence in Score-based Structure Learning

Fabian Bleile, Sarah Lumpp, Mathias Drton

原文摘要

Score-based structure learning estimates causal graphs by optimizing a data-dependent objective over structural equation models. We study how prior knowledge that selected pairs of variables are marginally independent can be incorporated into such causal discovery methods. Under faithfulness, marginally independent pairs cannot be connected by a trek, so the knowledge becomes a graphical no-trek constraint, which we call NOTREKS information. We introduce a power-series trek (PSTrek) penalty for gradient-based optimization and a trek constraint for order-based search, and we analyze why such information helps in finite samples and how it restricts the search space. Our numerical experiments illustrate to what extent NOTREKS information helps in causal discovery. In particular, using synthetic benchmarks with oracle NOTREKS information, we show that these constraints can improve both structural recovery and adjustment-based effect identification.

stat.ML · cs.LG · stat.ME

新论文 · v1arXiv:2611.24012

FlyVQA: Seeing Video Frame Interpolation Quality through Fly Eyes

Baoliang Chen, Lingyu Zhu, Zhiwei Zhong, Shiqi Wang

原文摘要

The ultimate ambition of visual quality assessment is to reproduce the neural computations of human vision and thereby achieve full alignment with human perception. However, the immense complexity of human visual circuitry makes this goal difficult to realize. Recently released fly visual connectomes provide a tractable biological starting point. Despite differences between fly and human vision, the fly's well-characterized motion pathways motivate us to investigate their potential for assessing the perceptual impact of temporal distortions. In this paper, we use a shared, frozen fly visual circuit to perform full-reference quality assessment of frame-interpolated videos, whose artifacts can disrupt temporal consistency. Specifically, compound-eye sampling maps reference and distorted sequences into the circuit, while a connectome-aware readout quantifies discrepancies in cell-type-specific activity and excitatory--inhibitory synaptic dynamics. Reference-guided temporal pooling and a lightweight regression head integrate these differences into a quality score. Experiments across multiple interpolation methods demonstrate better agreement with human ratings than CNN, RNN, and Transformer baselines with comparable parameters, supporting a biologically grounded approach to perceptual quality modeling.

cs.CV

新论文 · v1arXiv:2611.24011

WAM-Policy: World Action Models with On-Policy Distillation for Quadrupedal Loco-Manipulation

Junlin Long, Xu Deng, Yiran Wang, Yue Yang, Yang Zhao, Zeyu Zhang

原文摘要

Arm-free quadrupeds can perform loco-manipulation, walking on three legs while manipulating with a front leg, yet no existing policy for it follows language instructions. World action models (WAMs) have emerged as effective language-conditioned manipulation policies, but are pretrained for robot arms and sample slowly. WAM-Policy turns one WAM into a quadrupedal loco-manipulation policy via two stages. The first, Cross-Morphology Policy Adaptation and Acceleration, adapts the arm-centric WAM to quadrupeds and distills the transferred policy into a student with one video and two action steps by on-policy self-distillation (OPSD). This student, however, is bounded by its teacher, which only imitates demonstrations. The second stage, Task-Specific Improvement and Merging, therefore tunes the teacher by reinforcement learning (RL) and merges the slow specialists into one few-step student by multi-teacher on-policy distillation (M-OPD). On QLM-Bench, ten simulated tasks with 1,000 demonstrations synthesized without teleoperation, the transferred policy reaches 77.0%, and the OPSD student keeps 76.7% while sampling 14 times faster. Task-specific RL and M-OPD lift it to 85.0%. We also deploy the OPSD student on a real Unitree Go2 Air. WAM-Policy thus achieves a stronger quadrupedal policy at a fraction of the inference cost.

cs.RO · cs.CV

版本更新 · v2arXiv:2609.24657

Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models

Xiaoqiang Wang, Mengyang Xiong, Jun Dai, Bang Liu

原文摘要

Improving pretrained language models with limited adaptation data calls for computational modules that are both effective and scalable. Parameterized quantum circuits offer expressive transformations for language modeling, yet existing quantum-enhanced language models apply the same predefined circuit design to every token in an input sequence, regardless of its content. This limitation is particularly acute in masked-diffusion language models, where token representations evolve across iterative denoising steps while the circuit design remains fixed. We introduce HyperQ, a quantum-augmented masked-diffusion language model that dynamically synthesizes token-specific quantum circuits. Built upon an IQP-inspired architecture, HyperQ employs a lightweight circuit hypernetwork to generate rotation angles and measurement bases conditioned on each token's hidden state. The resulting quantum expectation values are projected back into the frozen language-model backbone through a residual connection. To support wider quantum registers, HyperQ bounds circuit interaction degree, maintaining per-qubit gradient scale and readout cost independent of register width. Across six zero-shot benchmarks, scaling HyperQ from 16 to 64 qubits improves average accuracy from 47.65 to 54.30, surpassing the frozen backbone's 49.59 by 4.71 points while using only one tenth of the fine-tuning data used by classical baselines. We further execute the generated circuits on an IBM 156-qubit superconducting quantum processor, demonstrating their feasibility on physical quantum hardware.

quant-ph · cs.CL

新论文 · v1arXiv:2611.24010

HHW-Ego: DSLR-Quality Enhancement for Multi-Source Wearable Ego Imaging

Yunfei Tong, Qianqian Sun, Jixiang Luo, Dell Zhang, Hao Sun

原文摘要

Wearable ego-centric images are now in high demand for scenarios ranging from daily smart glass usage to embodied intelligence. But the image quality is far behind smart phone due to the lacking paired high-quality reference images and the dedicated enhancement systems. To solve this, a customized degradation pipeline is designed to generate paired samples matching wearable camera images, boosting the upper limit of enhancement performance. Besides a two-stage enhancement framework is further built: first, tuning an efficient model on the paired dataset to enhance real wearable images; second, using hyperspectral data to refine color temperature for better quality. Moreover we present HHW-Ego, a multi-source paired dataset integrating with Hyperspectral, High-dynamic range and Wearable Ego-centric data, which includes 5,000 image groups spanning indoor/outdoor and day/night scenes. On held-out paired data, Stage-1 fine-tuning improves PSNR, SSIM, Lab distance, and LPIPS for Real-ESRGAN and PFT-SR. On real wearable images, no-reference metrics, human preference, gamut analysis, and visual comparisons characterize the effects of Stage 2.

cs.CV

新论文 · v1arXiv:2611.24008

Modelling the human-exoskeleton interaction interface - Benchmarking MuJoCo's deformable model

Lisette Masselink, Xiaolong Zhu Thomas George Thuruthel, Mohamed Irfan Refai

原文摘要

The human-exoskeleton interaction interface, consisting of the exoskeleton attachment and the underlying human soft tissue, can affect the transfer of assistance. MuJoCo's \textit{flexcomp} has been previously used to model the soft tissue, but its accuracy has not been benchmarked against a finite element model. We benchmarked the \textit{flexcomp} Saint Venant-Kirchhoff (StVK) and Stable Neo-Hookean (SNH) models against COMSOL's Yeoh model in three cases: \textit{case 1}) spherical indentation, \textit{case 2}) compression, and \textit{case 3}) compression of a thigh. We compared force and strain energy as a function of indentation depth, hysteresis and computation time. MuJoCo's models capture force trends with a correlation of 0.97-0.99, but showed a stiffer response, which could be attributed to the volumetric locking of the linear finite elements. The MuJoCo models systematically underestimated hysteresis as MuJoCo's Rayleigh damping could not substitute a viscoelastic model. Moreover, MuJoCo's computational advantage was speed dependent: it was 2-2.5 times faster for spherical indentation, but COMSOL was faster for the other cases, which have more degrees of freedom and contacts. Although MuJoCo's \textit{flexcomp} offers a combination of soft-tissue modelling and multibody dynamics, the limitations regarding the stiffening and hysteresis should be addressed to be used for the analysis of the human-exoskeleton interaction interface.

cs.RO

版本更新 · v2arXiv:2610.20823

Feasibility Ceilings Before Learning: Sizing and Timing Bounds for Drone-Mesh Interception

Dmytro Babarytskyi

原文摘要

A mesh of interceptors defending a fixed site must spread over the predicted arrival point of an approaching object. This is a recurring task in multi-agent robotics: N agents, each covering a disc of radius r, spread over a probability density so that a point drawn from it falls within some agent's disc. We give closed forms for the quantities that bound performance before any policy is chosen, and validate each by Monte Carlo. The uncertainty of a point predicted by extrapolating a noisy linear track follows from least-squares variance propagation plus a delta-method term for the uncertain arrival time, agreeing with simulation to within 1.8%. The coverage probability of a packed mesh admits a closed form accurate to 0.007 absolute, with a volumetric analogue. A naive area ratio misses a ceiling: while agents stay at least 2r apart, no mesh exceeds 90.69% coverage in the plane or 74.05% in a volume. This ceiling belongs to the separation constraint, not to the problem - permitting overlap substitutes Kershner's thinnest-covering density and removes it, the better regime above a crossover at p=0.80. Hexagonal packing is optimal among five arrangements; the centroidal-Voronoi configuration coverage control supplies reaches only half its coverage at small budgets. The Gaussian assumption is conservative under heavy tails and anisotropy but fragile under bias: a one-sigma aim-point offset costs 14 points of coverage. A repositioning team must also choose a commit time, and the admissible window can be empty. Against the applicable ceiling, analytic placement attains 85% of what the configuration permits while centralised PPO averages 15% over three trainer seeds, with a paired bootstrap against a null policy containing zero at every seed. We argue such ceilings should be computed before any learning experiment and quoted alongside every result.

cs.RO · cs.LG · cs.MA

新论文 · v1arXiv:2611.24007

Freeforward4d: Annotation-free feed-forward 4d reconstruction of driving scenes

Luosong Guo, Xiang Yang, Chaoyang Li, Ao Gao, Jiangming Shi, Yanyun Qu, Zhizhong Zhang, Jingyu Gong 等 9 位作者

原文摘要

Feed-forward 4D reconstruction enables efficient creation of renderable driving scenes for autonomous driving simulation. However, most existing methods rely heavily on dataset-provided cameras, LiDAR depth, or 3D box annotations, limiting their applicability to unannotated driving videos. Pretrained visual models can predict cameras, depth, and object tracks from RGB alone, but their geometry is mutually inconsistent: multi-view predictions come in short windows with independent scales and frames, while monocular depth is metric only per image. Our key insight is that, once reconciled into a single metric frame, these priors can replace dataset annotations for feed-forward 4D reconstruction. We present \textbf{FreeForward4D}, which calibrates overlapping prediction windows against monocular metric depth and registers them into one frame across time. On this geometry, 2D tracks are associated across cameras in 3D, and objects move through hierarchical motion that combines a shared object velocity with local Gaussian corrections, so that both training and inference use only RGB videos. On Waymo, FreeForward4D achieves 27.66 dB PSNR and 0.836 SSIM while recovering metric-scale cameras and depth without scale alignment. It surpasses STORM, SLARM-F, UFO, DGGT, and StreetForward, which rely on dataset annotations, in full-image PSNR and attains the best RGB fidelity on 8-second windows. RGB-only fine-tuning further adapts the framework to nuScenes and Argoverse 2. Code will be released.

cs.CV

新论文 · v1arXiv:2611.24005

How Reward Gain Imbalance Shapes Ranking: Rethinking Rubric-Based Reward Aggregation

Zhengyuan Fan, Zhonghua Wu, Tianyu Cheng, Qun Chen

原文摘要

Rubric-based reinforcement learning constructs rewards for aligning large language models with human preferences, typically by equally aggregating continuous scores that a judge assigns to individual criteria. However, scoring heterogeneity across criteria can distort candidate rankings. Existing work has focused on improving judges, learning criterion weights, or refining aggregation, whereas the interaction between scoring heterogeneity and ranking remains insufficiently understood. We formalize this heterogeneity as \emph{reward gain imbalance}: each criterion enters the aggregated reward with its own reward gain, the gap between its expected scores on satisfied and unsatisfied responses. Counterintuitively, our experiments show that removing this imbalance, even with ground-truth labels, lowers ranking accuracy. To explain this, we derive an exact decomposition of the reward difference between any two candidates into a base satisfaction signal, a reward gain imbalance term, and a residual term, showing that reward gain imbalance can attenuate or amplify the base signal, and finding that misrankings usually concentrate on pairs where it attenuates. Guided by this analysis, we propose the adaptive \textbf{D}ual-\textbf{C}enter \textbf{C}lipping aggregation (DCC), which bounds each criterion's contribution to the reward difference instead of simply removing the imbalance. Using only the scores of the current candidate group, it determines a clipping interval that imposes a common upper bound on per-criterion score differences between candidates, limiting the excessive influence of extreme scores while preserving continuous judgment information....

stat.ML · cs.AI

新论文 · v1arXiv:2611.24006

MARS Technical Report

Tong Liu, Chaoqun Hou, Longxiang Xiong, Junhong Lou, Jiaqi Zheng, Qixin Li, Zixin Zhao, Yong Duan 等 17 位作者

原文摘要

Modern industrial recommender systems use multi-stage cascades--retrieval, pre-ranking, ranking, and re-ranking--to narrow millions of candidates to a personalized list. While each stage deploys sophisticated models, pipeline-level decisions on channel activation, quotas, model selection, and score fusion remain engineer-tuned and user-agnostic within each scenario. This report presents MARS (Multi-stage Agentic Recommendation System), extending personalization from individual-stage predictions to full pipeline orchestration. A near-line agent built on fine-tuned Qwen3-0.6B generates per-user configurations--a seven-dimensional action covering pipeline mode, retrieval quotas, model selection, fusion weights, and reranker settings--from a constrained action space. Configurations are validated, cached, and consumed asynchronously; the cascade never waits for LLM inference. Schema checks, fallbacks, and a kill switch ensure serving safety. The policy is trained in three stages: Confidence-aware SFT distills schema-valid generation from a teacher model; Format-Anchored Preference Optimization (FAPO) learns action preferences via ActionMask with posterior weighting; Group Relative Policy Optimization (GRPO) refines the policy through Sandbox replay with a frozen reward model, without exposing exploratory actions to live traffic. Two-week A/B tests across five Taobao scenarios with over ten million daily users show positive gains on all key metrics. The largest reach +5.22% V2P and +7.34% GMV, with positive CTR lifts on both click surfaces. About 20% of requests use a lightweight Minimal mode, and deployment shows 12 ms lower mean serving latency versus production.

cs.IR

版本更新 · v2arXiv:2611.22362

HealthCLBench:Evaluating Context Learning in Health Conversations through Controlled Case Clusters

Ting Yang, Zijing Hong, Chengjie Wang, Peng Wei, Chunxiao Guo, Yun Yue, Xurui Li, Jinqun Guan 等 10 位作者

原文摘要

Complex health conversations require answers grounded in individual information and currently valid evidence. We evaluate health context learning: acquiring, integrating, and applying relevant context during inference with fixed model parameters to answer health questions and respond appropriately to changes in facts, evidence, or task goals. To our knowledge, Chinese-language medical benchmarks have yet to systematically combine explicit contextual difficulties, controlled case variations, and member-specific medical criteria for open-ended answers. We introduce HealthCLBench, comprising 328 controlled clusters, 1,103 cases, and 4,931 rubric criteria across medical consultation and everyday health management. Members share backgrounds while evidence, patient states, or task goals change; each has its own medical scoring requirements. A 70-person medical team annotates and reviews the simulated cases and their rubrics. Human review of 700 full-context responses from the original evaluation yields 90.5% pooled agreement with the original automated judgments at the rubric-item level. We report full-context and query-only results for seven general-purpose models and Ant Afu. Across the eight systems, scores with full context are 11.83 to 31.76 case points and 10.87 to 38.97 geometric cluster points higher than those with the current question alone. GPT-6 Astra leads both full-context metrics at 75.03 and 60.42, followed by Claude Opus 5.5 and Ant Afu. Cross-condition differences describe score changes under the reported evaluation settings. Response comparisons reveal failures in checking historical information, expressing uncertainty when warranted, and ensuring recommendations respect required conditions. The resource supports model comparison and targeted follow-up evaluation.

cs.AI

新论文 · v1arXiv:2611.24004

Space-X: Self-Evolving Spatial Agents Weaving Clues into Evidence Chains

Zijian Zhang, Wenqing Tian, Qiang Liu, Liang Wang

原文摘要

Spatial reasoning connects visual observations, geometric estimates, and linguistic decisions into a coherent derivation. Yet tool-augmented agents often acquire evidence without clear targets, combine outputs under inconsistent object or reference-frame semantics, and misjudge evidence sufficiency. Thus, more tools or calls do not reliably improve reasoning. We introduce Space-X, a spatial-reasoning framework that self-evolves toward complete, continuous evidence-chain construction. An Execution Agent acquires, associates, and judges evidence per problem using role-specific memory. A Control Agent diagnoses evidence-chain breaks from execution traces and jointly revises tools, interfaces, skills, memory organization, and decision rules. This loop co-evolves capability and evidence use: evidence needs guide capability development; usable results guide actions. Across multiple benchmarks, Space-X yields gains with four base models. Relative to baselines, GPT-6-sol improves answer accuracy on ViewSpatial and MMSI by 50.39% and 23.07%, respectively; Gemini-3.8-Flash gains 47.50% and 25.22% on these benchmarks. This provides a unified route from fragmented spatial clues to traceable, derivable answers.

cs.AI