跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 13:28 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 13:57 — 2026-11-08 13:57（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：2026-11-08 13:28最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 12,919 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 13:25（北京时间）
版本更新 · v3arXiv:2512.17581

Medical Imaging AI Competitions Lack Fairness

Annika Reinke, Evangelia Christodoulou, Sthuthi Sadananda, A. Emre Kavur, Khrystyna Faryna, Daan Schouten, Bennett A. Landman, Carole Sudre 等 37 位作者

原文摘要

Benchmarking competitions are central to the development of artificial intelligence (AI) in medical imaging, defining performance standards and shaping methodological progress. However, it remains unclear whether these benchmarks provide data that are sufficiently representative, accessible, and reusable to support clinically meaningful AI. In this work, we assess fairness along two complementary dimensions: (1) whether challenge datasets capture the diversity of real-world clinical data, and (2) whether they are accessible and legally reusable in line with the FAIR principles. To address this question, we conducted a large-scale systematic study of 249 biomedical image analysis challenges comprising 458 tasks across 19 imaging modalities. Our findings reveal limited representation across challenge datasets with respect to geographic location, imaging modalities, and problem types, raising concerns about how well current benchmarks reflect real-world clinical diversity. Despite their widespread influence, challenge datasets were frequently constrained by restrictive or ambiguous access conditions, inconsistent or non-compliant licensing practices, and incomplete documentation, limiting reproducibility and long-term reuse. Together, these shortcomings expose foundational fairness limitations in our benchmarking ecosystem and highlight a disconnect between leaderboard success and clinical relevance.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07994

Reviving the Discarded High-Resolution Feature for Transformer-Based Tiny Object Detection

Zehao Wang, Si Wu, Guiping Cao, Xin Li, Yaowei Wang

原文摘要

Tiny object detection remains challenging because tiny instances occupy only a few pixels, and their fine-grained details are easily lost during feature downsampling. Although the highest-resolution feature preserves rich local details for tiny objects, DETR-like detectors often discard it due to its large computational cost, while directly reintroducing this feature also brings dense background noise. To address this problem, we propose ReDHF, a novel framework that Revives the Discarded High-resolution Feature for tiny object detection. ReDHF has three cooperative components. Cross-Scale Deformable Fusion (CSDF) first constructs a semantically enhanced highest-resolution feature and injects its fine-grained details into the shallow feature under a moderate cost. Ellipse-Guided Shallow Supervision (EGSS) then guides the enhanced feature to learn more reliable classification and localization priors by applying geometry-adaptive auxiliary supervision. Full-Scale Query Interaction (FSQI) further enables decoder queries to access both low-level details and high-level semantic information, allowing them to aggregate richer cues for tiny objects. Extensive experiments show that ReDHF consistently improves multiple baselines across different DETR variants and achieves state-of-the-art performance on the evaluated benchmarks. The best ReDHF variants surpass their baselines by +1.4 AP on AI-TOD-v2, +1.6 AP on VisDrone, and +1.5 AP on SODA-D, with especially notable gains on tiny and small objects.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2511.08371

Multi-objective Hyperparameter Optimization with Expert Priors

Soham Basu, Nastaran Alipour, Frank Hutter, Danny Stoll

原文摘要

While Deep Learning (DL) experts often have prior knowledge about which hyperparameter settings yield strong performance, only few Hyperparameter Optimization (HPO) algorithms can leverage such prior knowledge and none incorporate priors over multiple objectives. As DL practitioners often need to optimize not just one but many objectives, this is a blind spot in the algorithmic landscape of HPO. To address this shortcoming, we propose the novel problem setting of multi-objective HPO with expert priors and introduce PriMO, the first HPO algorithm that can integrate user beliefs over multiple objectives. We show PriMO achieves state-of-the-art performance across 8 DL benchmarks in the multi-objective and single-objective setting. Further, we demonstrate that PriMO remains state-of-the-art at large scales by optimizing a vision-language model over three objectives.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2606.13657

Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation

Guo Yu, Wenlin Liu, Yulan Hu, Hao-Xuan Ma, Jun-Peng Jiang, Han-Jia Ye

原文摘要

On-policy distillation (OPD) has recently become a prominent post-training recipe by combining two desirable ingredients: on-policy student-generated trajectories and dense token-level teacher supervision. Yet how this hybrid training regime shapes a model remains poorly understood. We characterize the sparsity and geometry of OPD parameter updates across several language and vision-language model pairs and application settings. OPD updates are small and coordinate-sparse, while remaining distributed across layers and modules. This sparse support is operationally meaningful: masked training on the discovered subnetwork nearly recovers full-training performance. At the matrix level, the updates are numerically full-rank but spectrally concentrated. Their visible supports avoid coordinates emphasized by the source's principal structure and favor low-magnitude source coordinates, while the source singular-value spectra change little. Together, these findings show that OPD exhibits important weight-space signatures of on-policy post-training despite using dense teacher supervision.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07988

Compression Through a Context Lens: Evaluating Adaptation, Quantization, and Distillation in Arabic Legal LLMs

Md. Rafiul Biswas, George Mikros, Wajdi Zaghouani

原文摘要

Model compression can facilitate the deployment of large language models in resource-constrained legal settings, but its effects on domain-specific performance may depend on the evaluation protocol. We investigate this issue using ArabLegalEval, a Saudi Arabic legal benchmark, under both with-context and no-context evaluation. The former provides supporting legal passages, while the latter assesses performance without external context. Removing the context produces accuracy gaps of up to 27 percentage points for the base model. We examine three stages: domain adaptation, quantization, and knowledge distillation across FANAR-9B, JAIS-8B, and Qwen2.5-7B. Four-bit quantization reduces model memory by 64-71%, with changes in no-context MCQ accuracy ranging from -3.2 to +1.6 percentage points. Distillation produces more variable results, with accuracy generally declining as student size decreases. A Qwen2.5-7B student distilled from FANAR achieves 76.6% no-context accuracy, compared with 77.2% for its teacher. Our findings suggest that no-context evaluation provides a useful complement to context-supported testing when assessing the effects of adaptation and compression on Arabic legal language models.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07984

Technohybridism: Recursive Semantic Normalization in AI-Mediated Societies

Charalampos M. Liapis, Epameinondas Panagopoulos

原文摘要

Language-generating AI systems are no longer only objects of linguistic interaction: their outputs increasingly re-enter the communicative and institutional practices from which their training material was drawn. Drawing on social theory, social epistemology, and the philosophy of language, this article develops a sociotechnical account of that re-entry. We introduce recursive semantic normalization: the process through which machine-generated formulations, once recurrently taken up, evaluated, reused, and institutionally retained, participate in the reproduction and transformation of semantic regularities. Under the heading of technohybridism, we argue that the relevant unit of analysis is the hybrid semantic system, a recursively coupled configuration of human practices, computational generation, and institutional uptake. First, we distinguish the concept from neighbouring accounts, including model collapse, looping effects, machine habitus, machine culture, and the epistemology of AI testimony. Second, we develop an analytical model that separates generation, selection, uptake, and persistence and distinguishes machine-attributable change from change that would have occurred anyway. Third, we analyse uptake as routinized, institutionally diffused, and socially stratified practice and state conditions under which machine-derived regularities become norms. Fourth, we identify social-epistemic consequences: the laundering of provenance that weakens epistemic vigilance, the erosion of the cognitive diversity on which collective inquiry depends, and the narrowing of shared hermeneutical resources. An evidential ladder for empirical research follows. The account attributes no normative authority to machine outputs; what changes is the field within which human and institutional uptake operates.

cs.CY · cs.AI · cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2608.08600

Population-Scalable Multi-Agent World Modeling across Scene Geometries

Renjie Zhao, Yuxiang Wu, Mingyu Zhang, Jiaxin Li, Sisi Li, He Li, Yimin Sheng, Tianxi Tan 等 12 位作者

原文摘要

World models have recently achieved impressive progress in visual prediction and interactive generation, but extending them to multi-agent environments introduces a fundamental scalability challenge. Existing methods generally assume a fixed number of agents during training and inference, which ties the model to a pre-determined agent population and limits inference-time scalability. Our key insight is that cross-view consistency should arise from a shared world state whose evolution does not assume a predefined number of agents, while agent-specific observations should be generated by querying this state through a unified rendering interface. Based on this insight, we propose Khora, a scalable multi-agent world model that supports inference-time expansion to arbitrary numbers of agents without retraining. Our framework decouples world-state evolution from visual rendering and introduces a population-agnostic rendering mechanism for incorporating other agent information. This design maintains cross-view consistency through the shared world state rather than through dense interactions among observation streams inside the expensive video generator, enabling approximately linear practical scaling with the number of queried views. Qualitative experiments demonstrate that our approach generalizes to unseen numbers of agents while maintaining visual quality and multi-agent consistency. We further implement a real-time interactive system to demonstrate scalable open-world simulation.

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07980

Solving Linear Programs in the Matrix Multiplication Time

Zhao Song

原文摘要

We give a randomized algorithm for feasible bounded-box linear programs with $n$ variables and $d\le n=O(d)$ linearly independent equality constraints. For additive accuracy $ε$, its expected running time is $O((n^ω+n^2\log n)\log(1/ε))$, where $ω$ is the matrix multiplication exponent. This answers the matrix-multiplication-time open question posted in Song's Ph.D. thesis [Son19] in this setting.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07979

Perception Over Geometry: Rethinking Gaussian Allocation in Mesh-based Splatting

Yuting Wang, Yang Zhao, Shanding Diao, Penglin Wang, Yuan Chen, Wei Jia, Ronggang Wang

原文摘要

3D Gaussian Splatting (3DGS) enables photorealistic novel-view synthesis but lacks explicit topology for geometric editing. Existing mesh-based methods enable geometric manipulation by associating Gaussians with triangular mesh faces, typically assigning a fixed number of Gaussians to each face. However, the representation capacity required for appearance reconstruction depends on local appearance complexity rather than merely on mesh tessellation density. To address these limitations, we propose P-MGS, a framework that separates appearance modeling from geometric control to achieve high quality rendering, compact representation, and flexible mesh editing. P-MGS introduces a perceptual complexity guided allocation strategy that distributes Gaussians according to surface appearance demand estimated from multiview observations. To preserve reconstruction flexibility, Gaussians are optimized without mesh constraints and subsequently associated with the original mesh through post hoc binding, retaining adaptive refinement while preserving mesh topology. During mesh editing, local affine deformation transfer updates Gaussian centers and covariances under mesh deformation, reducing misalignment and floating artifacts. Experiments demonstrate superior average novel view synthesis quality with fewer Gaussians and coherent mesh editing.

cs.GR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07976

QRAE: Query-Relevant Attention Entropy for Context Compression in DeepSearch Agents

Yingjie Tan, Haiquan Qiu, Quanming Yao, Manyi Zhong, Xianzhi Yu, Yaqing Wang

原文摘要

DeepSearch LLM agents repeatedly search and carry retrieved sources into subsequent reasoning steps. This expanding context increases token consumption and latency, although many results do not contribute to later reasoning. We propose Query-Relevant Attention Entropy (QRAE), an online context compression method that uses sparse evidence-assessment heads to decide which intact retrieved chunks should persist across reasoning steps. It scores bounded candidate batches through paired prefills: a query-free control suppresses shared attention responses, while normalized entropy measures the breadth of the positive response within each chunk. High-scoring chunks enter a persistent evidence whitelist and are included in the reasoning context. Uncertain chunks remain outside the reasoning context but are retained in a candidate cache, where they can be retrieved for later reevaluation. QRAE requires neither an additional generative compression pass nor modification of the attention operator. Across multiple DeepSearch benchmarks and reasoning models, QRAE improves task success by an average of 2.35 percentage points and reduces end-to-end latency and reported token usage by an average of 30% and 45%, respectively. These benefits generalize to a model with nearly 100B parameters.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07977

Stealthy Malicious Interference Detection in UAV Formations: A Power-Domain Signaling Game Approach

Jianle Ba, Shaolong Guo, Yuntao Wang, Xin Wu, Zhou Su, Zhendong Li

原文摘要

Reliable intra-swarm communication is fundamental to cooperative sensing, control, and mission execution in unmanned aerial vehicle (UAV) swarms. In open low-altitude shared-spectrum environments, coexisting UAVs may cause benign interference through spectrum reuse and signal leakage, while jamming UAVs may deliberately degrade critical intra-swarm links. Since a jamming UAV can adjust its transmit power to disguise signal-to-interference-plus-noise ratio (SINR) degradation as link fluctuation in benign interference, stealthy jammer UAV detection remains a challenge. In this paper, we propose a novel belief-driven stealthy jammer UAV detection scheme from the perspective of Bayesian security game. To capture stealthy interference in shared-spectrum UAV swarms, the interfering UAV is modeled as a hidden benign or jamming type, whose transmit power strategy induces the SINR observed by the defender. The defender updates its posterior belief from the observed SINR and decides whether to maintain normal operation or trigger defensive power boosting. We characterize pure-strategy perfect Bayesian equilibrium (PBE) conditions under separating structures with distinguishable type and pooling structures with indistinguishable observations. Numerical results show that the proposed scheme improves the defender's expected utility compared to the conventional schemes.

cs.CR · cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.02851

Streaming Persistent 3D Gaussian Proxies for View-Flexible Remote Rendering

Matti Siekkinen, Teemu Kämäräinen, Ahmad Alhilal

原文摘要

Cloud rendering executes demanding real-time graphics on a remote server, but conventional video transmission constrains the displayed image to the server-rendered viewpoint. Image-space warping can compensate for client motion during transport and display latency, although its accuracy decreases with pose offset. We investigate an alternative approach in which the server constructs a persistent, client-renderable 3D Gaussian proxy online from game-engine render buffers and progressively transmits independently renderable spatial tiles. Our Unity prototype supports continuous optimization and expansion, approximate relighting, and engine-tracked rigid-object motion, while the client renders locally from its current viewpoint. We evaluate four scenes under controlled pose offsets and encoded walkthroughs, comparing the proxy with stale server-rendered frames, depth-assisted warping using HEVC with one, three, or five reference views. The proxy maintains stable quality as pose offset increases. At 50 Mbit/s, it achieves higher SSIM than all evaluated warping configurations at 367 ms on all four scenes and at 183 ms on three of the four scenes. The results identify complementary operating regimes: image warping is effective at small pose offsets, conventional video is rate-efficient when only the server-rendered viewpoint is required, while the persistent proxy provides robust viewpoint flexibility when the original renderer cannot be executed at the client.

eess.IV · cs.GR · cs.MM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07973

Tight Asymptotic Bounds on the Maximum Number of Linear Regions of Piecewise-Linear Kolmogorov--Arnold networks

Ye Su, Yong Liu

原文摘要

Schoots et al.~\citep{schoots2025relating} (AISTATS 2025) established a generally loose upper bound on the number of linear regions of continuous piecewise-linear (CPWL) Kolmogorov--Arnold networks (KANs), without providing a lower bound. We consider a $T$-layer network with width vector $\mathbf n=(n_0,\ldots,n_T)$, input dimension $n_0=d$, output width $n_T=1$, and at most $k\geq2$ affine segments per edge. Our matching upper and lower bounds determine the tight growth order $Θ_{\mathbf n}(k^{\sum_{\ell=1}^{T}ρ_{\ell-1}})$ in $k$, where $ρ_{\ell-1}:=\min_{0\leq s\leq\ell-1}n_s$. When every hidden width is at least $d$, the tight order simplifies to $Θ_{\mathbf n}(k^{dT})$. The upper bound of \citep{schoots2025relating} is $k^{\sum_{\ell=1}^{T}n_{\ell-1}n_\ell}$. Our upper bound improves it by a factor of $Θ_{\mathbf n}\!\left(k^{\sum_{\ell=1}^{T}n_{\ell-1}n_\ell-\sum_{\ell=1}^{T}ρ_{\ell-1}} \right)$, with strict asymptotic improvement whenever a hidden layer has width greater than one. We further compare CPWL KANs with rectified linear unit (ReLU) networks using dense parameterizations with at most $Λ$ parameters per model and the same fixed nonlinear depth $T$. Counting trainable knot locations and optimizing the widths and $k$, we prove that the maximum region count of CPWL KANs divided by that of ReLU networks is $Θ_{d,T}(Λ^{d\lfloor T/2\rfloor})$ as $Λ\to\infty$, yielding a polynomial advantage for KANs when $T\geq2$. These tight bounds characterize the attainable geometric complexity of CPWL KANs, providing a foundation for understanding their expressive power and guiding architectural design.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07972

A Little Derandomization Goes a Long Way: Unconditional Circuit Lower Bounds using Low-Degree PIT

Nikolai Chukhin, Karthik Gajulapalli, Alexander Golovnev, Ivan Mihajlin

原文摘要

We prove unconditionally that either NE contains a language requiring Boolean circuits of size at least $2^n/(2n)$, or $VP^0_{\mathbb{Z}}\ne VNP^0_{\mathbb{Z}}$, a constant-free version of Valiant's conjecture over the integers. The Boolean alternative implies that $NP\not\subseteq SIZE[n^k]$ for every constant $k\ge1$. Our proof gives a fine-grained variant of the connection between Polynomial Identity Testing (PIT) and circuit lower bounds established by Kabanets and Impagliazzo (2004). We show that the specific identity tests required by this argument can be performed over the integers without a derandomization assumption. Over a fixed finite field $\mathbb{F}$, we first give a deterministic $O(st^{d-1})$-time algorithm for PIT on size-$s$ circuits computing degree-$d$ polynomials in $t$ variables. We further show that, for any fixed $d\ge2$ and $\varepsilon>0$, improving this running time by a factor of $t^{\varepsilon}$, even nondeterministically, implies either the same Boolean lower bound or an arithmetic circuit lower bound of $t^{1+\varepsilon/2}$ for a polynomial family from $VNP_{\mathbb{F}}$. If nondeterministic PIT instead runs in time $s^{o(d)}t^{(1-\varepsilon)d}$ for infinitely many degrees $d$, then the arithmetic lower bound strengthens to $VP_{\mathbb{F}}\ne VNP_{\mathbb{F}}$. Over the integers, we give a deterministic PIT algorithm for syntactically set-multilinear circuits running in time $s^{O(1)}t^{5d/6}$, which yields the unconditional result above. Combining the Kabanets-Impagliazzo argument with range avoidance, we show that an NP algorithm for PIT over $\mathbb{Z}$ gives a purely arithmetic win-win: either $VP_{\mathbb{Z}}\ne VNP_{\mathbb{Z}}$, or constant-degree polynomials of maximum circuit complexity can be constructed in FNP.

cs.CC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.41697

TSBPO: Tree-Structured Branching for Policy Optimization in Interactive Language Agents

Rui Yu, Chong Mu, Jinchuan Zhang

原文摘要

Terminal feedback in multi-turn agent training leaves both rollout allocation and local credit underdetermined. Dynamics-Predictive Sampling (DPS) [9] provides a task-level predictive sampling reference, but interactive agents also need to choose which visited states merit further continuations. We introduce TSBPO with two method components. A lightweight, fine-grained Root/Branch budget allocator distributes factual rollouts across tasks and additional suffixes across replayable states using likelihood-fitted estimates of terminal-outcome contrast. On the resulting physical rollout trees, a tree-aware step-level credit assignment algorithm compares immediate sibling segments and assigns their local outcome contrasts to the turns they contain. Exact task/observation groups provide a complementary step term. The allocator selects what to sample; observed outcomes determine the subsequent credit. With a Qwen2.5-1.5B actor, fixed checkpoints attain 97.79% seen and 96.64% unseen stochastic success on ALFWorld, and an 81.07% per-episode success rate over six stochastic episodes for each of the 500 WebShop test goals. At the WebShop update-100 checkpoint, removing the observation-group step term yields 75.93% under the same evaluation. These results describe the evaluated training configurations on two interactive benchmarks.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.04992

ContractLens: Latent Security Knowledge for Malicious Smart Contract Detection

Shuyi Miao, Xinyi Huang, Wangjie Qiu, Fei Shen, Jinchun He, Zhiming Zheng, Tat-Seng Chua

原文摘要

Detecting malicious smart contracts is essential to safeguarding the Web3.0 ecosystem. However, existing auditing methods based on large language models (LLMs) largely rely on prompt engineering or attack-specific fine-tuning, while the internal representations that support malicious logic detection remain poorly characterized. To address this gap, we propose ContractLens, a framework that localizes and uses latent security knowledge in pretrained LLMs for interpretable malicious smart contract detection. Specifically, we first use layerwise linear probes to identify candidate layers that distinguish malicious from benign contracts, then select critical layers based on their sensitivity to malicious logic removal and stability under behaviour-preserving surface modifications. Next, within these critical layers, we combine activation contrast, malicious-logic specificity, and probe weights into a tri-factor importance score and adaptively select malicious contract-discriminative units (MCDUs) using the knee point of the ranked score curve. Finally, we concatenate the selected units' activations into a compact representation and train a lightweight classifier for detection, keeping the pretrained model frozen throughout. Neuron masking experiments show that masking MCDUs causes larger drops in detection performance than masking randomly selected neurons or neurons matched in activation magnitude. ContractLens achieves higher average detection accuracy than the evaluated methods on all three pretrained models. Further evaluations demonstrate generalization to unseen malicious intents and show that, with the identified MCDUs fixed, a classifier trained on few labelled samples can still achieve strong detection performance.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07964

Time-Indexed Skill Success Models for Latency-Aware Skill Selection and Timing in Dynamic Manipulation

Mohsen Omidi, Maria Chiara Leva, Brian Vaughan

原文摘要

Robots that manipulate moving objects act on observations that are outdated when the chosen skill starts, and the best skill can change within a few hundred milliseconds. Skill competence models, however, predict success for a launch at the moment of observation. We propose time-indexed skill success models, which predict whole-task success when a skill is launched after a given delay. Trained on rollouts branched at a grid of launch delays, they let a receding-horizon planner select both the skill and its launch time under fixed or random latency. In a MuJoCo study in which a UR5e captures a sliding puck with three skills, the planner exceeded a static competence model by 2.8 to 6.2 percentage points at 100 to 300 ms of latency, including when that model was evaluated on point or sampled forecasts of the launch state. Across five complete runs (three training seeds and two distribution shifts), all 80 paired 95% intervals against four baselines excluded zero. On delayed launches, the time-indexed model was calibrated (expected calibration error 0.009 against 0.239), and pausing the world during latency overstated success by up to 23 points. On a real UR5e that captures a rolling ball after 0.2 s of injected latency, a static model trained in a hardware-matched simulator predicted 99% success on a prespecified subset of 35 delayed launches that it rated at least 0.8. Of these, 63% succeeded (95% interval 46 to 77%), and the time-indexed model predicted 56%. In this single-skill, predictable regime, a matched physics-based forecast was also well calibrated.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07962

TCSExam: Evaluating Frontier LLMs on the Full Range of TCS Research

Yifan Luo, Zhengying Liu, Yang Yuan, Zhilin Yang, Andrew Chi-Chih Yao

原文摘要

Can large language models (LLMs) advance theoretical computer science and resolve its long-standing open conjectures? To study progress toward this goal, we introduce TCSExam, a unified framework and benchmark covering the full range of TCS research. It evaluates theorem proving, solver engineering, and constructions alongside direct attempts to resolve open conjectures, capturing both concrete research accomplishments and progress toward long-standing research goals. TCSExam-Full contains 100 expert-reviewed tasks, with submissions checked by the Lean kernel or an executable task checker. TCSExam-Lite selects 20 tasks, five per track, reducing the number of task attempts by 80% at the same per-attempt budget. We evaluate eight agents on Full and nine on Lite. The TCSExam Index combines all four tracks: GPT-6 Astra leads Full (71.9), and Opus 5.5 leads Lite (72.3). Full and Lite rankings are strongly aligned across eight shared agents (Spearman's $ρ=0.93$), supporting Lite as a compact, discriminative benchmark. The evaluations yield improved solver outputs and mathematical constructions, together with independently verified special cases and bounds from open-conjecture attempts. TCSExam provides an extensible framework with task sources, Docker build recipes, and evaluation tools for reproducible use.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07961

Bri3D: Bridging the Object-Scene Gap in Single-Image 3D Generation via Scene-Anchor

Hongye Hou, Shuai Zhang, Hongjie Li, Zhuoxiao Li, Haiping Wang, Yuan Liu, Wufan Zhao

原文摘要

Generating compositional 3D scenes from a single image requires recovering detailed object geometry and coherent spatial arrangements. Existing object-to-scene methods, including SAM3D and MIDI, extend object generation through image-context reasoning or inter-instance modeling. Coordinating objects remains challenging with limited scene-level supervision. Directly extending object-centric generators to entire scenes can degrade geometry and fail to preserve instance scale, orientation, and pose. We propose Bri3D, a framework bridging scene-level structural reasoning and object-level generative priors through instance-aware voxel scene anchors. Bri3D predicts a color-coded scene scaffold encoding coarse object geometry and spatial arrangements. Each instance is extracted as a scene anchor and refined into a pose-preserving, prior-compatible voxel support, enabling a frozen object generator to synthesize detailed textured geometry in the anchor-defined spatial reference. This coarse-to-fine design separates scene organization from object-scale detail synthesis, focusing scene-level training on spatial organization and anchor refinement while reusing pretrained object priors. Experiments demonstrate improvements in scene layout, object geometry, visual quality, and generalization. Bri3D predicts scene layouts efficiently; full scene generation is faster than SceneGen and SAM3D.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07959

CoRD: Coupled Rollouts Fill the Blind Spot of On-Policy Distillation

Guhan Chen, Bohan Li, Jun Rao, Hejin Wang, Songtao Tian, Yexin Xie, Xiaojun Meng, Peng Yuan 等 11 位作者

原文摘要

On-policy distillation trains a student on its own rollouts, so states the teacher would reach but the student does not are seldom supervised. We introduce CoRD (coupled-rollout distillation), which keeps the on-policy loss and moves only the distribution of training states toward the teacher, drawing rollouts from a geometric interpolation of student and teacher through the maximal coupling of speculative decoding. The coupling keeps the student's token wherever the two distributions agree and otherwise substitutes a token from the part of the target the student underweights, so interventions are as rare as any exact sampler allows and recede as the student learns. Across six base students from two model families (Qwen3 and Qwen3.5, 0.6B to 4B), CoRD raises average pass@1 over on-policy distillation by 0.9 to 2.0 points and pass@8 by 1.2 to 3.4 points on five public math benchmarks at equal steps and data. On frozen teacher-reached states, a 4B student trained with CoRD reaches in 16 steps a gap closure that on-policy distillation does not reach in 80, and substitution rules intervening at least as often in other directions fall short of CoRD.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07955

Rotation Is Token-Blind: A Structural Criterion for Post-Training Quantization of Feed-Forward Geometry Transformers

Huanfei He, Bohao Zhang, Jiaxin Zhang, Wei Sui, John See, Zeyd Boukhers, Cong Yang

原文摘要

Feed-forward 3D models use Transformers to predict camera poses, depth, and structure in one pass, avoiding iterative multi-view optimization. Long sequences and deep attention incur high compute and memory costs, motivating Post-Training Quantization (PTQ) for deployment. Existing PTQ methods mainly suppress channel-wise outliers by smoothing or orthogonal rotation. Geometry Transformers introduce a different challenge: heterogeneous token types share one activation quantization grid. A few special tokens may exert high leverage over global outputs and be updated by only a subset of blocks. Token-blind transforms, which apply the same transformation to every token, reduce overall quantization error but cannot remove differentiated degradation across token types. We propose QMapAnything, a structure-aware PTQ framework. We cast floating-point-preserving rotation and smoothing as a token-blind reparameterization group, and prove that they yield common-mode gains while leaving relative token SNR unchanged. We introduce a statistic $Γ$ that combines a special token's quantization disadvantage and output leverage to predict whether differentiated bias correction is needed beyond rotation. Experiments on geometric benchmarks show that W4A8 closely matches full-precision performance. Under W8A8, peak memory falls by $2.2$--$3.1\times$ versus FP32, with up to $3.1\times$ speedup on real hardware. These results provide a principled and efficient approach to deploying feed-forward 3D reconstruction models in resource-constrained edges.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:1803.06878

Parameterized Complexity of Fair Vertex Evaluation Problems

Dušan Knop, Tomáš Masařík, Tomáš Toufar

原文摘要

Graph modification problems form a unifying framework for many classical graph problems, where the goal is to remove a minimum number of vertices so that the resulting graph satisfies a desired property $π$. In this work, we replace the classical objective of minimizing the solution size with the fair objective [Lin&Sahni: Fair edge deletion problems. IEEE Trans. Comput. 89], which minimizes the maximum number of deleted neighbors incident to any vertex. This fairness criterion aims to distribute deletions evenly across the graph and leads to new algorithmic and complexity challenges. We study fair deletion and evaluation problems in the logical setting, where the target property~$π$ is defined by a formula in a logic $\mathsf{L}$. In particular, we consider the Fair $\mathsf{L}$ Vertex Evaluation problem, which asks whether there exists a vertex set $W$ of bounded fair cost such that a given formula $\varphi(X)$ holds in the input graph $G$. Our main result is an FPT algorithm for the Fair MSO$_1$ Vertex Evaluation problem with one free variable, parameterized by the twin cover number of the input graph and the quantifier length of the formula. We further show that extending this result to formulas with $\ell$ free variables is unlikely: the $\ell$-Fair FO Vertex Evaluation problem is W[1]-hard for parameter $\ell$ even on graphs of twin cover one. As a concrete case study, we investigate the Fair Vertex Cover}\ problem, one of the simplest fairness-aware graph problems. We prove that it is W[1]-hard when parameterized by the combined treedepth and feedback vertex set, but admits an FPT algorithm for the parameter modular width.

cs.CC · cs.DS · cs.LO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.14414

CytoBERT: A Foundation Model for Cytometry Data

Syed Abdul Haseeb Qadri, Bjarne C. Hiller, Felix Blanke, Vanja Sophie Cangalovic, Kutalmış Coşkun, Amin Mirzaei, Tom Siegl, Sebastian Bader 等 10 位作者

原文摘要

Cytometry measures the complex characteristics of single cells (e.g., counts and protein expression of immune cells) and is widely used across immunological research and clinical settings. However, cytometry data is highly heterogeneous and unstandardized due to experimental protocols and the choice of measured features. While machine learning methods hold the potential to gain deeper insights into cell biology, these challenges make them difficult to apply and transfer across studies. Recent advances in foundation models can alleviate these issues, but corresponding approaches are still scarce in this field. To address this, we provide CytoBERT, a publicly available, open-source, open-weight foundation model for single-cell cytometry data with variable marker panels. CytoBERT is pretrained in a self-supervised manner on a large-scale cytometry corpus (15 human datasets with heterogeneous marker panels and more than 50 million cells) curated through marker standardization, enabling it to learn transferable inter-marker relationships within cells. Fine-tuning CytoBERT for sample-level classification demonstrates that transfer learning across heterogeneous cytometry datasets is feasible, providing a starting point for scalable, generalizable cytometry analysis. Code is available at GitHub.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.23183

Dequantization Barriers for Guided Stoquastic Hamiltonians

Yassine Hamoudi, Yvan Le Borgne, Shrinidhi Teganahally Sridhara

原文摘要

We construct a probability distribution, induced by the Perron--Frobenius eigenvector of an exponentially large graph, that cannot be efficiently sampled by any classical algorithm, even when given the best-possible warm-start distribution. In the quantum setting, this problem can be viewed as preparing the ground state of a stoquastic Hamiltonian given a guiding state as input, and is known to be efficiently solvable on a quantum computer. We further show that even estimating the ground-state energy of that Hamiltonian remains classically hard. Our results suggest that no efficient classical algorithm can solve a broad class of stoquastic ground-state problems. Our graph is constructed from a class of high-degree, high-girth spectral expanders (such as the LPS Ramanujan graphs) to which self-similar trees are attached. This builds on and extends prior work of Gilyén, Hastings, and Vazirani (Quantum 2021, STOC 2021), which ruled out dequantization for a specific stoquastic adiabatic path algorithm. We strengthen their result by ruling out any classical algorithm for guided ground-state preparation or energy estimation, while also providing a derandomized construction.

quant-ph · cs.CC · cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07953

A Behavioural Framework for Predicting and Understanding Loss of Control in Frontier Artificial Intelligence Systems

Yao Huang, Yichi Zhang, Yifan Wang, Yitong Sun, Haoyu Dong, Jifan Ma, Jinzhe Tu, Xiaojian Li 等 11 位作者

原文摘要

Frontier artificial intelligence (AI) systems are increasingly operating over longer horizons with diminishing human oversight, raising the risk of loss of control: systems acting beyond effective human control with potentially irreversible consequences. Because such failures may become observable only after containment is difficult, they must be assessed prospectively. We introduce a behavioural framework that decomposes loss-of-control risk into three factors: misaligned motive, harm-enabling capability, and monitoring evasion. We operationalise these factors through 13 measurable aspects and 29 evaluation tasks, whose scores are combined into a single loss-of-control (LoC) score. Across 13 frontier models, the LoC score shows strong prospective validity, correlating with failure rates in contained long-horizon risk scenarios (Pearson r = 0.84). Risk varies systematically across models and cannot be explained by capability alone. We further show that the framework can guide targeted mitigations: fine-tuning and monitoring directed at diagnosed vulnerabilities reduce failure rates while largely preserving general performance. These results provide a practical basis for predicting, understanding, and mitigating loss-of-control risk before it materialises.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07951

Requirements Nobody Wrote Down: Emergence in a Public-Sector ML Pipeline

Ronivaldo Ferreira, Vinicius Costa Girard, Cleidson de Souza, Igor Steinmacher, Carla Aguiar, Filipe Roseiro Cogo, Gustavo Pinto

原文摘要

Governments increasingly use machine learning (ML) to handle data volumes beyond their analytical capacity, yet little is known about how requirements arise and evolve as an ML experiment moves toward operational use. Requirements Engineering (RE) for ML often assumes that requirements can be elicited upfront; in the public sector, however, demands arrive vague, stakeholders speak different professional languages, and what counts as a ``good'' result is unknown in advance. We report a 15-month case study of a thematic classification pipeline for Brazil's national digital participation platform, which holds over 60,000 citizen proposals, triangulating 43 project artifacts with interviews of six project participants. Institutional demands arrived as broad goals, endorsed but not sponsored, and only 40\% of the 95 reconstructed requirements and criteria were ever formalized. The pipeline's key requirements emerged largely from experiments, model outputs, and integration work, shaped by technical decisions and institutional constraints; the central one, the classification categories, was settled by a government taxonomy chosen for its institutional legitimacy. Acceptance relied on technical metrics, domain judgment, and political assessment, without shared thresholds or validation of usefulness in practice. In public-sector ML, technical and institutional artifacts thus act as elicitation instruments, and experimentation and integration belong to the requirements process.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07950

Leakage- and Label-Aware Benchmarking of Class-Imbalance Strategies for Multimodal Chest X-Ray and EHR Classification

Dang-Khoa Bui, Quang-Huy Tran, Minh-Khoi Nguyen-Bui, Duc-Tuan Ngo, Thanh-Trong Tran, Tuan-Khoi Nguyen, Hoang-Anh Ngo

原文摘要

Benchmarks of class-imbalance strategies for multimodal chest X-ray (CXR) and electronic health record (EHR) prediction are often evaluated on record-level splits of cohorts in which one patient contributes several radiographs. We audit such a benchmark on 29,083 MIMIC-CXR radiographs of 10,479 patients with eight diagnosis targets. First, the record-split benchmark was misleading: a lookup table that copies the label of a development-set radiograph with the same EHR vector nearly matched the best model, and on unseen patients every model fell to the level of predicting every case positive. Second, tracing the labels back to MIMIC-IV explained why: each patient's labels are keyword matches on the diagnosis codes of a single admission, copied, with one EHR vector per patient, to all of the patient's radiographs, so about a third of the radiographs carry labels that differ from the codes of their own admission. Third, under patient-separated evaluation with admission-aligned and rule-refined labels, the initial conclusions do not hold: in the evaluated configurations no imbalance strategy raised the observed mean macro F2 over no augmentation by more than 0.01, tuned tree ensembles showed no consistent advantage over tuned logistic regression, and the released EHR variables stayed at the level of the all-positive baseline, whereas the diagnostic history available at imaging time and image embeddings exceeded it, including, with rule-refined labels, a CheXpert-trained encoder that never saw these radiographs; RAD-DINO had seen 96.6% of them during self-supervised pretraining. Adding either encoder to the diagnostic history gave no statistically significant F2 gain; exploratory AUROC gains were significant with RAD-DINO but not with DenseNet. We provide reusable diagnostics, a leakage-aware protocol and a checklist.

cs.LG · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07949

Beyond the Keyword: A Human-Annotated Benchmark for Arabic Anxiety-Related Discourse

Shimaa Ibrahim, Mabrouka Bessghaier, Md. Rafiul Biswas, Insaf Elouard, Wajdi Zaghouani

原文摘要

Keyword retrieval returns expressions of personal anxiety together with many other uses of anxiety-related language. We present a benchmark of 1,000 Arabic Twitter/X posts retrieved with the keyword qalaq ("anxiety/worry") and annotated for six discourse functions. Two native Arabic-speaking annotators labeled every post independently, reaching 51.1% raw agreement (Cohen's $κ= 0.378$). We then reviewed all 489 disagreements and all 511 agreements under the same guidelines. The review changed 120 of the agreed labels (23.5%), which shows that agreements need auditing as well as disagreements. The final labels form a consensus reference; on a random sample of 200 posts, an additional annotator agreed with it on 60.5% of posts ($κ= 0.517$). Against this reference, Fanar-C-2-27B reaches 79.8% accuracy and macro-F1 0.784 ($κ= 0.749$). Its errors concentrate in the residual category (41.1% of errors; precision 0.905, recall 0.447), whose definition is internally inconsistent in the executed prompt, so the low recall cannot be attributed to the model alone. Sociopolitical Anxiety (27.1%) outnumbers Personal Emotional Expression (22.0%); these are assignment proportions in the sample, not estimates of prevalence or retrieval precision. We release the guidelines, a residual-subtype scheme, a fixed data split, label provenance, and evaluation code.

cs.CL · cs.SI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07948

Circe: Training-Free LLM Self-Evaluation via Component Interaction Consistency

Shuyi Miao, Zheng Li, Xu Xie, Linrui Xu, Fei Shen, Xiaoyu Du, Tat-Seng Chua

原文摘要

As large language models (LLMs) are increasingly deployed in real-world applications, evaluating the correctness of their responses is crucial for reliable use. However, such evaluation is challenging because reference answers are rarely available in practice. Existing reference-free methods mainly rely on output signals, which may assign high scores to incorrect responses and thus do not necessarily reflect correctness. This motivates exploring the model's internal computation for complementary correctness signals. Recent studies exploit internal states, but they mainly analyze hidden-state trajectories across layers, which record only the combined updates of attention and feed-forward networks (FFNs) and overlook how these components interact. We therefore propose Circe, a training-free self-evaluation method that assesses a response using both internal and external signals, without reference answers or repeated sampling. For internal signals, we first introduce component interaction consistency (CIC), which measures the directional alignment between attention updates in earlier layers and attention-induced FFN output changes in later layers. We further incorporate representation geometry (RG) to characterize normalized displacement and angular changes along layerwise hidden-state trajectories. For the external signal, we convert the mean negative log-likelihood of generated tokens into a bounded likelihood confidence (LC) score. Finally, we fuse CIC, RG, and LC into a unified correctness score. Experiments on five LLMs and six benchmarks across four domains show that our method distinguishes correct from incorrect responses more effectively than existing baselines, and generalizes to multilingual, multimodal, and open-world settings.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07947

ChemE-as-Code: An Open-Source Platform for Agentic AI in Chemical Engineering

Artur M. Schweidtmann

原文摘要

ChemE-as-Code provides an open-source environment in which AI agents built on large language models (LLMs) can carry out chemical engineering work and engineers can check it. Its calculation tools range from catalysis through process simulation to plant layout, HAZOP and life cycle assessment, and skills tell a general-purpose agent how to use them. Engineering files are linked, machine-readable and versioned in Git; calculations run outside the LLM, each value records its origin, and automated checks report inconsistencies and out-of-date results by file and line. In an illustrative ammonia case, agents developed a written task into a preliminary basic-engineering package (simulation files, P&IDs, layout, HAZOP, datasheets, relief) for USD 224 of API cost in the design sessions. Planted faults and engineering changes show that the checks find what their rules cover and miss the rest, so they guide human review rather than replace it. No independent engineer has reviewed the design.

cs.AI

查看论文
arXiv ↗PDF ↗