跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

arXiv 最近完成扫描:2026-11-22 08:44 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 11:19 — 2026-11-22 11:19(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:2026-11-22 08:44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 21,490 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 08:42(北京时间)
版本更新 · v2arXiv:2605.01919

Refining and Repairing Signed Distance Data With Global Consistency

Letao Chen, Sanju Mupparaju, Christopher Batty, Silvia Sellán, Oded Stein

原文摘要

We propose a method to interpolate exact Signed Distance Function (SDF) data from a discrete set of samples. Unlike prior work, our approach ensures that the new SDF data values are fully consistent with the input and each other, such that the augmented data still corresponds to a geometrically realizable surface. We express the theoretical properties of exact SDFs as hard geometric constraints, and construct an efficient greedy algorithm for consistent SDF interpolation that is made even faster with powerful parallelized GPU preprocessing. We exemplify the usefulness of our method by evaluating it on three practical applications: global SDF refinement, in which the SDF data is upsampled without knowledge of the ground truth; mesh reconstruction, where our method can reconstruct highly detailed surfaces using global information from coarse input SDFs; and repair of pseudo-SDFs, which result from many pipelines such as CSG Boolean operations and must be turned into valid SDFs for downstream processing tasks. Our refined SDFs are guaranteed to be consistent with the input, where previous methods have no such guarantee.

cs.GR

版本更新 · v4arXiv:2510.01632

BioBlobs: Unsupervised Discovery of Functional Substructures

Xin Wang, Kaiwen Shi, Carlos Oliver

原文摘要

Protein function is often localized to cohesive substructures, such as catalytic triads, binding pockets, and structural motifs, that occupy only a small fraction of a protein's residues. Yet existing predictive pipelines typically aggregate residue-level embeddings and do not explicitly model or infer these functional substructures, leaving the central biological question unanswered: which substructure of a protein is responsible for its function? We introduce BioBlobs, an encoder-agnostic, end-to-end differentiable framework that compresses a protein into a small set of cohesive substructures (blobs) and predicts function from these blobs alone, so that each blob corresponds to a candidate functional region. Across diverse protein function prediction tasks and both sequence-only and structure-aware protein language models, BioBlobs is competitive with strong baselines while operating on only a small fraction of residues. Trained only on protein function labels, BioBlobs recovers expert-curated functional sites in InterPro and experimentally annotated catalytic sites in the Mechanism and Catalytic Site Atlas, demonstrating unsupervised functional substructure discovery and opening a path to large-scale functional site discovery in unannotated proteins. The discovered blobs adapt their spatial scale to the task, ranging from local catalytic sites to entire structural domains. Code is available at https://github.com/OliverLaboratory/BioBlobs.

q-bio.BM · cs.AI

版本更新 · v4arXiv:2601.21636

Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation

Jan Schuchardt, Nikita Kalinin

原文摘要

We study privacy amplification for differentially private model training with matrix factorization under random allocation (also known as the balls-in-bins model). Recent work by Choquette-Choo et al. (2025) proposes a sampling-based Monte Carlo approach to compute amplification parameters in this setting. However, their guarantees either only hold with some high probability or require random abstention by the mechanism. Furthermore, the required number of samples for ensuring $(ε,δ)$-DP is inversely proportional to $δ$. In contrast, we develop sampling-free bounds based on Rényi divergence and conditional composition. The former is facilitated by a dynamic programming formulation to efficiently compute the bounds. The latter complements it by offering stronger privacy guarantees for small $ε$, where Rényi divergence bounds inherently lead to an over-approximation. Our framework applies to arbitrary banded and non-banded matrices. Through numerical comparisons, we demonstrate the efficacy of our approach across a broad range of matrix mechanisms used in research and practice.

cs.LG · cs.CR · stat.ML

新论文 · v1arXiv:2611.10202

Semiprime Factorization with Discrete Diffusion and Beam Search: Scaling Laws

Brendan O Donoghue, Nenad Tomasev, Volodymyr Mnih, Timothy Nguyen, Dalin Guo, Arun Nair, Kenneth Yang, Alexandre Frechette 等 15 位作者

原文摘要

We demonstrate that transformer architectures trained with discrete denoising diffusion and decoded via guided test-time beam search can learn to recover the prime factors of semiprime integers directly from data. Our approach establishes a new frontier for learning-based semiprime factorization, successfully factoring 68-bit integers-a substantial advance over the prior 56-bit state of the art. While computationally less efficient than classical factoring algorithms, our model requires no domain-specific number-theoretic priors and learns purely from training examples. In practice, the diffusion model acts as a generative prior, identifying promising factor candidates where exact verification or lattice-based post-processing can complete the factorization. Furthermore, we derive empirical scaling laws relating approximation quality to training data volume, model size, and test-time computation. In contrast to language, problem size is the key driver of scaling behavior. Achieving a fixed accuracy on a held-out test set requires compute that scales exponentially with bit length. Consequently, our findings pose no threat to security, as the projected compute cost required to factorize cryptographically relevant integers remains prohibitive.

cs.LG

版本更新 · v2arXiv:2609.30667

StarWM: Self-Supervised Trained Attention Routing for Robust World Models

Zeqiang Zhang, Fabian Wurzberger, Maximilian Otte, Daniel Schmid, Sebastian Gottwald, Arne Peter Raulf, Daniel Alexander Braun

原文摘要

A robust world model must strike the balance between faithfully capturing environmental dynamics and abstracting away from irrelevant content. While reconstruction-based world models ensure faithful supervision, they misallocate representational capacity by pixel area rather than dynamics relevance for visual tasks, which can cause task-irrelevant content to dominate the learned representation. Alternatively, reconstruction-free methods avoid this bias but risk discarding possibly relevant information. We propose StarWM, which uses a cross-attention module trained on self-supervised dynamics to decide where reconstruction applies. A dual-stream decoder then restricts reconstruction to the attended regions, with stop-gradient barriers preventing interference between the two objectives. These components allows reconstruction to supervise the visual content of attended regions without contaminating the latent with non-predictive information. On DeepMind Control with dynamic video backgrounds, default (reward-free) StarWM achieves the strongest performance under random-frame distractors and substantially outperforms reconstruction-based baselines under sequential video. In addition, its reward-augmented variant matches or exceeds reconstruction-free methods on sequential video, achieving the highest overall return across all distractor regimes. Mechanistic probing confirms \starwm{} preserves state attributes with near-perfect fidelity through long-horizon imagination while systematically discarding distractors. Code is available on GitHub.

cs.CV · cs.LG

新论文 · v1arXiv:2611.10199

RigidGS: Geometry-Aware Object Decoupling for Rigid-Body Interaction in 3D Gaussian Splatting

Paul Sansah Gyreyiri, Diksha Shukla

原文摘要

Interactive VR/MR applications demand photorealistic 3D representations that support real-time rendering and object-level manipulation. While 3D Gaussian Splatting (3DGS) achieves high rendering quality, it represents scenes as unstructured, monolithic primitives. Existing object-aware 3DGS methods jointly optimize geometry and semantic states but suffer from two key failure modes: noisy foundation-model masks on complex geometry, and label-geometry coupling, in which co-optimized identity gradients mislabel boundary Gaussians. We introduce RigidGS, an end-to-end pipeline that decouples geometric learning from object identity. We propose a depth- and temporally-aware mask refinement module that addresses two complementary SAM2 failures: over-inclusion on thin structures and under-inclusion on multimodal-depth objects. We then determine object identities entirely upstream via COLMAP projection voting and freeze them during training, directing mask supervision solely toward geometric optimization. Refined masks alone substantially improve competing methods, yet a residual gap in label-geometry coupling persists that our fixed-identity design eliminates. RigidGS outperforms prior object-aware 3DGS methods on LLFF/NVOS, Mip-NeRF~360, and iNeRF360, improving segmentation and boundary IoU by 7.7 and 14.5 points on LLFF/NVOS. Finally, RigidGS enables real-time rigid-body manipulation on Meta Quest~2 without mesh extraction. Our code and project page are available at https://gyreyirisansah.github.io/rigidgs.

cs.CV

新论文 · v1arXiv:2611.10198

BO-Arena: An Evolving Benchmark for High-Dimensional Bayesian Optimisation

Colin Doumont, Thomas Christie, Henry Moss, Philipp Hennig

原文摘要

High-dimensional Bayesian optimisation (HDBO) is an increasingly crowded field with new methods proposed at every major conference, making it ever harder to answer a deceptively simple question: "Which method is currently state-of-the-art?" In this paper, we question the efficacy of benchmarking practices in the field, and find them to be systematically ineffective: multiple published works fail to benchmark against the strongest available baselines, or even include incorrect implementations of key methods. Without a shared reference implementation, such errors are difficult to detect during peer review. We therefore introduce BO-Arena, an actively maintained and extensible package providing canonical implementations of state-of-the-art algorithms, which allows researchers to develop new methods and benchmark them rigorously. Using BO-Arena, we find that what currently drives performance in HDBO is even simpler than previously thought. We use these insights to propose a new algorithm which is competitive with the state of the art on problems with many observations, without resorting to the complex GP approximations used in recent methods. Finally, we question whether there is currently sufficient evidence that any more complex method outperforms a simple Gaussian process baseline for HDBO.

cs.LG

版本更新 · v2arXiv:2603.25687

On Neural Scaling Laws for Weather Emulation through Continual Training

Shashank Subramanian, Alexander Kiefer, Arnur Nigmetov, Amir Gholami, Dmitriy Morozov, Michael W. Mahoney

原文摘要

Neural scaling laws, which in some domains can predict the performance of large neural networks as a function of model, data, and compute scale, are the cornerstone of building foundation models in Natural Language Processing and Computer Vision. We study neural scaling in Scientific Machine Learning, focusing on models for weather forecasting. To analyze scaling behavior in as simple a setting as possible, we adopt a minimal, scalable, general-purpose Swin Transformer architecture, and we use continual training with constant learning rates and periodic cooldowns as an efficient training strategy. We show that models trained in this minimalist way follow predictable scaling trends and can outperform standard cosine learning rate schedules. Cooldown phases can be repurposed to improve downstream performance, e.g., enabling accurate multi-step rollouts over longer forecast horizons or sharper predictions through spectral loss adjustments. We also systematically explore a wide range of model and dataset sizes under various compute budgets to construct IsoFLOP curves, and we identify compute-optimal training regimes. Extrapolating these trends to larger scales highlights potential performance limits, demonstrating that neural scaling can serve as an important diagnostic for efficient resource allocation. We open-source our code for reproducibility

cs.LG

版本更新 · v2arXiv:2606.17310

SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues

Suttisak Wizadwongsa, Hyelin Nam, Supasorn Suwajanakorn, Jeong Joon Park

原文摘要

Generating novel renderings of a scene along user-defined camera trajectories from a single monocular video, dubbed video retaking, is a compelling but difficult problem in content creation and visual effects. Existing geometry-guided approaches reconstruct a 4D representation from the source video and render it along the target trajectory to condition video diffusion models. However, this guidance degrades as the target camera departs from the source trajectory, leaving newly revealed regions sparse or entirely missing. We propose SierpinskiCam, which addresses this limitation by augmenting geometry-based guidance with Sierpinski dome texture cues that contains rich trackable features even under large viewpoint changes. We further introduce a reference video conditioning mechanism that appends source-video tokens to the target-token sequence and separates the two streams with negative RoPE indices, enabling appearance grounding without architectural modification or per-video adaptation. Extensive experiments show that SierpinskiCam achieves significant gains in camera controllability, geometric consistency, and video quality across diverse and challenging retaking scenarios. Project page: https://hyelinnam.github.io/SierpinskiCam/.

cs.CV

版本更新 · v2arXiv:2611.00403

MXCode: Vector Quantization for MX-Native Inference at Scale

Gaurav Kolhe, Cansu Demirkiran, Shubhi Tyagi, Sulaiman Sadiq, Boyao Wang, Richard Wang, Maximiliana Behnke, Shreyas Labhsetwar 等 11 位作者

原文摘要

Memory capacity and bandwidth are major bottlenecks in LLM inference, motivating weight compression beyond conventional 4-bit quantization. Vector quantization (VQ) enables approximately 2-bit weight storage but often relies on codebooks incompatible with native FP4 computation. We introduce MXCode (MX-Native Codebook Quantization), a framework bridging ultra-low-bit VQ compression with MicroXcaling (MX)-native FP4 computation. MXCode proposes three strategies: PostScale, which quantizes learned codebooks to MXFP4; PreScale, which extracts MX scales before codebook learning; and PreScale+, which further compresses these scales using VQ. These strategies explore tradeoffs among quantization quality, scale overhead, and codebook granularity. All reconstruct MX-native W4A4 operands without materializing intermediate high-precision weights. We evaluate MXCode on Qwen3 (235B), DeepSeek-R1 (671B), and GLM-5.2 (753B) using the Microsoft MX Emulation Library. MXCode achieves approximately 2 bits per weight with competitive, workload-dependent model quality. On GB300 hardware, experiments with Qwen3 (235B) show approximately 50% lower model-load memory than Native FP4 while maintaining near-Native-FP4 serving throughput. Under memory-constrained prefix reuse, P90 TTFT improves by up to 94.5%. These results demonstrate software-based reconstruction on existing FP4 hardware and inform the development of future MX-native inference systems.

cs.LG

版本更新 · v2arXiv:2611.07654

English Calibration Erodes Lithuanian in Expert-Pruned Mixture-of-Experts Language Models

Tomas Rasymas, Povilas Kvedaras

原文摘要

Expert pruning compresses Mixture-of-Experts (MoE) language models by removing the experts that a calibration set marks as unimportant. Studies of high-resource languages largely find that English calibration transfers well to other languages. We test this for Lithuanian: we pruned four MoE models with REAP, removing 25% or 50% of the experts with English, Lithuanian or mixed calibration, and evaluated both languages on reading comprehension, translation and language modelling. English calibration does not transfer to Lithuanian: at 25% pruning, English comprehension fell by a median of 1.7 points but Lithuanian by 21.4. The transfer is asymmetric. Lithuanian calibration removed most of the Lithuanian loss and never significantly hurt English comprehension, which was on average 2.5 points better than under English calibration; only English language modeling got slightly worse. Routing suggests why: in the last layers, Lithuanian sends 55-72% of its expert selections to just eight experts, against 19-39% for English, and English calibration removes some of these experts. Compressed models should be calibrated, and evaluated, in every language they must serve.

cs.CL · cs.LG

新论文 · v1arXiv:2611.10193

Ensemble Routing for Prompt-Adaptive Cost-Aware LLM Inference

Saul Urso, Emanuele Carlini, Patrizio Dazzi, Matteo Mordacchini

原文摘要

Large language models (LLMs) increasingly support Web-based services that must balance response quality and inference cost across heterogeneous requests. Conventional routing selects one model per prompt, while fixed ensembles cannot adapt their composition and cost to individual requests. We introduce PISA, a prompt-adaptive, cost-aware single-model router, and PISA-E, its extension to ensemble routing. At the core of both methods, PISA combines soft cluster memberships with model-specific predictors to estimate individual model capabilities. Building on these estimates, PISA-E jointly selects ensemble composition and cardinality under an explicit cost--quality preference that can be adjusted at inference time without retraining. A tractable ensemble-success surrogate and efficient candidate selection enable this extension without ensemble-specific training. Across four LLM routing benchmarks under in-distribution (ID) and out-of-distribution (OOD) conditions, PISA achieves the highest macro-average cost--performance hypervolume among the evaluated single-model routers in both settings. Meanwhile, PISA-E achieves the highest macro-average task performance among the evaluated ensemble approaches when prioritizing response quality, surpassing the strongest competitors by 2.09 and 2.87 percentage points under ID and OOD conditions, respectively. At selected lower-cost operating points, it also exceeds the strongest ensemble competitors' macro-average task performance while reducing average inference cost by approximately 36% and 25%, respectively. These results demonstrate the effectiveness of prompt-adaptive capability estimation for both single-model routing and selective ensembling.

cs.AI

新论文 · v1arXiv:2611.10192

Lightweight Neural Prediction for MDCT-Based Perceptual Audio Coding

Niccolo Abate, Gabriel Soule, Marina Bosi

原文摘要

Perceptual audio codecs often use predictive coding to further reduce signal redundancy. Rather than learning the entire codec pipeline end-to-end, we insert a small neural network as a drop-in, deterministic predictor in an otherwise conventional codec: the network estimates the next Modified Discrete Cosine Transform (MDCT) coefficient block from a short context of reconstructed blocks, and the encoder transmits the quantized residual. We compare Multilayer Perceptron (MLP) and Convolutional Neural Network (CNN) predictors against a non-predictive baseline and a per-line Normalized Least Mean Squares (NLMS) linear predictor (similar to the MPEG-2 AAC Main Profile predictor). The CNN consistently outperforms the MLP, the linear predictor, and the baseline in signal-to-noise ratio (SNR), noise-to-mask ratio (NMR), and MUSHRA evaluation scores. Using a 512-sample analysis window (w = 512), our neural predictors recover, and the CNN exceeds, the coded quality obtained by the non-predictive baseline after quadrupling the analysis-window length to w = 2048, at substantially lower algorithmic delay. The CNN uses only 0.13M parameters (roughly 20x fewer than the MLP) and has a decoder real-time factor (RTF) of ~0.10 on a consumer CPU.

eess.AS · cs.SD

新论文 · v1arXiv:2611.10186

Projected Neural Additive Models as Universal Approximators

Nhon N. Phan, Qiang Du, John D. Clayton, WaiChing Sun

原文摘要

Neural additive models (NAMs) offer interpretability but lack expressivity due to their rigid additive structure, whereas multi-layer perceptrons (MLPs) achieve universal approximation at the cost of transparency. We establish the first theoretical foundation for projected neural additive models (PNAMs), which augment NAMs with a learnable linear transformation $\boldsymbol{T}$ to capture cross-variable interactions. While standard NAMs cannot approximate even the simplest interaction term $χ_1 χ_2$ because their cross-derivatives are identically zero, we prove that PNAMs are universal approximators and characterize the minimum number of projections required for exact polynomial representation. Furthermore, we derive an approximation rate of $\mathcal{O}(M^{-s / (N - 1)})$ for $\mathcal{C}^s$ functions (i.e., functions with $s$ continuous derivatives), where $M$ denotes the number of projections and $N$ the input dimension; this rate is known to be optimal for ridge function approximation. To recover interpretability from the projected inputs, we introduce structured sparsity regularizers and post-hoc symbolic regression techniques that enable global input ranking, parameter pruning, and the conversion of learned bases into compact analytical expressions. Experiments on knot theory invariants, MNIST, and phase field fracture mechanics demonstrate that PNAMs match or surpass similar architectures in accuracy while discovering salient features and yielding symbolic models with orders of magnitude fewer parameters.

cs.LG

新论文 · v1arXiv:2611.10185

GSynPEF: A Privacy Evaluation Framework for Synthetic Graphs

Yu Duan, Luca Baldesi, Carter T. Butts, Athina Markopoulou

原文摘要

It is often desirable to generate and release synthetic graphs, which resemble real-world data, in a privacy-preserving way. While substantial progress has been made in designing private graph synthesizers (PGS), opportunities remain for more explicit connections between synthesizer models and privacy evaluation, and better accounting for output variation. This paper proposes GSynPEF, a practical framework for empirical evaluation of privacy and utility in settings for which a real-world graph is given as input and output synthetic graph(s) are observed. Our framework links a broad class of graph synthesizers (both statistical and deep-learning based) with privacy metrics, expanding evaluation dimensions to practical utility and risk, through empirical analysis of multiple actual outputs. The framework accommodates both an Exact Solution scenario, where synthesizer behavior is directly observable, and a Monte Carlo Approximation scenario where only synthetic outputs from a black box synthesizer are available. Extensive experiments on four real-world datasets and seven widely used graph synthesizers demonstrate framework's versatility, enabling privacy evaluation for different attack goals (e.g., to infer an edge or node) and capabilities (e.g., observing one or multiple synthetic graphs). We analyze evaluation results by examining the relationship between graph statistics and synthesizer design choices, providing insights for data curators in PGS selection and researchers for improved PGS design.

cs.CR · cs.AI · cs.SI

版本更新 · v2arXiv:2610.16776

Game-Creation-Agents: Autonomous Game Production

Xiangxin Zhou, Jiaqi Tang, Ke Ma, Wenhao Yang, Jiarui Yao, Boye Niu, Haiyang Guo, Yifei Zhao 等 17 位作者

原文摘要

Game-Creation-Agents (GCA) turns a natural-language request into a runnable Phaser 4 browser game. The pipeline first builds a multimodal game design document that couples mechanics and scene contracts to grounded visual references. It then projects that document into a runtime scaffold, machine-readable contracts, and deterministic tests. Eight specialized agents next carry out production: scenes are implemented serially, assets are produced in parallel, and one reduced manifest joins the two branches into a single build. Build-linked real-UI checks and a code-blind critic then verify that build and decide whether the game may ship. Each blocker returns to the agent that owns the affected artifact for a bounded repair, and the game is released once all the gates pass. We evaluate finished games separately, through their rendered interfaces alone, over prompt-matched tasks run under a common protocol. GCA achieves stronger requirement satisfaction, core mechanics, content depth, and functional visuals than a comparable open pipeline. In a side-by-side human study, raters also score GCA's games higher on every dimension and prefer them overall.

cs.AI · cs.MA

新论文 · v1arXiv:2611.10184

Fully Dynamic Correlation Clustering with Vertex Updates in Polylogarithmic Update Time

Vladimir Braverman, Prathamesh Dharangutte, Chenglin Fan, Chen Wang, Shenghao Xie, Samson Zhou

原文摘要

We present a fully dynamic algorithm for correlation clustering that supports \emph{vertex} insertions and deletions while maintaining an $O(1)$ approximation in polylogarithmic amortized update time. This resolves an open problem of vertex deletions posed by a recent line of work on dynamic correlation clustering. We adopt the min-disagreement objective for correlation clustering, i.e., given a signed complete graph $G=(V,E^+\cup E^-)$, we want to minimize the total number of $(+)$ edge crossing clusters and $(-)$ edges within clusters. The input is given in the adjacency list model, where each update inserts or deletes a node along with its full set of $(+)$ neighbors. Our main technical contribution is a fault-tolerant sparse-dense decomposition framework which unlike the existing decomposition-based frameworks allows for structural inconsistencies as long as the induced cost is bounded. We also show a separation between explicitly maintaining the (stronger) sparse-dense decomposition and maintaining a constant-factor approximation to correlation clustering, which may be of independent interest.

cs.DS

新论文 · v1arXiv:2611.10182

ATLAS: A Multi-Procedure Benchmark and Context-Aware Model for Surgical Anatomy Segmentation

Ronald L. P. D. de Jong, Tim J. M. Jaspers, Raf A. H. Vervoort, Aron F. H. A. Bakker, Anna L. Dijk, Yiping Li, Jip L. Tolenaar, Jelle P. Ruurda 等 13 位作者

原文摘要

Recognizing anatomical structures during minimally invasive surgery (MIS) could support intraoperative navigation and improve patient safety, but progress is limited by small, single-procedure datasets and by segmentation methods developed for natural scenes. This work addresses both limitations through a new dataset and model. First, we introduce ATLAS-120k, a clip-level semantic segmentation dataset of 121,018 annotated frames from 100 surgical videos, covering 14 laparoscopic and robot-assisted procedures and 41 classes. Annotations were created with a pipeline that combines manual labeling, tracker-based propagation, and review by surgeons. Second, we propose ATLAS (Anatomy Recognition with Context Learning using Foundation Representations), a video semantic segmentation model for surgical anatomy recognition. ATLAS builds on in-domain foundation-model embeddings and adds context queries for the procedure and surgical phase, together with query propagation between frames for short-term memory. ATLAS outperforms state-of-the-art natural-image and in-domain foundation models in both segmentation accuracy and temporal consistency, achieving a Dice score of 0.70 with ViT-L while running in real time at 76.2 FPS. Ablations show that the context queries improve accuracy and that query propagation improves temporal consistency. ATLAS also generalizes well, matching a dedicated model zero-shot on CholecSeg8k and improving phase recognition on AutoLaparo over SurgeNet initialization. The model weights, dataset annotations, and annotation tool are publicly available at https://github.com/TimJaspers0801/ATLAS.

cs.CV

新论文 · v1arXiv:2611.10180

Generative Active Learning for Label-Efficient Pan-Organ Ultrasound Diagnosis

Yaofei Duan, Yuhao Huang, Yuan Gao, Ruixiang Qi, Tianyu Zhang, Yanlin Geng, Yue Sun, Sio-Kei Im 等 12 位作者

原文摘要

Medical ultrasound (US) enables real-time, non-invasive diagnosis, yet building US-based AI systems is limited by data scarcity, costly expert annotation, and limited cross-center generalizability. Privacy constraints and instance-level reporting hinder the collection of diverse abnormal cases and frame-level labels, while repeated retraining for new centers increases computational cost. We introduce EvoDiff, a generative active learning framework that integrates diffusion modelling with information-theoretic objectives, evolutionary search, and curriculum-based sampling to select informative samples across heterogeneous US datasets. EvoDiff formulates sample selection as a generate-to-retrieve process, in which diffusion-based optimization in feature space guided by information gain produces synthetic probes, and only the real unlabeled samples retrieved by these probes are annotated and used for downstream training. Across six benchmarks covering fifteen datasets and 16,696 images, we evaluate EvoDiff on convolutional network and transformer-based foundation model. EvoDiff approaches fully supervised performance with substantially fewer labels, outperforms active learning baselines, and improves foundation model generalization under cross-domain external validation on unseen cohorts. A reader study with six radiologists indicates the potential to support clinical annotation workflows, with a model-based estimated 24% to 84% reduction in annotation workload at matched downstream performance.

cs.AI · cs.HC

新论文 · v1arXiv:2611.10178

The Storage View Of KV Cache: Characterizing Cache Behavior Across LLM Workloads

Talia Q. Chen, Daniel Waddington, Narangerelt Batsoyol, Vijay Chidambaram

原文摘要

Modern LLM serving increasingly extends KV caches beyond GPU memory into host DRAM, SSDs, and remote storage, yet these stores remain largely governed by workload-agnostic policies such as LRU and fixed TTLs. We ask what execution context is needed by storage to make retention, reclamation, and placement decisions across heterogeneous workloads. We characterize KV-cache reuse, lifetime, and footprint at block granularity across 11 production and public traces spanning chat, API serving, RAG, coding agents, tool-using agents, and multi-lineage workflows. We examine reuse sources, recurrence timing and frequency, useful lifetimes, and storage consumption. Across workloads, KV state takes two recurring forms. Single-session state is reused within one execution: its footprint grows as sessions deepen and accumulates across concurrent sessions; it can remain useful through long idle periods but loses value at session completion. Multi-session state recurs across sessions of the same workload, outlives individual sessions, and spans hot prefixes and a large infrequent tail. While prior systems often exploit application-, agent-, or workflow-specific knowledge, our results suggest that three generic signals (a workload identifier, a session identifier, and session completion) expose much of the structure needed for KV-storage management. Trace-driven comparisons show that workload-specific recurrence estimates retain up to 22% more within-session hits and reduce dead state by up to 40%; a session completion signal eliminates the fundamental idle-time reclamation tradeoff for single-session state; and session-aware reuse classification identifies shared state 4-700x more selectively than request-level access counts. These results motivate a small cross-layer interface for workload-aware KV storage without application-specific semantics.

cs.OS

版本更新 · v3arXiv:2609.33158

FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs

David Restrepo, Chenwei Wu, Luis Filipe Nakayama, Miguel L. Martins, Stergios Christodoulidis, Maria Vakalopoulou, Enzo Ferrante

原文摘要

Progress in AI-based retinal image analysis has accelerated with the adoption of foundation models, yet evaluating their real-world reliability remains challenging. Performance reported on a single dataset does not capture how models behave under dataset shift, across clinical definitions, or for different patient subgroups. This limitation is particularly critical in medical imaging, where robustness, calibration, and fairness are essential for safe deployment. We introduce FOCUS (Foundation Ophthalmic Cross-Dataset Understanding under Shift), a cross-dataset benchmark evaluating retinal fundus models across vision-only encoder models (VM), vision-language dual-encoder models (VLM), and multimodal large language models (MLLM). FOCUS harmonizes binary diabetic retinopathy, referable diabetic retinopathy, and glaucomatous optic neuropathy tasks across ten public datasets spanning diverse geographies, acquisition conditions, and label protocols. The benchmark evaluates models through a unified analysis layer that measures ranking performance, calibration, subgroup disparities, and image-quality robustness. We present a large-scale evaluation covering 532 base configurations and 228 MLLM configurations adapted via LoRA fine-tuning. Results show no model family consistently dominates across tasks and datasets: general VM encoders achieve the strongest average ranking performance, medical MLLMs are competitive but variable, and dual-encoder VLMs benefit substantially from lightweight adaptation. Fine-tuning improves in-domain performance but exhibits heterogeneous transfer to external datasets, particularly in calibration. FOCUS provides a practical framework and public benchmark to assess generalization, reliability, and robustness beyond single-dataset leaderboards.

cs.CV · cs.AI

新论文 · v1arXiv:2611.10176

AVCORP: Identifying and Resisting Deception via Communication Theory and Theory of Mind

Fardin Saad, Zhe Zhang, Sanjana Cheerla, Amanul Haque, Munindar P. Singh

原文摘要

Today's LLM-based agents are vulnerable to deception by users and other agents. Defending against deception requires Theory of Mind (ToM) reasoning to infer the beliefs and goals of others as well as modeling tactics based on communication theory. To enable training models to detect deception, we adopt the well-known deception game, Avalon. We present a corpus, AVCORP, of 5,000 annotated utterances from 250 games of Avalon. AVCORP includes (1) 37 tactics mapped to a 4x4 behavior matrix, and (2) reasoning traces capturing abductive hypotheses, suspicion levels, and nested ToM beliefs. We train Qwen3-8B on AVCORP and evaluate it on 25 held-out games and 20 games played by humans. On held-out games, our best trained detector outperforms its untrained baseline and frontier models (GPT-5.6 Sol, Gemini 3.1 Pro, DeepSeek-V4-Pro), matching Claude Opus 5.5. On human games, every trained detector exceeds the untrained model in F1 score across all rounds.

cs.AI · cs.CL · cs.LG

版本更新 · v2arXiv:2605.05413

From History to State: Constant-Context Skill Learning for LLM Agents

Haoyang Xie, Xinyuan Wang, Yancheng Wang, Puda Zhao, Feng Ju

原文摘要

Large language model (LLM) agents are increasingly used to operate browsers, files, code and tools, making personal assistants a natural deployment target. Yet personal agents face a privacy-cost-capability tension: cloud models execute multi-step workflows well but expose sensitive intermediate context to external APIs, while local models preserve privacy but remain less reliable. Both settings also pay repeatedly for long skill prompts and growing histories. We propose constant-context skill learning, a context-to-weights framework for recurring agent workflows: reusable procedures are learned in lightweight task-family modules, while inference conditions only on the current observation and a compact state block. A deterministic tracker renders this state block from task progress and supplies aligned subgoal rewards, so each module can be trained with step-level SFT and refined through online RL. Across ALFWorld, WebShop, and SciWorld, our agents achieve strong performance across Qwen3-4B, Qwen3-8B, Qwen3-14B, and Llama-3.1-8B. With Qwen3-8B, SFT+RL reaches 89.6% unseen success on ALFWorld, 76.8% success on WebShop, and 66.4% unseen success on SciWorld. They match or exceed strong published agent-training results while reducing prompt tokens per turn by 2-7x relative to controlled ReAct prompting baselines, showing that procedural context can be moved from prompts into weights. Code is available at https://github.com/haoyangxie/constant-context-skill-learning.

cs.AI

新论文 · v1arXiv:2611.10175

ASCENT: Scale-Complementary External State for Frozen Long-Context Language Models

Xingjian Zhang

原文摘要

External state should become more valuable as a reader becomes more capable, yet long-context evaluations measure memory utility at a single model scale. This paper formulates scale complementarity: the absolute gain from external state increases when reader capacity and a compact state budget are jointly scaled. ASCENT realizes this principle with a target-blind causal writer, nested typed state, and a bounded query-conditioned readout; every language model remains frozen. Under log loss, the value of a nested refinement equals its target-relevant conditional information; a full factorial makes the reader-by-state interaction identifiable. Official 16K BABILong experiments show Qwen2.5 accuracy gains of 10.50, 78.88, and 82.63 percentage points at 0.5B, 1.5B, and 3B parameters, with both adjacent directional contrasts significant after family-wise correction. At 7B, Foundation accuracy rises to 33.25% while four-slot ASCENT answers every question, which caps the gain at 66.75 points; the 3B-to-7B accuracy increment is -15.88 points [-20.55, -11.20]. The accuracy-side claim is therefore established from 0.5B to 3B; the 7B conclusion rests on the non-saturated negative-log-likelihood factorial. A three-model by three-state factorial yields co-scaled negative log-likelihood gains of 0.388, 2.099, and 7.406 nats at 1.5B, 3B, and 7B; all interaction and gain contrasts retain positive simultaneous lower bounds. Five public 7B-8B readers obtain 66.75-85.63 point gains, and ASCENT exceeds task-trained retrieval checkpoints at the two larger shared scales. Controls, baselines, systems accounting, matched-hardware reproduction, and a cross-architecture sensitivity analysis accompany the experiments. The results establish scale-complementary external state under the evaluated benchmarks, metrics, and state schema.

cs.CL · cs.LG

版本更新 · v3arXiv:2605.07483

Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization

Leonel Aguilar, Jan Nagler, Christoph Hoelscher, Nino Antulov-Fantulin

原文摘要

Deep neural networks can learn salient features from an in-distribution (ID) training window without identifying the data-generating structure needed for out-of-distribution (OOD) generalization. Understanding this limitation requires examining the identifiability of the data-generating process (DGP). From a single training window, the DGP that yields the correct OOD extrapolation is not identifiable: infinitely many DGPs are observationally equivalent within a fixed tolerance on that window yet diverge arbitrarily beyond it, and no ID criterion alone can reliably distinguish them. A structural commitment---the feature map, label map, and model class $(\varphi, ψ, \mathcal{M})$---specifies the assumed DGP and governs OOD generalization while leaving ID performance essentially unchanged. When architecture, pretraining, data augmentation, input formats, or domain knowledge implicitly supply the correct commitment, the model generalizes beyond the training window. When it cannot infer OOD-relevant structure from ID evidence, it fails to generalize. When the commitment is correct {\em and} identifiable, OOD error vanishes. We demonstrate this mechanism in models trained from scratch and in foundation models across four natural-science settings (chemistry, physics, biology, and histopathology), as well as in a positional-encoding study spanning Transformer, Mamba, and S4D architectures. Finally, a controlled study shows that correct features are necessary but not sufficient for OOD generalization.

cs.LG · cs.AI

版本更新 · v3arXiv:2510.13879

Catch Your Breath: Adaptive Computation for Self-Paced Sequence Production

Alexandre Galashov, Matt Jones, Rosemary Ke, Yuan Cao, Vaishnavh Nagarajan, Michael C. Mozer

原文摘要

Within the landscape of inference-time scaling methods for foundation models, a width-based approach to scaling--which involves the insertion of <pause> tokens in the input stream to delay model responses--offers a unique advantage by increasing model expressivity while remaining highly parallelizable at both training and inference. The existing literature on training models to utilize <pause> tokens relies on the standard cross-entropy objective in which the model output is read out and evaluated only at the final step of a pause sequence. This approach provides no mechanism for the model to regulate its own processing or to signal readiness to respond, treating the additional compute steps as a barrier to skip over rather than a resource to be used adaptively. We propose a supervised loss, Catch Your Breath (CYB), framed as a sequential-decision problem, that trains a model to dynamically and autonomously scale the number of compute steps used for each input token. The model indicates the need for additional compute steps by emitting a special <don't know> output, delaying its response via a pause. The model can abstain multiple times to obtain longer delays. Our experiments demonstrate that when <pause> tokens are included in the input stream, pretraining or fine-tuning with CYB significantly outperforms standard cross-entropy, reducing perplexity and enhancing downstream accuracy with no additional computational or memory cost.

cs.CL · cs.AI

新论文 · v1arXiv:2611.10174

CXR-CMFA: A Cross-Modal Feature Aggregation Network for Chest X-Ray Pathology Classification

Talukder Hasnat Zadid, Jahin Sultana, Felipe Bochini Brisola, Kishore Roy, Mysha Rahman, Syeda Asrafa Islam, Md. Abdullah-Al-Jubair

原文摘要

Chest X-ray (CXR) interpretation remains challenging because subtle pathology can be obscured by overlapping anatomy, image-quality variation, and limited visual evidence in isolated radiographs. Although image-only deep learning models provide useful baselines, they discard the complementary diagnostic context available in radiology reports, while large vision-language models can be computationally expensive for practical deployment. This paper presents CXR-CMFA, a lightweight cross-modal feature aggregation network for binary CXR pathology classification. The proposed framework combines a dual-stream visual encoder, using EfficientNet-B0 for global anatomical representation and DenseNet-121 for local pathological detail, with a TF-IDF-MLP report encoder. Two fusion modules integrate these modalities: the Dual-Modal Spatial Attention Module (DMSAM) uses the report embedding to gate global and local visual features, and the Cross-Modal Gated Feature Fusion (CGFF) module learns per-instance weights for visual and textual contributions. Experiments on the MIMIC-CXR benchmark, using the provided train, validation, and test splits, show that CXR-CMFA achieves 93.45% accuracy, 99.88% precision, 91.8% recall, 95.7% F1-score, and 99.19% AUC on the held-out test set. The model produces only four false positives among 984 normal test cases, supporting its suitability for high-specificity screening workflows. An ablation study further demonstrates a 22.47 percentage-point AUC improvement over the global-image-only variant, confirming the value of adaptive cross-modal fusion. These results indicate that compact report-conditioned fusion can provide strong discriminative performance without relying on large pretrained language models.

cs.CV · cs.AI

新论文 · v1arXiv:2611.10170

Where Did the Evidence Go? Diagnosing Proof-Set Loss in Long-Term Conversational Memory

Bogdan Roshchupkin, Maria Khodorchenko

原文摘要

Long-term conversational question answering can require several separated dialogue turns that support an answer only together. We introduce EviCover, a retrieval approach designed to retain this complementary evidence. It converts questions into observable evidence requirements, checks requirement coverage using retrieved source identifiers, and selects turns jointly. We track annotated support sets - the benchmark-labeled dialogue turns associated with each question - through retrieval, reranking, and final answer-generation context. We evaluate the baseline memory pipeline on generated, human-verified LoCoMo conversations and human-written REALTALK conversations, and examine EviCover on REALTALK's 108 multi-hop questions. Compared with the hybrid lexical/dense baseline, support-turn recall among 60 candidate turns rises from 0.526 to 0.575, and recall in the final ten-turn context rises from 0.349 to 0.379. The evidence funnel identifies separate discovery and selection failures, while paired answer evaluation shows that greater evidence recall does not yet establish a correctness gain. This analysis locates where complementary evidence is lost and distinguishes evidence retrieval from its use in answer generation.

cs.CL · cs.AI

新论文 · v1arXiv:2611.10169

Capturability-Aware Footstep Planning in Cluttered Environments: A Recursively Feasible Sequential MPC on Axis-Aligned Safe Corridors

Athanasios Kyriakopoulos, Shubham S. Kumbhar, Kunal S. Narkhede, Abhijeet M. Kulkarni, Ioannis Poulakakis

原文摘要

A fundamental aspect of humanoid footstep planning is to jointly guarantee obstacle avoidance and locomotion stability. This paper presents a capturability-aware sequential Model Predictive Control (MPC) framework for Linear Inverted Pendulum (LIP)-based humanoid footstep planning in the presence of obstacles. The proposed method combines obstacle avoidance with capturability constraints through safe corridors constructed as sequences of intersecting rectangles, yielding a sequential MPC framework with recursive feasibility guarantees for the LIP-based planning layer. The planner autonomously adapts to constrained scenarios, switching to in-place walking when obstructions---such as doors assumed to be open during planning but unexpectedly found to be closed during execution---block forward motion. Performance is largely independent of the prediction horizon, allowing high success rates while keeping the computational cost low. The approach is validated in high-fidelity simulations with the humanoid robot Digit, demonstrating a practical solution for capturable humanoid footstep planning in cluttered environments.

cs.RO

版本更新 · v3arXiv:2601.09920

SyncTwin: Fast Digital Twin Construction and Synchronization for Safe Robotic Manipulation

Ruopeng Huang, Boyu Yang, Wenlong Gui, Jeremy Morgan, Erdem Biyik, Jiachen Li

原文摘要

Accurate and safe robotic manipulation under dynamic and visually occluded conditions remains a core challenge in real-world deployment. We introduce SyncTwin, a novel digital twin framework that unifies fast 3D scene reconstruction and real-to-sim synchronization for robust and safety-aware robotic manipulation in such environments. In the offline stage, we employ VGGT to rapidly reconstruct object-level 3D assets from RGB images, forming a reusable geometry library. During execution, SyncTwin continuously synchronizes the digital twin by tracking real-world object states and uses stored assets to complete partially observed geometry. The synchronized twin enables motion planners to compute collision-aware robot trajectories in simulation, with execution on the real robot closing the real-to-sim-to-real loop. Experiments in dynamic and occluded scenes show that SyncTwin improves manipulation performance and motion safety, demonstrating the effectiveness of digital twin synchronization for real-world robotic execution.

cs.RO